Real-time tracking control of DC motor based on neural network

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.