https://scholars.lib.ntu.edu.tw/handle/123456789/576852
標題: | Reinforcement learning control for six-phase permanent magnet synchronous motor position servo drive | 作者: | Peng W.-L Lan Y.-W Chen S.-G Lin F.-J Chang R.-I Ho J.-M. RAY-I CHANG |
關鍵字: | Controllers; Deep learning; Patents and inventions; Permanent magnets; Reinforcement learning; Synchronous motors; Cerebellar model articulation; Comparison study; Ideal controllers; Nonlinear dynamic behaviors; Permanent Magnet Synchronous Motor; Reference trajectories; Reinforcement learning control; Tracking errors; Electric machine control | 公開日期: | 2020 | 起(迄)頁: | 332-335 | 來源出版物: | Proceedings of the 3rd IEEE International Conference on Knowledge Innovation and Invention 2020, ICKII 2020 | 摘要: | Since the permanent magnet synchronous motor (PMSM) has nonlinear dynamic behavior characteristics, it is difficult to develop an ideal controller. In this paper, we develop a novel method for the six-phase PMSM (6PPMSM) position servo drive based on deep reinforcement learning (RL). Comparison studies between the proposed controller and the recurrent fuzzy neural cerebellar model articulation network (RFNCMAN) controller are presented. The results show that our controller can follow the reference trajectories more precisely in general cases, where the average tracking error obtained is 90% smaller than that of RFNCMAN. ? 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100525939&doi=10.1109%2fICKII50300.2020.9318882&partnerID=40&md5=a77d3a11a2f310c71079a655a0c07214 https://scholars.lib.ntu.edu.tw/handle/123456789/576852 |
DOI: | 10.1109/ICKII50300.2020.9318882 |
顯示於: | 工程科學及海洋工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。