基于神经网络的直流电动机实时跟踪控制

Real-Time Tracking Control of DC Motor Based on Neural Network

研究了三层对角回归神经网络 (DRNN)用于直流电动机实时控制的方法。首先采用动态反传算法训练神经网络以辨识直流电动机的逆模型 ,然后将这一训练后的网络作为前馈控制器与常规反馈控制器一起输出控制电压 ,以控制系统跟踪位置或速度指令。该算法简单、计算量小 ,适于实时控制。仿真结果表明了该方法的有效性。

In this paper, three layers DRNN is used in the real-time identification and control of DC motor. Firstly, the DRNN is trained using dynamic error back propagation algorithm (DBP) to learn the inverse dynamics of the system and when the training is completed, combining with the conventional fixed gain feedback controller, the neural network is used as a feedforward controller to generate control voltage to force the motor to follow a pre-selected trajectories in position or speed. The iteration algorithm is simple and much less calculation time is needed. Simulation results show the effectiveness of the algorithm.