(100.26.179.251) 您好!臺灣時間:2021/04/12 21:49
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:張至維
研究生(外文):Chang, Chih-Wei
論文名稱:應用模型參數識別及類神經網路於結構健康診斷
論文名稱(外文):Applications of Neural Network Models for Structural Health Monitoring based on Derived Modal Properties
指導教授:林子剛
指導教授(外文):Lin, Tzu-Kang
口試委員:黃尹男歐昱辰曾榮川洪士林
口試日期:2018-07-26
學位類別:碩士
校院名稱:國立交通大學
系所名稱:土木工程系所
學門:工程學門
學類:土木工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:107
語文別:中文
論文頁數:89
中文關鍵詞:類神經網絡系統結構健康診斷隨機子空間系統識別破壞位置
外文關鍵詞:artificial neural networkstructural health monitoringstochastic subspace identificationdamage location
相關次數:
  • 被引用被引用:0
  • 點閱點閱:56
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
近年來結構健康診斷運用於實務工程上已經進入成熟階段,利用相關理論研究判定出結構物的破壞位置及損壞程度,甚至是損壞構件的殘餘性能,因此本研究提出了一種新型結構健康監測方針,是根據人工智慧(Artificial Intelligence, AI)的類神經網絡系統(Artificial Neural Network, ANN)去做整合與開發。本研究根據環境擾動下所識別的模態特性結果得到實驗之數值模型,並利用matlab建立神經網絡訓練模型。首先利用隨機子空間系統識別(Stochastic Subspace Identification, SSI)分析健康結構的自然頻率和模態振型,再根據結果推衍此結構的簡化模型,進而改變樓層勁度來建構各種損傷模式,最後依據損傷模式之模態參數來訓練神經網絡,提出一項全新的結構健康監測技術。若發生重要事件之後,即可使用該神經網絡系統來估計此結構之損傷狀態。此研究中將以數值模型執行三組不同之損傷情況來做驗證,其中包含單層和多層損壞的七層樓建物,以評估所提出的結構健康監測系統之性能表現。此外利用地震模擬振動台進行縮尺化雙塔模型實驗,輸入地震歷時及白噪音事件進行振動試驗,將弱斜撐桿件安裝在指定樓層形成結構物之軟弱層,隨後根據隨機子空間系統辨識所得到結構的模態特性,建立初始結構物以及各式樓層勁度折減之簡化模型,再透過神經網絡模型進行結構物損傷檢測,判斷損傷位置和破壞程度。因此,此研究所提出的新穎整合系統對於識別之模態特性與類神經網絡技術相對精確且可靠,將會是一套相當有效及具實用性的結構健康診斷系統。
The study proposes a new artificial intelligence-based structural health monitoring strategy based on neural network modeling. A neural network model is developed in accordance with a numerical model which is derived from the identified modal properties under ambient vibrations. The stochastic subspace system identification is first implemented to derive the natural frequencies and mode shapes of a healthy structure. These modal properties are then employed to derive a simplified model of this structure, allowing changing stiffness terms to construct various damage patterns. A neural network model is trained and built by the modal properties of the structure with these damage patterns. After a critical event occurs, this neural network model can be employed to estimate the damage patterns in terms of stiffness reduction. In this study, a numerical example studies a seven-story building with a single and multiple damaged columns in order to evaluate performance of the proposed strategy. Moreover, the system is also applied to an experimental test of a scaled twin-tower building with weak braces in some floors. After seismic events, the proposed artificial intelligence-based structural health monitoring strategy is employed to carry damage locations and levels of this building. As a result, the system is quite effective to locate damage if the identified modal properties are relatively accurate.
摘要 I
ABSTRACT II
誌謝 III
論文目錄 IV
表目錄 VI
圖目錄 VIII
第一章 緒論 1
1.1研究背景與目的 1
1.2研究方法 2
1.3 論文章節架構 3
第二章 文獻回顧 5
2.1隨機子空間識別理論 5
2.2類神經網路 8
第三章 研究理論與方法 11
3.1隨機子空間識別理論 11
3.2類神經網路理論 16
3.2.1神經網路介紹 16
3.2.2倒傳遞神經網路 19
3.2.3倒傳遞神經網路參數之決定 21
3.2.4神經網路使用上之限制 23
第四章 數值模擬 30
4.1數值模型建立 30
4.2類神經網路資料庫建立 30
4.3類神經網路之參數設定 31
4.4數值模擬驗證結果 31
第五章 實驗驗證 54
5.1中科雙塔縮尺模型介紹 54
5.1.1實驗試體材料介紹 54
5.1.2標竿結構破壞試驗案例 55
5.2振動台與數據量測系統介紹 55
5.2.1加速度計與訊號集錄器 55
5.2.2儀器配置 56
5.3 振動台試驗 56
5.4 實驗分析結果 57
第六章 結論與建議 82
6.1 結論 82
6.2 建議與未來展望 84
參考文獻 86
[1] Hart, GC. and Yao, JTP., “System identification in structural dynamics”, Journal of Engineering Mechanics Division, ASCE; 103(EM6), pp.1089-1104., 1977.
[2] Ljung, L. and Stoica, T., Theory and Practice of Recursive Identification, Asco.Trade Typesetting Ltd., Hong Kong., 1983.
[3] Yun, C.B. and Shinozuka, M., “Program LINEARID for identification of linear structural dynamic systems”, technical report, NCEER-90-0011, National Center for Earthquake Engineering Research, Buffalo, N.Y., 1990.
[4] Shinizuka, M. and Ghanem, R., “Structural system identification Π: experimental verification”, Journal of Engineering Mechanics, ASCE, 121(2), pp.265-273, 1995.
[5] Ghanem, R. and Shinozuka, M., “Structural-system identification Ι: theory”, Journal of Engineering Mechanics, ASCE, 121(2), pp.255-264, 1995.
[6] Saridis, G.N., “Comparison of six on-line identification algorithm”, Automatica, 10, pp.69-79, 1974.
[7] Farrar C.R., Worden K., “An introduction to structural health monitoring”, Philosophical Transactions of the Royal Society of London A, 373, pp.303-315, 2007.
[8] Sim S.H., Spencer B.F. Jr., “Decentralized strategies for monitoring structures using wireless smart sensor networks”, Newmark Structural Engineering Laboratory Report Series, No. 019, University of Illinois at Urbana-Champaign, 2009.
[9] Mottershead J.E., Friswell M.I., “Model updating in structural dynamics”, a survey, Journal of sound and vibration, 167(2), pp.347-375, 1993.
[10] Zhang Q.W., Chang C.C., Chang T.Y.P., “Finite element model updating for structures with parametric constraints”, Earthquake engineering & structural dynamics, 29(7), pp.927-944, 2000.
[11] Jaishi B., Ren W.X., “Structural finite element model updating using ambient vibration test results”, Journal of Structural Engineering, 131(4), pp.617-628, 2005.
[12] Carden E.P., Fanning P., “Vibration based condition monitoring”, a review, Structural Health Monitoring, 3(4), pp.355-377, 2004.
[13] Berman A., “Inherently incomplete finite element model and its effects on model updating”, AIAA Journal, 38(11), pp.2142–2146, 2000.
[14] Casas J.R., Aparicio A.C., “Structural damage identification from dynamic-test data”, Journal of Structural Engineering, 120(8), pp.2437–2450, 1994.
[15] Wahab M.M.A., De Roeck G., Peeters B., “Parameterization of damage in reinforced concrete structures using model updating”, Journal of Sound and Vibration, 228(4), pp.717–730, 1999.
[16] Chen J.D., Loh C.H., “Tracking modal parameters of building structures from experimental studies and earthquake response measurements”, Structural Health Monitoring, 16(5), pp.551-567, 2017.
[17] Van Overschee P., De Moor B., “Subspace algorithms for the stochastic identification problem”, 30th IEEE Conference on Decision and Control, Brighton, UK, pp.1321-1326, 1991.
[18] Peeters B., De Roeck G., “Reference-based stochastic subspace identification for output-only modal analysis”, Mechanical Systems and Signal Processing, 13(6), pp.855-878, 1999.
[19] Peeters B., De Roeck G., “Stochastic system identification for operational modal analysis”, a review, Journal of Dynamic Systems, Measurement, and Control, 123(4), pp.659-667, 2001.
[20] Brownjohn J.M.W., “Ambient vibration studies for system identification of tall buildings”, Earthquake Engineering and Structural Dynamics, 32, pp.71-95, 2003.
[21] Lynch J.P., Wang Y., Loh KJ, Yi J-H, Yun C-B, “Performance monitoring of the Geumdang Bridge using a dense network of high-resolution wireless sensors”, Smart Materials and Structures, 15, pp.1561-1575, 2006.
[22] Siringoringo D.M., Fujino Y., “System identification of a suspension bridge from ambient vibration response”, Engineering Structures, 30, pp.462-477, 2008.
[23] Weng J-H, Loh C-H, Lynch J.P., Lu K-C, Lin P-Y, Wang Y., “Output-only modal identification of a cable-stayed bridge using wireless monitoring systems”, Engineering Structures, 30, pp.1820-1830, 2008.
[24] Chang C.M., Loh C.H., “Improved stochastic subspace system identification for structural health monitoring”, Journal of Physics: Conference Series, 628, 012010,2015.
[25] Wu, X., et al., “Use of neural networks in detection of structural damage”, Computers and Structures, 42(4), pp.649-659, 1992.
[26] Elkordy, M. F., et al., “Neural networks trained by analytically simulated damage states”, Journal of Computing in Civil Engineering, ASCE, 7(2), pp.130-145, 1993.
[27] Szewczyk, Z. P. and Hajela, P., “Damage detection in structures based on feature-sensitive neural network”, Journal of Computing in Civil Engineering, ASCE, 8(2), pp.163-178, 1994.
[28] Pandey, P. C. and Barai, S. V., “Multilayer perceptron in damage detection of bridge structures”, Computers and Structures, 54(4), pp.597-608, 1995.
[29] Zhao, J., et al., “Structural damage detection using artificial neural networks”, Journal of Infrastructure Systems, ASCE, 4(3), pp.93-101, 1998.
[30] Masri, S.F., et al., “Application of neural networks for detection of changes in nonlinear systems”, Journal of Engineering Mechanics, ASCE, 126(7), pp.666-676, 2000.
[31] Okafor A.C., Chandrashekhara K., Jiang Y.P., “Delamination prediction in composite beams with built-in piezoelectric devices using modal analysis and neural network”, Smart materials and structures, 5(3), pp.338, 1996.
[32] Luo H., Hanagud S., “Dynamic learning rate neural network training and composite structural damage detection”, AIAA journal, 35(9), pp.1522-1527, 1997.
[33] Hartmann D., Smarsly K., Development of an Autonomous Monitoring System for Safety-Relevant Engineering Structures, Res. Project, Institute for Computational Engineering, 2005.
[34] Ko J.M., Ni Y.Q., “Technology developments in structural health monitoring of large-scale bridges”, Engineering structures, 27(12), pp.1715-1725, 2005.
[35] Madani S.A., Ulieru M., “An Application of Industrial Agents to Concrete Bridge Monitoring”, IEEE ICINCO, 6, 2006.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔