Recurrent neural fuzzy network for high-precision motion control of PMLSM drives 林文麒、陳昭雄
E-mail: [email protected]
ABSTRACT
This thesis proposes a recurrent neural fuzzy network (RNFN) for the high-precision motion control of permanent magnet linear synchronous motor (PMLSM) drives. The RNFN Control system consists of two network structures; namely, RNFN identifier (RNFI) and RNFN Controller (RNFC). The RNFI is first trained to capture the inverse dynamics of the PMLSM drive and then is used as a feedforward controller to calculate the desired control force of the PMLSM along a desired trajectory; while RNFC is used as an error-feedback Compensator to minimize the trajectory tracking error resulted from system uncertainties. Structure and Parameter learning algorithms are concurrently preformed is RNFN online. A recursive recurrent learning algorithm based on the gradient descent method is derived for the parameter learning. An analytical method based on a discrete-type Lyapunov function is proposed to guarantee the convergence of RNFN by choosing varied rates. The experimental setup is comprised by a host computer, a servo controller board, a motor driver and a PMLSM. Simulation sand experiments performed on a PMLSM drive demonstrate the effectiveness off the proposed control system.
Keywords : Recurrent neural fuzzy network、Linear synchronous motor、Network convergence theorem Table of Contents
目錄 封面內頁 簽名頁 授權書...iii 中文摘要...iv 英文摘 要...v 致謝...vi 目錄...vii 圖目
錄...ix 表目錄...xi 符號說明...xii 第一章 緒 論...1 1.1 研究動機...1 1.2 研究目的與方法...2 1.3 文獻回
顧...3 1.4 論文結構...4 第二章 系統硬體架構介紹...6 2.1永磁式同步線性馬達 硬體系統架構...6 2.2線性同步馬達動作原理與分類...14 2.2.1線性同步馬達分類...14 2.2.2線性同 步馬達作動原理...15 第三章 永磁同步線性馬達數學模型計...18 3.1座標轉換...18 3.2 永磁式同步線性馬達數學模型...21 第四章 模糊類神經網路控制系統...24 4.1 反覆類神經模糊網路的結 構...24 4.2 結構學習算法...27 4.3參數學習算法...29 4.4 RNFN控制系
統...34 4.5 RNFI和RNFC的敘述...35 4.6 RNFN的收斂分析...37 第五章 模擬、實驗 與結果...42 5.1線性永磁式同步馬達驅動系統的實驗平台...42 5.2線性永磁式同步馬達逆向動態建 模...43 5.3控制系統模擬...44 5.3.1 CASE1的模擬結果...47 5.3.2 CASE2的模擬 結果...52 5.3.3 CASE3的模擬結果...57 5.4控制系統實驗...62 5.4.1 CASE1的實驗結果...62 5.4.2 CASE2的實驗結果...67 第六章 結論...72 參考文獻...73
REFERENCES
[1] 蔡凱宸 (民 95)，“以DSP為控制架構之線性馬達驅動系統之研究”，大葉大學，機電自動畫研究所，碩士論文。
[2] 林法正，魏榮宗(民91)，“電機控制”，頁284-290，滄海書局。
[3] 劉昌煥（民94），“電動機控制:向量控制與直接轉矩控制原理”， 東華書局。
[4] 張育暢，“具小腦模型之永磁式線性同步馬達控制器之設計與實現 ，大同大學電機工程系，碩士論文，2003。
[5] 楊柏森，“線性馬達系統推導與控制模擬 ，逢甲大學自動控制工程學系，碩士論文，2000。
[6] H. Wakiwaka, H. Yajima, and H. Yamada, “Design and evaluation of linear DC motor for pen recorder”, IEEE Transactions on Magnetics, Vol.31, No.6, pp.3755-3757， 1955.
[7] H. Yajima, H. Wakiwaka, and S. Senoh, “Consideration on high-response of a linear DC motor”, IEEE Transactions on Magnetics, Vol.33, No.5, pp.3880-3882, 1997.
[8] P. Famouri, “Control of linear permanent magnet brushless DC motor via exact linearization methods”, IEEE Transactions on Encrgy Conversion, Vol.7, No.3, pp.544-551, 1992.
[9] Y.S. Kung, Design and implementation of a high-performance PMLSM drives using DSP chip,IEEE Transactions on Industrial Electronics (55)
(3) (2008) 1341-1351.
[10] K.K. Shyu and H.J. Shieh, “A new Switching surface sliding-mode speed control for induction motor drive systems”, IEEE Transactions on Power Electronics, Vol.11, No.4, pp.660-667, 1996.
[11] F.J. Lin, “Incremental motion control of linear synchronous motor”, IEEE Transaction on Aerospace and Electronic Systems Vol.38, No.3, pp.1011-1022, 2002.
[12] D.S. Reay, M.Mirkazemi-Moud, and B.W. Williams, “On the appropriate uses of fuzzy systems: Fuzzy sliding mode position control of a switched reluctance motor”, IEEE International Symposium on 27-29 Aug, pp.371-376, 1995.
[13] F.-J. Lin, “Robust controller design with recurrent neural network for linear synchronous motor drive”, IEEE Transactions on Industrial Electronics, Vol.50, No.3, pp.456-470, 2003. ∞H [14] C.H. Lin, W.D. Chou, and F.J. Lin, “Adaptive hybrid control using a recurrent neural network for a linear synchronous motor servo-drive system”, IEE Proc.-Control Theory Appl., Vol.148, No.2, pp.156-168, 2001.
[15] W.T. Su, C.M. Liaw, Adaptive positioning control for a LPMSM drive based on adapted inverse model and robust disturbance observer, IEEE Transactions on Power Electronics (21)(2) (2006) 505-517.
[16] F.J. Lin, “Hybrid supervisory control using recurrent fuzzy neural network for tracking periodic inputs”, IEEE Transactions on Neural Networks, Vol.12, No.1, pp.68-90, 2001.
[17] F.J. Lin, “On-line gain-tuning IP controller using RFNN”, IEEE Transactions on Aerospace and Electronic Systems, Vol.37, No.2, pp.655-670, 2001.
[18] K. K. Tan, T. H. Lee, H. F. Dou, S. J. Chin, S. Zhao, Precision motion control with disturbance observer for pulsewidth-modulated-driven permanent-magnet linear motors, IEEE Transactions on Magnetics (39) (3) (2003) 1813–1818.
[19]J. F. Gieras and Z. J. Piech, “Linear synchronous motors: transportation and automation systems,” CRC Press, 2000.
[20] Z.H. Su, K. Khorasani, A neural-network-based controller for a single-link flexible manipulator using the inverse dynamics approach, IEEE Transactions on Industrial Electronics (48) (6) (2001) 1074-1086.
[21] C.H. Lee, C.C. Teng, Identification and control of dynamic systems using recurrent fuzzy neural networks, IEEE Transactions on Fuzzy Systems (8) (4) (2000) 349-366.
