In this episode of the Industrial Data Quality Podcast, I talk with with John Walmsley of Aluminate Technologies, about what AI actually does in heavy industry today, cutting through the hype to explore real applications and challenges.

John brings experience from semiconductors to medical devices to AI in heavy industry. The conversation covers three levels of industrial AI: continuous monitoring, multi-sensor analysis, and autonomous optimization. Using aluminum industry examples, we explore why AI projects get stuck in pilot phase and what it takes to scale solutions enterprise-wide.

Notable Quotes

Key Learnings

1. Multi-sensor approach works: Single-sensor solutions stay stuck in pilots; combining multiple data streams creates valuable insights worth scaling.
2. Infrastructure over algorithms: Enterprise deployment needs robust, maintainable data architecture, not just clever code.
3. Products beat projects: Successful AI needs ongoing support and evolution, not one-time engineering solutions.
4. New pressures create opportunities: CO2 regulations and grid stabilization markets are driving fresh AI adoption in heavy industry.
5. Start with problems, not technology: Identify significant operational challenges first, then find appropriate AI solutions.

Reach out to John Walmsley on LinkedIn.

In this episode of the Industrial Data Podcast, I interview Lonnie Bowling about the evolution of operational technology (OT) data integration from the 1990s to present day (2025). Lonnie, who runs Diemus consulting, shares insights from his extensive career in industrial automation and data integration. The discussion traces how manufacturing and utility companies moved from focusing purely on automation to recognizing the value of operational data, the rise of historian systems like OSIsoft PI, challenges with proprietary formats and data quality, and the industry's current shift toward cloud computing and AI-powered analytics. Both of us acknowledge that while new technologies will transform the landscape, legacy systems will remain an essential part of industrial operations for decades to come.

Key Ideas:

• Historians evolved from simple trend-viewing tools within SCADA systems to specialized products like OSIsoft PI that could connect multiple systems. 
• The industry is experiencing consolidation, with AVEVA (now part of Schneider) acquiring OSIsoft PI and other players to build integrated stacks. 
• Despite technological advances, legacy systems will remain for decades, especially in control functions. 
• Problems include proprietary formats, inconsistent naming conventions, connectivity issues with distributed systems, and poor data quality. 
• Companies are increasingly moving data to cloud platforms like Databricks for better analytics capabilities and computing power, though often without clear objectives.

Reach out to Lonnie Bowling:

• Email: [email protected]
• Diemus website: https://diemus.com/

In this episode Denis invites Thomas to speak on the topic of industrial time series data quality. we delve into the challenges and importance of ensuring data reliability and observability in industrial settings. Thomas shares his extensive background in industrial time series data and his current work with Timeseer, a platform focused on data quality and observability. The conversation covers various aspects, including the differences between data reliability and observability, the challenges of moving data from the shop floor to the cloud, and the need for a proactive approach to data quality management. Finally, we discuss real-world examples and the technical and organizational components required to address data quality issues.

Notable Quotes

• Data quality is not just a technical issue — it's a people and process problem, deeply tied to governance and ownership.
• Data management at many companies is still reactive — fixing issues only after models break or KPIs look suspicious. When companies scale their data-driven operations, they need to turn to proactive data management to avoid ending up in firefighting mode.
• Data maturity varies by company and by industry — utilities and pharma often lead, some other industries may still view data as a byproduct.
• Data should be treated like a product — with quality checks, documentation, and accountability — especially as you scale analytics. This is also true for OT data.
• AI needs data quality — ML and AI depend on quality inputs and sensor drift or misconfigured tags can quietly corrupt your entire model output. Interestingly, AI is also a key enabler in scaling data quality.
• Moving data to the cloud introduces new risks — missing context, inconsistent pipelines, and ownership confusion.

Reach out to Thomas 

• Thomas Dhollander LinkedIn
• Timeseer website
• E-Mail [email protected]

This podcast episode was originally recorded as a video on my YouTube channel. In this episode I give a chronological overview of the first six years of my career in data. I do not have a background in programming or computer science, so I hope my store may inspire other people to transition into this field

Welcome to my podcast! In this very first episode I introduce the topics of this podcast and explain my background in data.