基于BP神经网络的同步电机转矩控制技术研究  

Research on Torque Control Technology for Synchronous Motor Based on BP Neural Network

作　　者：邱腾飞 殷振环 刘伟志 黄少东 QIU Teng-fei;YIN Zhen-huan;LIU Wei-zhi;HUANG Shao-dong(Locomotive and Car Research Institute of China Academy of Railway Sciences Corporation Limited,Beijing100081,China;不详)

机构地区：[1]中国铁道科学研究院集团有限公司机车车辆研究所,北京100081 [2]北京纵横机电科技有限公司,北京100094 [3]中车唐山机车车辆有限公司,河北唐山063035

出　　处：《电力电子技术》2022年第12期95-98,共4页Power Electronics

基　　金：中国铁道科学研究院集团有限公司院基金课题(2151ZHN501)。

摘　　要：弱磁控制和转矩精确控制是永磁同步电机(PMSM)控制系统的两个难点。通过利用反向传播(BP)神经网络结构,提出一种PMSM转矩控制方法。该方法在恒转矩区和弱磁区均能够实现转矩的精确控制,同时避免了弱磁比例积分(PI)参数对控制性能的影响。通过对一台100kW的永磁电机进行实验,证明了该方法的有效性。Field-weakening control and high-precision torque control are two key points of permanent magnet synchronous motor(PMSM)control system.By using back propagation(BP)neural network structure,a new method for torque control of PMSM is presented.This method can realize the precise control of the torque in the constant torque region and the field-weakening region,and avoid the influence of the field-weakening proportional integral(PI)parameters on the control performance.An experimental verification of a 100 kW permanent magnet motor is carried out to demonstrate the effectiveness of the proposed method.

关 键 词：永磁同步电机 弱磁控制 神经网络 转矩控制 

分 类 号：TM351[电气工程—电机]