International Journal of Research in Advent Technology, Vol.2, No.7, July 2014 E-ISSN: 2321-9637 187 Grey ANFIS Approach for Monitor Fault Pattern of Induction Motor 1 Anant G. Kulkarni, 2 Dr. M. F. Qureshi, 3 Dr. Manoj Jha 1 Research scholar, Dr. C. V. Raman University, Bilaspur, India, 2 Department of Electrical Engineering, Government Polytechnic, Kanker, Buster, India, 3 Department of Mathematics, Rungta Engineering College, Raipur, India, 1 anant.kulkarni@rungta.ac.in , 2 mfq_pro@rediffmail.com , 3 manojjha.2010@rediffmail.com Abstract: Grey GM (1, 1) is GrGM and neuro fuzzy system or neuro-fuzzy interface system (ANFIS) is discussed in this paper. ANFIS is used as a decision tool and GrGM combines with ANFIS. With the help of MATLAB simulation tool, studied simulation of bear game for evaluating the impact of proposed system using Grey ANFIS system. This paper studied the response of grey GM (1, 1) forecasting with ANFIS based order decision model, which is applied for diagnosis of fault pattern of induction motor. 1. INTRODUCTION When system faces difficulties of lake of sufficient amount of information and uncertainties then grey system theory (GST) overcome above two difficulties (Deng L.J. et. al, 1989). Now GST applied in the area of military, medical and engineering control applications. The term ‘grey’ indicates the system information that lies between the clearly and certainly known ones (the white part) and the unknown ones which contains no knowledge of the system structure (the black part). For GST model n is order of ordinary differential equation and m is number of grey variable, then regular differential equation is represented by GM (n, m). GM (n, m) consist accumulated generating operation (AGO) and inverse accumulated generic operation (IAGO). Discrete time sequence data is used to construct regular differential equation. m define the order of AGO and IAGO. GM is referred as grey differential model. Order n and grey variable m are increases then increases in the computation time exponentially causing likely defects and correctness. Model GM (1, 1) is important foundation for grey forecasting and most widely used model. Fewer requirements for computation and the usage for any kind of data distribution including small data sets are two advantages of GST. In GST accumulated generating operation (AGO) appears from its capability of turning unimproved stochastic data to useful regular’s series. In GST inverse accumulated generic operation (IAGO) convert this AGO generated regular series to row data sequences. An ANFIS is a network structure having nodes and directional links through which the nodes are connected. Grey ANFIS is grey GM (1, 1) forecasting with ANFIS based order decision model. Grey GM (1, 1) is GrGM and neuro fuzzy system or neuro-fuzzy interface system (ANFIS) will discuss. Grey system theory and neuro fuzzy system are explained below. Information concern for the system, many times there are lack of sufficient amount of information, uncertainties so grey system or grey system theory (GST) is referred (Deng L.J. et. al, 1989). It was initiated in 1982.In narrow way, human body, hydrology, agriculture, earthquake, faults in motors, etc are grey systems. It is closer to fuzzy logic in nature, new and completely crisp. Block diagram of GST is shown in figure 1, which the system information (Grey portion) that lies between the clearly and certainly known ones (the white part) and the unknown ones which contains any knowledge of the system structure (the black part). Grey system includes partially known and partially unknown characteristics. Figure 1: Grey system theory (GST) GREY SYSTEM THEORY KNOWN PARTIALLY KNOWN PARTIALLY UNKNOWN UNKNOWN