臺灣博碩士論文加值系統

時變系統被非常廣泛地應用於很多領域裡。在機械和土木工程中，修正剛度或阻尼的主動控制裝置是時變系統。當一個結構在動力荷載的作用下受到損害，結構亦通常展現剛度和阻尼隨著時間改變。因此，在結構物的損害評估中，由時變系統識別瞬時模態參數是一個很重要的課題。
本文發展建立一個時變類神經網路，並且從架構的神經網路，根據系統識別的程序來估算瞬時模態參數。程序步驟是首先將位移反應及外力輸入倒傳遞神經網路，其連結的權重和門檻值假設為時間的函數，並以多項式展開。然後，利用權重最小平方差法來決定各多項式之係數。由於採用權重最小平方差法，各多項式的係數亦時間之函數；因此，不須高階多項式。
為了驗證此程序的可行性，先用時變線性系統及非線性系統之數值模擬來驗證本文所建立的程序；探討對權重最小平方差法中之加權函數、多項式階數，以及雜訊對建立一個合適的時變類神經網路程序，或估算瞬時模態參數之影響。最後，將本程序應用至分析鋼筋混凝土結構的振動台試驗，此實驗結構的反應進入非線性行為。所估算瞬時模態參數隨時間之變化趨勢與量測力-位移數據之斜率變化趨勢一致。

Time varying systems find many applications in various fields. In mechanical and civil engineering, a system with active control devices of modifying stiffness or damping of the system is a time varying system. When a structure is damaged under dynamic loading, the structure normally displays changes in stiffness and damping with time. The changes with time in stiffness and damping of a system result in time varying instantaneous model parameters is an important issue in damage assessment of a structure.
The present work develops a novel procedure of establishing BP neural network of a time varying system and estimating instantaneous model parameters of the system from established neural network. The connective weights and thresholds in a neural network are assumed as functions of time and are expanded by polynomials. A weighted least-squares approach is applied to determine the coefficients of the polynomials. Because of using the weighted least-squares approach, the coefficients of the polynomials also depend on time. Consequently, only low orders of polynomials are needed to expand the connective weights and thresholds.
The feasibility of the proposed procedure is demonstrated by processing numerically simulated dynamic responses of a nonlinear system and a time-varying linear system. It is also performed to investigate the effects of weighting function in the weighted least-square approach, polynomial order, and noise on establishing a suitable neural network and determining instantaneous model parameters. Finally, the proposed procedure is applied to process measured dynamics responses of a RC structure under shaking table tests. The experimental structure has been shaken to perform nonlinear behaviors. When dramatic changes are observed in the slope of the measured relationship between force and displacement for the experimental structure, the identified instantaneous model parameters also show significant changes.

中文摘要 I
英文摘要 II
誌謝 IV
目錄 V
表目錄 VII
圖目錄 VIII
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 1
1.3 研究方法與步驟 3
1.4 本文內容 5
第二章 時變類神經網路 6
2.1 類神經網路介紹 6
2.2 建立時變類神經網路之程序 8
2.3 指數型加權函數 14
2.4 時變類神經網路與 TVARX 之對等關係 14
2.5 瞬時動態特性之估算 17
第三章 時變系統之數值模擬 20
3.1 時變線性系統之數值模擬 20
3.1.1 緩變係數系統 22
3.1.2 週期變化系統 23
3.1.3 雜訊之影響 24
3.2 非線性系統之數值模擬 27
3.2.1 非線性系統 27
3.2.2 轉換函數 29
3.2.3 非線性系統預測結果之誤差 30
第四章 實測資料之識別結果 32
4.1 待測結構物介紹 32
4.2 等效勁度與阻尼之迴歸 33
4.3 動態反應初判 34
4.4 實測資料之識別結果 35
第五章 結論與建議 38
5.1 結論 38
5.2 建議 39
參考文獻 41
附表 43
附圖 53

1. McCulloch, W. S. and Pitts, W. H.,“Logical calculus of the ideas immanent in nervous activity“, Bulletin of Mathematical Biophysics ,5,pp.115,1943.
2. 蔡中輝、徐德修,“以類神經網路評估鋼筋混凝土結構之損壞”, 中國土木水利工程學刊 ,第 10 卷,第 1 期, pp.31∼38,1998.
3. Karunanithi, N., Grenney, W. J., Whitley, D. and Bovee, K.,“Neural networks for river flow prediction”, Journal of Computing in Civil Engineering ,8(2),pp.201∼220,1994.
4. Sofge, D. A.,“Structural health monitoring using neural network based vibrational system identification”, Intelligent Information Systems ,pp.91∼94,1994.
5. Levin, E.,“Hidden control neural architecture modeling of nonlinear time varying systems and its applications”, IEEE Transactions on Neural Networks ,Vol. 4,pp.109∼116,1993.
6. Takahashi, Y.,“Adaptive predictive control of nonlinear time-varying systems using neural network”, IEEE International Conference on Neural Networks ,Vol. 3,pp.1464∼1468,1993.
7. Gu, C. K., Wang, Z. G. and Sun, Y. M.,”Nonlinear time-variant systems identification based on neural networks combined with basis sequence approximation”, Proceedings of the Second International Conference on Machine Learning and Cybernetics , Xi'an ,2-5,November 2003.
8. Zoubir, A. M.,”Identification of quadratic Volterra system driven by non-Gaussian processes“, IEEE Transactions on Signal Processing ,Vol. 43, pp.1302∼1306,l995.
9. Wang, Z. O. and Zhao, C. H.,”Identification of nonlinear time variant using feedforward neural networks“, Transactions of Tianjin University , 6 (1) , pp.8∼13,2000.
10. Lim, T. W., Cabell, R. H. and Silcox, R. J.,”On-line identification of modal parameters using artificial neural networks“, Journal of Vibration and Acoustics ,Vol. 118,pp.649∼656,1996.
11. 黃致傑,“應用類神經網路於含消能結構之系統識別”, 國立台灣大學 ,碩士論文,2000.
12. 凃宗廷,”類神經網路於房屋結構系統識別之應用“, 國立交通大學 ,碩士論文,2001.
13. Villiers, J. de and Barnard, E.,”Backpropagation neural nets with one and two hidden layers“, IEEE Transactions on Neural Networks , Vol. 4 , No. 1 , 1992.
14. 黃炯憲,蘇威智,”發展基於小波轉換之系統識別方法–線性時變系統“, 行政院國家科學委員會 ,成果報告,2006.
15. 黃炯憲,”微動量測分析工具探討 (二)–時間序列法“, 國家地震工程研究中心報告 ,NCREE - 99 - 018,1999.
16. 黃炯憲,蘇威智,”發展基於小波轉換之系統識別方法–線性系統“, 行政院國家科學委員會 ,成果報告,2005.
17. Wu, C. L., Loh, C. H. and Yang, Y. S.,”Shake table tests on gravity load collapse of low-ductility RC frames under near-fault earthquake excitation”, Advances in Experimental Structural Engineering ,pp. 725∼732,2005.