International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-9 Issue-3, February, 2020 1722 Retrieval Number: C5634029320/2020©BEIESP DOI: 10.35940/ijeat.C5634.029320 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Abstract: This article proposes a new solution method for diagnosing faults in a multi phase induction motor using least mean square filter (LMS) and a new hybrid neural network with mind evolution computation algorithm. The entire procedure for teaching an artificial neural network (ANN) is popularly thought of among the toughest activities in system learning and also it has lately attracted lots of research workers. The proposed hybrid fault diagnosing method includes an efficient feature extractor based on LMS and a fault classifier based on a hybrid neural network. First, the LMS method is used to extract the effective features. The mind evolution computation algorithm is employed to train the neural network. The performance and efficiency of the presented hybrid neural network classifier is estimated by testing a total of 600 samples, which are modeled on the basis of the failure model. The average correct classification with and without mind evolution computation algorithm is about 98% and 96.17% for various fault signals respectively. The outcome got from the simulation analysis shows the potency of the proposed hybrid neural network for fault diagnosis in multi phase induction motor. Keywords : Fault diagnosis, feature extraction, least mean square, multi layer perceptron neural network, mind evolution computation algorithm. I. INTRODUCTION The multiphase induction motor's fault investigation and identification are essential in products diagnosis procedure. On account of construction faculties of motors and its working theory, fault diagnosis processes and the identification procedures have many characteristics [1]. A fault in electrical engine commonly has lots of outward symptoms, as an instance, as soon as a bar of motor has been broken, and lots of symptoms correlated each other occur, for example, instance shaking increment, start up time prolongation, current swing of stator, slip augmentation, speed rate and torque undulation, temperature shift, etc [2]. Once a bar is broken and the motor continues to run, the range of broken bar will grow up, outward symptoms are far more and more noticeable, and malfunction eventually become much more and more acute; and also finally motor is going to probably likely soon undoubtedly be destroyed. On the flip side, same symptoms are caused by quite many faults. Many circumstance changes may cause electric-motor Revised Manuscript Received on February 06, 2020. * Correspondence Author Balamurugan Annamalai*, Research Scholar, Dept. of EEE, Sathyabama Institute of Science and Technology, Tamil Nadu, India. Email: at.balamurugan@gmail.com Sivakumaran Thangavel Swaminathan, Professor & Principal, Dept. of EEE, Sasurie College of Engineering, Tiruppur, Tamil Nadu, India. malfunction, for example, loading variation and other motor functionality that all types of signs and symptoms; hence the relation is very difficult [3]. For this reason, it's quite tricky to identify motor's fault. For very long period, processes and several identification methods are obtained for example current analysis, vibration evaluation, thermal analysis and therefore forth. Some skilled strategies for fault identification of multiphase induction motor are grown [4]. At the moment, exploration fault investigation and identification process continues to be a substantial problem due to the fact that (i) the relationship between fault reason and symptom is quite sophisticated; (ii) the convenience of fault identification procedure for multiphase induction motor is quite confined; (iii) the artificial-intelligence identification procedure predicated on principle discursion, you can find lots of issues like comprehension expression and receiving, principle suit, etc. The procedure and the basic theory of fault identification of multiphase induction motor are all discussed [5, 6]. To the grounds of this study, the motor voltage and its slope are used as the features to diagnosis the fault in multiphase induction motor; and a identification system based on neural network has been now exhibited. By motor's state parameters, the procedure could recognize the different fault. This proposed approach is smart, dependable and accurate. The application of an artificial neural network (ANN) has stood out as a facilitating mechanism in solving problems in many areas [7]. In this perspective, a study was carried out through the implementation and analysis of radial basis function (RBF) neural network and multilayer perceptron (MLP), with the objective of comparing the results based on quantitative procedures, with emphasis on training and testing, assisting in the classification of fault in induction motor [8]. The article demonstrates the problems of diagnosing asynchronous motors in case of a malfunction of the rotor, stator and shaft bearing [9, 10]. For diagnostic purposes, methods of artificial intelligence on the basis of ANN are used. A feed forward neural network (FFNN) is used [8]. In this work, the ANN is trained and tested with the motor voltage and its slope. The effectiveness of the developed FFNN is estimated for fault diagnosis in multiphase induction motor. Fault Diagnosis in Multi Phase Induction Machine using Mind Evolution Computation Algorithm Optimized Neural Network Balamurugan Annamalai, Sivakumaran Thangavel Swaminathan