Hermite neural network-based second-order sliding-mode control of synchronous reluctance motor drive systems

This paper proposes a novel Hermite neural network-based second-order sliding-mode (HNN-SOSM) control strategy for the synchronous reluctance motor (SynRM) drive system. The proposed HNN-SOSM is nonlinear vector consisting of speed loop and current loop. adopts composite controller, which composed three components: 1) standard super-twisting algorithm-based SOSM (STA-SOSM) controller achieving rotor angular tracking control, 2) HNN-based disturbance estimator (HNN-DE) compensating lumped disturbance, external disturbances parametric uncertainties, 3) an error compensator approximation HNN-DE. learning laws HNN-DE are derived by Lyapunov synthesis approach. In loop, considering magnetic saturation effect, two controllers, each comprises STA-SOSM designed to make direct quadrature axes stator components in reference frame track their references, respectively. Comparative hardware-in-the-loop (HIL) tests between conventional SynRM system performed. results HIL validate feasibility superiority strategy.