Torque Ripple Minimization of Variable Reluctance Motor Using Reinforcement Dual NNs Learning Architecture

The torque ripples in a switched reluctance motor (SRM) are minimized via an optimal adaptive dynamic regulator that is presented this research. A novel reinforcement neural network learning approach based on machine adopted to find the best solution for tracking problem of SRM drive real time. reference signal model which minimizes pulsations combined with error construct augmented structure drive. discounted cost function described assess performance signal. In order track trajectory, (NN)-based RL has been developed. This method achieves response Hamilton–Jacobi–Bellman (HJB) equation nonlinear system. To do so, two networks (NNs) have trained online individually acquire control policy allow motor. Simulation findings undertaken confirm viability suggested strategy.