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

"The two words to remember every time you think you've got a great solution that will generate more data for someone is 'so what?'" - John

"The reason for projects getting stuck at pilot is that the value they propose to deliver is not sufficient to clear that potential barrier for everyone involved to take the risk of investment and failure to roll it out." - John

"Companies often assume data is just lying around ready to be used, but it's a bit like saying you have aluminum in the ground: you can just dig it up with a shovel. But no, to get it in pure metal form, you need a lot of processing." - Denis

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.