結合幅狀基底函數網路與滑動模式控制之機器手臂控制器設計

DESIGN OF RADIAL BASIS FUNCTION NEURAL NETWORK WITH SLIDING MODE CONTROL FOR ROBOTIC MANIPULATORS

邱志聖(Chih-sheng Chiu)

指導教授 ： 呂虹慶

大同大學/電機資訊學院/電機工程學系所/碩士(2007年)

摘要

本論文提出了一個具有幅狀基底函數網路與滑動模式控制器並且使用雙軸(two-link)機器手臂針對週期性軌跡與預定軌跡的追蹤控制。幅狀基底函數網路使用函數逼近的方式來完成非線性的映射。當外在干擾存在的情況下，不可避免的網路學習過程使得系統的暫態性能下降。滑動模式控制雖然能夠有效的克服系統的不確定性而且具有快速的暫態響應，但是會產生不連續的控制力以及切跳現象。針對這個缺點，我們利用飽和函數來加以改善。分別使用倒傳遞演算法與里亞普諾夫(Lyapunov)穩定理論來個別地決定合適的網路更新法則與滑動模式切換增益。因此，可以得到令人滿意的效能，而且性能更優於使用單一幅狀基底函數類神經網路控制器或滑動模式控制器。本文的模擬部分是使用雙軸機器手臂並考慮關節(joint)摩擦力、軸質量變化與外在干擾的因素下來完成，同時證明了本文所提出的控制器的效能。

關鍵字

幅狀基底函數網路 ； 滑動模式控制器 ； 倒傳遞演算法 ； 機器手臂

並列摘要

In this thesis, radial basis function network (RBFN) with sliding-mode controller (SMC) is designed to the joint position control of two-link robot manipulators for periodic motion and predefined trajectory tracking control. Radial basis function uses curve fitting mode to obtain the nonlinear mapping. The unavoidable learning procedure degrades its transient performance in the existence of disturbance. Sliding-mode control is effective in overcoming uncertainties and has a fast transient response, while the control effort is discontinuous and creates chattering. For this defect, a saturation function is utilized to improve it. The back-propagation (BP) algorithm and Lyapunov stability theorem are used to decide a suitable update law and sliding-mode switch gain, respectively. Thus, the satisfactory performance will be obtained, which better than the controller with single RBFN controller or SMC. The simulated results of a two-link robotic manipulator for the joint frictions, changing link masses and adding external disturbances are provided to show that the effectiveness of the proposed control scheme.

並列關鍵字

radial basis function network ； sliding-mode controller ； back-propagation algorithm ； robot manipulators

參考文獻

[1] S. Haykin, Neural Networks: A Comprehensive Foundation. Macmillan College Publishing Company, New York, 1994.

[2] H. D. Patino and D. Liu, “Neural network-based model reference adaptive control system,” IEEE Trans. Syst., Man, Cybern. B, vol. 30, no. 1, pp. 198-204, Feb. 2000.

[3] S. Seshagiri and H. K. Khail, “Output feedback control of nonlinear systems using RBF neural networks,” IEEE Trans. Neural Netw., vol. 11, no. 1, pp. 69-79, Jan. 2000.

[4] Y. Li, S. Qiang, X. Zhuang, and O. Kaynak, “Robust and adaptive back-stepping control for nonlinear systems using RBF neural networks,” IEEE Trans. Neural Networks., vol. 15, no. 3, pp. 693-701, May 2004.

[5] C. T. Lin, “A neural fuzzy control system with structure and parameter learning,” Fuzzy Sets Syst., vol. 70, no. 2-3, pp. 183-212, March. 1995.