Diagnostic Analytics Powered by IoT and Machine Learning for the Fault Evaluation of a Heavy-Industry Gearbox

Predictive maintenance based on vibration monitoring can significantly improve gearbox reliability in heavy-industry environments. Although it is well established in vibration engineering that operating regimes influence vibration levels, the contribution of this work lies in providing an integrated, data-driven diagnostic linkage between continuously acquired IoT vibration indicators and key process/operational variables to identify and quantify the dominant drivers of vibration escalation. This study deployed wireless IoT sensors for continuous acquisition of RMS vibration and lubrication temperature in gearboxes operating in cement and mining plants and applied multivariate machine learning models to detect anomalies and identify root causes. We compared boosted multilayer feedforward neural networks, boosted trees, and k-nearest neighbors using RMS vibration and process variables including mill feed, lubrication pressures, and temperature. The boosted neural network delivered superior validation performance and isolated low or near-zero mill feed during operation as the primary driver of elevated RMS vibration, with lubrication instability acting as a secondary interacting factor. This shifts the diagnosis from a generic “high vibration during transients” statement to actionable operational mitigations—minimum feed set-points, controlled ramping logic, and lubrication pressure governance—supported by multivariate evidence. Our results motivate further validation with k-fold and out-of-time tests.