Composite control based on FNTSMC and adaptive neural network for PMSM system

In this paper, a novel fixed-time non-singular terminal sliding mode control (NFNTSMC) method with an adaptive neural network (ANN) is proposed for permanent magnet synchronous motor (PMSM) system to improve PMSM performance. For nominal PMSM system without disturbance, a novel fixed-time non-singular terminal sliding mode control is designed to achieve fixed-time convergence property to improve the dynamic performance of the system. However, parameters mismatch and external load disturbances generally exist in PMSM system, the controller designed by NFNTSMC requires a large switching gain to ensure the robustness of the system, which will cause high-frequency sliding mode chattering. Therefore, an adaptive radial basis function (RBF) neural network is designed to approximate the unknown nonlinear lumped disturbance including parameters mismatch and external load disturbances online, and then the output of the neural network can be compensated to the NFNTSMC controller to reduce the switching gain and sliding mode chattering. Finally, the fixed-time convergence property and stability of the system are proved by Lyapunov method. The simulation and experimental results show that the presented strategy possesses satisfactory dynamic performance and strong robustness for PMSM system. And the proposed control scheme also provides an effective and systematic idea of the controller design for PMSM.