Detection of Electric Motor Damage Through Analysis of Sound Signals Using Bayesian Neural Networks

TL;DR

This paper introduces a Bayesian neural network approach for detecting and classifying faults in electric motors using sound signals, effectively handling imbalanced datasets and demonstrating robustness on real-world data.

Contribution

The study presents a novel application of Bayesian neural networks for electric motor fault diagnosis, addressing data imbalance issues and validating performance on real signals.

Findings

Effective fault detection on real-life signals

Robustness to data imbalance demonstrated

Improved reliability in motor diagnostics

Abstract

Fault monitoring and diagnostics are important to ensure reliability of electric motors. Efficient algorithms for fault detection improve reliability, yet development of cost-effective and reliable classifiers for diagnostics of equipment is challenging, in particular due to unavailability of well-balanced datasets, with signals from properly functioning equipment and those from faulty equipment. Thus, we propose to use a Bayesian neural network to detect and classify faults in electric motors, given its efficacy with imbalanced training data. The performance of the proposed network is demonstrated on real life signals, and a robustness analysis of the proposed solution is provided.