使用粒子群聚演算法設計最佳化灰色PID與模糊控制器

Design of Optimal Grey PID and Fuzzy Controllers Using Particle Swarm Algorithms

張文郁(Wen-Yu Chang)

指導教授 ： 蔡舜宏 ； 王偉彥

國立臺北科技大學/機電學院/自動化科技研究所/碩士(2010年)

摘要

本文針對PID控制器與模糊控制器提出運用粒子群聚最佳化演算法與Nelder-Mead粒子群聚最佳化演算法來設計控制器的參數，藉此可以避免傳統在設計控制器參數時往往需要專家經驗或訓練樣本，或者是需要不斷嘗試錯誤的主觀設計法。灰色PID控制器是基於灰色系統理論提出的灰色模型來建立預測系統，用來改善在實際控制可能會因為雜訊的干擾而造成系統的不穩定。模糊控制的模糊法則設計與PID控制器的參數設計一樣是需要專家經驗，所以本文為使模糊控制可以省力且省時的設計參數，而運用演算法來設計模糊法則。在模擬實驗中，運用簡單的模糊控制器架構且經由演算法搜尋相關參數，設計出較佳的模糊控制器，使得倒單擺系統可以將單擺成功的控制垂直向上且快速穩定。

關鍵字

粒子群聚最佳化演算法 ； Nelder-Mead粒子群聚最佳化演算法 ； 灰色系 統理論 ； 模糊控制器 ； PID控制器

並列摘要

This paper proposes a design method using particle swarm optimization (PSO) and Nelder-Mead PSO (NMPSO) to adjust the parameters of PID controllers and fuzzy controllers so that we can avoid that in traditional to design of the controller parameters often requires expert experience or training samples. We propose the grey model based on the grey system theory to combine with PID control to establish the PID prediction control system so that we can improve the instability which cause by noise in the real system. It both needs the expertise to design of the fuzzy rules of fuzzy controls and the parameters of PID controllers; therefore we use the algorithm to design the fuzzy rules so that we don't have to waste a lot of time to design the rules. In simulation, we use simple fuzzy controllers which have the parameter search by the algorithm. By design the better fuzzy controllers which can control the inverted pendulum system keeping balance and stable.

並列關鍵字

Particle Swarm Optimization ； Nelder-Mead Particle Swarm Optimization ； Grey System Theory ； Fuzzy Controller ； PID Controller

參考文獻

[10] G. D. Li and C. H. Wang, “The PID Prediction Control System using Particle Swarm Optimization and Genetic Algorithms,” Proc. IEEE International Conference Grey Systems and Intelligent Services, November 2009, pp.687-691.

[1] J. G. Ziegler and N. B. Nichols, “Optimum settings for automatic controllers,” Tran. ASME, Vol. 64, 1942, pp.759-768.

[2] C. Ou, W. Lin, “Comparison between PSO and GA for Parameters Optimization of PID Controller,” Proc. IEEE International Conference Macaronis and Automation, 2006, pp.2471-2475.

[6] P. N. Suganthan, “Particle swarm optimizer with neighborhood operator,” Proceedings of the 1999 Congress on Evolutionary Computing, 6-9 July 1999, Vol. 3, pp.1958-1962.

[7] Y. Shi and R.C. Eberhart, “Parameter selection in particle swarm optimization,” in Evolutionary Programming VII: Proc. EP98, New York, 1998, pp.591-600.