Extreme learning machine-based super-twisting integral terminal sliding mode speed control of permanent magnet synchronous motors

Abstract

This article proposes an extreme learning machine (ELM)-based super-twisting integral terminal sliding mode control (STITSMC) for speed regulation of a permanent magnet synchronous motor (PMSM). First, the PMSM is modeled in a non-cascade control structure for fast system response and uncertainty compensation in the speed and torque loops. Second, the STITSMC is designed with integral actions in both the sliding surface and the reaching law to reduce chattering. Third, the ELM is constructed to compensate for the system lumped disturbance, and relax the disturbance upper bound required by the controller which further reduces the chattering. Fourth, the stability of the whole control system is proved based on the Lyapunov method and the finite time convergence regions are derived for both the reaching and the sliding phases. Finally, the comparative simulations and experiments are conducted to show the superiority of the proposed control.