Using Technical Data in Modern Manufacturing

Many manufacturers today have invested heavily in data infrastructure: PLCs, SCADA, MES, historians, dashboards. Yet when you dig into the architecture, especially on high-speed or complex lines, a common gap emerges. Critical short-duration events are not being captured accurately or with enough context to drive actionable insights. This is not due to lack of technology. Modern PLCs, edge devices, and platforms are more than capable. The problem is architectural. Many plants still rely on SCADA and MES systems that poll PLCs at relatively slow intervals, typically 1000 milliseconds. That polling interval creates a blind spot. Meanwhile, PLC scan cycles typically run between 3 and 5 milliseconds. In high-speed lines, servo-based systems, robotics, and motion applications, critical events happen on sub-second timescales. Operator inputs, cascading alarms, motion faults, and intermittent product jams often occur and resolve in less than a second. If these events are not buffered properly at the PLC layer or edge, they are simply lost to higher-level systems. This leads to a familiar pattern. • OEE reports that do not explain why downtime occurred • Fault logs that fail to show which fault triggered first • Product loss and yield issues that cannot be traced to specific machine behaviors • Maintenance teams spending hours reviewing PLC logic and guesswork post-mortems The bigger risk is that leadership decisions get made on incomplete data. Continuous improvement efforts stall. Predictive maintenance strategies fail to get off the ground. McKinsey & Company data suggests that manufacturers who close this gap and build modern data architectures can reduce unplanned downtime by up to 50% and improve productivity by 10 to 20%. But this requires capturing data with the right fidelity, at the right layer, and with the right context. From my experience, this is true not only on high-speed systems where products are moving faster than the eye can see and $100,000 high-speed cameras are used to diagnose failures. It is equally true on slower lines where operators and engineers struggle to explain recurring issues because key data is missing. If you are running below 60 percent OEE, you likely have more foundational work to do first. But if your goal is to move from reactive to proactive operations, to reduce variability, and to enable next-generation capabilities like advanced analytics and machine learning, this is an architectural conversation that needs to happen. I work with manufacturers who want to modernize these architectures and close this visibility gap. If you are looking at these challenges or want to benchmark your current architecture against best practices, feel free to reach out. I would be happy to share insights and lessons learned.

Modern machines generate enormous amounts of data. Pressures, temperatures, positions, times, forces. Every cycle produces hundreds or thousands of data points. Most of it goes unused. Collecting data is easy. Extracting value from data is hard. The challenge is connecting machine data to outcomes that matter. Knowing that pressure reached 1,847 bar on cycle 14,523 is meaningless unless you can connect it to part quality, efficiency, or reliability. Raw data is just noise until it becomes insight. Useful applications of machine data include process monitoring, trend analysis, and predictive maintenance. Process monitoring compares each cycle to established limits. When a parameter exceeds normal range, it flags for attention. This catches problems early, before they produce defects or cause damage. Trend analysis tracks parameters over time to identify drift. Gradual changes that would not trigger a single-cycle alarm become visible when viewed across days or weeks. This reveals wear patterns, material variation, and process degradation. Predictive maintenance uses machine data to anticipate component failure. Changing patterns in motor current, hydraulic response, or vibration signature can indicate impending problems before they cause downtime. All of these require infrastructure beyond just collecting data. Storage, processing, analysis tools, and most importantly, people who understand both the data and the process well enough to act on insights. If your machines generate data that nobody looks at, the data has no value. If you want to capture value from machine data, the question is what decisions it will inform and how it will reach the people who make those decisions. How much of the data your machines generate is actually being used to improve operations?

Earlier this week, I was speaking with a CEO about his search for a technology leader. Given the role is in a manufacturing realm, I wanted to enlighten him to how IT/OT Convergence is no longer a strategic roadmap item. Instead, it's a massive, immediate challenge creating both innovation opportunities and cybersecurity risks. It's fair to say that traditional IT and OT don't speak the same language. OT runs the physical machines (PLCs, SCADA), while IT manages the corporate network. This gap is the reason so many industrial companies are stalling on their transformation goals. The way I see it, there are three urgencies driving demand. The first being the legacy environment and the roadblock(s) these create. Companies pursuing AI, automation, and data strategies are more likely than not hitting a wall. The old machines are simply not compatible with the need for real-time data. This is the leader's first priority. To retrofit and enable those aging assets. Next is the impact from the geopolitical shift. Increased demand for modern, U.S.-based manufacturing often requires building a shop floor from the ground up. A task impossible without leaders who master both IT and OT knowledge. Lastly, is what I have come to embrace as the Tesla/Amazon gap. This is best reflected by companies that are not investing in talent and are being left behind by industry leaders who have long integrated digital manufacturing, allowing them to move faster and drive down costs through higher production and less downtime. Now, a skilled practitioner and technology executive can turn mayhem into results by embracing a role that essentially creates a "mini-CIO" for manufacturing operations. Their goals are consistent, to reduce costs, improve efficiency, and modernize operations. My advice is always to seek the quick wins as these build momentum but more importantly trust. Extracting data from aging machines and capturing legacy knowledge from retiring technicians is critical in these efforts. At the same time, focusing on a long-term strategy must also be prioritized. Implementing comprehensive shop floor connectivity using advanced tools like digital twin technology can reduce risk and accelerate the roadmap. The ideal OT/IT leader is essentially the glue that connects the organization. These leaders are key to identifying organizational bottleneck that channels competing executive digital initiatives into a unified, strategic roadmap, preventing "mayhem" on the factory floor. At the same time the ideal leader must be a translator, and teacher. They need experience in both IT and OT, possess a deep business outcomes focus, and demonstrate an executive presence that builds trust with both engineers on the floor and executives in the C-suite. #DigitalManufacturing #Industry40 #ITOTConvergence #CIO #SupplyChain #SmartManufacturing

One of the biggest things I see with manufacturers isn’t a lack of data. It’s a lack of understanding of its value. Plants invest in data collection, frontline apps, point solutions—often lots of them. And to be fair, they work. You get something done quickly. A report. A workflow. A dashboard. But without a unified, governed data layer across the plant—or the enterprise—that data is just sitting in silos. Ungoverned. Unrelated. Hard to trust. Quick feels good in the moment. Quick almost always comes with a ceiling. Over time, those fast decisions turn into fragmented systems that are hard to manage, hard to scale, and even harder to evolve. Every new requirement means more glue, more tools, more reconciliation, and customization. A model-driven approach asks for a little more effort up front. A few extra hours thinking about objects, relationships, and state. But on the other side of that effort? Traceability. Accountability. Scheduling. Capacity planning. Data governance. Orchestrated integrations. Real operational intelligence. We hear this constantly from customers who’ve outgrown their existing CFW apps and point solutions. They didn’t make a bad choice—they made the only choice available at the time. There weren’t true model-driven platforms when many of those decisions were made. After living with the tools for a while, the need becomes obvious: to build left to right, with data leading the way. Data isn’t just something you collect. It’s something you organize, govern, and use to run the operation.

I've been in manufacturing software for years, and I keep hearing the same debate: "MES is about transactions." "No, it's about data collection." "Actually, it's about functions." Why are we limiting #MES / #MOM to just one thing? In every successful implementation I've seen, MES delivers value across multiple dimensions: → It executes transactions that keep production moving → It captures real-time data from the shop floor → It connects disparate operations into a cohesive system → It provides the context needed for smart decisions But if I had to pick the biggest game-changer? It's the data. 📊 Because without accurate, granular data from your manufacturing operations, you're unable to make effective decisions to drive continuous improvement. → You can't optimise what you can't measure. → You can't improve what you don't understand. → You can't make informed decisions without the full picture. And here's what makes MES/MOM data so powerful - it's not siloed. When your MES spans across operations, the data overlaps and interacts. → Quality issues connect to production schedules. → Material usage ties to equipment performance. → Maintenance and production are aligned. → Everything has context. ✨ That interconnected view is what enables continuous improvement, process optimisation, and strategic decision-making. And this is why disparate point solutions are less effective than a single joined up, contextualised application. So yes, MES handles transactions. But it's also creating a comprehensive, real-time picture of everything happening on your factory floor. 🏭 And that's where the real value lives.

Most factories don’t struggle because of lack of data. They struggle because data never becomes action. Dashboards multiply. Reports expand. Metrics look impressive. Yet performance barely moves. Because raw numbers alone don’t create operational excellence. Transformation begins only when data starts driving decisions. 𝐒𝐦𝐚𝐫𝐭 𝐦𝐚𝐧𝐮𝐟𝐚𝐜𝐭𝐮𝐫𝐢𝐧𝐠 𝐥𝐞𝐚𝐝𝐞𝐫𝐬 𝐟𝐨𝐥𝐥𝐨𝐰 𝐚 𝐝𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭 𝐩𝐚𝐭𝐡: 𝐃𝐚𝐭𝐚 → 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 → 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 → 𝐈𝐧𝐬𝐢𝐠𝐡𝐭 → 𝐄𝐱𝐞𝐜𝐮𝐭𝐢𝐨𝐧 → 𝐓𝐫𝐚𝐧𝐬𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧. Not as theory. As a repeatable operating discipline that turns signals into scalable impact. They connect machine logs to bottlenecks. Shift reports to flow decisions. Quality data to root causes. Operator insights to real improvement. And something powerful happens: Quality improves. Lead times shrink. Costs fall. Customers trust more. Growth becomes predictable. This is the real separation in modern manufacturing: Some plants collect data. Others convert it into competitive advantage. 𝐒𝐨 𝐭𝐡𝐞 𝐂-𝐥𝐞𝐯𝐞𝐥 𝐪𝐮𝐞𝐬𝐭𝐢𝐨𝐧𝐬 𝐭𝐡𝐚𝐭 𝐦𝐚𝐭𝐭𝐞𝐫 𝐦𝐨𝐬𝐭 𝐚𝐫𝐞: • 𝐖𝐡𝐢𝐜𝐡 𝐨𝐟 𝐨𝐮𝐫 𝐦𝐞𝐭𝐫𝐢𝐜𝐬 𝐚𝐜𝐭𝐮𝐚𝐥𝐥𝐲 𝐜𝐡𝐚𝐧𝐠𝐞 𝐝𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐬? • 𝐖𝐡𝐞𝐫𝐞 𝐢𝐬 𝐯𝐚𝐥𝐮𝐚𝐛𝐥𝐞 𝐝𝐚𝐭𝐚 𝐬𝐭𝐢𝐥𝐥 𝐝𝐢𝐬𝐜𝐨𝐧𝐧𝐞𝐜𝐭𝐞𝐝 𝐟𝐫𝐨𝐦 𝐚𝐜𝐭𝐢𝐨𝐧? • 𝐀𝐫𝐞 𝐢𝐧𝐬𝐢𝐠𝐡𝐭𝐬 𝐫𝐞𝐚𝐜𝐡𝐢𝐧𝐠 𝐭𝐡𝐞 𝐬𝐡𝐨𝐩 𝐟𝐥𝐨𝐨𝐫—𝐨𝐫 𝐬𝐭𝐚𝐲𝐢𝐧𝐠 𝐢𝐧 𝐫𝐞𝐩𝐨𝐫𝐭𝐬? • 𝐖𝐡𝐚𝐭 𝐞𝐱𝐞𝐜𝐮𝐭𝐢𝐨𝐧 𝐩𝐫𝐨𝐨𝐟 𝐬𝐡𝐨𝐰𝐬 𝐝𝐚𝐭𝐚 𝐢𝐬 𝐝𝐫𝐢𝐯𝐢𝐧𝐠 𝐫𝐞𝐬𝐮𝐥𝐭𝐬? And most importantly— are we measuring performance… or transforming it? Data doesn’t create impact. Decisions powered by data do.

Operational efficiency at scale depends on visibility, speed, and disciplined execution. Panasonic Energy Corporation of North America’s Reno gigafactory produces six million lithium-ion batteries daily -- and that demands peak efficiency. The implementation of SAP S/4HANA in just seven months reduced lead times, improved cash flow, simplified processes, and accelerated financial closure while providing real-time visibility. With Capgemini's support, the goal was to maintain a clean core, streamline processes, and enhance decision-making on the shop floor. By consolidating data and using SAP Analytics Cloud, operators gained essential insights for quick action and continuous performance improvement. This exemplifies the transformation in modern manufacturing, where technology drives operational excellence and produces measurable results. Watch the story to see intelligent industry results at scale. https://ow.ly/ma4W50Yhctx

Companies often start their IIoT journey by connecting machines and installing sensors. But real industrial value comes when those connected systems improve operations, reduce downtime, and optimize production. Industrial IoT (IIoT) is not just about collecting machine data — it’s about turning operational data into measurable improvements across manufacturing systems. From monitoring equipment health to optimizing supply chains and simulating digital twins, IIoT enables factories to become data-driven and intelligent. This framework shows six key areas where IIoT delivers the most operational impact. ➞ Asset Monitoring Track machine performance in real time using connected sensors and centralized dashboards. ➞ Predictive Maintenance Use IoT data and analytics to predict failures and schedule maintenance before breakdowns occur. ➞ Quality Optimization Monitor production processes continuously to detect defects and improve product consistency. ➞ Energy Management Analyze energy consumption across machines and facilities to optimize efficiency and reduce costs. ➞ Supply Chain Integration Connect production systems with logistics and enterprise platforms for end-to-end operational visibility. ➞ Digital Twin Integration Create virtual replicas of machines and processes to simulate scenarios and optimize performance. Industrial IoT turns factories into connected, intelligent production systems. 🔁 Repost if you’re building the future of smart manufacturing. ➕ Follow Nick Tudor for more insights on AI + IoT systems that actually ship.