REMOTE DIAGNOSIS SYSTEM OF HYDRO-GENERATOR SETS BASED ON WAVELET-NEURAL NETWORK

X.Y. Chen and W. Wu

Keywords

Wavelet packet decomposition, energy feature, BP Neural Network, remote diagnosis, Matlab Web Server, hydrogenerator sets

Abstract

According to diversity and complexity of hydro-generator sets faults, a type of remote monitoring and diagnosis system is brought forward which is based on wavelet packet decomposition, BP Neural Network and Matlab Web Server. Firstly, wavelet packet decomposition is introduced to acquire energy of hydro-generator sets signal’s frequency band to be feature parameter. Secondly, BP Neural Network algorithm is analysed. Momentum term is introduced to improve BP Neural Network learning rate. It reduces BP Network input dimension and improves BP Neural Network performance by use of extracting some energy features as BP Network input variables. Thirdly, it is the first time to adopt Matlab Web Server to hydro-generator sets faults diagnosis to implement distributed remote monitoring and diagnosis system. Therefore, remote diagnosis application is independent from operating system (OS) used on server side. Most of all, clients can finish remote diagnosis by web browser and without installation of Matlab software.

Important Links:



Go Back