A state-space model for induction machine stator inter-turn fault and its evaluation at low severities by PCA

Abstract

Early fault detection in rotating machines saves time, money and labor that must be spent repairing or replacing the machine caused by a abrupt breakdown while stopping the production process. Due to this reason, industries invest in routine maintenance, intending to diagnose faults and take preventive measures before the problem becomes severe. This paper presents a state-space model of the healthy and faulty induction motor. The fault considered in this study is the stator inter-turn fault, with the severity ranging from 0.3%-2.11% in a phase. This article gives an overview of the simulated model and shows how the healthy three-phase current signature is different from the faulty ones. The Principal Component Analysis (PCA) and Space Vector Loci (SVL), in particular, have been utilized to visualize and present the differences between the healthy and faulty current signatures. Furthermore, both PCA and SVL have also been instrumental in denoting minor fault severities.