A PCA and Two-Stage Bayesian Sensor Fusion Approach for Diagnosing Electrical and Mechanical Faults in Induction Motors

Abstract

Induction motors are widely used in industrial plants for critical operations. Stator faults, bearing faults, or rotor faults can lead to unplanned downtime with associated cost and safety implications. Different sensors may be used to monitor the health state of induction motors with each sensor typically being better suited for diagnosing different faults. Condition monitoring approaches that fuse data from multiple sensors have the potential to diagnose a greater number of faults. In this paper, a sensor fusion approach based on the combination of a two-stage Bayesian method and principal component analysis (PCA) is proposed for diagnosing both electrical and mechanical faults in induction motors. Acoustic, electric, and vibration signals are gathered from motors operating under different loading conditions and health states. The inclusion of the PCA step ensures robustness to varying loading conditions. The obtained results highlight that the proposed method performs better than the equivalent single-stage or feature-based Bayesian methods.