INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING Vol. 1, Issue 1, April 2013 Copyright to IJIREEICE www.ijireeice.com 10 ISSN 2321 – 2004 A NEW ADAPTIVE HYBRID NEURAL NETWORK AND FUZZY LOGIC BASED FAULT CLASSIFICATION APPROACH FOR TRANSMISSION LINES PROTECTION Prasad B 1 , B.Pakkiraiah 2 , Santosh Bejugam 3 , Ch Subba Reddy 4 Assistant Professor,Dept of EIE,GITAM University,Hyderabad, India 1 M.Tech Student, Dept of EEE, Vathsalya Institute of Science & Tech, Hyderabad, India 2,3,4 Abstract: Dynamic neural networks have been applied in system identification and control for those systems for last few years. A wide class of nonlinear physical systems contains slow and fast dynamic processes that occur at different moments. An adaptive hybrid neural networks and fuzzy logic based algorithm is proposed in this research to classify fault types in transmission lines. The proposed method is able to identify all the available shunt faults in transmission lines with high level of robustness against variable conditions such as measured amplitudes and fault resistance. In this method, a two-end unsynchronized measurement of the signals is used which can be incorporated in digital distance relays that are able to be programmed, it can also be shared and discourse data with all protective and monitoring device. The process has been carried over by a number of simulations using in MATLAB software. Key words: Fuzzy Logic System, Adaptive Artificial Neural Networks, Transmission Lines Protection. I INTRODUCTION The continuous growth of the demand for a reliable power supply results in a greater emphasis on the efficient operations of power systems. Therefore, the issues related to reduction in the duration of power supply interruptions are being raised more and more. In this regards, when a fault occurs in transmission networks, it is important to estimate the fault section quickly in order to restore the stable power supply as soon as possible .So, accurate, fast, and reliable fault classification technique is an important operational requirement in modern power transmission systems. The protection of transmission lines is very significant because large amounts of power are commonly shipped across a transmission system. Although the fundamentals of transmission lines protection were considered many years ago theoretical principles as well as practical applications are still common topics of investigation. With digital technology and advanced control strategies being ever increasingly adopted in power substations, more particularly in the protection field, protective relays have experienced some improvements, mainly related to efficient filtering methods (such as Fourier, Kalman, …etc.). As a consequence, shorter decision time has been the main objective, and was achieved in many researches. This research work employs Adaptive Neuro Fuzzy Inference System (ANFIS). This adaptive-network-based fuzzy inference system is used mainly here for fault classification in the transmission lines. Neural network has the shortcoming of implicit knowledge representation, whereas, fuzzy logic systems are subjective and heuristic. The determination of fuzzy rules, input and output scaling factors and choice of membership functions depend on trial and error that makes the design of fuzzy logic system a time consuming task. These drawbacks of neural network and fuzzy logic systems are overcome by the integration between the neural network technology and the fuzzy logic systems. II Design of the Proposed ANFIS for Fault Location A parallel-series ANFIS block is designed by using the MATLAB/SIMULINK software program according to the types of fault, as shown in Fig. 2. The design consists of 10 parallel main blocks represented by integers 1 to 10 for all