Neural-Network-Estimator-Based Twin Sliding Mode Controller Design for Vector Controlled Induction Motor Drives

This work presents a twin sliding mode controller (TSMC) and neural network-based estimators for vector controlled induction motor (IM) drives. The proposed TSMC is used as a speed controller. In contrast with conventional sliding mode control (SMC), the TSMC can more significantly improve the dynamic response and eliminate the chattering effect. Additionally, estimators are implemented respectively by designing a novel neural network PI controller to provide a real-time adaptive estimation of the motor speed and the rotor resistance. Experiments performed on a 3hp IM confirm the effectiveness of the proposed approach.