AI in Manufacturing

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.

Many factories today grapple with recurring production issues and inefficiencies; whether it’s inconsistent quality, unpredictable downtime, or process bottlenecks.