Adaptive recurrent neural network intelligent sliding mode control of permanent magnet linear synchronous motor

In permanent magnet linear synchronous motor systems, the nonlinear system functions in the dynamic model are difficult to obtain accurately, which leads to the reduction of system control performance. In this paper, an adaptive recurrent neural network intelligent sliding mode control (ARNISMC) strategy is proposed. The sliding mode controller is designed to improve the robustness of the system. Secondly, considering the nonlinear system function in the dynamic model of linear motor, it is approximated by recursive radial basis function neural network (RRBFNN). Then, the weight of RRBFNN is learned online by the adaptive algorithm and the approximation error of the nonlinear function is robustly compensated. The stability and convergence of the closed-loop system are proved based on the Lyapunov theory. Finally, the experimental results verify that the proposed ARNISMC not only achieves strong robustness, but also has better control accuracy than the original sliding mode control and radial basis function neural network sliding mode control method. In addition, it also shows the advantages of intelligent control.