Authors: Tejaswini Taware
Abstract: This seminar work presents a reinforcement learn-ing based field-oriented control strategy for Permanent Magnet Synchronous Motor (PMSM) drives. A Twin Delayed Deep Deterministic Policy Gradient (TD3) agent is used to replace the conventional PI current controller in the dq-axis current loop. The controller is validated using a 10 s staircase per-unit speed profile with repeated acceleration and braking transitions. The obtained results show fast tracking, low overshoot, stable dq current regulation, and improved robustness for practical intelligent drive applications.
DOI: https://doi.org/10.5281/zenodo.20180838
