Fault Pattern Recognition of Turbine-Generator Set Based on Wavelet Network and Fractal Theory

In order to improve fault detection sensibility, a fault diagnosis method for turbine-generator based on wavelet network and fractal theory is presented. In this method, wavelet transform is used to extract fault characteristics and neural network is used to diagnose the fault mode. In a view of the inter relationship of wavelet transform between fractal theory, the whole and local fractal exponents obtained from wavelet transform coefficients as features are presented for extracting fault signals, which are inputted into radial basis function for fault pattern recognition. The fault diagnosis model of turbine-generator set is established and the improved Levenberg-Marquardt optimization technique is used to fulfill the network structure and parameter identification. The wavelet fractal network is most suitable for post-fault detection and steady-state signal analysis in industrial distribution power system. The application results are shown and they indicate that the proposed method can be used as an effective tool for concurrent fault diagnosis, and the computational burden is reduced rapidly.