Neural Network PID Controller for PMSM Drives

The design of MLP NN (Multilayer perceptron neural network) self-tuning PID controller for PMSM drive is proposed in this paper. To cope with the system and external load uncertainly, a self-tuning PID controller using MLP NN is adopted and derived for PMSM drive. MLP is used to identify the plant first. Then the Jacobian information of controlled plant obtained by MLP NN identification is used to adjust the gain of PID controller. A robust parameters self-tuning learning algorithm is used to train the NN for fast convergence. Simulation results show that the proposed controller has the adaptability, strong robustness and satisfactory control performance in PMSM servo system.