Convolutional Neural Network for Ladder-Secondary Linear Induction Motor Fault Diagnosis

This paper presents a comprehensive approach for modeling and classification of air gap asymmetry inter-turn short circuit faults in ladder-secondary linear induction motors (LS-LIMs). It is based on modified Magnetic Equivalent Circuit (MEC) model incorporated with current signal-based fault detection method using convolution neural network (CNN). The feature sets the mentioned are classified separately by convolutional network, training test data extracted three-phase currents obtained from MEC. For this purpose, both healthy faulty modeled initially proposed MEC to generate different labeled designed CNNs. also shown that diagnosis motor Fast Fourier transform (FFT) not possible. Finally, networks trained Finite Element Method (FEM) validate their accuracy. Since LS-LIMs CNN has been introduced relevant literature so far, it presented first time.