A Novel Terminal Sliding Mode Control Based on RBF Neural Network For The Permanent Magnet Synchronous Motor

This paper presents a novel terminal sliding mode control (TSMC) based on the radial basis functions neural network (RBFNN) for the permanent magnet synchronous motor (PMSM). The designed controller is composed of a RBFNN and a terminal sliding mode controller. The RBFNN is introduced to approximate the uncertainties of the PMSM system. And a novel adaptive algorithm is proposed to achieve the finite time convergence of the connection weights of RBFNN to the ideal value, which improves the system control performance and reduces the chattering. Combined with the RBFNN, a terminal sliding mode controller is designed for the PMSM speed tracking. The stability of the closed loop system is proved according to Lyapunov stability theory. The effectiveness of the proposed method is verified by the corresponding simulations, and the results show that the proposed controller possesses the better speed tracking performance.