“Aviation is a global industry […] My interest in predictive maintenance was sparked by a near decade of hands-on experience as an airworthiness inspector. Over the years, I’ve seen how relying on reactive maintenance […] waiting for something to go wrong and this usually puts safety at risk, interrupts operations, and drives up maintenance costs. This issue is even more pressing coming from a Nigerian experience, where older aircraft, limited diagnostic tools, and fragmented data systems often delay the early detection of wear and aircraft degradation. That’s what actually drew me to predictive maintenance. I saw it as a practical and scalable solution, one that you can use machine learning, AI and data to predict failures before they happen, even in a resource-constrained setting,” he said.