Smart Monitoring of Industrial Lubricants: a Lab-on-Chip IoT approach for Enhanced Predictive Maintenance and Green Energy Sustainability

Lubricating oils are the lifeblood of industrial machinery and ensure smooth operation and long life by reducing wear and friction. Their condition reflects not only their degradation, but also the health of the entire machine, just as a blood test reveals the health of the human body. In an industrial landscape increasingly characterised by the need for operational efficiency and environmental responsibility, traditional oil monitoring methods, which rely on periodic laboratory analysis, are unable to provide usable information in real time. This thesis addresses this critical gap by presenting L-HUB™, an innovative Industrial Internet of Things (IIoT) system based on Lab-on-Chip (LOC) technology, designed for real-time, automated monitoring of lubricating oils. The L-HUB™ system integrates advanced sensing technologies, microfluidic designs and cloud-based platforms to provide comprehensive diagnostics of oil conditions, including viscosity, oxidation levels, water content and particle morphology. By enabling continuous monitoring, it not only detects potential machine failures at an early stage, but also supports predictive maintenance strategies that optimise maintenance schedules, reduce downtime and minimise operating costs. Furthermore, by drastically reducing lubricant waste and extending machine life, the system significantly reduces the carbon footprint of industrial operations, aligning with global sustainability goals. The research also led to the development of Hivor™, a simpler and more autonomous sensor that is already commercially available. These systems harness the power of Amazon Web Services (AWS) for centralised data management, anomaly detection and real-time visualisation, offering industries a seamless and efficient way to remotely manage equipment health. The contributions of this research are transformative and bridge the gap between oil analysis in the laboratory and real-time on-site monitoring, while addressing the issue of sustainability. By optimising the use of lubricants and minimising waste, the solutions proposed in this thesis reduce the environmental impact of industrial activities and contribute to the long-term sustainability of operations. The L-HUB™ system sets a new benchmark for oil condition monitoring, with the future potential to incorporate time series prediction for advanced predictive maintenance.