Automatically generated rules and membership functions for a neural fuzzy-based fault classifier

A new learning algorithm for an adaptive neural fuzzy (NF) system is proposed to automatically generate fuzzy rules as well membership functions. This adaptive neural fuzzy system is used for classifying faults in a power system. Remarkable results using this fuzzy fault classifier are reported in this paper. Furthermore, a fuzzy chip is used as the fuzzy classifier to achieve a low-cost real-time implementation.