The Fourth Generation Podcast: Recent Episodes
Kudzai Manditereza - Industry40.tv
Each episode of The Fourth Generation Podcast will treat you to an in-depth interview with some of the world‘s leading IIoT practitioners where we really dive deep into technical and actionable details of building Industrial IoT Solutions.
Context isn't static.
It's a living layer of knowledge built through problem-solving, conversation, and understanding the complex relationships on the factory floor.
This simple truth is often overlooked in industrial data strategies.
We’ve been conditioned to believe that context can be predefined; baked into standards, taxonomies, and hierarchies.
But in real-world manufacturing, things change, people think differently, and use cases evolve.
So how can we build this dynamic layer of understanding for industrial AI?
In our latest AI in Manufacturing episode, I spoke with Bob van de Kuilen, Director at Thred, about a more human-centric approach to industrial data contextualisation using Knowledge Graphs.
Thred is a tool that plugs into Ignition Platform, enabling users to visualize their factory assets in a knowledge graph, link related data points, embed domain expertise, and deliver structured, contextualized data to AI and analytics tools.
We discuss:
✅ Why traditional approaches to data context often fail
✅ Knowledge Graphs act as a mind map for data
✅ The practical steps to building context
✅ How this new context layer serves as the perfect foundation for AI agents.
SA-95 is a standard that’s often misunderstood, but incredibly powerful.
While many think ISA-95 is rigid or overly complex, it actually enables flexibility by:
⇨ 𝐃𝐞𝐟𝐢𝐧𝐢𝐧𝐠 𝐚 𝐬𝐡𝐚𝐫𝐞𝐝 𝐯𝐨𝐜𝐚𝐛𝐮𝐥𝐚𝐫𝐲 for manufacturing concepts, creating a true ontology for your data.
⇨ 𝐂𝐫𝐞𝐚𝐭𝐢𝐧𝐠 𝐬𝐜𝐚𝐥𝐚𝐛𝐥𝐞 𝐩𝐥𝐚𝐜𝐞𝐡𝐨𝐥𝐝𝐞𝐫𝐬 for every type of data, so you can start small and add new use cases later without rebuilding everything.
⇨ 𝐏𝐫𝐨𝐯𝐢𝐝𝐢𝐧𝐠 𝐭𝐡𝐞 "𝐰𝐡𝐲" 𝐛𝐞𝐡𝐢𝐧𝐝 𝐞𝐯𝐞𝐧𝐭𝐬, not just the "what," giving crucial context to your analytics and AI models.
But how do you move from theory to a practical, modern implementation?
In our latest AI in Manufacturing podcast episode, we explore exactly that with ISA-95 expert Jeroen Janssen, who is an MES/MOM Consultant at Rhize Manufacturing Data Hub.
In the episode, you’ll learn:
✅ How to overcome a data culture that creates so many silos.
✅ The "use case stacking" method for a phased, value-driven implementation.
✅ What a native ISA-95 data hub looks like and how a graph database can bring it to life.
✅ Why this standardized approach is the key to unlo
Is the Timebase free historian getting an AI-Native DataOps component with Knowledge Graphs capability? You’ll hear it here first.
In the latest episode of the AI in Manufacturing podcast, I sit down with Jeff Knepper, President at Flow Software Inc., to discuss the intersection of Information Management and AI in modern manufacturing, plus the exciting announcement of Timebase Atlas launch.
Here’s some of what we cover in this episode:
✅ Why manufacturers struggle to make use of their data
✅ Building reliable pipelines for AI-driven use cases
✅ AI Agents in Manufacturing – Where they fit and what they need
✅ Unified Analytics Framework vs. Unified Namespace
✅ Historization Strategies – Best practices from edge to cloud
✅ Timebase Atlas Launch Announcement: Data Modeling, Pipelines, Knowledge Graphs, and AI interfaces
✅ MCP and Flow AI Gateway: Beyond APIs to Context-Aware Agent Interfaces
Most data-quality initiatives focus on things like freshness or schema. That works for IT data, but not for sensor data.
Sensor data is different. It reflects physics. To trust it, you need contextual, physics-aware checks.
That means spotting:
→ Impossible jumps
→ Flatlines (long quiet periods)
→ Oscillations
→ Broken causal patterns (e.g., valve opens → flow should increase)
It’s no surprise that poor data quality is one of the biggest reasons manufacturers struggle to scale AI initiatives.
This isn’t just data science, it’s operations science.
Think of data quality as infrastructure: a trust layer between your OT data sources and your AI tools.
Making that real requires four building blocks:
- 𝐒𝐜𝐨𝐫𝐢𝐧𝐠 – Physics-aware anomaly rules, baselines
- 𝐌𝐨𝐧𝐢𝐭𝐨𝐫𝐢𝐧𝐠 – Continuous validation at the right cadence (real-time or daily)
- 𝐂𝐥𝐞𝐚𝐧𝐢𝐧𝐠 & 𝐕𝐚𝐥𝐢𝐝𝐚𝐭𝐢𝐨𝐧 – Auto-fix what you can; escalate what you can’t
- 𝐔𝐧𝐢𝐟𝐨𝐫𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧 & 𝐒𝐋𝐀𝐬 – Define “good enough” and enforce it before data is consumed
Why it matters:
✅ Data teams – Less cleansing, faster delivery
✅ AI models – Reliable inputs = repeatable results
✅ Ops teams – Catch failing sensors before downtime
✅ Business – Avoid safety incidents, billing errors, bad decisions
In the latest episode of the AI in Manufacturing podcast, I sat down with Bert Baeck, Co-Founder of Timeseer.AI, to discuss time-series data quality and reliability strategies for AI in manufacturing applications.
What really makes data and AI innovation teams succeed in manufacturing?
In this episode of the AI in Manufacturing Podcast, I speak with Van Tucker, VP of Harbor Lockers by Luxer One, a company that develops and manufactures smart public lockers.
We discuss the challenges and strategies for building effective innovation teams in manufacturing.
Here are some of the insights that Van shared:
𝐂𝐮𝐥𝐭𝐮𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐟𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧
Innovation thrives when people, from the boardroom to the factory floor, believe in the mission. Core values must be lived daily, not just written on posters.
𝐀𝐠𝐢𝐥𝐢𝐭𝐲 𝐨𝐯𝐞𝐫 𝐩𝐞𝐫𝐟𝐞𝐜𝐭𝐢𝐨𝐧
Instead of waiting months for a polished rollout, start simple. Test small ideas quickly, gather feedback, and iterate. Even in hardware manufacturing, lightweight R&D “sandboxes” allow experimentation without disrupting core production.
𝐌𝐚𝐧𝐚𝐠𝐢𝐧𝐠 𝐩𝐫𝐞𝐬𝐬𝐮𝐫𝐞 𝐚𝐧𝐝 𝐛𝐮𝐫𝐧𝐨𝐮𝐭
Burnout shows up in declining quality and disengagement. The best leaders don’t wait, they stay close to their teams, recognize early warning signs, and act before problems escalate.
𝐁𝐫𝐢𝐝𝐠𝐢𝐧𝐠 𝐈𝐓 𝐚𝐧𝐝 𝐎𝐓
The old silos are gone. Effective leaders create environments where engineers from IT and OT collaborate, not compete. Quick collaborative wins build trust and momentum across functions.
Most industrial processes still run on the same foundation:
- Hard-coded logic in PLCs that follows predefined rules.
- The intuition of process and plant engineers, built from years of experience.
This combination has powered industry for decades, but it has limits.
When the challenge involves many interacting variables, unknown relationships, and non-linear effects, traditional control starts to strain.
Why?
Because fixed rules can’t adapt fast enough to changing conditions, and even the best human intuition can only process so much complexity at once.
Instead of relying on fixed instructions, RL agents learn directly from real-time feedback.
They can:
✅ Adapt continuously to new conditions.
✅ Handle high-dimensional problems with countless variables.
✅ Uncover novel, more efficient strategies that humans might overlook.
The result?
An optimization layer that works alongside your existing control system, making it smarter, more adaptive, and capable of delivering gains where complexity used to be a roadblock
In the latest episode of the AI in Manufacturing podcast, I sat down with Dr. Kyrill Schmid, the Lead AI Engineer at MaibornWolff GmbH, to discuss the application of reinforcement learning agents for optimizing industrial plants.
Can AI agents really make decisions in high-stakes industrial environments?
Generative AI agents, on their own, do not have a robust understanding of cause-and-effect for real-world decision-making.
However, when combined with Deep Reinforcement Learning, AI agents gain the ability to reason, learn from interaction, and make decisions that solve operational problems in complex, real-world environments, like the plant floor.
Case in point.
Bryan DeBois and his team at RoviSys developed an Autonomous AI agent to manage a notoriously difficult glass bottle production process, where small disruptions like temperature fluctuations can quickly push the process out of specification.
Here’s how they approached it:
✅ 𝐒𝐭𝐞𝐩 1 - 𝐌𝐚𝐜𝐡𝐢𝐧𝐞 𝐓𝐞𝐚𝐜𝐡𝐢𝐧𝐠
They captured the knowledge and decision-making strategies of expert human operators and used this to train the AI agent, essentially teaching it how to respond to different operating conditions.
✅ 𝐒𝐭𝐞𝐩 2 - 𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧 𝐒𝐮𝐩𝐩𝐨𝐫𝐭 𝐌𝐨𝐝𝐞
Initially, the agent didn’t control the process directly. It simply made recommendations.
Operators reviewed the suggestions and gave feedback using a simple green/red button system. This built trust and allowed the team to validate the AI’s decisions without risk.
✅ 𝐒𝐭𝐞𝐩 3 - 𝐂𝐥𝐨𝐬𝐞𝐝 𝐋𝐨𝐨𝐩 𝐂𝐨𝐧𝐭𝐫𝐨𝐥
Only after months of successful operation in support mode did they enable full automation.
Even then, strict safety measures were in place:
⇨ Limited control authority
⇨ Clearly defined operating boundaries
⇨ Automatic handover to human operators if conditions exceeded the agent’s training
The Results:
⇨ Human operators typically needed 7–20 minutes to bring the process back into spec
⇨ The AI agent consistently did it in under 5 minutes
⇨ And it maintained safety by operating strictly within validated limits
In the latest episode of the AI in Manufacturing podcast, I sat down with Bryan, Director of Industrial AI at RoviSys, to dive deeper into how manufacturers can leverage AI and autonomous agents to optimize manufacturing operations and improve efficiency
The industrial data stack was never built for enterprise-wide intelligence. It was built in silos, optimized for local decisions.
As a result, it is not designed to support unified, contextualized, and scalable data management across an organization.
And that’s why Industrial Data Platforms are essential for scaling digital transformation.
To help organizations understand what makes such a platform effective, David Ariens and The IT/OT Insider team created the Industrial Data Platform Capability Map, outlining the seven key capabilities every platform should have:
-
𝐂𝐨𝐧𝐧𝐞𝐜𝐭𝐢𝐯𝐢𝐭𝐲 – a secure and scalable connectivity layer to integrate different data sources into the Industrial Data Platform.
-
𝐂𝐨𝐧𝐭𝐞𝐱𝐭𝐮𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 & 𝐃𝐚𝐭𝐚 𝐌𝐚𝐧𝐚𝐠𝐞𝐦𝐞𝐧𝐭 – delivering data enriched with the right context, so users don’t have to gather and piece together information from multiple sources manually.
-
𝐃𝐚𝐭𝐚 𝐐𝐮𝐚𝐥𝐢𝐭𝐲 – Detecting and fixing data issues in your pipeline, from sensor to final report.
-
𝐃𝐚𝐭𝐚 𝐁𝐫𝐨𝐤𝐞𝐫 𝐚𝐧𝐝 𝐒𝐭𝐨𝐫𝐞 – The ability to ingest, store, and manage contextualized data at scale, enabling efficient data subscription and large-scale querying.
-
𝐄𝐝𝐠𝐞 𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 – The capability to perform analytics and machine learning within the data platform, or at the edge, close to where the data is generated.
-
𝐕𝐢𝐬𝐮𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 – The capability to deliver high-quality, contextualized data to users through intuitive and accessible interfaces for fast, informed decision-making.
-
𝐃𝐚𝐭𝐚 𝐒𝐡𝐚𝐫𝐢𝐧𝐠 – The capability to openly expose platform data to external users and applications through standard interfaces and integrations.
In the latest episode of the AI in Manufacturing podcast, I sat down with David, Founder of IT/OT Insider, to dive deeper into these capabilities and how organizations can implement them.
We also discussed the IT/OT Academy, an online training program designed to help IT and OT professionals build a shared vocabulary, framework, and collaboration strategy to move digital initiatives beyond pilot projects and into full-scale plant deployment.
Instead of sending data to the cloud for processing, Edge AI analyzes data right where it’s generated, on the machine, in the plant, in real time.
It’s the difference between reacting later and responding now.
What Happens When You Keep Intelligence at the Source?
𝐑𝐞𝐚𝐥-𝐭𝐢𝐦𝐞 𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐬
A conveyor motor vibrates abnormally.
Edge AI detects the anomaly instantly and slows the line before damage occurs.
𝐒𝐦𝐚𝐫𝐭𝐞𝐫 𝐌𝐚𝐢𝐧𝐭𝐞𝐧𝐚𝐧𝐜𝐞
Time-series models forecast when a press will wear out, so teams fix it during scheduled downtime, not after it fails.
𝐐𝐮𝐚𝐥𝐢𝐭𝐲 𝐂𝐨𝐧𝐭𝐫𝐨𝐥 𝐚𝐭 𝐭𝐡𝐞 𝐄𝐝𝐠𝐞
Cameras inspect every product.
Edge AI flags visual defects without ever uploading a frame to the cloud.
In the latest episode of the AI in Manufacturing podcast, I sat down with Rainer Maidel, Business Development Manager at BE.services GmbH, the creators of Coligo Edge AIoT Software. We had an in-depth discussion about the application of Edge AI in the digitalization of industrial processes.
The first foundation model purpose-built for refining and petrochemicals?
Here's the thing.
The oil, gas, and petrochemical industry is under pressure like never before.
⇨ Demand is set to double in 15 years
⇨ Facilities are shutting down
⇨ Energy transition is colliding with operational cost realities
At the same time, companies are being told AI will solve it all.
But here’s the truth.
Most AI was built for the internet, not industrial plants.
❌ It can’t explain its decisions
❌ It hallucinates
❌ It’s fragile with messy, real-world data
❌ It struggles with incomplete time series and unstructured reports
Now apply that to a refinery running 24/7, filled with volatile compounds and extreme conditions.
And you start to see the problem.
AI that can’t be trusted is worse than no AI at all.
That’s why Callum Adamson and his team built Orbital. The first foundation model designed specifically for refining and petrochemicals.
Instead of trying to stretch general-purpose AI into high-consequence environments, Orbital is:
✅ Purpose-built
✅ Physics-aware
✅ Production-grade
But more importantly, it takes a Tri-Modal Architecture that combines the following into federated intelligence:
1. 𝐓𝐢𝐦𝐞 𝐒𝐞𝐫𝐢𝐞𝐬 𝐌𝐨𝐝𝐞𝐥 – For signals and sensor data
2. 𝐏𝐡𝐲𝐬𝐢𝐜𝐬-𝐁𝐚𝐬𝐞𝐝 𝐌𝐨𝐝𝐞𝐥 – For real-world grounding
3. 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥 – For intuitive interaction and explanation
In the latest episode of the AI in Manufacturing podcast, I sat down with Callum, who is the Co-Founder and CEO of Applied Computing, to discuss the application of Superintelligenece in Oil, Gas, and Petrochemicals.
Part traceability in manufacturing has long relied on traditional barcodes that fail where it matters most: under heat, blasting, and coating, e.t.c.
As a result, manufacturers normally place barcodes after key part transformations.
That means, for 70%+ of the production process, you're flying blind. You're guessing which parts went through which treatments.
And when something fails? You're looking at massive recalls, supplier penalties, and lost time.
What if we could code physical parts in a way that never fades?
That’s exactly what Serra Tuzcuoglu and her Co-Founder invented. CDOT AI Code, a frequency-based, AI-readable identifier that can survive the harshest industrial conditions.
Unlike traditional visual patterns, it uses signal recognition instead of contrast, enabling it to be read even when surfaces are scratched, painted, or distorted.
A global appliance manufacturer gave them a challenge: “If your code can survive enamelling and high heat, we’ll use it.”
It did. That was the beginning. CDOT AI Code Code is now deployed globally, from Renault crankshafts to Ford EV battery trays, military tanks to printing cylinders.
In the latest episode of the AI in Manufacturing podcast, I sat down with Serra Tuzcuoglu, the CEO and Co-Founder of COSMODOT, to discuss:
✅ How CDOT AI Code works
✅ Solution Architecture & Integration into the factory network
✅ Readiness for AI-based quality analytics and creation of digital twins.
✅ Real-world examples and Case Studies
Learn how Jonathan and his team at Albemarle Corp went from pilots to $150M in annual improvements through a business-first, scalable AI strategy.
In the latest episode of the AI in Manufacturing podcast, I spoke with Jonathan Alexander, Global Manufacturing AI and Advanced Analytics Manager at Albemarle Corporation, about building, scaling and sustaining AI-driven Transformation in Manufacturing.
Here’s the outline of our conversation:
⇨ Key Data Challenges in Implementing AI at Scale
⇨ Data Contextualization for Analytics and Decision Making
⇨ Data Architecture & Interoperability
⇨ Standardization & Scaling of AI Applications
⇨ Driving Sustained Action from AI Insights
⇨ Sustaining AI Adoption & Value Creation on the Plant-Floor
⇨ Change Management & Culture
Industrial teams still rely on fragmented and manual processes to match complex product specs with use-case-specific needs.
Take this example:
You're selling a vision sensor to a factory. To get it right, you need to know:
⇨ What’s the size and speed of the conveyor line?
⇨ Is the plant located in Munich or Arizona?
⇨ Will this sensor withstand that temperature range?
⇨ What PLC is the customer using — Siemens or Rockwell?
⇨ Will the sensor integrate without conflict?
⇨ Are there newer models in the portfolio that fit better?
⇨ Can it be installed without disrupting production?
Now imagine trying to answer all of that...
⇨ Using PDFs.
⇨Email chains.
⇨ Gut instinct.
⇨ And hoping Bob from Engineering isn’t on vacation.
With an AI Agents trained on your connected industrial knowledge:
✅ All technical documentation, manuals, spec sheets, CAD drawings, becomes queryable
✅ Reps and engineers can ask natural-language questions and get verified answers
✅ Compliance, compatibility, and environmental fit can be checked in seconds
✅ Human experts stay in the loop, but no longer stuck in the weeds
I recently sat down with Fay Goldstein Co-Founder and CEO of Folio to discuss the application of AI Agents for Industrial Sales and Application Engineers.
ABOUT FOLIO:
Folio’s AI platform empowers industrial sales and application engineers by turning technical specs, configuration data, and application info into instant answers, recommendations, and agentic workflows, speeding work, cutting errors, and boosting revenue for industrial manufacturers and distributors. Learn more at www.folio.build
ABOUT FAY:
Fay Goldstein is the Co-Founder and CEO of Folio, an AI-powered platform that transforms how manufacturers and distributors sell and support complex and technical industrial product portfolios. Before founding Folio, she spent her summers managing direct and online sales at local automotive AC condenser and compressor shop, led strategic GTM and communications at an automotive telematics data company, and worked at an early-stage venture capital firm, where she supported dozens of early-stage startups on their initial GTM and communication strategies. Fay graduated magna cum laude from Florida International University and holds an MBA from Reichman University.
CONNECT WITH FAY
🌐 Website: https://www.folio.build/
💼 LinkedIn: https://www.linkedin.com/in/faygoldstein/
In theory, AI should learn, adapt, and improve continuously. But in reality, most deployments are static and disconnected from the evolving complexity of shop floor operations.
Most businesses lack tools to close the loop between:
⇨ Data collection
⇨ AI training
⇨ Deployment
⇨ Continuous retraining
⇨ Business impact validation
And they struggle to connect domain experts with data scientists.
To learn more about building and scaling closed-loop AI for industrial operations I recently sat down with Dr. Nikita Golovko who is a Software Architect for Industrial AI at Siemens.
Many small and mid-sized manufacturers want to explore AI to improve efficiency, reduce waste, or make their processes smarter.
However, this process requires OT and IT knowledge not present in many
industrial companies, mainly SMEs.
Ander Garcia Gangoiti and his team built a micro-service edge architecture based on MQTT, TimescaleDB, Node-Red and Grafana stack to ease the integration of soft AI models into industrial system.
The architecture has been successfully validated controlling the vacuum
generation process of an industrial machine.
Soft AI models applied to real-time data of the machine analyze the vacuum value to decide when the most suitable time is:
⇨ to start the second pump of the machine,
⇨ to finish the process, and
⇨ to stop the process due to the detection of humidity.
Ander is the Director of Data Intelligence for Industry at Vicomtech and I recently sat down with him on the AI in Manufacturing podcast.
Imagine a control system that learns, optimizes in real-time, and integrates seamlessly with both field assets and cloud-native AI platforms.
This is the next chapter of industrial process automation.
Already implemented at the largest Oil refinery in the world, Software-defined control systems break the traditional link between hardware and logic.
This separation allows for dynamic control, centralized intelligence, and flexible deployment across complex industrial environments.
When integrated with time-series foundation models, these systems harness AI for intelligent loop control, advanced process optimization, and even reinforcement learning, driving unprecedented levels of performance in control environments.
In the latest episode of the AI in Manufacturing podcast, I sat down with Huize Zhang to explore this transformation. Huize is the Vice President at SUPCON, China’s leading DCS provider, and the founder of FREEZONEX, an open-source IIoT platform.
Here’s the outline of our conversation:
-The Control Platform of The Future
-Open Standards and Platforms
-AI-Driven Optimization in Process Industries
-Time-Series Pre-Trained Transformers
-Reinforcement Learning in Process Industries
-UNS Integration with AI Agents
In manufacturing, time-series data is everywhere, but most plants are still relying on static dashboards, lagging insights, and manual root-cause analysis.
The result?
- Downtime that’s explained, not prevented
- Insights that arrive, after the line slows down
- Human effort wasted on repeat investigations
AI agents transform the way manufacturers harness time-series data.
They process live sensor feeds while simultaneously referencing historical records, enabling instant anomaly detection and context-aware decisions.
They can correlate vast time-series data with external factors to uncover insights missed by rigid statistical models.
They can trigger actions like maintenance tickets or production adjustments directly from analytics, bypassing manual interpretation steps.
They connect the dots across thousands of data streams in real time, automatically identifying root causes and recommending actions on the fly.
In the latest episode of the AI in Manufacturing podcast, I sat down with Jeff Tao to learn more about the application of AI Agents for Advanced Time Series Data Analytics. Jeff is the CEO and Founder of TDengine, the developers of TDengine an IIoT time-series database, TDgpt time-series AI Agent, and TDtsfm, a Time-Series Foundation Model.
Learn how Joao and and team are using Knowledge Graphs and IIoT to power Industrial AI and Digital Twin use cases at Scania.
Here’s the outline of our conversation:
- Core Challenges in Managing Industrial Data for Data‑Driven Manufacturing
- The Role of Ontologies and Knowledge Graphs in Advancing Industrial Data Interoperability and Analytics
- IIoT Data Integration and Standardization Approaches
- Semantic‑Modeling Best Practices for Scaling Value Creation
- Using Knowledge Graphs as Infrastructure for Digital Twins and Industrial AI
- Industrial AI Use Cases Powered by Knowledge Graphs
- The Real Business Value of Digital Twins in Manufacturing
- Building the Next-Gen Digital Twins with AI, LLMs, and Knowledge Graphs
- AI Agents, and MCP for Distributed Intelligence on Digital Twins
- Multi-Agent AI Systems for the Future of Manufacturing Digitalization
As manufacturing demands increase, integrating AI-powered visual systems into quality inspection processes becomes increasingly beneficial.
While traditional inspection methods have been the cornerstone of quality control in manufacturing, they come with limitations such as subjectivity, fatigue, and scalability challenges.
AI-powered visual inspection systems address these issues.
Leveraging advanced algorithms and machine‑learning models, they analyze images with high accuracy, identifying defects that may be invisible to the human eye.
This not only enhances the reliability of quality assessments but also increases operational efficiency, allowing manufacturers to streamline their processes and reduce costs.
The capability to detect anomalies in real-time empowers companies to address issues before they escalate, ensuring that only the highest-quality components progress through production.
To find out more about the application of Visual AI Inspection in manufacturing, I recently sat down with Priyansha Bagaria who is the Founder and CEO of Loopr AI.
Modern manufacturing environments generate a staggering amount of data from machines, processes, quality checks, logistics, and inventory. And yet, most of it goes unseen, unused, and unanalyzed.
Why?
Because the data is too vast, too fast, and too fragmented for any human to handle in real-time.
Even the best engineers can’t monitor thousands of variables 24/7.
And failing to harness this data has real consequences. Critical warning signs of equipment problems or process inefficiencies can be missed, leading to unplanned downtime and quality issues.
The biggest challenge AI Agents solve in industrial enterprises is transforming this overwhelming amount of complex data into actionable intelligence.
However, AI Agents are only powerful for manufacturing data analytics when paired with the right context.
That means feeding them, sensor data, maintenance logs, ERP & MES records, operator notes, engineering drawings, and SOP documents e.t.c. And quickly surfacing the most relevant information to power rapid AI-driven decision-making.
This is where Vector Storage and Search comes into play.
To learn more about Vector Databases and Data Structure for Industrial AI Agents I had a chat with Humza Akhtar, PhD who is the Senior Industry Principal for Manufacturing and Automotive at MongoDB.
Every minute a machine is offline costs money. That’s why Mean Time to Repair (MTTR) is one of the most vital metrics in manufacturing.
It tells you how fast your team can identify an issue, find the solution, and get the line moving again.
Unfortunately, in many facilities, this process is slow and cumbersome: when a technician sees an error code, they often have to sift through hundreds of pages of documentation while the clock is ticking.
A long MTTR doesn’t just mean downtime; it means:
- Lost production
- Missed delivery deadlines
- Heightened stress on frontline teams
- Frustration for leadership and customers
By using Generative AI to access your entire library of manuals, maintenance logs, and SOPs, maintenance teams can quickly find the answers they need and take swift action to minimize downtime.
To learn more about Reducing Machine Downtime with AI-Powered Knowledge Management I had a chat with Jose Dos Santos, Co-Founder and CEO of Industrial AI
For decades, manufacturers have relied on traditional analytics—correlations, trendlines, dashboards—to make operational decisions. But there's a limit:
Correlation ≠ Causation
Just because two variables move together doesn’t mean one causes the other.
This blind spot can lead to poor decisions and surface-level fixes that don’t solve the real issue.
For example, a machine’s temperature spikes often coincide with defects. Traditional analytics might alert you when it happens—but not why. Is it the temperature? A faulty sensor? Operator error?
Causal Inference flips the script. Instead of just observing data patterns, it asks:
“What actually caused this outcome?”
I recently sat down with Daniele Gamba, CEO of AISent Srl to learn more about building industrial intelligence solutions with Caussal AI.
Manufacturing leaders are familiar with physical waste; scrap, rework, and inefficiencies in production.
But digital waste is the hidden inefficiency that’s just as costly. It includes:
𝐔𝐧𝐮𝐬𝐞𝐝 𝐃𝐚𝐭𝐚: Factories generate massive amounts of data, but much of it is never analyzed or leveraged for decision-making.
𝐈𝐧𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐭 𝐃𝐚𝐭𝐚 𝐇𝐚𝐧𝐝𝐥𝐢𝐧𝐠: Engineers waste time manually entering, cleaning, or searching for information that should be automated.
𝐒𝐢𝐥𝐨𝐞𝐝 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧: Key insights are trapped in different departments or legacy systems, preventing AI-driven optimization.
Digital waste silently drains resources, increasing operational costs while blocking AI from delivering its full potential.
Once manufacturers recognize digital waste, the next step is identifying where AI can generate the biggest returns.
To learn more about finding opportunities for the application of AI in manufacturing, I recently sat down with Patrick Byrne, Co-Founder and CEO of Annora AI.
Manufacturers are constantly battling two critical challenges:
Inefficiencies in Equipment Usage: Downtime, slow cycle times, and unidentified bottlenecks reduce Overall Equipment Effectiveness (OEE), leading to wasted resources and missed production targets.
Safety Risks: Ensuring worker safety while maintaining productivity is difficult, especially in environments with heavy machinery and fast-moving processes.
Despite best efforts, traditional methods struggle to keep up with the complexity and speed of modern manufacturing.
By using computer vision and deep learning, Video AI Agents bring continuous, detection and response of issues—far beyond what traditional methods alone can achieve.
I recently sat down with Karim Saleh, Co-founder and CEO at Cerrion to learn more about how to Maximize OEE and production Line Safety with Video AI Agents
AI’s success in manufacturing depends on the ability to seamlessly integrate data from machines and systems across the factory floor and supply chain.
Without strong connectivity, AI remains underutilized, limited by data silos, and inconsistent integration.
Connectivity isn’t just about linking devices; it’s about creating a unified data environment where AI can operate at its full potential—powering everything from predictive maintenance to automated quality control and beyond.
To learn more about IT/OT connectivity for enabling AI use cases in manufacturing I had a conversation with Bernd Hafenrichter who is the CTO of soffico GmbH.
Frontline workers are the backbone of manufacturing, but they’re often held back by manual data entry, process inefficiencies, and knowledge gaps.
AI-powered Industrial Copilots offer a solution that elevates their capabilities:
𝐍𝐨 𝐌𝐨𝐫𝐞 𝐌𝐚𝐧𝐮𝐚𝐥 𝐃𝐚𝐭𝐚 𝐄𝐧𝐭𝐫𝐲
AI Copilots automate data capture and seamlessly integrate with existing systems—eliminating wasted time and inaccuracies.
𝐒𝐦𝐚𝐫𝐭𝐞𝐫, 𝐅𝐚𝐬𝐭𝐞𝐫 𝐖𝐨𝐫𝐤𝐟𝐥𝐨𝐰𝐬
AI surfaces real-time insights, helping teams reduce downtime, optimize production, and make data-driven decisions on the fly.
𝐂𝐥𝐨𝐬𝐢𝐧𝐠 𝐭𝐡𝐞 𝐄𝐱𝐩𝐞𝐫𝐭𝐢𝐬𝐞 𝐆𝐚𝐩
AI-driven step-by-step guides provide instant troubleshooting and best practices, ensuring even new employees perform like seasoned experts.
𝐒𝐜𝐚𝐥𝐢𝐧𝐠 𝐎𝐩𝐞𝐫𝐚𝐭𝐢𝐨𝐧𝐬
As operations grow, AI Copilots adapt to new processes, machinery, and industries, ensuring a future-proofed approach to efficiency and innovation.
To learn more about the application of AI Copilots for enhancing Frontline Operations in Manufacturing, I had a chat with Mason Glidden Chief Product and Engineering Officer at Tulip Interfaces.
Many factories today grapple with recurring production issues and inefficiencies; whether it’s inconsistent quality, unpredictable downtime, or process bottlenecks.
The cost of inefficiencies keeps mounting, and while human intuition and manual checks have been valuable tools, they’re no longer enough to drive significant breakthroughs.
AI offers an opportunity to uncover hidden patterns that human teams might miss. For instance:
- By analyzing machine sensor data, AI can trace yield drops to subtle temperature fluctuations.
- AI can identify bad material batches from suppliers or reveal operational bottlenecks.
- Instead of vague reports, AI delivers precise, actionable insights, helping teams shift from guesswork to targeted, data-driven solutions.
To learn more about how Manufacturers can achieve operational excellence through data-driven manufacturing optimisation with AI, I had a conversation with Zhitao(Steven) Gao who is the CEO and Co-Founder of eXlens.ai.
While the promise of AI is immense, many manufacturers find themselves stuck in pilot projects, unable to unlock its full potential.
The key lies in addressing foundational challenges and adopting a clear, phased strategy to transform operations.
Fundamentally, AI offers manufacturers a pathway to achieving operational excellence by moving through the four stages of analytics maturity:
1️⃣ Descriptive Analytics – Understanding what happened.
2️⃣ Diagnostic Analytics – Pinpointing root causes.
3️⃣ Predictive Analytics – Forecasting potential equipment failures or quality issues.
4️⃣ Prescriptive Analytics – Recommending the best actions to address challenges.
Despite its promise, many manufacturers struggle with significant obstacles, which include data fragmentation.
I recently had a sit down with Andrew Scheuermann the CEO and Co-Founder of Arch Systems to discuss why building a comprehensive Digital Twin is the key to overcoming these barriers and how manufacturers can use AI to enhance manufacturing workflow efficiency.
In our latest episode of the AI in Manufacturing Podcast, I sat down with Zeeshan Zia, co-founder and CEO of Retrocausal, to dive deep into how AI co-pilots are transforming the manufacturing sector. Here are three key takeaways:
1️⃣ Labor Challenges Meet Smart Solutions
- Manufacturers face critical labor shortages, resulting in significant costs. Zeeshan shared how AI-powered Assembly Co-Pilots are slashing error rates and scrap costs by up to 90% while empowering workers with real-time guidance.
2️⃣ Merging Lean Principles with AI
- Traditional lean manufacturing focuses on quality, productivity, and safety. RetroCausal’s tools like Kaizen Co-Pilot and Ergo Co-Pilot seamlessly integrate lean methodologies with advanced AI, accelerating time studies and ergonomic assessments in hours instead of weeks.
3️⃣ Scalability Across Diverse Workflows
- From discrete manufacturing to medical devices, AI co-pilots are not just for single processes—they scale efficiently across multiple sites, even in highly regulated industries.
Today's manufacturing industry faces significant challenges in managing its data environment.
Vast amounts of unorganized data collected from various sources often become "data swamps," making it difficult to extract meaningful insights and generate value.
This overwhelming complexity hinders decision-making and slows down innovation.
Additionally, the analytics tools currently available are often too complex and static for domain experts to use effectively, leaving them without the critical insights needed to improve processes, optimize production, and make informed decisions.
AI assistants offer a promising solution by bridging the gap between complex data sets and user-friendly interfaces.
They transform unstructured data into actionable insights accessible to everyone in the organization.
To learn more about the application of AI assistants for advanced manufacturing data analytics, I sat down with Stefan Suwelack, the CEO and Co-Founder of Renumics.
In this episode, we explore how artificial intelligence is transforming manufacturing from the ground up. We dive into cutting-edge applications and discuss the benefits and challenges AI introduces to the industry.
Here’s a sneak peek at what we cover:
-
Predictive Maintenance for Machinery
-
AI helps manufacturers predict equipment failures before they happen, reducing downtime and saving costs. With predictive maintenance, companies can transition from reactive to proactive maintenance, leading to longer machine life and fewer unexpected breakdowns.
-
Quality Control and Defect Detection
-
AI-powered visual inspections now identify defects faster and more accurately than human inspectors, ensuring product consistency and quality. We discuss how AI-driven quality control is reducing waste and improving overall customer satisfaction.
-
Supply Chain Optimization
-
AI tools are optimizing supply chains by predicting demand and adjusting inventory accordingly. In the episode, we break down how smarter supply chains are helping manufacturers avoid bottlenecks and reduce delays, especially during unpredictable market conditions.
-
Enhanced Worker Safety
-
From monitoring working conditions to analyzing data for potential hazards, AI is making factory floors safer. Learn how wearable technology and smart sensors are helping manufacturers reduce workplace injuries and improve employee well-being.
-
Energy Efficiency and Sustainability
-
AI is enabling manufacturers to cut down on energy usage and reduce their environmental footprint. This is a critical step as companies aim to meet sustainability goals and reduce costs.
🎧 Tune in to the full episode to discover how AI is reshaping the future of manufacturing—and what it means for businesses aiming to stay competitive.
While large language models hold immense potential, there's a significant gap between what these tools offer out of the box and what the manufacturing industry needs.
Manufacturing presents unique challenges that generic AI solutions often can't effectively address.
However, by customizing Generative AI systems to meet industry-specific requirements, this gap can be effectively bridged:
-
Tailoring AI to understand specialized language and scenarios enhances its relevance and effectiveness.
-
Integrating additional data sources, such as knowledge graphs, enriches the AI's understanding of relationships and processes unique to manufacturing.
-
Implementing safety checks and operational boundaries ensures that AI recommendations are viable, safe, and compliant with industry standards.
When these measures are in place, Generative AI becomes a powerful tool applicable to a wide range of use cases.
Tune in to the full episode with Vlad Larichev, the Industrial AI Lead at Accenture Industry X to learn more about Generative AI Use Cases in Engineering and Manufacturing.
In this episode, I sat down with Michael Kuehne-Schlinkert, CEO of Katulu to discuss how Federated Machine Learning is transforming industrial AI.
Here are some key takeaways:
Federated Learning Enables Cross-Factory CollaborationFederated learning allows multiple factories to improve AI models without sharing sensitive data. By exchanging learnings, factories can build more robust models while maintaining data privacy and compliance.
Collaboration on Model Training Without Compromising PrivacyOne of the biggest challenges in industrial AI is accessing the right data without compromising privacy. Federated learning addresses this by keeping sensitive data local, allowing companies to enhance their AI models collectively without exposing each other’s proprietary or sensitive information.
Cost-Effective Scaling of AI Models Through ReuseScaling AI across multiple factories typically involves high costs and complexity. Federated learning significantly reduces development, integration, and operation costs by allowing the reuse of models across different sites without duplicating efforts.
Steamlined Development of Predictive Maintenance and Quality Control ModelsFederated learning helps streamline the development of ML models for predictive maintenance and quality control by aggregating insights from multiple sites, reducing the need for extensive data science expertise and making advanced AI accessible to more organizations
Curious about how federated learning can scale industrial AI? Tune in to the full episode to learn more!
In the latest episode of the AI in Manufacturing podcast on Industry 4.0 TV, host Kudzai Manditereza sits down with Ashan Posohi, CEO and co-founder of Third Wave Automation, to explore how AI-powered robots are transforming material handling. The focus is on autonomous forklifts and their impact on productivity, safety, and the future of manufacturing.
Arshan Poursohi brings a rich background in robotics and research, having worked with Sun Microsystems, Google Research, and Toyota Research. His experiences exposed him to global labor challenges, such as aging workforces and a shortage of young people entering physically demanding jobs. Recognizing the urgent need to address these issues, Arshan founded Third Wave Automation to apply modern AI and robotics solutions to material handling in warehouses and manufacturing environments.
The Business Benefits of AI-Powered RobotsThe discussion highlights how AI and robotics are revolutionizing the manufacturing industry by automating "dull, dirty, and dangerous" tasks.
Key benefits include:
- Increased Productivity: Operators can manage an entire fleet of autonomous forklifts from a single workstation, significantly boosting the number of pallets moved per day.
- Enhanced Safety: By removing operators from hazardous environments, the risk of workplace accidents decreases.
- Immediate ROI: Third Wave Automation's as-a-service model allows companies to see immediate returns, with predictable uptime and reduced labor costs.
Shared Autonomy: A Unique ApproachThird Wave Automation introduces the concept of shared autonomy or human-in-the-loop machine learning. Unlike fully autonomous systems that aim for "lights out" operations, this approach keeps humans in the loop:
- Collaborative Operations: Robots perform tasks but can recognize when human intervention is needed, such as when a payload is precariously positioned.
- Continuous Learning: Human inputs help train the AI models in real-time, improving performance and adapting to new scenarios.
- User-Friendly Interface: Operators control robots using familiar tools like steering wheels and screens, making the system accessible even to those without advanced technical skills.
Real-World Impact: A Compelling Case StudyArshan shares a success story involving a customer who deals with large bags of powder prone to shifting—a challenge for automation due to safety concerns. Using shared autonomy, the autonomous forklifts learned to handle these unstable payloads safely and efficiently:
- Adaptive Learning: The AI models quickly adapted to recognize when human assistance was needed.
- Safety Assurance: Operators could intervene remotely, ensuring safe handling without halting operations.
- Productivity Gains: The customer saw immediate improvements in efficiency and safety, validating the effectiveness of Third Wave Automation's approach.
Listen to the full episode to learn more.
In this episode, I sat down with Yousef Mohassab, CEO of Facilis.ai, to explore how Agentic AI is transforming the manufacturing industry. If you're looking for practical insights on scaling AI and boosting operational efficiency, this is the episode you can't miss!
Here are the key takeaways:
The Shift from Centralized to Agentic AI Manufacturers can no longer afford to rely on centralized data science teams that create bottlenecks. Agentic AI empowers subject matter experts (SMEs) to directly access and analyze data, significantly cutting down response times from weeks to minutes.
A Human-Level Automation Approach Agentic AI mirrors human problem-solving by breaking down complex challenges into smaller tasks. This approach enables real-time, adaptive solutions that evolve with the operational landscape, especially when processes change or equipment gets upgraded.
Beyond Traditional Machine Learning Unlike static models that rely on historical data, self-adaptive systems continuously learn in real-time. This makes AI solutions more relevant to the current operational environment, minimizing the need for human intervention.
Real-World Applications and Results Youssf shared compelling use cases where agentic AI is deployed for quality monitoring, helping companies address shifts in product metrics faster and more effectively. Whether it's vibration analytics or yield optimization, the results are astonishing.
In this episode, I had the pleasure of interviewing Jonathan Wise, Chief Technology Architect at CESMII (Smart Manufacturing Institute).
We discussed how you can modernize your industrial data architecture to harness the full potential of AI, enhancing both production efficiency and innovation.
Jonathan highlighted three key pillars essential for AI readiness:
Data Accessibility - You can’t train AI without accessible data. Jonathan explains why ensuring your data flows seamlessly across systems is the first critical step.
Data Contextualization - Simply having data isn’t enough. Meaningful, contextualized data is crucial for any AI project to deliver accurate and actionable insights.
Data Relationships - It’s not just about isolated data points. AI thrives on the connections between data points, much like how your operations depend on the synergy between suppliers and internal systems.
Listen to the episode to learn more.
In this episode, we dive deep into the world of smart manufacturing with industry expert Nikunj Mehta from Falkonry. If you're curious about how data is transforming industrial operations and the future of maintenance and reliability, this episode is for you!
Here are some key takeaways:
82% of Failures Are Random
Nikunj explains that a staggering 82% of failures in industrial systems appear random. Without understanding their causes, manufacturers struggle to prevent them. This is where smart, data-driven actions come into play to improve decision-making and reduce failures.
Condition-Based Actions: A Game Changer
In manufacturing, decisions often rely on experience, which can take years to accumulate. Condition-based actions allow manufacturers to make smarter decisions without needing decades of experience. By detecting and acting on real-time conditions, manufacturers can optimize maintenance, improve quality, and reduce emissions.
Real-Time Data = Real-Time Decisions
From mining to steel production, the power of real-time data can revolutionize how we handle variations in materials, weather conditions, and equipment performance. Nikunj shares how timely insights enable proactive decision-making, reducing downtime and energy waste.
Smart Guidance Systems
Smart manufacturing requires systems that can analyze data in real-time and offer actionable guidance. Think of it like a GPS for your factory: these systems navigate complex production challenges and direct optimal actions for maintenance, quality control, and emissions.
What's Next for Smart Manufacturing?
Nikunj forecasts that the next step in manufacturing will be integrating smart guidance systems across various processes—from maintenance to quality assurance—allowing companies to move from reactive to proactive management.
In our latest podcast episode, I had the pleasure of speaking with Cyrus Shaoul, CEO of Leela AI, about visual intelligence and its transformative impact on manufacturing operations.
Here are some Key Takeaways:
1️⃣ Beyond Traditional Machine Vision
Unlike traditional machine vision systems that focus on product inspection, visual intelligence looks at the entire manufacturing process. It helps identify value-adding activities in real-time, ensuring operational excellence is met consistently.
2️⃣ Uncover Hidden Performance Insights
By integrating visual intelligence, companies can detect bottlenecks and wasted time during manual operations. In one case, Lila AI improved line capacity by 20% by identifying areas where standard operating procedures weren’t being followed.
3️⃣ Boost Safety & Compliance
With advanced monitoring, manufacturers can significantly reduce safety violations. One customer saw a 50% reduction in non-compliant events, leading to fewer accidents and a safer work environment.
4️⃣ Improving Quality Control
Visual intelligence doesn’t just ensure processes run smoothly; it improves quality control by catching invisible defects in real-time, boosting yields by 10%. This kind of proactive monitoring helps prevent costly mistakes that traditional methods might miss.
5️⃣ Faster, Data-Driven Decisions
With visual intelligence, data is constantly collected and analyzed, allowing teams to make real-time adjustments and enhance productivity, safety, and quality simultaneously. The ROI on this technology speaks for itself.
🎧 Tune in to hear the full conversation and explore how visual intelligence is reshaping the future of manufacturing.
In my latest AI in Manufacturing podcast episode, I had the pleasure of interviewing Peter, CEO of XMPRO where we discussed How to Build Intelligent Digital Twins with Generative AI.
Here are five key takeaways:
- Digital Twins Are Evolving: What was once just a static data model has now become anticipatory. Digital twins are now being embedded with AI, moving from being reactive (responding to issues) to proactive (predicting issues before they occur).2. Generative AI is Revolutionizing Business Processes: Generative AI models are not just helping manufacturers with personal productivity tasks like drafting emails—they’re driving large-scale process improvements. For example, EV manufacturers have used AI to reduce human involvement in generating specifications by 90%.3. The ‘Utility’ of AI is Like Electricity: Much like the railroads and electricity in the past, generative AI is creating a new utility that industries can tap into without needing to build their own models from scratch, unlocking countless business opportunities.4. The Rise of Multi-Agent Generative Systems: We’re now seeing the development of multi-agent systems where digital twins act as virtual employees. These agents can observe, reflect, and even recommend or take action based on real-time data, enhancing operational efficiency.5. Start Small and Scale: Peter emphasized not trying to "boil the ocean" when implementing new technologies. Begin with small, incremental changes that can demonstrate value and build out from there.
Peter Sorowka is a recognized expert in Industrial IoT and the technical architecture of data-driven industrial production. In 2015, he founded Cybus - a software company specializing in secure and governance-strong IIoT Edge and Smart Factory solutions.
As CEO of Cybus, he has been advising and guiding global enterprises towards decentralized, secure Smart Factory and data-driven Smart Services across various industries such as automotive and battery manufacturing, machinery and tool builders or metal processing.
Outline
Introduction to Infrastructure as Code for Industrial Digitalisation
IaC workflow for streamlining the deployment of industrial digital solutions
IaC for management of industrial software configuration
Balance between UI and DevOps for OT Engineers
What does High Availability and Scalability mean for OT?
Effective data governance strategy for digital transformation?
Cybus Connectware IaC architectural layout
Azure IoT operations vs HiveMQ and Cybus
IaC Case Studies
The Future of IaC
Had the pleasure of hosting Jim Gavigan on my latest podcast episode, where we deep-dived into "Data-Driven Optimization in Process Industries."
We discussed leveraging data for efficiency, the challenges of data quality, and choosing between foundational principles and cutting-edge ML algorithms.
Jim also highlighted the significance of tools and strategies in this sphere, emphasizing the urgency of digitizing domain knowledge in the face of an impending knowledge drain.
Jim, is the President and Founder of Industrial Insight, Inc. where he helps industrial companies turn data into actionable information to deliver tangible results for their organization.
Here is the outline of our conversation:
✅ Principles of Data-Driven Process Optimization
✅ Opportunities in data-driven optimization and use case
✅ Challenges faced by industries when implementing data-driven optimization strategies?
✅ Overcoming the hurdles of data quality and fidelity?
✅ First principles vs. Multivariate data analysis vs. ML algorithms?
✅ Evaluating readiness to effectively integrate AI/ML in process optimization
✅ Tech stack for data-driven optimization
✅ Impending knowledge drain, and capturing domain knowledge into digital tools.
By now, we're all aware of the profound impact Generative AI promises for manufacturing. Beyond just assisting engineers in application development, it equips managers with cutting-edge analytics and delivers invaluable error resolution insights to technicians, etc. - all through intuitive interactions.
That's why I'm excited about Tulip Interfaces' new "Frontline Copilot" which uses LLMs for natural language interaction between operators and manufacturing systems.
To truly comprehend its significance and the broader implications of Applied AI in manufacturing, I spoke with Roey Mechrez, PhD in my latest podcast episode.
Roey is the Head of AI and EMEA MD at Tulip Interfaces where he is overseeing Tulip's Machine Learning and Computer Vision strategy.
Here's the outline of our conversation:
Outline
✅ Introduction to the Tulip Ecosystem
✅ Composable, App-based solutions vs. Monolithic MES
✅ Tulip for Process Engineer, Operator, Manager End Users
✅ Technology stack for Modern Manufacturing
✅ Tulip Ecosystem for Applied AI in manufacturing
✅ Connecting shop-floor visuals to advanced analytics tools.
✅ How Data is Shaping the Next Layer of Manufacturing
✅ Tulip connectivity and AI integrations for building shop-floor solutions
✅ Introducing Tulip Frontline Copilot: Why Generative AI Matters for Manufacturing
✅ Natural Language Operator Interaction with Tulip Copilot, Use Cases
✅ Integrating legacy machine data into modern systems with Machine Learning and Edge Connectivity
✅ Computer Vision Capabilities and Third-party Integrations in the Tulip Ecosystem.
✅ Driving Forces for AI Adoption in Manufacturing
✅ The Future of AI in Manufacturing
For years, manufacturers have had to navigate in relative blindness, implementing improvements on an as-needed, reactive basis.
This approach, although functional, has been markedly inefficient and reactive, particularly in terms of process optimisation and asset reliability, two vital aspects of industrial operations that can profoundly impact efficiency and profitability.
Digital Twins represent a transformative shift from this reactive approach to a proactive, predictive one. They facilitate a deeper understanding of how systems behave, providing industrial operators with actionable insights that were previously unavailable.
To learn more about the application of digital twins in manufacturing, I had a podcast conversation with Erik Udstuen, who is the CEO and co-founder of TwinThread, a company that provides a digital twin platform that combines Industrial Data with Industrial AI in an integrated development environment for engineers and data scientists.
Here's the outline of our conversation
✅ Challenges driving Digital Twins adoption in modern manufacturing ✅ Key Functions of Digital Twins in Manufacturing ✅ Industrial AI Ops ✅ Use Cases for Asset and Process Digital Twins ✅ Connectivity standards for physical assets to digital twins ✅ Best practices for modelling assets and processes for digital twins ✅ Effective infrastructure abstraction techniques for Digital Twin Implementation ✅ ISA 88 / 95, and Data Modeling standards for Digital twins ✅ Principles-based vs Machine Learning-based modelling for advanced analytics ✅ Practical examples of successful digital twin applications in Manufacturing ✅ Selecting a digital twin platform and evaluating capabilities ✅ TwinThread Digital Twin Integrated development environment
DataOps for Digital Transformation In Manufacturing. In this episode, Kudzai Manditereza interviews Aron Semle, the CTO of Highbyte. HighByte is an industrial software company founded in 2018 with headquarters in Portland, Maine USA. The company builds solutions that address the data architecture and integration challenges created by Industry 4.0. HighByte Intelligence Hub, the company’s award-winning Industrial DataOps software, provides modeled, ready-to-use data to the Cloud using a codeless interface to speed integration time and accelerate analytics.
Outline ✅ What is DataOps, and Why is it relevant for Digital Transformation? ✅Key Steps of Implementing DataOps for a digital transformation strategy. ✅ The Role of DataOps in a Unified Namespace Architecture ✅Typical Data Sources for Integrating into DataOps Pipeline ✅ Effective practices for modeling, normalization, and contextualization of Industrial data. ✅ Data Modeling Standards for DataOps, Pros, and Cons ✅The role of MQTT and Sparkplug in a DataOps-based Strategy ✅ The role of OPC UA in DataOps Strategy ✅ DataOps for Historical Data in the Unified Namespace ✅ REST API for real-time and transactional data harmonization ✅ Best practices for DataOps deployment
As companies with industrial operations struggle to economically access data from intelligent devices located in remote and challenging environments, LoRaWAN presents itself as a cost-effective solution.
With the capacity to locally integrate industrial data and transfer it via a private LoRaWAN network over vast distances, LoRaWAN simplifies protocol conversion and enhances data recovery.
To learn more about the LoRaWAN for Industrial IoT applications I had a chat with Wienke Giezeman. Wienke is the CEO & Co-founder at The Things Industries, a scalable LoRaWAN solutions provider, and the initiator of The Things Network, the first crowdsourced free and open 'Internet of Things'
Here's the outline of our conversation.
✅ Introduction to LoRaWAN and The Things Stack ✅ Common LoRaWAN Use Cases in Industrial IoT. ✅ Typical architecture of a LoRaWAN solution for IIoT. What are the key edge components involved? ✅ Key considerations for designing a LoRaWAN wireless sensor network for IoT. ✅ Best practices for Integrating LoRaWAN data into IIoT Platforms and Controls Networks. ✅ LoRaWAN gateway and node selection. ✅ Security in LoRaWAN networks ✅ The role of MQTT and other IIoT protocols in LoRaWAN deployments. ✅ Enterprise and cloud integration capabilities of The Things Stack ✅ Emerging trends or features in the LoRaWAN space.
Digital transformation in manufacturing fundamentally involves transforming unprocessed data into valuable insights to guide business decisions through automated systems or human intervention.
Consequently, implementing a well-thought-out data modelling strategy is key to successful digital transformation as it helps to express the meaning of the data to digital systems.
To learn more about Data modelling for Industrial IoT in general and for Digital Twin use cases in particular, I had a podcast conversation with Erich Barnstedt.
Erich is the Chief Architect for Standards, Consortia and Industrial IoT in the Azure Edge and Platform team at Microsoft
Here's the outline of our conversation
✅ Importance of data modelling for Industrial IoT. ✅ Key Elements of an Effective IIoT Data Model ✅ Standardising Configuration Interface for OPC UA Connectivity Mapping ✅ Manufacturing Ontologies Reference Solution for Digital Twins ✅ UA Cloud Publisher and UA Cloud Twin for Mappping Industrial Assets to Azure Digital Twins using ISA95 ✅ Significance of UA Cloud Commander at the Industrial Edge ✅ OPC UA Information Model Integration using UA Cloud Library ✅ Data Modelling Standards ✅ Web of Things for Endpoint and Interface Description of Industrial Assets. ✅ ChatGPT for fully automating onboarding of non-discoverable industrial assets ✅ Converting proprietary interfaces into OPC UA Information Model using UA Edge Translator. ✅ The role of the IEC/ISO in standardizing data models for IIoT ✅ The Scope OPC UA PubSub Over MQTT in Industrial IoT ✅ Metadata and Type Information in OPC UA PubSub ✅ Industrial Metaverse Reference Architecture with Open Interoperability Standards
In the face of a rapidly evolving industrial landscape, agility and innovation have emerged as core drivers of growth. It is essential for manufacturers to adapt swiftly to changes, harnessing new technologies and embracing new processes that fuel their development. But achieving this level of agility and innovation is not without its challenges.
So how do organizations successfully navigate these hurdles to lay the groundwork for a meaningful digital transformation? To understand the complexities of implementing Industry 4.0 digitalization programs and a robust pathway to digital transformation I had a podcast conversation with Sandeep Sreekumar.
Sandeep is the Co-founder and COO of IndustryApps, a company focused on the Advanced Industrial data space and an Open Appstore for Industry 4.0.
Below is the outline of our conversation:
✅ Importance of agility in implementing Industry 4.0 digitalization programs.
✅ Key challenges organizations face when trying to implement agile digitalization processes.
✅ An Open Platform Strategy for open innovation in the context of Industry 4.0
✅ Scaling Governance and Compliance checks for Industry Apps
✅ Example use case of an Open Platform Strategy
✅ Scaling an open platform strategy across varying plants
✅ Industrial Data Space in Industry 4.0, and why is it critical for future business sustainability.
✅ Data modeling technologies for Industrial data space
✅ Ensuring security and privacy while leveraging the benefits of an Industrial Data Space
✅ Best practices to fully embrace the potential of Industry 4.0
In smart manufacturing, effective data collection and analysis are crucial. But to truly succeed, it's essential to integrate the coordination of personnel, equipment, and materials into the process.
For the factory worker, this would typically be through a series of digital nudges that guide their decision-making throughout the day, enabling them to work in harmony with smart machines for optimal results.
To discuss more the value and implementation of human-machine collaborative systems for smart manufacturing, I talked with Rafael Amaral.
Rafael is the CTO and Co-Founder of TilliT, a cloud-based digital operations platform that provides alternative approaches to traditional supply-chain management systems, MES platforms, and OEE software.
Below is the outline of our conversation.
✅ Opportunities for human-to-machine collaboration in manufacturing
✅ Benefits of effective orchestration of human-machine collaboration
✅ Assessing and redesigning processes to facilitate seamless human-machine collaboration.
✅ Connectivity Guideline for Real-Time updates
✅ Understanding human efficiency in influencing the operational value
✅ Identifying and resolving value-destroying behaviors on the shop-floor
✅ Impact of knowledge retention for digital transformation
✅ Selecting technology platforms for frontline workers
✅ Role of Unified Namespace in driving human-machine collaboration systems.
✅ Performance metrics and monitoring strategies for human-machine collaboration
✅ Deliver effective training programs to prepare frontline workers
✅ Case studies on implementing human-machine collaborative systems.
The Node-Red project turns ten this year.🎉
And yet, its remarkable potential remains largely untapped in the industrial software domain.
Having been a Node-Red user and promoter since its early days, I've observed that its preparedness for enterprise deployments is a key challenge limiting its broader adoption.
To discover the most effective strategies for deploying and managing enterprise-grade Node-Red applications in Industrial IoT, I invited Nick O'Leary for a podcast conversation.
As the co-creator of Node-Red and the CTO and Founder of FlowForge—a DevOps platform for Node-Red—Nick brought invaluable insights to the discussion.
Below is the outline of our discussion.
✅ Origins and Evolution of Node-Red
✅ Challenges and best practices for deploying Node-RED in Industrial environments
✅ DevOps for Node-RED in IIoT
✅ Key Features of Enterprise Ready Node-RED
✅ Best practices for industrial data acquisition using Node-Red
✅ Suitability of Node-Red for Semantic Modelling
✅ Node-Red vs Off-Shelf Solutions
✅ Use cases for Edge vs Cloud deployment of Node-Red
✅ Best Practices for Scaling Node-Red in large-scale IIoT deployments.
✅ Access control, data encryption, and authentication in Node-Red.
✅ Examples of successful IIoT projects using Node-Red
✅ The Future of Node-Red in Industrial IoT Applications
Digital transformation of a manufacturing enterprise is a complex process that goes far beyond simply sending data to the cloud and implementing “predictive maintenance”.
It requires a strategic architectural approach that effectively utilizes your data ecosystem to make informed decisions in real-time and drive innovation at every level of your organization.
While there are various architectural approaches, the Unified Namespace (UNS) stands out as the most effective approach to achieve optimal results and reap the full economic benefits of digital transformation.
The UNS serves as a critical building block for your overall strategy.
I had the pleasure of interviewing Walker Reynolds, the President of 4.0 Solutions, a renowned industrial IoT expert who introduced and popularized UNS. He provides a masterclass on understanding, implementing, and benefitting from the Unified Namespace approach.
If you'd like to gain a solid understanding of leveraging the Unified Namespace for your manufacturing enterprise, don't miss out on this valuable conversation.
Outline
✅ Origins and evolution of Unified Namespace
✅ A Description of the Unified Namespace
✅ Why MQTT is the de-facto protocol for UNS implementation
✅ The role of MQTT Sparkplug in UNS Implementation
✅ The role of OPC UA in UNS Implementation
✅ Workflow for designing a Unified Namespace for IIoT System
✅ Mapping physical assets and devices to a Unified Namespace, tools and techniques.
✅ Metadata definition for consistency and accuracy across different systems and devices in UNS
✅ How MES fits into UNS architecture, specific functions and capabilities
✅ Challenges and Mitigation strategies in implementing a Unified Namespace
✅ Impact of Industry4.0 Community Discord Platform
✅ Industry4.0 Influencer Lists
✅ Impact of ChatGPT on Digital Transformation
iot #iiot #industry40 #industrialiot #uns
In this latest episode, I explore the capabilities of OPC UA PubSub and how it can be integrated with Time Sensitive Networking (TSN) to standardize industrial field-level data transfer.
I speak with Melvin Francis, the Project Manager for OPC UA and TSN-related services at BE.services GmbH, to discuss the challenges faced in developing related applications due to the lack of ready-made OPC UA + TSN stacks or SDKs.
We also delve into the value of OPC UA + TSN integration and how it can address the requirements of time-critical industrial systems.
Furthermore, we explore the ongoing research project by BE Services, in partnership with Hochschule Offsberg University, the German government, and various hardware vendors, to develop a hardware and OS-independent low-footprint OPC UA + TSN SDK for wired and wireless TSN networks.
Below is the outline of our conversation.
✅ How Time Sensitive Networking (TSN) Works
✅ OPC UA PubSub + TSN Integration
✅ Low-footprint OPC UA PubSub TSN Architecture
✅ SDK Test Suite for low-cost testing ecosystem
✅ Practical Demonstration
The Unified Namespace has countless advantages over traditional architectural approaches when it comes to IIoT implementation in manufacturing.Some of these are:👉 More efficient communication and data sharing between different devices and systems.👉 Improved scalability due to a unified interface that is consistent across the entire enterprise network.But how do you go actually go about building a Unified Namespace Architecture?To gain an understanding of this, I invited David Schultz for a podcast session.David is the President of G5 Consulting where he works with manufacturers to help them develop and execute strategies for their digital transformation and asset management initiatives.Below is the outline of our conversation.✅ What is The Unified Namespace?✅ MQTT/Sparkplug for Unified Namespace✅ Tools and Strategies for Building the Unified Namespace✅ Data Normalisation and Contextualisation Techniques for UNS✅ Role and Significance of ISA 95 Schema in UNS✅ Using Multiple MQTT Brokers for a Unified namespace✅ Role played by Historian, MES, and ERP in UNS Architecture✅ Use Cases and Technologies for Data lake Integration with UNS✅ Approaches for Extending UNS with transactional Capabilities
When you look around a factory, you are likely to see objects interacting with other objects. And there are specific things that each object can do. It, therefore, makes sense that, in order to build autonomously reconfiguring factories, each object needs to be able to describe its capabilities to other objects so that they can interact with no human intervention. OPC UA Information Modelling is an effort to enable the description of complex industrial systems through a standardised and object-oriented interface. To gain a deeper understanding of how it works, I invited Jouni Aro for a podcast conversation. Jouni is the Chief Technology Officer at Prosys OPC Ltd, a leading provider of OPC and OPC UA technology with over 20 years of experience in the field. He's been the main architect for Prosys OPC UA SDKs and is an active member of the Technical Advisory Council and several working groups of the OPC Foundation. Below is the outline of our conversation ✅ What is OPC UA Information Modelling ✅ Benefits of Information Modelling for Industry 4.0 ✅ OPC UA Unified Object Model for Description of Complex Systems ✅ Tools for Building and Managing OPC UA information models ✅ OPC UA Companion Specifications, Custom Information Models ✅ OPC Cloud Library, Online Information Model Repository ✅ Workflow for integrating OPC UA Information Model into Products ✅ OPC UA Information Modelling in Industrial System Integration ✅ OPC UA Information Modelling and ISA95 ✅ OPC UA Information Modelling for Vertical Integration ✅ OPC UA Information Modelling for Horizontal Integration ✅ Is OPC UA Information Modelling Future-Proof? ✅ Information Modelling for OPC UA PubSub Over MQTT
Gaining competitive advantage is the main driver of innovation in nature as much as it is in technology. And the manufacturing ecosystem is no different. In manufacturing, this manifests in the deployment of production automation systems on the shop floor, and enterprise planning systems on the top floor. But yet, there's a grey area in between that has, for the most part, remained underutilised or wrongly implemented altogether. This is where a Manufacturing Execution System (MES) would live. To understand how manufacturers can gain a competitive advantage by leveraging a Modern MES Architecture for data-driven manufacturing, I invited Kevin Jones for a podcast conversation. Kevin is the CEO and Lead Strategist at Ectobox, Inc., a Manufacturing Intelligence Solutions company and Industry 4.0 systems integrator based in Pittsburgh, PA. Below is the outline of our conversation
✅ Drivers for Data-Driven Manufacturing ✅ Introducing MES for Manufacturing ✅ Functions of Manufacturing Execution Systems ✅ Selecting and Implementing an MES System ✅ Modern Manufacturing Execution System Architecture ✅ Problems with Current Manufacturing Data Systems ✅ Unified Namespace for Manufacturing Execution System ✅ Brownfield Integration into Unified Namespace Architecture ✅ The Future of MES in Manufacturing
I invited Maciek Wasiak for a podcast conversation on Predictive Analytics in Manufacturing and he delivered a masterclass. Maciek is the CEO and Founder of Xpanse AI, a company that develops technology that rapidly accelerates Data Science delivery by replacing manual data science with AI-driven processing Here's the outline of our conversation: ✅ Xpanse AI ✅ Introduction to Predictive Analytics ✅ Real-World Data Science Use Cases in Manufacturing ✅ Semiconductor Fabrication Predictive Analytics Solution Demo ✅ Traditional vs Automated Predictive Analytics ✅ Predictive Analytics Workflow Based on AI and ML ✅ Identifying and qualifying plant-floor data sources for Predictive Analytics ✅ Managing plant-floor data variety for Predictive Modelling ✅ Predictive Modelling Techniques ✅ Meeting plant-floor real-time requirements with ML Processes ✅ Role played by domain-level expertise in Predictive Analytics ✅ Role Played by Industrial System Integrators in Predictive Analytics implementation ✅ Working with AI and ML platforms for non data scientists
Whenever you're faced with information overload on any subject matter, as is the case with many manufacturers considering Smart Manufacturing, it's important to take a step back and understand its first principles. Without which it would be difficult and costly to realise the vision of Smart Manufacturing. To help bring the First Principles of Smart Manufacturing to light, I invited Conrad Leiva for a podcast conversation. Conrad is the VP of Ecosystem and Workforce Development at the Clean Energy Smart Manufacturing Innovation Institute, CESMII. CESMII is a US Government funded institute with a mission to democratise Smart Manufacturing and make its methodologies and technologies more affordable and accessible to SME manufacturers. Here's the outline of our conversation ✅ Clean Energy Smart Manufacturing Innovation Institute (CESMII) ✅ A Brief History of Smart Manufacturing ✅ Smart Manufacturing Definition and Description of Key Terms ✅ The Seven Principles of Smart Manufacturing ✅ Flat and Real-Time Principle ✅ Scalability Principle, Enabled by Cloud and Edge ✅ Interoperable and Open Principle, Information Modelling ✅ The Role of ISA 95 in Smart Manufacturing ✅ Proactive and Semi-Autonomous Principle ✅ Sustainable and Energy Efficient
More than anything else, the foundational power of personnel in fieldwork merely lies in the fact that we can see. By extension, it makes sense that the biggest impact on industrial digital transformation will come from embedding vision in intelligent connected components. More so when embedded vision and AI software are widely deployed in mobile and battery-powered field equipment. To learn more about building this capability into industrial products, I invited Taylor Cooper for a chat on the podcast. Taylor is the CEO and Principal Engineer at MistyWest where he's recently led the company in developing an Embedded Vision System on Module (MistySOM), based on the Renesas RZ/V2L processor, that enables the embedding of vision-based AI capabilities in field equipment. Below is the outline of our conversation. ✅ Misty West, Embedded Vision & IIoT ✅ Latest Trends in Industrial IoT, and Chip Shortage ✅ Google IoT Core Retirement, IoT Boom and Bust ✅ MQTT in IIoT and Computer Vision ✅ Delivering AI Capabilities for IIoT with Renesas RZ/V2L Based System on Module ✅ Potential Applications of Low Power System on Module in Connected Intelligence, ✅ Workflow for developing Embedded Vision for Connected Products ✅ AI versus Rules-Based Image Processing in Embedded vision ✅ Selecting Embedded Vision Middleware ✅ Selecting wireless connectivity for Embedded Vision Applications
Here's the thing. Containerisation is not only an IT technology, it is an advanced IT technology. And yet, it already looms on the horizon for Operations Technology. And, while the technology opens up massive opportunities for optimisation and efficiency in the OT network, it demands a fundamental rethink of industrial software distribution and management. To find out what this actually means for vendors, engineers, and system integrators in the industrial space, I invited Neil Cresswell for a conversation. Neil is the CEO and Co-Founder of a company called Portainer.io, the most popular Docker Container Management platform that abstracts the complexities of container management with a feature-rich and easy-to-use Graphical User Interface. Below is the outline of our conversation. ✅ What are containers? ✅ Benefits of containerisation at the Industrial Edge ✅ Challenges of adopting containers for Industrial Edge Compute ✅ Key differences between containerisation at the edge and in the cloud ✅ Containerization Approaches and Microservices for IIoT ✅ What is Portainer and How it Works ✅ Use Cases in Industrial IoT ✅ Portainer Products ✅ Reference Architectures for Managing software in OT ✅ Best Practices Containerisation at the Industrial Edge ✅ How a Containerised PLC functions ✅ Impact of Containerisation on Industrial System Integration ✅ The Future of Industrial Software Distribution
While there may be disagreements on what data modeling, encoding, and transportation technologies to adopt for Industrial IoT, there's one aspect that's evidently being agreed upon across the board. The fact that Publish-Subscribe architectures are, by far, more suitable for this new world of hyper-connectivity. One implementation of such an architecture for IIoT is OPC UA PubSub, which defines a mapping of Binary and JSON encoding over an MQTT, AMQP, and UDP-based PubSub network. To understand how OPC UA PubSub can be applied in Real-World Industrial scenarios, I had a conversation with Praveen Kumar Singh, who is the Chief OPC Solutions Architect at Utthunga, a Product Engineering and Industrial Solutions company that engineers industrial-grade digital products and solutions for industrial OEMs, Industries, ISVs, and Service Providers. Below is the outline of our conversation. ✅ What is OPC UA PubSub? ✅ Real World Applications of OPC UA PubSub ✅ Embedded OPC UA PubSub Applications ✅ Configuration Mechanism of OPC UA PubSub Components ✅ How Discovery works in OPC UA PubSub networks ✅ How Information Modelling Works in OPC UA PubSub ✅ Consuming OPC UA PubSub using Third Party Applications ✅ OPC UA PubSub over TSN explained ✅ Use Cases for OPC UA Client-Server combined with PubSub ✅ Sensor to Cloud Using OPC UA PubSub ✅ Security mechanisms in OPC UA PubSub communication ✅ uOPC PubSub Bridge overview ✅ About Utthunga
Advanced as they may be, modern analytics systems fall short of enabling the complete digital transformation of manufacturing enterprises. For example, instead of only detecting symptoms of impending machine failure, what would be more valuable would be to determine the actual cause of failure. Causal Machine Learning, a recent advance in ML holds the problem to solve this problem. To understand how it can be applied in Digital Twins to enable complete digital transformation for manufacturers, I had a conversation with Dr. PG Madhavan. PG has deep expertise in Data Science and extensive experience in advanced analytics development, both in industry and academia. Below is the outline of our conversation: ✅ Enthusiasm about Digital Twins Today ✅ Why Predictive Maintenance is not the Killer App for IIoT ✅ What is the central purpose of a Digital Twin? ✅ Challenges in Integrating Digital Technologies for DT Realisation ✅ Role of Industrial IoT in Digital Twins ✅ Machine Learning Methods in Digital Twins ✅ Application of Root Cause Analytics Method in DTs ✅ Application of Causality in Industrial IoT Data ✅ Key Steps to Digital Transformation in Manufacturing ✅ Manufacturing Digital Transformation through Digital Twins ✅ PyWhy, an open-source repository of AWS & Microsoft joint work in Causality for machine learning. ✅ Systems Analytics Solutions
Done right, the digital transformation of manufacturing enterprises has less to do with plugging in smart objects to collect data from the factory floor. Rather, it has a lot to do with laying down a reliable, secure, and scalable data processing infrastructure in such a manner that it allows you to automate your entire manufacturing business process. And for engineers and architects tasked with building IIoT solutions, it involves picking the right tools for each part of your data processing pipeline, from the edge of the network to systems at the highest level of your enterprise. To understand why and how to achieve that using open source tools, I had a conversation with Jeremy Theocharis who is the Co-Founder and CTO of United Manufacturing Hub, a company centered around an Open Source Project that combines state-of-the-art IT/OT tools to help engineers build Industrial IoT solutions. Here's the outline of our conversation which you can watch by clicking on the link below: Outline: Challenges in IT/OT Integration Introduction to United Manufacturing Hub (UMH) Why Open Source Matters Criteria for picking the core technologies for the UMH stack. Modernising Industrial Systems Architecture Using Microservices Why MQTT and Kafka for the IIoT Data Pipeline The role played by OPC UA in the UMH stack Unified Namespace Architectural Approach Factors influencing the design of the UMH DataModel Multisite Data Integration Using UMH Machine Vision Use Cases on the UMH Platform Historian vs Open-Source databases
By now, It's no longer up for debate whether artificial intelligence will permeate the industrial automation space as much as it has the commercial sector.
The biggest challenge, I'd imagine, is how do we build a robust enough nervous system that brings data to the AI agents at the industrial edge for processing, with unlimited horizontal scale.
To understand in-depth how that could work, I invited Angelo Corsaro for a chat.
Angelo is CEO and CTO at ZettaScale Technology, a company working to bring to every connected human and machine the unconstrained freedom to communicate, compute and store anywhere, at any scale, efficiently and securely.
Up until recently, Angelo was CTO at ADLINK Technology, a company that provides edge software and hardware for building and deploying Edge AI solutions, and it is from ADLINK where ZettaScale was "spinned-off".
Further, Angelo was one of the original members of the Data Distribution Service connectivity standard at the Object Management Group, where he was also a Member Board of Directors.
Below is the outline of our conversation to the linked video
Outline
Edge Computing as a Cloud-to-device continuum Benefits of intelligent edge computing in Industrial Automation Example Applications of AI at the Industrial Edge Challenges in building and deploying Intelligence at the Industrial Edge Edge AI Architecture for implementation in Manufacturing Approach for Big-Data Driven Edge-Cloud Collaboration in Industrial facilities High-Performance Real-Time Communication at the Edge using Eclipse Zenoh and Cyclone DDS OS Projects Integration of Eclipse Zenoh with MQTT ZettaScale, what it is, why it exists, and key concepts Security Threats and Countermeasures in Edge Computing for IIoT Architects The Role of 5G in Industrial Edge AI ZettaScale team and vision for the future of building industrial systems
Naturally, standard Ethernet does not guarantee real-time communication.
So, to provide guaranteed cycle times and latencies for machine control and process automation using Ethernet, vendors implemented real-time Fieldbus protocols on top of it.
Thereby creating a specialised type of Ethernet that is unusable for anything else, and causes fragmentation of industrial networks due to incompatibilities of Fieldbus protocols.
But yet, for the success of Industry 4.0, what is required is one type of Ethernet network that is usable for both, executing time-critical OT processes, as well as for non-time-critical collection of data from machines in a standardised and vendor-independent manner.
And this is what Time-Sensitive Networking (TSN) seeks to achieve.
To understand how TSN is able to solve these challenges and its combination with OPC UA, I had a conversation with Bhagath Singh Karunakaran
Bhagath is the CEO and Founder of Kalycito Infotech Pvt Ltd, India, an IIoT Software Solutions Company with Full-Stack device to cloud capabilities, and is a recognised thought leader in this space due to its pioneering effort to create an Open-Source ecosystem around OPC UA and TSN on real-time Linux. Including the world's first OPC UA Pub-Sub implementation.
You can watch our conversation below, and here's the outline:
✔️ What is TSN and how does it work ✔️ Advantages of TSN over traditional Industrial Ethernet networks. ✔️ Running Fieldbus Protocols on TSN ✔️ Core elements of TSN for achieving time-deterministic communication ✔️ Requirements for machines to participate in TSN network ✔️ Importance of achieving field-level communication using OPC UA ✔️ Combination of OPC UA with TSN ✔️ The role played by OPC UA over TSN play in Industry4.0 ✔️ OPC UA Pub-Sub over TSN for Sensor to cloud communication ✔️ Use cases of OPC UA over TSN in Manufacturing ✔️ Convergence of OPC UA over TSN and 5G for Industry 4.0 ✔️ Commercialised products implementing OPC UA over TSN ✔️ Open Source crowd-funded OPC UA and TSN project
As the saying goes, "Don't throw the baby out with the bathwater".
Many people in the manufacturing space are quick to dismiss Web 3, and justifiably, because of the recent sensationalism created around it by Big Tech.
And yet, Web 3 has the potential to massively impact how we build production systems. In fact, the success of Industry 4.0 lies, to some extent, in the enablement of decentralised peer-to-peer networking of factories, with decentralised storage, compute, and connectivity.
In any case, now that Web 3 has come to the fore, I decided to invite Rex St. John, a passionate advocate for Web 3, to discuss the Application of Web 3 in Industrial Edge Computing.
Rex has spent over a decade building developer relations programs at companies such as Intel, ARM, and NVIDIA, where he is currently building a global software ecosystem for NVIDIA Jetson.
Here's the outline of our discussion linked below.
✔️ What Web 3 Really is and its Key Drivers ✔️ How will Web 3 impact Industrial IoT in Manufacturing ✔️ Current challenges of Web 3 Application in Industrial Edge Computing ✔️ Architectural Approach for decentralizing compute, storage, and connectivity using Web 3 ✔️ Existing projects for decentralised compute, storage, and connectivity. ✔️ Subsidising hardware for Web 3 in Industrial Edge Computing ✔️ Practical Use Cases of Web 3 and Edge Computing in Industry ✔️ Distributed Training of Artificial Intelligence models using Web 3 ✔️ The future potential of Web 3 and Edge Computing in Industry
Another year has come and gone, and still, almost every IIoT use case in manufacturing requires some sort of compute capability near the source of the data in order to solve some of the toughest challenges in Manufacturing Digital Transformation.
But yet, the currently dominant model for Industrial IoT is the Cloud-Based Platform-As-A-Service.
The issue is, while Edge Computing architectures do provide immense power and capabilities such as system resilience through delegation of computational workloads to autonomous IIoT devices in Distributed Edge Computing, it brings with it implementation complexity in manufacturing enterprises.
So, to provide you with practical guidance on Edge Computing, Architectures, and the building blocks necessary for an Edge Computing implementation in manufacturing, I invited Dominik Pilat, who is the Vice President of Customer Support & Field CTO at Hivecell, and John Kalfayan who is the Vice President of Energy, also at Hivecell.
Hivecell is a complete Edge-As-A-Service solution that allows companies to process vast amounts of raw data from smart machines and IoT Devices in real-time, at the Edge. It is both a hardware and software solution that supports the most widely used platforms today such as Kubernetes and Apache Kafka.
Outline ✔️ Key Drivers for Deployment of Compute Capabilities at the Industrial Edge ✔️ Industrial IoT Edge Computing Technology Stack ✔️ Characteristics of Distributed Edge Computing Model for IIoT ✔️ Management and Monitoring of Edge Deployed Software ✔️ Data Governance in Industrial Edge Computing ✔️ Apache Kafka Deployment at The Edge for IIoT ✔️ How Edge Compute Enables AI at the Industrial Edge ✔️ Hardware for Running AI Applications at the Edge ✔️ Practical Use Case of Industrial Edge Computing and AI ✔️ Hivecell Edge As A Services Solution
I wish you all a prosperous 2022.
The biggest challenge in the transition to Industry4.0 lies in the horizontal and vertical integration of information flow within and across manufacturing organisations, and the digitalisation of the engineering processes involved.
Among the technologies and standards developed to enable this flow of information, is the compelling combination of AutomationML, OPC UA, and the Asset Administration Shell.
To discuss this combination, I talked with Dr. Miriam Schleipen, the Chief Research Officer at EKS InTec GmbH where she deals with semantic interoperability in automation ecosystems based on Digital Twins and their application in automation environments.
Miriam is head of the joint working group of OPC foundation and AutomationML e.V., leads the German Glossary Industrie 4.0, and participates in national and international standardization groups dealing with semantic interoperability for Industrie 4.0.
Outline:
✔️ Introduction to AutomationML and its role in Industry4.0 ✔️ Why and How AutomationML Integrates with OPC UA ✔️ Fundamentals of The Asset Administration Shell ✔️ Defining an Information Model Inside an Asset Administration Shell ✔️ Interrelation of the Asset Administration Shell and the AutomationML ✔️ Software Tools for Describing Models in AutomationML ✔️ Standardisation of the Asset Administration Shell ✔️ Benefits and Uses Cases of AutomationML, AAS, and OPC UA Combination ✔️ Best Practices for Implementing Asset Administration Shell Ecosystems ✔️ Role played by AutomationML, AAS, and OPC UA in Digital Twin Implementation ✔️ Distributed Digital Twins for Smart Manufacturing ✔️ AutomationML Association ✔️ EKS InTec GmbH
Perhaps the most common silos of information in Process Industries are the skilled workers who possess rare knowledge on how to optimise processes and maintain production equipment using traditional methods.
The good news is, the future of manufacturing is one where plant assets and operations have the capability to autonomously learn and self adapt in order to optimise processes with minimal human intervention, thereby freeing the skilled human resource for more value-added tasks. And that future has already begun!
To learn more about how Artificial Intelligence is currently being applied to solve problems in Process Industries, I invited Simon Rogers for a chat.
Simon is a Digital Transformation Consultant at Yokogawa in South Korea, where he helps Process Industries move from Industrial Automation to Industrial Autonomy by applying the latest digital technologies including Cloud Computing, IIoT, and Artificial Intelligence. He was previously the Vice-President of Digital Solutions at Yokogawa Headquarters in Japan, among many other previous roles at companies such as Honeywell, ABB, and KBC.
You can check out our full conversation on the video linked below.
Outline:
✔️ Importance of AI in Continuous Process Industries ✔️ Technologies Enabling Digital Transformation in the Process Industries ✔️ Benefits of Data-Driven Process Optimisation vs Traditional Methods ✔️ Using Natural language Processing for Industrial Data Management ✔️ Improving Safety and Reliability in Industrial Operations using Semantic AI ✔️ Applicability of Machine Learning in Process Simulation ✔️ Application of Digital Twins in the Process Industries ✔️ Common Use Cases of AI Application in the Process Industry ✔️ Current Challenges of AI Application in Process Industries ✔️ Future Potential of AI Application in Process Industries ✔️ The Shift from Industrial Automation to Industrial Autonomy ✔️ Yokogawa Electric Corporation - Process Automation and Digital Solutions
Based on the undeniable success of Advanced Data Analytics in Internet Companies, there's no doubt that manufacturers could reap massive benefits from adopting this "Data First' approach.
And for manufacturers, having this intelligent layer at the edge, closer to industrial data sources has proven to be more fitting and valuable.
To gain an understanding of the application of Edge Analytics for intelligent automation, I had a conversation with Martin Thunman. Martin is the CEO and Co-Founder of Crosser, a platform that was built with the realisation that low code edge analytics, automation, and integration software will play a critical role in accelerating the digital transformation journey of Industrial and asset-rich organizations.
You can check out the full conversation on the video linked below.
Outline:
✔️ Challenges in Industrial Legacy System integration with Industry4.0 technologies ✔️ Requirements for next-generation industrial system integration solutions ✔️ Edge Analytics and Opportunities it provides for Industrial Automation ✔️ Functional Composition of an Industrial Edge Analytics Solution ✔️ ISA95 vs Any-to-Any Hub Architecture ✔️ Data Modelling Best Practices for Edge Analytics Solution ✔️ Introduction to Edge Machine Learning Ops ✔️ Required Hardware and OS Capabilities for Edge Analytics ✔️ Crosser - Connectivity to Legacy Industrial Control Systems and Enterprise Applications ✔️ Crosser - Data Management and Orchestration ✔️ Common Uses Cases of Edge Analytics in Manufacturing ✔️ The future of Low Code Platforms in Industrial Automation ✔️ About Crosser
iot #iiot #industry40 #EdgeAnalytics
While IIoT protocols play a crucial role in communicating information from one industrial system to the next, the full value of IIoT can only be realised by standardising the vocabulary with which this information is communicated.
The MTConnect Standard offers such a semantic vocabulary for manufacturing equipment like Machine Tool Controllers, Robotic Arms, CNC Machines, etc. And more importantly, it integrates with other communication standards.
To understand how MTConnect works and its role in Industrial IoT, I had a conversation with Russell Waddell who is the Managing Director at the MTConnect Institute and is responsible for day-to-day business operations and standards development activity.
You can check out our conversation in the video linked below, and here's the outline:
✔️ Semantic Interoperability and its Benefits for IIoT ✔️ Introduction to MTConnect ✔️ Basics of MTConnect Information Model, ✔️ Components Required to Build an MTConnect System ✔️ Data Transportation Mechanism in MTConnect ✔️ Developer Support, Tools, and Frameworks for MTConnect ✔️ What Differentiates MTConnect from other communication standards ✔️ MTConnect Integration with OPC UA ✔️ MTConnect Use Cases ✔️ Security considerations in MTConnect ✔️ About The Association for Manufacturing Technology and MTConnect Institute
By nature, industrial facilities consist of physical assets and processes that evolve through time. Therefore, each data point generated by such systems is essentially a snapshot of events at that particular point in time.
By extension, this data wants to be stored in a way that reflects the sequential order of events, so that it can be rapidly queried and analysed, among many other reasons.
But yet, this isn't a capability that is inherently baked into the more common Relational and NoSQL databases. Hence the rise in popularity of Time-Series Databases for industrial Telemetry Data storage over the past few years.
At the forefront of this revolution is InfluxDB, an Open-Source Time-Series Database platform developed by InfluxData.
To understand how Time-Series Databases work, and InfluxDB in particular, I had a chat with Brian Gilmore who is the Product Manager for IoT at InfluxData.
Check out our full conversation in the video linked below.
Outline: ✔️ Characteristics of IIoT Data ✔️ Why Time-Series Databases Matter for IIoT ✔️ Common IIoT Use Cases for Time Series Database ✔️ How to Plan an IIoT Data Architecture ✔️ InfluxDB Time-Series DB Platform ✔️ InfluxDB - Open Source vs Cloud vs Enterprise ✔️ InfluxDB Time-Series DB Migration ✔️ InfluxDB Deployment Options ✔️ Acquiring Industrial Telemetry Data into InfluxDB ✔️ Industrial Telemetry Data Enrichment in InfluxDB ✔️ InfluxDB Integration with Analytics & Visualisation Platforms ✔️ Factory-Floor to InfluxDB Data Pipeline
The success of a fully realised Industry4.0 lies in the democratisation of intelligence and the capacity for Industrial "Things" to autonomously act based on the knowledge they have.
Effectively, turning each and every factory into a computer that is made up of modular processes within, in the form of Cyber-Physical systems.
And central to that success, is the ease with which Industrial things like pumps and sensors can be embedded with Machine Learning functionality.
To learn more about Embedded ML, I had a chat with Zin Thein Kyaw who is a Sr Success Engineer at Edge Impulse, a company on a mission to enable the ultimate development experience for machine learning on embedded devices for sensors, audio, and computer vision, at scale.
You can check out our conversation at the link below
Outline: ✔️ Integrating ML into industrial machines and sensors ✔️ Benefits of ML at the Edge of IIoT Network ✔️ Current applications of Embedded ML in industrial assets ✔️ Choosing an Embedded Processor for ML ✔️ Workflow for developing and deploying Embedded ML models ✔️ Integration of Edge Impulse with Tensorflow and Resource Optimisation ✔️ Industrial Data Collection and Data Availability ✔️ Application of Deep Learning in Industrial Systems ✔️ The Future of Embedded ML ✔️ The Edge Impulse Ecosystem & Developer Resources
As Industrial IoT matures, most of the components in the IIoT stack have become commoditised. Things like hardware, OSes, drivers, protocols, databases e.t.c
But yet, many organisations still develop custom interfaces for these components, instead of adopting standards. And in cases where there is adoption, there lacks an industry-wide consistent approach to standardisation.
To understand the importance of standardisation for IIoT and how vendors and end-users should engage standards, I had a conversation with Claude Baudoin.
Claude is the co-author of a recently published whitepaper on Global Industry Standards for IIoT by the Industrial Internet Consortium (IIC). He is the owner of cébé IT & Knowledge Management LLC, advisor to the OMG, IIC, and senior consultant at the Cutter Consortium.
Here's the outline of our conversation in the video linked below:
✔️ Importance of Standardisation for IIoT ✔️ Phases of a Standard Life Cycle ✔️ Standards Engagement Strategy ✔️ Identifying areas for standardisation ✔️ Adapting Open Standards to an Industrial Architecture ✔️ IIoT Connectivity Standards ✔️ Standards related to IIoT Security ✔️ Barriers to Agreeing on Standards and How to avoid building new silos ✔️ Building IIoT Solutions Vs Buying Off-The-Shelf Solutions ✔️ IIC in IIoT Standardisation ✔️ cébé
At the present moment, it is quite clear that the future of industrial automation will be driven by software. More so, that of IIoT.
And, due to the merits that have allowed it to dominate in the IT space, Open Source software is likely to lead the industrial software revolution. Regardless of the conservative nature of the industry.
To discuss the use of Open Source in building IIoT solutions, I had a conversation with Frédéric Desbiens.
Frédéric is the Program Manager for IoT and Edge Computing at the Eclipse Foundation, managing close to 50 Open Source projects under Eclipse IoT.
Here's the outline of the discussion.
✔️ Key Challenges for Implementing IIoT ✔️ Why Open Source Matters for IIoT Implementation ✔️ Key Components of an Industrial IoT Solution ✔️ Open Source Stack for IIoT Gateways ✔️ Open Standards for IIoT Data Aggregation ✔️ Why Semantic Interoperability Matters for IIoT ✔️ Real Value of MQTT Sparkplug to Implementers ✔️ Real Value of MQTT Sparkplug to End-Users ✔️ Is MQTT Sparkplug a Lock-In? ✔️ Open Source Digital Twin Frameworks and how they work ✔️ Open Source Software for IIoT Security ✔️ Role of Eclipse Foundation and Eclipse IoT
Nowadays, with so many IIoT concepts in the air, you can't help but breathe it in.
But sometimes it's helpful to take a step back and put all of this in context to understand how we got here, as that might help shed light on what IIoT is and isn't about.
To gain a fundamental understanding of OT-IT integration, I had a conversation with Benson Hougland.
Benson is VP of Product Strategy at Opto 22, a company that has been at the forefront of OT-IT integration for close to 30 years. From being a founding member of OPC to introducing the first Ethernet-based I/O Unit in the nineties, and more recently, introducing the first Edge Programmable Industrial Controller.
Below is an outline of our discussion in the linked video.
✔️ Why Should Manufacturers Care About IIoT? ✔️ Evolution of the IIoT Technology Stack ✔️ Open Technologies in IIoT ✔️ Principal Functions of an IIoT Edge Device ✔️ The Role of SCADA in an IIoT World ✔️ Brownfield and Greenfield Considerations for IIoT ✔️ Best Practices for IIoT Security ✔️ Critical Skills for IIoT System Integration ✔️ Integration of IIoT Solutions into Business Processes ✔️ Opto22
While it may be convenient to follow simple steps to get connectivity working for your IIoT solution, sometimes you are better off having an understanding of the elements that make up the broad spectrum of connectivity technologies.
To understand the foundations upon which IoT protocols are built, I had a conversation with Dominik Obermaier. Dominik is the Co-Founder & CTO of HiveMQ, a company that provides an MQTT broker and a client-based messaging platform to over 130 customers including many Fortune 500 companies for mission-critical use cases like connected cars, logistics, Industry 4.0, and connected #IoT products.
Dominik is also a member of the OASIS Technical Committee responsible for developing the MQTT specification, and he's also involved in the standardisation of Sparkplug.
Here's the outline of the discussion linked below:
✔️ IoT Connectivity Architectures ✔️ Data Encoding Mechanisms ✔️ COAP Protocol ✔️ AMQP Protocol ✔️ XMPP protocol ✔️ Fundamentals of MQTT Protocol ✔️ Plug and Play Interoperability Using Sparkplug B ✔️ Adoption of Sparkplug B in Manufacturing ✔️ #MQTT Broker Deployment Options ✔️ Kubernetes for High Availability MQTT Broker Deployments ✔️ Backend IoT Architecture for MQTT ✔️ #IIoT Security ✔️ MQTT Use Case in Smart Manufacturing ✔️ HiveMQ
Developed at LinkedIn in 2010, Apache Kafka - a stream processing engine, now powers web-scale Internet companies such as Netflix, Uber, Twitter, Airbnb, and more. Profoundly impacting real-time user experience.
Of equal impact, is its application in creating a continuous streaming pipeline of manufacturing data, from the factory-floor to data centers. Fundamentally changing the structural organisation of manufacturing systems.
To gain an understanding of Kafka in IIoT, I had a conversation with Kai Waehner. Kai is Field CTO and Global Technology Advisor at Confluent, a company that was founded by Kafka creators and is behind the open-source project.
Here are the contents of our discussion
✔️ Stream processing in Manufacturing ✔️ Apache Kafka and Its Role in IIoT ✔️ Kafka vs MQTT ✔️ Architecture Patterns for Kafka Deployments ✔️ Connectivity to Industrial Control Systems ✔️ Data Ingestion to enterprise Applications ✔️ Examples of Real-Time Streaming Analytics ✔️ Using Kafka as a Data Historian ✔️ Re-Engineering ERP Suites with Kafka ✔️ Using Kafka to Drive Machine Learning ✔️ Hybrid Kafka Deployments ✔️ Kafka as a Platform for the Digital Twin ✔️ Kafka's Role in Augmented Reality ✔️ Kafka Use Cases in Manufacturing ✔️ Confluent
So here's the thing, data from industrial sources is inherently messy. For example, a typical PLC system manages thousands of tags from both physical instruments and internal calculations, but this data is often unstructured, not linked to a unifying data model, and uses naming conventions that are vague to the outside world.
This makes data from such sources not readily usable in analytics applications and has led to the emergence of a new field of industrial data preprocessing for IIoT, called Industrial DataOps.
To discuss more on industrial DataOps, I had a conversation with John Harrington who is the Co-Founder of HighByte, a company pioneering this field with their HighByte Intelligence Hub.
Here some of the topics that we discussed.
✔️ What is Industrial IoT DataOps ✔️ Limitations of the Purdue Model/ISA-95 ✔️ The importance of Data Quality ✔️ Data Standardisation, Normalisation and Contextualisation ✔️ Best Practices for integrating industrial data silos ✔️ Principles of IIoT Data Modelling ✔️ How DataOps enforces privacy and security ✔️ HighByte Intelligence Hub
John has previously worked as the VP of Business Strategy at PTC, and he's also served as the VP of Product Management at Kepware Technologies.
Cliché as it may sound, data IS the new Oil. But, to fully reap the benefits, data needs to be properly collected and advanced analytics correctly applied to it.
To better understand the process, I had a conversation with one person who has close to 3 decades of building industrial data aggregation and advanced visualisation tools, Marcos Taccolini.
Marc is currently the Founder and CTO of Tatsoft, a platform developer for real-time factory-floor data monitoring, SCADA and HMI Systems, Distributed Data Aggregation, and Advanced Visualization Tools.
Below, is the outline of our conversation.
✔️Collecting Real-Time Data ✔️Collecting Enterprise Data ✔️Plant-Floor to Cloud Integration ✔️Integrating Structured and Unstructured Data ✔️Data Lakes for Plant-Floor Data ✔️MQTT Sparkplug B ✔️Role of OPC UA in IIoT Dataflow ✔️Real-Time Metrics Tracking ✔️Advanced Analytics Best Approach ✔️OEE Explained ✔️Plant-Floor Machine Learning Applications ✔️Operational Intelligence with the Digital Twin ✔️Tatsoft, FrameworX, and Factory Studio
Marc also previously served as the Founder of Indusoft, a provider of HMI and embedded intelligent device software, which was acquired by Invensys. He was also the co-founder of Unitec and Unisoft.
While the connectivity of industrial systems is the most important aspect of IIoT, there is currently a confusing mix of connectivity technologies and standards.
To understand IIoT Connectivity I had a conversation with Stan Schneider, who specialises in innovation where pervasive networking meets functional AI
Stan is CEO of Real-Time Innovations (RTI), the world’s largest software framework provider for smart machines & real-world systems such as power plants & autonomous vehicles
Here's what we discussed
✔️ Industrial Internet Connectivity Framework ✔️ Why Connectivity Technologies Don't overlap ✔️ Why Connectivity Wrappers Don't Work ✔️ Industrial Connectivity Stack ✔️ The Core Connectivity Standard Architecture ✔️ Data Distribution Service Explained ✔️ OPC UA vs DDS
RTI software runs over 1500 designs including the largest power plants in North America, the Canadian Air Traffic Control system, NASA's launch control system, nearly all Navy ships, GE Healthcare's hospital device networks, Siemens wind turbine farms, trains, & metro control systems, & over 250 autonomous vehicle designs
Stan holds a PhD from Stanford in Electrical Engineering & Computer Science with a focus on Autonomous Systems.
The success of IIoT in mission-critical applications depends on its ability to support local storage, compute, and connectivity for real-time responses, while sending selected data to the cloud for additional analytics. In short, Edge Computing
To gain a comprehensive understanding of Edge Computing, I sat down with somebody whose day job is strategising and executing at the intersection of 5G, Edge Computing, and the Internet of Things, Rob Tiffany
Rob is currently VP and Head of IoT Strategy at Ericsson
Here's what we discussed
✔️ Edge Computing Intro ✔️ Edge Computing Architecture Trends ✔️ Edge Computing Frameworks ✔️ Edge Analytics ✔️ Digital Twins in Edge Computing ✔️ Edge Solution Orchestration ✔️ Security Challenges & Solutions ✔️ Role of Edge Computing in 5G ✔️ Moab Foundation
Rob was previously, the CTO & Global Product Manager at Hitachi, where he created the Lumada IIoT platform. He was also the Global Technology Lead at Microsoft, where he was one of the co-authors of the Azure IoT Reference Architecture. Rob is the Executive Director of the Moab Foundation, a non-profit organisation working to create a more sustainable planet through the application of connected intelligence
Having a solid understanding of the key components of an IIoT architecture and how to integrate them is the most important aspect of building an IIoT application, both as an in-house solution and as a service offering
So, to help shed light on the principles of IIoT architecture design, I had a discussion with one person who is best positioned to speak on the subject, Rick Bullotta
Rick Co-Founded Thingworx, which is one of the first and arguably the most successful IIoT platform to date
Here's what we discussed
✔️ IIoT Architectural Patterns ✔️ Edge Computing ✔️ IIoT Gateway Selection ✔️ Integration Mechanisms ✔️ Communication Protocols ✔️ IIoT Security ✔️ Request-Response vs Publish-Subscribe ✔️ IIoT Platform selection ✔️ Avoiding Vendor Lock-In ✔️ Cloud to Cloud Integration ✔️ Effects of Data Residency ✔️ Private Cloud vs Public Cloud
Among other diverse roles, Rick previously served as Partner Director at Microsoft, where he helped define and drive Azure IoT Strategy. He was also previously CTO and Director at Wonderware, and he was a VP with SAP Research, focusing on future manufacturing. Rick was also the CTO and co-founder of Lighthammer Software Development
Digital Twins will, undoubtedly, transform how manufacturers build and maintain products. From consumer goods to complex structures such as buildings and aircraft.
But as of now, confusion and lack of its grasp are limiting adoption.
To understand the technology better, I had a conversation with Pieter van Schalkwyk, whose company has helped Fortune 10 companies build Digital Twins.
Here's what we discussed
✔️ What is a digital twin? ✔️ Digital modeling concepts ✔️ Types of digital twins ✔️ Digital Twin formats ✔️ Tools and frameworks ✔️ Step by Step Process ✔️ Interfacing with digital twins ✔️ Digital Twin vs Digital Thread ✔️ AI and ML in Digital Twins ✔️ Digital Twins and Blockchain ✔️ Digital Twin Consortium
Pieter is the CEO of XMPRO, a low-code application development platform that enables subject matter experts to build and deploy real-time applications in weeks.
He currently serves as the co-chair of the Natural Resources Working Group for the Digital Twin Consortium & previously co-chaired the Digital Twin Interoperability, Industrial Digital Transformation, & Distributed Ledger Task Groups at the Industrial Internet Consortium (IIC)