A Fault Classification Method Based on Wavelet Neural Networks and Fault Record Data
Yue Quan-ming · Proceedings of the CSEE · 2006
When complicated faults in a large area are happened in a power system, it is difficult for management and running personnel to judge them accurately according to the shift information of relays and switches contact from SCADA system only. The analog information that comes from fault record equipments becomes the important basis of fault diagnosis and system recovery more and more. In order to improve fault recognition capability and computational speed of the fault diagnosis system, this paper presents a new wavelet neural network mode constructed from lifting wavelet and PNN neural network. The coefficients of fault currents in the low frequency band between 0 and 375 Hz that decomposed by bior3.1 lifting wavelet are put into the neural network. Through ATP simulation and the test of real fault record data from the power network in East of China, the result indicates that the mentioned model in this paper has very high recognition rate and convergence speed. It is likely to apply this model in a fault diagnosis system of a power network.