Distribution Network Fault Diagnosis Method Based on Granular Computing-BP

Abstract

To deal with the complexity and uncertainty of distribution network fault information, a method of fault diagnosis based on granular computing and BP is proposed. This method uses attribute reduction advantages of granular computing theory and self-learning and knowledge acquisition ability of BP neural network. It put granular computing theory as the front-end processor of the BP neural network, namely simplify primitive information making use of granular computing reduction, and according to the concepts of relative granularity and significance of attributes based on binary granular computing are proposed to select input of BP, thereby reducing solving scale, and then construct neural network based on the minimum attribute sets, using BP neural network to model and parameter identify, reduce the BP study training time, improve the accuracy of the fault diagnosis. The distribution network example verifies the rationality and effectiveness of the proposed method. DOI: http://dx.doi.org/10.11591/telkomnika.v11i3.2184