基于小波神经网络PID的永磁同步电机转速控制

提出了基于小波神经网络PID的永磁同步电机(PMSM)转速控制策略。根据系统运行参数的变化,采用三层前馈式人工神经网络,基于梯度下降纠正误差法在线训练实时更新PID参数值。采用小波神经网络和增量式PID共同构成转速环控制器。建立PMSM数学模型,设计PMSM速度环控制器,构建S函数,对控制算法进行仿真试验,验证了该控制算法的先进性。试验结果表明,所提控制策略比传统PID转速控制具有更好的动态性能和抗干扰能力。

Speed Control of Permanent Magnet Synchronous Motor Based onWavelet Neural Network PID

A speed control strategy of permanent magnet synchronous motor (PMSM) based on wavelet neural network PID was proposed. According to the change of system operation parameters, a threelayer feedforward artificial neural network was used to update the PID parameters. It trained the PID parameters online based on gradient descent correction error method in real time. Wavelet neural network and incremental PID were used to construct the speed loop controller. The mathematic model of PMSM was established. The speed loop controller of PMSM was designed. The S function was constructed to simulate the control algorithm, which verified the progressiveness of the control algorithm. The experimental results showed that the proposed control strategy had better dynamic performance and antiinterference ability than traditional PID speed control.