Fault Analysis And Predictive Maintenance Of Induction Motor Using Machine Learning

TL;DR

This paper develops a machine learning-based system using neural networks to detect and classify faults in induction motors in real time, aiming to prevent damage and improve maintenance efficiency.

Contribution

It introduces a fast neural network model for fault detection using only motor input signals, enabling real-time diagnosis without additional sensors.

Findings

Accurately detects common electrical faults in induction motors

Classifies faults in real time with high precision

Demonstrates effectiveness on a 0.33 HP motor

Abstract

Induction motors are one of the most crucial electrical equipment and are extensively used in industries in a wide range of applications. This paper presents a machine learning model for the fault detection and classification of induction motor faults by using three phase voltages and currents as inputs. The aim of this work is to protect vital electrical components and to prevent abnormal event progression through early detection and diagnosis. This work presents a fast forward artificial neural network model to detect some of the commonly occurring electrical faults like overvoltage, under voltage, single phasing, unbalanced voltage, overload, ground fault. A separate model free monitoring system wherein the motor itself acts like a sensor is presented and the only monitored signals are the input given to the motor. Limits for current and voltage values are set for the faulty and healthy conditions, which is done by a classifier. Real time data from a 0.33 HP induction motor is used to train and test the neural network. The model so developed analyses the voltage and current values given at a particular instant and classifies the data into no fault or the specific fault. The model is then interfaced with a real motor to accurately detect and classify the faults so that further necessary action can be taken.