Low Severity Inter Turn Short Circuit Fault Diagnosis in Permanent Magnet Synchronous Motors Using Machine Learning

Abstract

The study represents the diagnosis of the low severity inter turn short circuit (ITSC) fault in the permanent magnet synchronous motors (PMSMs). A pre-recorded in-house three-phase current data is used to distinguish between the healthy, 2% ITSC, and 5% ITSC fault detection in the stator winding at a fixed speed and load. This analysis is targeted at condition monitoring and predictive maintenance of the system. The supervised machine learning techniques take recorded time series of three-phase current data as a key ingredient for classification. Specifically, four supervised machine learning (ML) algorithms decision tree (DT), random forest (RF), extreme gradient boosting (XGB), and support vector machine (SVM) are used to evaluate the performance of the classification for different fault severity level with the healthy condition. For this classification, statistical features like crest, impulse, kurtosis, etc. factors with a total of 9 other statistical features are determined to serve the purpose. Wrapper-based feature selection (WFS) technique is employed for finding the optimal subset of features to get the maximum accuracy while reducing computational complexity using the mentioned supervised machine learning algorithms. It is vital to note that the combination of root mean square (RMS) factor, standard deviation factor, and crest factor is the optimal performing feature for both classifications between healthy to 2% ITSC and healthy to 5% ITSC fault with the accuracy percentage of around 85% and 98.33% in level 3 of SVM algorithm.