基于自适应人工神经网络的无刷直流电机换相转矩波动抑制新方法.pdf

22 1 Vol. 22 No. 1 Jan. 2002 2002 1 Proceedings of t he CSEE 2002 Chin. Soc. for Elec. Eng . (2002) 01005 05 夏长亮, 文 德, 王 娟 ( 天津大学电气自动化与能源工程学院, 天津300072) A NEW APPROACH OF MINIMIZING COMMUTATION TORQUE RIPPLE FOR BRUSHLESS DC MOTOR BASED ON ADAPTIVE ANN XIA Changliang, WEN De, WANG Juan ( School of Electrical Engineering and Energy , T ianjin U niversity, Tianjin 300072, China) ABSTRACT: In this paper, t he principle of commutation torque , ripple ( CTR) for brushless DC motor is analyzed, and a new approach of minimizing CT R is presented, which is based on adaptive artificial neural netw ork ( ANN) control. Tw o three layer forw ard artificial neural networks are trained both in off : ; ; line and in online ways, and the weights in netw orks are up : TM383 : A dated using the error back propagation ( BP) algorithm. One of t he networks is used to estimate the commutation parameters of 1 t he motor online. T he other is used to regulate the terminal voltages using the parameters estimated by the former network during commutation. In this way, the w hole model can be con , , sidered as a voltage selftuning regulator ( STR) . Through reg , ulating the terminal voltages of motor, the ST R makes the ris ing ratio and dropping ratio of the phase currents be approxi mate in order to keep the amplitude of the total current in the circuit constant , so as to minimize CTR. This approach is un , necessary to know the accurate system parameters, and can [ 1,2] Carlson modify the model adaptively w hile parameters are changed. The [ 1]