跳到主要內容

臺灣博碩士論文加值系統

(35.153.100.128) 您好!臺灣時間:2022/01/22 07:58
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

: 
twitterline
研究生:高清雲
研究生(外文):Kao Ching-Yun
論文名稱:類神經網路系統識別模式於結構健康檢測之研究
論文名稱(外文):Artificial-Neural-Network-Based System Identification Models for Structural Health Monitoring
指導教授:洪士林洪士林引用關係
指導教授(外文):Hung Shih-Lin
學位類別:博士
校院名稱:國立交通大學
系所名稱:土木工程系
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:2002
畢業學年度:90
語文別:英文
論文頁數:117
中文關鍵詞:類神經網路系統識別結構健康檢測結構損壞偵測
外文關鍵詞:Artificial Neural NetwrkSystem IdentificationStructural Health MonitoringStructural Damage Detection
相關次數:
  • 被引用被引用:10
  • 點閱點閱:966
  • 評分評分:
  • 下載下載:271
  • 收藏至我的研究室書目清單書目收藏:6
傳統的類神經網路結構損壞評估方法使用類神經網路來萃取及儲存未損壞和損壞結構反應之樣本的知識。因為結構的破壞模式變化很大而且無法預測,所以使用破壞狀態及其相對應之反應所組成的樣本訓練類神經網路是不可行的方法。
類神經網路具有穩健(Robust)及容錯(Fault Tolerant)的特性,並且能夠有效地處理不確定及不完全的資料,因此類神經網路非常適合用來識別結構動力系統。識別結構動力系統之類神經網路的權值儲存著被識別之結構系統的結構特性。本文之目的即是直接或間接從識別結構系統之類神經網路的權值找出一些與結構系統參數有關的指標以作為整體結構健康檢測之用。文中提出了三個類神經網路系統識別模式-偏微分形式模式(Partial Derivative Form Model)、等效線性系統模式(Equivalent Linear System Model)、以及自由振動模式(Free Vibration Model)-來檢測結構是否健全。每一個模式都包括兩個步驟。第一個步驟是系統識別:使用神經系統識別網路(Neural System Identification Networks)識別結構系統未損壞及損壞之狀態。神經系統識別網路的輸入變數是前幾個時刻的結構反應、以及前幾個時刻和現時的外在擾動,輸出變數則是現時的結構反應。第二個步驟是結構損壞偵測:直接或間接從神經系統識別網路的權值找出有用的指標以作為結構損壞偵測之用。在偏微分形式模式、等效線性系統模式及自由振動模式中結構損壞偵測之有用指標分別為神經系統識別網路的輸出變數對輸入變數之一階偏微分值、等效線性系統之模態參數及經由訓練過的神經系統識別網路所產生之自由振動的週期和振幅。藉由比較結構未損壞和損壞狀態之指標值則可以評估結構系統變化的程度。
為了驗證本文所提之類神經網路系統識別模式於結構損壞偵測的可行性,文中列舉數值以及實驗之例子來說明。此外,我們建議未來的研究工作應該擴展到真實的結構物、研究如何決定損壞的位置及程度、研究結構特性和神經識別網路輸出變數對輸入變數之偏微分值的關係、以及發展即時結構健康檢測的方法。
Conventional artificial-neural-network-based (ANN-based) structural damage assessment methods use artificial neural networks (ANNs) to extract and store the knowledge of the patterns in the response of undamaged and damaged structure. Since the failure modes of a structure are so varied and so unpredictable, it is not feasible to train the neural network by furnishing it with pairs of failure states and corresponding diagnostic response.
ANNs are robust and fault tolerant. They can also effectively deal with qualitative, uncertain, and incomplete information, thereby making them highly promising for identifying systems that are typically encountered in structural dynamics. The weights of the approximating neural network store the knowledge of the structural properties of the identified system. The objective of this research was looking for some useful indices for global structural health monitoring directly or indirectly from the weights of the approximating neural network. Herein, three ANN-based system identification models (Partial Derivative Form models, Equivalent Linear System models, and Free Vibration models) for structural health monitoring were presented. Each model comprises two steps. In the first step, system identification, Neural System Identification Networks (NSINs) are used to identify the undamaged and damaged states of a structural system. The inputs of the NSIN are previous structural responses and previous and current external excitations, and the outputs are current structural responses. In the second step, structural damage detection, some useful indices for detecting structural damage are searched directly or indirectly from the weights of the NSIN. The useful indices for structural health monitoring in Partial Derivative Form model, Equivalent Linear System model, and Free Vibration model are partial derivatives of the outputs with respect to the inputs of a NSIN, modal parameters of an equivalent linear system, and the amplitudes and periods of the free vibrations generated from a NSIN respectively. By comparing the indices of damaged state with those of undamaged state, the extent of changes can be assessed.
Numerical and experimental examples were presented to demonstrate the feasibility of proposed models for structural health monitoring. Besides, further studies were suggested in the area of extending this work to realistic structures, investigating how to determine the location and extent of the damage, exploring relations between structural properties and partial derivatives of the outputs with respect to the inputs of a NSIN, and developing on-line structural health monitoring methods.
Abstract i
Acknowledgements iii
Table of Contents iv
List of Tables vi
List of Figures vii
Chapter One Introduction 1
1.1 Motivation 1
1.2 Definition of structural health monitoring 2
1.3 Purpose 4
1.4 Organization of the dissertation 4
Chapter Two Literature 6
2.1 Signature analysis or pattern recognition approaches 7
2.2 Modal updating and system identification 9
2.3 Neural network approaches 13
Chapter Three Artificial Neural Networks 19
3.1 A biological neuron and the network (Brain) 19
3.2 A artificial neuron and the artificial neural network
20
3.3 Backpropagation neural networks 22
3.4 Adaptive L-BFGS learning algorithm 24
Chapter Four Methodology 27
4.1 Partial Derivative Form model 28
4.1.1 Neural System Identification Network 29
4.1.2 Partial derivative form of the ANN 30
4.1.3 Neural Damage Detection Network 34
4.2 Equivalent Linear System model 35
4.2.1 LFT representation of the NSIN 36
4.2.2 Estimating modal parameters of the equivalent linear
system 39
4.3 Free Vibration model 42
4.3.1 Generating a free vibration response by the
trained NSIN 42
Chapter Five Illustrative Examples 44
5.1 Examples of PDF model 44
5.2 Examples of ELS model 50
5.3 Examples of FV model 57
5.4 Discussion 61
Chapter Six Summary and Conclusions 63
6.1 Summary 63
6.2 Recommendations for future research 65
References 68
Vita 116
1.Agbabian, M. S., and Masri, S. F. (eds.) (1988). Proceedings of International Workshop on Nondestructive Evaluation for Performance of Civil Structures, Department of Civil Engineering, School of Engineering, University of Southern California, Los Angeles, Calif.
2.Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). “Learning international representation by error propagation.” In: Parallel Distributed Processing, Rumelhart, D. E., McClelland, J. L., the PDP Research Group, eds., The MIT Press, Cambridge, MA, 318-362.
3.Adeli, H., and Hung, S. L. (1995). Machine Learning — Neural networks, Genetic Algorithms, and Fuzzy Systems, John Wiley & Sons, Inc., New York, N. Y. (ok)
4.Suykens, J., Vandewalle, J., and De Moor, B., Artificial Neural Networks for Modeling and Control of Non-Linear Systems, Kluwer Academic Publishers, Boston, 1996.
5.Journal of Engineering Mechanics (1997). Special Issue on Structural Control : Past, Present, and Future (September).
6.Organization for Economic Co-operation and Development (OECD). (1976) Bridge inspection. Paris, France.
7.Honeycombe, R. W. K., and Hancock, P. (1987). Non-destructive testing. Edward Arnold, Ltd., London, England.
8.Mix, P. E. (1987). Introduction to nondestructive testing: a training guide. John Wiley & Sons, Inc., New York, N.Y.
9.Boving, K. G. (ed.) (1989). NDE handbook: nondestructive examination methods for condition monitoring. Delft, The Netherlands.
10.Holbrook, J., and Bussiere, J. (eds.) (1989). Nondestructive monitoring of materials properties. Mat. Res. Soc., Pittsburgh, Pa.
11.Chong, K. P., and Scalzi, J. B. (1992). “New developments in nondestructive evaluation.” In: Intelligent structures-2, monitoring and control, Wen, Y. K., ed., 3-12.
12.Claus, R. O. (1992). “Optical fiber sensors for intelligent structures.” In: Intelligent structures-2, monitoring and control, Wen, Y. K., ed., 165-174.
13.Feuer, N. J., and Little, R. G. (1993). “Bridge inspection.” In: Bridge inspection and rehabilitation: a practical guide. Silano, L. G. and Henderson, A. C., eds., John Wiley & Sons, Inc., New York, N. Y., 1-23.
14.Tsou, H. S. (1993). “Measurements of linear and nonlinear structures with distributed shell sensors.” In: Safety evaluation based on identification approaches related to time-variant and nonlinear structures. Natke, H. G., Tominson, G. R., and Yao, J. T. P., eds., Freidrich Vieweg & Sohn Verlagsgesellschaft GmbH, 28-43.
15.Mandelis, A. (ed.) (1994). Nondestructive evaluation (NDE). Prentice-Hall, Inc., Englewood, N. J.
16.Flesch, R. G., and Kernbichler, K. (1988). “Bridge inspection by dynamic tests and calculations dynamic investigations of lavent bridge.” In: Structural safety evaluation based on system identification approaches, Natke, H. G., and Yao, J. T. P., eds., Vieweg & Sohn, Braunschweig, Germany, 433-459.
17.Stubbs, N., Broome, T. H., and Osegueda, R. (1990). “Nondestructive construction error detection in large space structures.” AIAA Journal, 28(1), 146-152.
18.Wen, Y. K. (ed.) (1992). “Intelligent structures 2: monitoring and control.” Proceedings of the International Workshop on Intelligent Systems, Elsevier Science Publishing Co., Inc., New York, N. Y.
19.Natke, H. G., Tomlinson, G. R., and Yao, J. T. P. (eds.) (1993). Safety evaluation based on identification approaches related to time-variant and nonlinear structures. Vieweg, Brunswick, Germany.
20.Stubbs, N., and Topole, K. G. (1993). “A damage localization algorithm for nonlinear structures.” In: Safety evaluation based on identification approaches related to time-variant and nonlinear structures. Natke, H. G., Tominson, G. R., and Yao, J. T. P., eds., Freidrich Vieweg & Sohn Verlagsgesellschaft GmbH, 93-106.
21.Kim, J. T., and Stubbs, N. (1995). “Damage detection in offshore jacket structures from limited modal information.” International Journal of Offshore and Polar Engineering, 5(1), 58-66.
22.Hung, S. L., and Kao, C. Y. (2002). “Structural damage detection using the optimal weights of the approximating artificial neural networks.” Earthquake Engineering and Structural Dynamics, 31(2), 217-234.
23.Mazurek, D. F., and DeWolf, J. T. (1990). “Experimental study of bridge monitoring technique.” Journal of Structural Engineering, ASCE, 116(9), 2532-2549.
24.Hearn, G., and Testa, R. B. (1991). “Modal Analysis for damage detection in structures.” Journal of Structural Engineering, ASCE, 117(10), 3042-3063.
25.Natke, H. G. (1988). “Updating computational models in the frequency domain based on measured data: a survey.” Probabilistic Engineering Mechanics, 8, 28-35.
26.Natke, H. G., and Yao, J. T. P. (eds.) (1988). Proceedings of the International Workshop on Structural Safety Evaluation Based on System Identification Approaches, Vieweg, Brunswick, Germany.
27.Mottershead, J. E., and Friswell, M. I. (1993). “Model updating in structural dynamics: a survey.” Journal of Sound and Vibration, 167, 347-375.
28.Caravani, P., Watson, M. L., and Thomson, W. T. (1977). “Recursive lease-squares time domain identification of structural parameters.” Journal of Applied Mechanics, 44, 135-140.
29.Lin, C. C., Soong, T. T., and Natke, H. G. (1990). “Real-time system identification of degrading structures.” Journal of Engineering Mechanics, 116(10), 2258-2274.
30.Sanayei, M., and Onipede, O. (1991). “Damage assessment of structures using static test data.” AIAA Journal, 29(7), 1174-1179.
31.Banan, M. R., Banan, M. R., and Hjelmstad, K. D. (1994). “Parameter estimation of structure from static response. I: Computational aspects.” Journal of Structural Engineering, ASCE, 120(11), 3243-3258.
32.Banan, M. R., Banan, M. R., and Hjelmstad, K. D. (1994). “Parameter estimation of structure from static response. II: Numerical simulation studies.” Journal of Structural Engineering, ASCE, 120(11), 3259-3283.
33.Hjelmstad, K. D., Banan, M. R., and Banan, M. R. (1995). “Time-domain parameter estimation algorithm for structures. I: Computational aspects” Journal of Engineering Mechanics, ASCE, 121(3), 424-434.
34.Banan, Mo. R., Banan, Ma. R., and Hjelmstad, K. D., (1995). “Time-domain parameter estimation algorithm for structures. II: Numerical simulation studies” Journal of Engineering Mechanics, ASCE, 121(3), 435-447.
35.Sheinman, I. (1996). “Damage detection and updating of stiffness and mass matrices using mode data.” Computers & Structures, 59(1), 149-156.
36.Kosmatka, J. B., and Ricles, J. M. (1999). “Damage detection in structures by modal vibration characterization.” Journal of Structural Engineering, 125(12), 1384-1392.
37.Koh, C.G., Hong, B., and Liaw, C.-Y. (2000). “Parameter identification of large structural systems in time domain.” Journal of Structural Engineering, 126(8), 957-963.
38.Bui, H. D. (1994). Inverse problems in the mechanics of materials: An introduction. CRC Press, Boca, Raton, Fla.
39.Hjelmstad, K. D. (1996). “On the uniqueness of modal parameter estimation.” Journal of Sound and Vibration, 192(2), 581-598.
40.Hjelmstad, K. D., and Shin, S. (1997). “Damage detection and assessment of structures from static response.” Journal of Engineering Mechanic, ASCE, 126(6), 568-576.
41.Goodwin, G. C., and Payne, R. L. (1977). Dynamic system identification, experiment design and data analysis. Academic Press, Inc., San Diego, Calif.
42.Natke, H. G. (ed.) (1982). Identification of vibrating structures. Springer-Verlag New York, Inc., New York, N. Y.
43.Beck, J. L., and Katafygiotis, L. S. (1992). “Probabilistic system identification and health monitoring of structures.” Proceedings of the tenth World Conference on Earthquake Engineering.
44.Beck, J. L., and Katafygiotis, L. S. (1998). “Updating models and their uncertainties. I: Bayesian statistical framework.” Journal of Engineering Mechanics, ASCE, 124(4), 455-461.
45.Katafygiotis, L. S., and Beck, J. L. (1998). “Updating models and their uncertainties. II: Modal identifiability.” Journal of Engineering Mechanics, ASCE, 124(4), 463-467.
46.Beck, J. L., Vanik, M. W., and Katafygiotis, L. S. (1994). “Determination of stiffness changes from modal parameter changes for structural health monitoring.” Proceedings of the First World Conference on Structural Control.
47.Sohn, H., and Law, K. H. (1997). “A bayesian probabilistic approach for structural damage detection.” Earthquake Engineerring and Structural Dynamics, 26(12), 1259-1281.
48.Fares, N., and Maloof, R. (1997). “A probabilistic framework for detecting and identifying anomalies.” Engineering Mechanics, 12, 63-73.
49.Yeo, I., Lee, H. S., and Chang, S. P. (2000). “Statistical damage assessment of framed structures from static responses.” Journal of Engineering Mechanics, 126(4), 414-421.
50.Ghaboussi, J., Garrett, J. H., and Wu, X. (1991). “Knowledge-based modeling of material behavior with neural networks.” Journal of Engineering Mechanics, 117(1), 132-153.
51.Wu, X., Ghaboussi, J., and Garrett J. H. Jr. (1992). “Use of neural networks in detection of structural damage.” Computers & Structures, 42(4). 649-659.
52.Elkody, M. F. (1992). “Application of neural networks in structural damage diagnosis and condition monitoring.” PhD dissertation, State University of New York at Bufflo.
53.Elkordy, M. F., Chang, K. C., and Lee, G. C. (1993) “Neural networks trained by analytically simulated damage states.” Journal of Computing in Civil Engineering, ASCE, 7(2), 130-145.
54.Szewezyk, P., and Hajela, P. (1994). “Damage detection in structures based on feature-sensitivity neural networks.” Journal of Computing in Civil Engineering, ASCE, 8(2), 163-179.
55.Pandy, P. C., and Barai, S. V. (1995). “Multilayer perception in damage detection of bridge structures.” Computers & Structures, 54(4), 597-608.
56.Zhao, J., Ivan, J. N., and DeWolf, J. T. (1998). “Structural damage detection using artificial networks.” Journal of Infrastructure systems, 4(3), 93-101.
57.Marwala, T. (2000). “Damage identification using committee of neural networks.” Journal of Engineering Mechanics, 126(1), 43-50.
58.Masri, S. F., Nakamura, M., Chassiakos, A. G., and Caughey, T. K. (1996). “Neural network approach to detection of changes in structural parameters.” Journal of Engineering Mechanics, ASCE, 122(5), 350-360.
59.Masri, S. F., Smyth, A. W., Chassiakos, A. G., Caughey, T. K., and Hunter, N. F. (2000). “Application of neural networks for detection of changes in nonlinear systems.” Journal of Engineering Mechanics, ASCE, 126(7), 666-676.
60.Masri, S. F., Miller, R. K., and Saud, A. F. (1987). “Identification of nonlinear vibrating structures: part I-formulation.” Journal of Applied Mechanics, 54, 918-922.
61.Masri, S. F., Miller, R. K., and Saud, A. F. (1987). “Identification of nonlinear vibrating structures: part I-applications.” Journal of Applied Mechanics, 54, 923-929.
62.Masri, S. F., Chassiakos, A. G., and Caughey, T. K. (1992). “Structure-unknown nonlinear dynamic systems: identification through neural networks.” Smart Materials and Structures, 1, 45-56.
63.Masri, S. F., Chassiakos, A. G., and Caughey, T. K. (1993). “Identification of nonlinear dynamic systems using neural networks.” Journal of Applied Mechanics, 60, 123-133.
64.Nakamura, M., Masri, S. F., Chassiakos, A. G., and Caughey, T. K. (1998). “A method for non-parametric damage detection through the use of neural networks.” Earthquake Engineering and Structural Dynamics, 27. 997-1010.
65.Hung, S. L., and Lin, Y. L. (1994). “Application of an L-BFGS neural network learning algorithm in engineering analysis and design.” Proceedings of the 2nd National Conference on Structural Engineering, Chinese Society of Structural Engineering, Nantou, Taiwan, R.O.C. , 221-230. (in Chinese)
66.Nocedal, J. (1980). “Updating quasi-newton matrix with limited storage.” Mathematics of Computation, 35, 20-33.
67.Coleman, T. F., and Li, Y. (1990). Large-Scale Numerical Optimization, Society for Industrial and Applied Mathematics, Philadelphia.
68.Cybenko, G. (1989). “Approximations by superpositions of a sigmoidal function.” Mathematics of Control, Signals and Systems, 2, 303-314.
69.Funahashai, K. (1989). “On the approximate realization of continuous mappings by neural networks.” Neural Networks, 2, 183-192.
70.Suykens, J., Vandewalle, J., and De Moor, B. (1995). “Nonlinear system identification using neural state space models, applicable to robust control design.” International Journal of Control, 62(1), 129-152.
71.Huang, C. S. (2001). “Structural identification from ambient vibration measurement using the multivariate AR model.” Journal of Sound and Vibration, 241(3), 337-359.
72.Huang, C. S. (1999). “A study on techniques for analyzing ambient vibration measurement (II)-time series methods.” Report No. NCREE-99-018, National Center for Research on Earthquake Engineering, R. O. C. (in Chinese)
73.Allemang, R. L., Brown, D. L. (1983). “A correlation coefficient for modal vector analysis.” Proceeding of the first International Model Analysis Conference, Bethel, Connecticut, U.S.A., 110-116.
74.Trifunac, D. (1972). “Comparison between ambient and forced vibration experiments.” Earthquake Engineering and Structural Dynamics, 1, 133-150.
75.Hung, S. L., Kao, C. Y., and Shieh, M. F. (2001). “Application of back-propagation neural networks in nonlinear hysteretic structural dynamic analysis.” Journal of The Chinese Institute of Civil and Hydraulic Engineering, 13(3), 567-583. (in Chinese)
76.Yeh, S. C., Cheng, C. P., and Loh, C. H. (1999). “Shaking table tests on scaled down five-story steel structures.” NCREE Report No. NCREE-99-002, National Center for Research on Earthquake Engineering, R. O. C. (in Chinese)
77.Huang, C. S., Hung, S. L., Lai, C. M., and Tu, T. T. (2002). “A neural network approach for structural identification and diagnosis of a building from seismic response data.” Earthquake Engineering and Structural Dynamics. (accepted)
78.Huang, C. S., and Lin, H. L. (2001). “Modal identification of structures from ambient vibration, and seismic response data via a subspace approach.” Earthquake Engineering and Structural Dynamics, 30(12), 1857-1878.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊