PID控制器是一種廣為人知的控制演算法，主要由於其控制結構簡單並且容易實現，因此在工業界中被廣泛使用，但是其控制參數的調整通常是利用經驗來加以設定。本文將一種基於遞迴學習調變的策略，加以改善成參數型遞迴學習調變法，並自行搜尋最佳的PID控制器參數。在此演算法中將採用兩段分工的概念，使用兩組不同參數的PID控制器來改善各自局部的區域響應，並且延續遞迴式學習調變法(Iterative Feedback Tuning, IFT)的優點，控制參數將依據設定的評量標準來進行遞迴學習調變，使其控制的區域評量標準達到最佳化的效果。最後，透過不同演算法的分析比較，本文提出之參數型遞迴學習調變法，改善單純的IFT性能，使其搜尋到更佳的控制參數。

PID controllers are often used in the industry, due to its simple structure. But how to determine PID controller parameters for better system performance is studied for many decades .In the industry, it always used the operator’s experience to set the PID controller parameters. In this thesis, a new algorithm is proposed for PID controller parameters tuning. This algorithm is based on the Iterative Feedback Tuning (IFT) method and two sets of PID controller parameters are tuned iteratively, it correspond to the transient response and steady-state response. First, tune the transient PID controller parameters to find the better parameters. When transient PID controller parameters have tuned, then tune the steady-state PID controller parameters. This proposed algorithm results show performance better than other classic tuning methods and the IFT method.

Cominos, P., Munro, N., 2002, PID controller: recent tuning methods and design to specification, IEE no.20020103 46-53

Moradi, M.H.,2003, New techniques for PID controller design, IEEE 903-908

Hjalmarsson, H., Gevers, M., Gunnarsson, S., & Lequin, O. (1998). Iterative feedback tuning:Theory and Applications. IEEE Control Systems Magazine, 18, 26–41.

Hsiao, Y.T., Chuang, C.L., Jiang,J.A.,2005, A Hybrid of ε-Constraint and Particle Swarm Optimization for Designing of PID Controllers ,IEEE conference

Lequin, O.,Gevers, M., Mossberg, M., Bosmans, E., Triest, L.,2003, Iterative feedback tuning of PID parameters: comparison with classical tuning rules, control engineering practice 111023-1033

Mann, G..K.I., Hu, B.G., Gosine, R.G., May 2001, Time-domain based design and analysis of new PID tuning rules, IEE Proc.-Control Theory AppL. Vol. 148, No. 3, NO.20010464,251-261

Rivera, D.E., Morari, M., Skogestad, S., 1986, Internal model control. 4.PID cotroller design, Ind. Eng. Chem. Res. 25(1) 252-265

Tan, K.K., Zhao, S., Chua, K., Yong, H., Weng K., and Tan ,W. Wan, 2006, Iterative learning approach toward closed loop automatic tuning of PID controllers Ind.eng.chem.res.2006,45,4093-4100

Tan, K.K., Zhao, S. and Xu, J.-X., 2006, Online automatic tuning of a proportional integral derivative controller based on an iterative learning control approach, The Institution of Engineering and Technology

Varol, H.A., Bingul, Z., 2004, A new PID technique use ant algorithm, American control conference Boston,massachusatt Jane30-July2 2154-2159

Wang, L., Barnes, T.J.D., Cluett, E.R., 1995, New frequency-domain design method for PID cotroller, IEE Proc.-Control Theory Appl., Vol. 142,No. 4, July 1995 VOl.4,265-271

Ziegler, J.G, Nichols, N.B.,1942,Optimum settings for automatic controllers, Trans. A.S.M.E. 64 759-768