A hybrid gwo-rbfnn model for inter-turn insulation fault detection and diagnosis in induction motor

This paper proposes an optimal detection and classification of inter-turn insulation faults in the induction motor (IM) using a hybrid optimization technique. The proposed hybrid optimization technique is the joined execution of both the Grey Wolf Optimization Algorithm (GWOA) and Radial Basis Function Neural Network (RBFNN) and in this way, it is named as GWORBFNN technique. The required fault training dataset is gathered through the client characterized framework show through the proposed GWO algorithm. In the proposed approach, RBFNN is utilized in two phases with the end goal of detection of the inter-turn insulation faults. The ordinary RBFNN first phase is utilized to recognize the motors healthy or unhealthy condition under various situations. The second phase of the RBFNN is playing out the classification of the unhealthy condition of motors to distinguish the correct inter-turn faults for protection. Here, the second phase RBFNN learning procedure is enhanced by using the GWOA in perspective of the minimum error objective function. The proposed GWO-RBFNN method plays an evaluation process to protect the induction machine and detect the fault in the IM at the inception stage. The proposed GWO-RBFNN technique guarantees the system with lessens complexity for the detection and classification of the inter-turn insulation fault and hence the accuracy of the system is raised. The proposed model is executed in MATLAB/Simulink working stage and the execution is assessed with the current procedures.