Improvement of Fault Identification and Localization Using Gustafson-Kessel Algorithm In Adaptive Neuro-Fuzzy Inference System

Most of the techniques on identifying fault location depend on parameters of power transmission line. Thus, a complex mathematical solution will be considered which at such conditions, the dependence on line parameters will limit performance of algorithms. An independent or parameters free algorithm is an option to overcome this problem by using an artificial intelligent technique. This paper presents a recent scheme including of fault identification, and fault localization to estimate the distance of fault. A 115 kV parallel transmission line system has been used to develop and implement the proposed scheme. We used the approach of hybrid intelligent method called adaptive neuro-fuzzy inference system (ANFIS) combine with discrete wavelet transform (DWT) to obtain a great performance. A novel approach of implementing Gustafson-Kessel (GK) clustering algorithm has improved the stability and accuracy of performance. Results show that the proposed scheme can contributes as an efficient tool to overcome the obstacles in analysis of fault data.