Neural-network-based adaptive sliding mode control for PMSM
基于神经网络的PMSM自适应滑模控制

With the combination of the merits of sliding-mode control and neural network,a neural-network-based adaptive sliding-mode control scheme for permanent magnet synchronous motor (PMSM) is proposed.First,a sliding-mode controller with an integral-operation switching surface is designed.Then a recurrent neural network is used to estimate the upper bound of uncertainties in real-time,which include parameter variations and external load disturbance,such that the control effort of the sliding-mode controller is reduced.Furthermore,in order to reduce the chattering phenomenon,the sign function in sliding-mode controller is replaced by the saturation function.Theoretical analysis and experiment simulation results show that the proposed strategy has high-performance dynamic characteristics and stronger robustness.