On-line gain tuning using RFNN for linear synchronous motor

F. J. Lin, C. H. Lin

研究成果: 雜誌貢獻會議論文同行評審

7 引文 斯高帕斯(Scopus)

摘要

In this study an integral-proportional (IP) controller with on-line gain tuning using a recurrent fuzzy-neural-network (RFNN) is proposed to control a permanent magnet linear synchronous motor (PMLSM) drive system. First, the structure and operating principle of the PMLSM are described in detail. Second, an IP controller with gain-tuning using a RFNN is proposed to control the position of the moving table of the PMLSM achieve high-precision position control with robustness. The backpropagation algorithm is used to train the RFNN online. Then, an IP controller with gain tuning using a RFNN is implemented in a PC-based computer control system. Finally, the effectiveness of an IP controller with gain tuning using a RFNN controlled PMLSM drive system is demonstrated by some experimental results. Accurate tracking response and superior dynamic performance can be obtained due to the powerful on-line learning capability of the RFNN. Furthermore, an IP controller with gain tuning using a RFNN is robust with regard to parametric variations.

原文???core.languages.en_GB???
頁(從 - 到)766-771
頁數6
期刊PESC Record - IEEE Annual Power Electronics Specialists Conference
2
出版狀態已出版 - 2001
事件2001 IEEE 32nd Annual Power Electronics Specialists Conference - Vancouver, BC, Canada
持續時間: 17 6月 200121 6月 2001

指紋

深入研究「On-line gain tuning using RFNN for linear synchronous motor」主題。共同形成了獨特的指紋。

引用此