A Non-Integer High-Order Sliding Mode Control of Induction Motor with Machine Learning-Based Speed Observer

The induction motor (IM) drives are prone to various uncertainties, disturbances, and non-linear dynamics. A high-performance control system is essential in the outer loop guarantee accurate convergence of speed torque required value. Super-twisting sliding mode (ST-SMC) fractional-order calculus have been widely used enhance (SMC) performance for IM drives. This paper combines ST-SMC attributes propose a novel super-twisting (ST-FOSMC) model predictive (MPTC)-based drive system. MPTC requires some additional sensors control. also presents machine learning-based Gaussian Process Regression (GPR) framework estimate IM. GPR trained using voltage current dataset obtained from simulation three-phase based GPR-based ST-FOSMC evaluated test cases, namely (a) electric fault incorporation, (b) parameter perturbation, (c) load variations Matlab/Simulink environment. stability validated Lyapunov function. proposed estimation strategy provides effective improved with minimal error compared conventional proportional integral (PI) SMC strategies.