A Robust and Adaptive RBF Neural Network Based on Sliding Mode Controller for Interior Permanent Magnet Synchronous Motors

Electric motors play an important role in consumer and manufacturing industries. Among all different kinds of electric motors, Interior Permanent Magnet Synchronous Motors (IPMSM) have a special place. That is because of their high torque to current ratio, large power to weight ratio, high efficiency, high power factor and robustness. In this paper a radial basis function (RBF) neural network based on sliding mode controller (SMC) is presented to control IPMSM. A RBF neural network is formulated as a controller whose parameters must be updated. To guarantee the robustness of the closed-loop system, a modified SMC methodology is designed to derive an adaptation law for the parameters of neural network controller. The weights of the neural network can be adaptively adjusted for the compensation of uncertain dynamics and the tracking error between the plant output and the model output can be guaranteed to converge to zero in a finite time. The effectiveness of the proposed control system is verified by some simulations results. Obtained results show the response time is also very fast despite the fact that the control strategy is based on bounded rationality. Key-Words: Speed Control, IPMSM, Disturbance, Nonlinear model, RBF neural network, Sliding mode control