Neural Networks for Synchronous Generator Fault Diagnosis

Abstract

Fault Diagnosis is play vital rule in the industrial applications and machine drives for the fault analysis (FA) and predicting the level of severity to optimise maintenance and improve reliability. Early detection of faults in the supervised process renders it possible to perform important preventative actions. In this paper, fault diagnosis of stator and rotor windings using field current as fault indicator. Static neural network (NN) has been implemented as fault classifier under different operating conditions. The results obtained from the real time simulation demonstrates the effectiveness and reliability of the proposed methodology. The detection and identification of faults in accurately way ensure the importance of the neural networks in the fault diagnosis field.