Wavelet neural network based transient fault signal detection and identification

This paper proposes a novel approach to detect and identify transient fault signals. Because the fault signals are non-stationary transient ones, the traditional signal analysis methods, such as the FFT, are not so efficient and useful for fault signal detection. A wavelet neural network (WNN) is used to extract the signal features, and then a feedforward neural network (FNN) is used to identify and classify these features to detect the fault signals. The simulation shows that this method is suitable for application of transient fault detection.