University of the West of Scotland and E.D.C. (Scotland) Limited KTP 24_25 R5

A fleet of delivery lorries, construction vehicles, and service vans will soon stream real-time data about their own mechanical health back to a central platform that predicts breakdowns before they happen. This project develops a smart Drive Analysis and Remote Telemetry platform that combines advanced machine learning, cybersecurity, and embedded systems. Current vehicle diagnostics typically flag problems only after they occur, forcing reactive repairs and unexpected downtime. The platform aims to shift from diagnostics—telling you what broke—to prognostics: forecasting component failure based on subtle patterns in sensor data, driving behaviour, and operational conditions. If successful, the platform could reduce unplanned vehicle downtime for logistics companies, public transport operators, and emergency services. Fewer roadside breakdowns mean fewer missed deliveries, lower maintenance costs, and safer roads. The cybersecurity component ensures that the constant stream of vehicle data remains protected from tampering or theft. The research is applied and commercially focused—the goal is a launch-ready product, not a theoretical advance. It targets a concrete industrial problem: making vehicle fleets more reliable through predictive maintenance rather than reactive repair.