Fuzzy logic based Fault Diagnosis in Induction Motor Greety Jose, P.G Scholar Dept.of Electrical&Electronics Amal Jyothi College of Engineering Kottayam,India greetyjose@ymail.com Victor Jose, Assistant Professor Dept. of Electrical&Electronics Amal Jyothi College of Engineering Kottayam,India victorjose@amaljyothi.ac.in Abstract— Induction motors are one of the commonly used electrical machines in industry because of many technical and economical reasons. They face various stresses during operating conditions leading to some modes of faults. Hence, condition monitoring becomes necessary in order to avoid catastrophic failures. Different fault monitoring techniques for induction motors can be broadly categorized as model based, signal processing based and soft computing techniques. It is difficult to obtain the accurate models of faulty machines and also to apply model based techniques. Soft computing techniques give good analysis of a faulty system even if accurate models are unavailable. These techniques are easy to extend and modify and also give improved performance. Here the different soft computing techniques for fault diagnosis are discussed. A methodology based on Park's Vector approach employing Fuzzy logic and Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to diagnose electrical faults. Different kinds of simulations are carried out corresponding to faults like stator voltage unbalance; stator open phase and stator short-circuit. Keywords- Induction Motor, Soft Computing, Signal Processing, Park’s Vector, Fuzzy Logic, Adaptive Neuro-Fuzzy Inference System (ANFIS) I. INTRODUCTION Induction motors are electro-mechanical devices used in most of the industrial applications. Although induction machines are considered relatively reliable and robust due to their simple design and well-developed manufacturing technologies, faults do occur and may severely disrupt industrial processes and even lead to disastrous accidents. If a fault is not detected or if it is allowed to develop further, it will lead to a failure. A variety of machine faults such as winding faults, broken rotor bars, unbalanced stator and rotor parameters, eccentricity and bearing faults may occur in an induction motor [1,2]. Several fault identification methods have been developed and been effectively applied to detect machine faults at different stages by using different machine variables, such as current, voltage, speed, temperature , efficiency and vibrations. Thus, considering safety and economic factors, it is essential to monitor the condition of motors of different sizes such as large and small. Condition monitoring involves taking measurements on a machine in order to detect faults with the aim of reducing both unexpected failures and maintenance costs. An effective condition-monitoring scheme is one that provides warning and predicts the faults at early stages. Monitoring system obtains information about the machine in the form of primary data and through the use of modern signal processing techniques; it is possible to give vital diagnostic information to equipment operator before it fails. The problem with this approach is that the results require constant human interpretation. The logical progression of condition-monitoring technologies is the automation of the diagnostic process. To automate the diagnostic process, a number of soft computing diagnostic techniques such as artificial neural network [13,14,15,16], fuzzy logic [19,20], adaptive neural fuzzy inference system and genetic algorithm [22] have been proposed. Soft computing techniques are employed to assist the diagnostic task to correctly interpret the fault data [3,4,5]. These techniques have gained popularity over other conventional techniques since they are easy to extend and modify besides their improved performance. The neural network can represent a non-linear model without knowledge of its actual structure. The use of above techniques increases the precision and accuracy of monitoring systems. Figure 1. The on-line condition monitoring process 14th National Conference on Technological Trends | 30 - 31, August 2013 | College of Engineering Trivandrum 150