空調系統在智慧型建築物中所佔耗電量相當大，所以空調系統的控制對於能源節省也就顯得重要。本論文主旨在探討以免建立程序模型適應性控制器應用於大樓中央空調系統之溫度控制效能。經由北部某一飯店進行實際溫度資料收集，透過一群組實際測量的數據，模擬餐廳空調負載模型及模擬免建立程序模型適應性控制器與PID控制器之輸入與輸出間之關係，再比較其達到安定溫度所花費時間的差異。本研究第一階段為模擬餐廳空調負載模型的訓練，類神經網路架構乃透過Matlab加以訓練，運用412筆多輸入及單輸出值資料。其輸入值為控制閥開度比、外氣溫度及定義餐廳熱能產生比例，輸出值為回風溫度，所模擬的模型與實際量測數據之平均誤差為1.055%。第二階段則以模糊控制理論做為模擬控制器模型的訓練，利用Matlab模擬控制器之模型，再改變設定溫度及外部環境變化，比較其至安定溫度所花費之時間。經由驗證結果顯示，MFA控制較優於傳統的PID控制，且適合應用於空調系統的控制，並得以加快達到安定溫度比PID控制約快7.78%，故可減少控制閥頻繁動作和節省能源。

A HVAC consumes heavy electricity in an intelligent building. It shows the importance of HVAC control for energy saving. This study investigates the performance of application of a Model Free Adaptive (MFA) controller to temperature control on a central air conditioning system. After collecting actual temperature data from a hotel in northern Taiwan, a simulated model of the HVAC load for restaurant is to built according to relationships between input and output. Then, both MFA and PID controllers are modeled and compared on the differences of time responses for steady state. In the first stage, a HVAC load model for restaurant is trained with Neural Network by using Matlab from collected 412 sets of data. The three inputs include control valve open, outside temperature, generated heat of restaurant, and the single output is the feedback temperature. The average trained error is around 1.055% between measured and simulated temperature. In second stage, simulated controller models with Fuzzy Control Theory are trained by using Matlab with inputs and outputs from both PID and MFA controller. By changing the setting parameters, the response time of steady state is measured for comparison. From the simulated results, the MFA controller has faster setting time of 7.78% than PID. It reduces action times of control valve and saves unnecessary energy wasting.

[1]工業技術研究院 能源與資源研究所，「空調系統能源查核及節約能源案例手冊」，經濟部能源局 委託 工業技術研究院 能源與資源研究所 執行計畫成果，2006。
[2]林坤蒼、李志鵬， “類神經網路智能控制技術在空調通風系統上之應用” 中華技術，No.74，2007。
[3]趙文華，「空調系統之操作節能策略」，正宜興業股份有限公司，2003。
[4]Wilbert F. Stoecker and Jerold W. Jones著，蘇金佳 譯，「冷凍與空調」，國立編譯館 麥格羅．希爾，1996 第二版。
[5]SIEMENS Building Technologies, “Insight 3.9 Customer Training Guide ”, Document No. 159-144, 2007.
[6]楊健一，「低壓工業配線」，全華圖書股份有限公司，2008 修訂三版。
[7]SIEMENS Building Technologies, “PXC Compact Series Technical Specification Sheet”，Siemens Building Technologies, Inc. Rev.1, December 2005 .
[8]SIEMENS Building Technologies, “Adaptive Control Application Guide ”, Document No. 125-4463 Rev. 5, 2008.
[9]SIEMENS Building Technologies, “SIEMENS Building Technologies HVAC Products ”, Siemens Building Technologies Document CA1N4330en, 2007.
[10]SIEMENS Building Technologies, “SIEMENS Building Technologies HVAC Products ”, Siemens Building Technologies Document CA1N4563E, 2003.
[11]SIEMENS Building Technologies, “SIEMENS Building Technologies HVAC Products ”, Siemens Building Technologies AG Document No. CA1N 1552E, 2003.
[12]SIEMENS Building Technologies, “Technical Specification Sheet ”, Document No. 149-261P25, 2008.
[13]SIEMENS Building Technologies, “Technical Specification Sheet ”, Document No. 149-992, 2009.
[14]IEEE Xplore,“Model-free adaptive control”, IEE Computing & Control Engineering, pp.28-33, 2004.
[15]Maresh K. Sinha and Madan M. Gupta, Soft Computing and Intelligent Systems Design, Academic Press, 2000.
[16]Aidong Xu, Yangbo Zheng, yan Song, Mingzhe Liu, “ An Improved Model Free Adaptive Control Algorithm” Fifth International Conference on Natural Computation, 2009.
[17]George Cheng, Model-Free Adaptive Control, in‘Instrument Engineers’Handbook-Process Control and Optimization, ed. Bela Liptak（CRC Press LLC, 2005）.
[18]George Cheng, MFA Control with CyboCon, CyboSoft General Cybernation Group Inc., 2002.
[19]George Cheng, “Model-Free Adaptive Control” in Techniques of Adaptive Control, ed. VanceVanDoren（Burlington: Elsevier Science, 2003）.
[20]Zhong-Sheng Hou, “On Model-free Adaptive Control: The State of the Art and Perspective ”, Control Theory & Applications Vol.23 No.4，2006.
[21]Shuxing George Cheng, “Model-free Adaptive process Control ”, Washington: United States Patent and Trademark Office of the United States Department of Commerce, 2000.
[22]Shuxing George Cheng, “Model-Free Adaptive Process Control,” United States Patent, 6055524[P]. April 25, 2000.
[23]Warren McCulloch and Walter Pitts, “A logical calculus of the ideal immanent in neurons activity”, Bulletin of Mathematical Biophysics, vol. 5, pp.115-133, 1943.
[24]Frank Rosenblatt, Principles of Neurodynamics, New York: Spartan, 1962.
[25]Marvin Minsky and Seymour Papert, Perceptrons, MIT Press Cambrige MA,1969.
[26]Bernard Widrow, Generalization and Information Storage in Networks of Adaline‘Neuron in Self-Organizing System 1962, M. Yovitz, G. Jacobi, amd G. Goldstein, Eds. Washington, DC：Spartan Books, 1962.
[27]John Hopfield, “Unlearning has a stabilizing effect in collective memories”, Nature 304, pp.158-159, 1983.
[28]David Rumelhart and James McClelland, “Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations”, MIT Press Cambridge, MA, USA, 1986.
[29]Christos Stergious and Dimitrios Siganos, Neural Networks Basic http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html.
[30]羅華強，「類神經網路-MATLAB的應用」，高立圖書有限公司，2008 第二版。
[31]曾繁絹，「專家系統淺論」，李德竹 編著，資訊科學與技術專題論輯，p.289, 1997。
[32]薛理桂，「專家系統在圖書館的應用」，國立中央圖書館台灣分館，1991 第五期，p.10。
[33]SIEMENS Building Technologies, “APOGEE Power Process Control Language （PPCL）User’s Manual ”, Document No. 125-1896 Rev. 6, 2006.
[34]B. C. KUO著，黃漢邦譯，「自動控制系統」，超級科技圖書社，1985。
[35]L. A. Zadch,“Fuzzy Sets”, Information and Control 8, pp.338- 353, 1965.
[36]ROY J. DOSSAT 原著，陸紀文 王輔仁 謝文健 譯， 「冷凍空調原理 第三版」， 蒼海書局，1997。
[37]J.-S.R.Jang, Neuro-Fuzzy AND Soft Computing, Prentice-Hall, Inc., 1997.