Adaptive Super-Twisting Sliding-Mode Control via TSK-Petri Fuzzy-Neural-Network for Induction Motor Servo Drive System

Abstract

This paper presents an adaptive super-twisting sliding-mode control (ASTSMC) scheme using Takagi-Sugeno-Kang recurrent Petri fuzzy-neural-network (TSK-RPFNN) for induction motor (IM) drive system with uncertain nonlinear dynamics. First, a super-twisting sliding-mode controller (STSMC) is adopted for reducing the chattering phenomenon and stabilizing the IM drive. However, the control performance may be affected due external disturbances and parameter disparities of the IM drive. In addition, the conservative selection of the control gains may affect the control performance. Therefore, to improve the robustness of the control system performance and to resolve these problems, an ASTSMC is proposed, which incorporates a STSMC with adaptive TSK-RPFNN estimators. For avoiding both the chattering and the constraints on the knowledge of disturbances and uncertainties upper bounds, TSK-RPFNN estimators are designed for approximating the nonlinear functions of the IM drive and computing the optimal control gains of the super-twisting algorithms online. Furthermore, the online adaptive laws are derived based on Lyapunov approach, so that the stability and robustness of the whole control system are assured. A real-time implementation is performed via dSPACE 1104 for verifying the proposed ASTSMC efficacy. Furthermore, the experimental results using ASTSMC endorse superior dynamic performance regardless of unknown model uncertainties and external disturbances.