Fault Diagnosis on Induction Motor using Machine Learning and Signal Processing

TL;DR

This paper presents a machine learning approach using signal processing techniques to detect and classify faults in induction motors, achieving high accuracy in simulated data for industrial fault diagnosis.

Contribution

It introduces a comprehensive simulation-based dataset and compares multiple machine learning models, identifying Decision Tree as the most accurate for fault classification.

Findings

Decision Tree achieved 92% accuracy in fault detection.

FFT effectively extracted features for fault classification.

Simulated data validated the approach for industrial applications.

Abstract

The detection and identification of induction motor faults using machine learning and signal processing is a valuable approach to avoiding plant disturbances and shutdowns in the context of Industry 4.0. In this work, we present a study on the detection and identification of induction motor faults using machine learning and signal processing with MATLAB Simulink. We developed a model of a three-phase induction motor in MATLAB Simulink to generate healthy and faulty motor data. The data collected included stator currents, rotor currents, input power, slip, rotor speed, and efficiency. We generated four faults in the induction motor: open circuit fault, short circuit fault, overload, and broken rotor bars. We collected a total of 150,000 data points with a 60-40% ratio of healthy to faulty motor data. We applied Fast Fourier Transform (FFT) to detect and identify healthy and unhealthy conditions and added a distinctive feature in our data. The generated dataset was trained different machine learning models. On comparing the accuracy of the models on the test set, we concluded that the Decision Tree algorithm performed the best with an accuracy of about 92%. Our study contributes to the literature by providing a valuable approach to fault detection and classification with machine learning models for industrial applications.