Optimal Tuning of Fractional Order Sliding Mode Controller for PMSM Speed Using Neural Network with Reinforcement Learning

An improved fractional-order sliding mode control (FOSMC) for PMSM is presented in this study to set the unavoidable parameters and improve permanent magnet synchronous motors (PMSMs) drive performance, such as current speed tracking accuracy. To determine optimal of FOSMC a drive, neural network algorithm with reinforcement learning (RLNNA) proposed. The are by ANN then adapted through enhance results. proposed controller using RLNNA based on (RLNNA-FOSMC) can motor achieve referred value finite period time, leading faster convergence For fair comparison evaluation, RLNNA-FOSMC compared conventional applying integral time multiplied absolute error an objective function. most commonly used functions literature were also compared, including square error, error. validate performance controller, different scenarios speeds steps carried out. computational results promising demonstrate effectiveness controller. Overall, system performed better than numerical simulations.