Analysis and Study of Fault Diagnosis of Induction Motor Drives Using Hybrid Artificial Intelligence

Abstract

Now days Hybrid Artificial Intelligence (AI) techniques such as the Genetic Algorithms (GA) and Artificial Neural Networks (ANN) are being widely used to find an optimal solution for a wide variety of complex problems including fault diagnosis and control and classification of the electrical machines. As the overall performance of the system and hence its reliability gets reduced due to imperfect and uncertain information processing, optimization techniques are to be employed to obtain the required efficiency and reliability. Hence, the hybrid AI system is tested on an Induction motor for fault diagnosis, to reduce the learning time and to obtain an efficient solution for the machine design. GA is used to select the characteristic parameters of the classifiers and the input features. For each trial, the ANNs are trained with a subset of the experimental data for known machine condition. The procedure is able to rectify all the faults especially stator fault and bearing faults of induction machine with minimum delay and maximum efficiency.