Fault Detection and Localization using Continuous Wavelet Transform and Artificial Neural Network Based Approach in Distribution System

Abstract

This article presents an advanced continuous wavelet transform (CWT) based approach for fault detection and localization in distribution systems using the artificial neural network (ANN). In this study, CWT extracts distinct features from the transient signals captured from the bus. The derived features are utilized to train and test appropriate ANN architecture in different stages to detect and localize the faults. The proposed scheme provides an optimum method for classification as well as localization of the various kinds of fault with different source short circuit (SSC) level in different locations. The whole detection and localization process consists of several stages. In the first stage, it detects faulty feeder. The faulty line is identified in the second stage. Finally, in the third stage, fault type and fault location are being calculated from the relaying point. The performance of the proposed CWT-ANN based approach is quite promising as compared to traditionally used algorithms. However, a correlation-based feature selection technique is also implemented to reduce training time and improve accuracy. This algorithm is tested in 11 kV radial Indian distribution network but can be applied in other distribution networks also.

Predicting The Number of Tourists Based on Backpropagation Algorithm

“…ANN is a system used to process data by adapting the structure of the human biological neural network in solving a problem [10]. ANN can be used for decision making as humans do with non-rigid thinking [11]. There are various kinds of algorithms in artificial neural networks, one of which is the backpropagation algorithm.…”