Modeling, Analysis, of Induction Motor's Stator Turns Fault Using Neuro-Fuzzy

Abstract

This chapter discusses modeling and analysis methods for fault detection and diagnosis of stator inter-turn short circuit in three-phase induction machines. dq frame was used to model the induction motor for both health and fault cases to facilitate recognition of motor current and simulate motor environment. Fault diagnosis system was designed with adaptive neuro-fuzzy inference system (ANFIS) to provide an efficient online diagnostic tool. ANFIS diagnostic tool was trained with simulated data that generated by induction motor healthy and faulty models. Approached tool is verified online with a motor under different loading conditions. It determines the fault severity values using the motor current signature analysis (MCSA). Developed tool performance is investigated with a case study of two HP three-phase induction motor using Matlab/Simulink® software.