The design of brushless DC motor servo system based on wavelet ANN

The paper presents a new approach to brushless DC motor servo system, which is based on artificial neural network (ANN) and wavelet transform. The approach is designed based on a three-layer forward artificial neural network, which trains and replaces network parameters in-line using a gradient descending error algorithm. The working and fault states of brushless DC motor are detected, in which the time-frequency characteristics of discrete wavelet transform (DWT) and local maximum of modulus of continuous wavelet transform (CWT) are used. The simulation result shows that the system using the approach has very good dynamic and static performances, it is sensitive to fault and robust to noise, and it has a vast applying prospect.