Time-Series Data Quality and Reliability for Manufacturing AI: Bert Baeck - Timeseer.AI
AI in ManufacturingShow Notes
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: 1. 𝐒𝐜𝐨𝐫𝐢𝐧𝐠 – Physics-aware anomaly rules, baselines 2. 𝐌𝐨𝐧𝐢𝐭𝐨𝐫𝐢𝐧𝐠 – Continuous validation at the right cadence (real-time or daily) 3. 𝐂𝐥𝐞𝐚𝐧𝐢𝐧𝐠 & 𝐕𝐚𝐥𝐢𝐝𝐚𝐭𝐢𝐨𝐧 – Auto-fix what you can; escalate what you can’t 4. 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.
More from AI in Manufacturing
AI Is Reshaping Industrial Software. Who Wins? | Michael Finocchiaro Will AI simply make established industrial software better, or will it fundamentally change which companies dominate the market? In this episode of AI in Manufacturing, I sit down with Michael Finocchiaro, founder of ThreadMoat Intelligence, to explore how AI is reshaping the competitive landscape of industrial technology, where AI-native startups are challenging established vendors, and what the industrial software market could look like over the next five years. We go beyond the competitive landscape to examine how the underlying technology architecture is evolving, from increasingly composable software and AI-driven orchestration to the changing roles of traditional systems like MES and PLM. In this episode, we explore: Why AI-native startups are challenging established industrial software vendors and where incumbents still have an advantage. How AI is changing traditional industrial software categories, including MES, PLM, and manufacturing data platforms. Why composable architectures and AI agents could fundamentally change how industrial systems are integrated and orchestrated. How manufacturers should think about data ownership, interoperability, and vendor lock-in when evaluating emerging technologies. What the industrial software landscape could look like in five years, including the evolving roles of AI agents, knowledge graphs, and human decision-making. Michael brings a broad perspective from tracking industrial technology startups, interviewing founders, and analyzing emerging trends across engineering and manufacturing software. Whether you're building industrial software, investing in emerging technologies, or shaping your organization's manufacturing technology strategy, this conversation offers valuable perspectives on the shifts already underway and what they could mean for the industry. Learn more: Industry40.tv: https://www.industry40.tv
# AI in Manufacturing Podcast
# AI in Manufacturing Podcast — Show Notes ## Episode: Scaling Industrial Intelligence with the I3X Common API
# AI in Manufacturing Podcast: Episode Show Notes
**Podcast Name:** AI in Manufacturing Podcast **Episode Title:** How to Build AI Solutions That Actually Work on the Factory Floor **Guest:** Renan De Villiers, Founder & CEO, OSS Ventures **Host:** Kudzai Manditereza