基于模糊RBF神经网络的永磁同步电机位置控制

针对比例-积分-微分(PID)控制器参数固定而引起永磁同步电机位置伺服系统控制效果不佳问题,设计了基于平滑切换的模糊PI控制和径向基函数(RBF)神经网络PID控制的位置控制器。暂态时,采用模糊PI控制;稳态时,采用RBF神经网络PID控制,两者中间采用模糊PI-RBF神经网络PID复合控制。该位置控制器既结合了模糊PI控制和RBF神经网络PID控制的优点又克服了各自的缺点。仿真结果表明,当永磁同步电机受到外部扰动时,采用模糊RBF神经网络控制器的永磁同步电机位置系统具有良好的动态性能,能够实现快速响应,做到精确定位,而且当负载变化时具有很强的抗干扰性。

Permanent Magnet Synchronous Motor Position Control Based on Fuzzy Radial Basis Function Neural Network

Aiming at the unsatisfactory control performance of permanent magnet synchronous motor （PMSM） position servo system which is caused by fixed parameters of proportional integral derivative （PID） controller,a position controller combined with fuzzy PI control and radial basis function （RBF） neural network PID control based on smooth switching is proposed in this paper.The fuzzy PI control is applied to the position control in the transient state,the RBF neural network PID control is applied to the position control in the steady state,and the compound control of fuzzy PI-RBF neural network PID is applied to the position control in the intermediate state.The position controller has advantages of both fuzzy PI control and RBF neural network PID control,and overcomes their shortcomings.The simulation results verify that the PMSM position servo system adopted fuzzy RBF neural network controller has good dynamic performance and high precise positioning under the occurrence of external disturbance.Furthermore,the system has better anti-interference to load disturbance variation.