永磁同步电机的无位置传感器控制参数优化

Sensorless control of permanent magnet synchronous motorparameter optimization

永磁同步电机无位置传感器控制依赖于转子位置观测器,观测器的精度直接影响电机的控制。针对转子位置观测器中参数整定过程计算较为复杂的问题,提出一种基于误差反向传播(BP)神经网络来优化转子位置观测器的方法,利用所提出的误差反向传播(BP)神经网络优化转子位置观测器的参数,实现永磁同步电机无位置传感器优化控制。通过MATLAB/Simulink搭建仿真实验平台证明,并通过和传统公式整定方法对比分析,误差反向传播(BP)神经元网络能够快速准确地计算出转子位置观测器中的参数。

The sensorless control of the PMSM depends on the rotor position observer,and the accuracy of the observer directly affects the control of the motor.In order to solve the complex problem of the parameter setting process in the rotor position observer,this paper proposes a method to optimize the rotor position observer based on the error back-propagation(BP)neural network,and uses the proposed error back-propagation(BP)neural network to optimize the parameters of the rotor position observer to realize the sensorless optimal control of permanent magnet synchronous motor.It is proved by MATLAB/Simulink that BP neural network can calculate the parameters of rotor position observer quickly and accurately by comparing with traditional formula setting method.