An Optimized Commutation Method for Sensorless Brushless DC Motor Based on Back Electromotive Force Using Backpropogation Neural Network

In this paper, an optimized commutation method based on BP neural network is proposed to solve the problem of slow response, large overshoot and power dissipation caused by algorithm deviation in conventional commutation strategy based on back electromotive force method. Performance of different commutation methods is compared by simulation. Experiment results show that the proposed method can realize a good commutation performance, with a 0.8% power deviation and a 15.906 mean square error compared with ideal condition, which improves 275 times than conventional strategy, 42 times than conventional Neural Network based strategy and has a better stability. The proposed method has better compensation ability for fixed errors such as signal transmission delay, signal filtering delay and motor armature effect at the same time.