Localized and decentralized identification for large-scale structures

• Autorzy: Xu B. , Wu Z.
• Konferencja: Neural Networks and Soft Computing/International Symposium (30.06-02.07.2005 ; Cracow, Poland)
• Języki publikacji: EN

Abstrakty

EN

Mathematical-model-based structural identification algorithms for the damage detection and performance evaluation of civil engineering structures have been widely proposed and their performance for small and simple structural models has been studied in the past two decades. Actual civil engineering structures, however, usually have a great number of degrees of freedom (DOFs). It is unpractical to directly apply these conventional methods for the identification of large-scale structures, because excessive computation time and computer memory are necessary for the search of optimal solutions in inverse analysis, which is often computationally inefficient and even numerically unstable. Moreover, for the identification of largescale structures, it is difficult to obtain unique estimates of all structural parameters by the optimization search processes involved in the conventional identification algorithms requiring the use of secant, tangent, or higher-order derivatives of the objective function. The ability of artificial neural networks to approximate arbitrary continuous function provides an efficient soft computing strategy for structural parametric identification. Based on the concept of localized and decentralized information architecture, novel decentralized and localized identification strategies for large-scale structure system by the direct use of structural vibration response measurements with neural networks are proposed in this paper. These methodologies does not require the extraction of structural frequencies and mode shapes from the measurements and have the potential of being a practical tool for on-line near-real time and damage detection and performance evaluation of large-scale engineering structures.

Słowa kluczowe

EN

neural network; soft computing; algorithms; civil engineering

PL

sieci neuronowe; algorytm; inżynieria lądowa

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2007
• Tom: Vol. 14, No. 2
• Strony: 361--378
• Opis fizyczny: Bibliogr. 24 poz., rys., tab.

Twórcy

autor

Xu B.

autor

Wu Z.

• College of Civil Engineering, Hunan University Yuelu Mountain, Changsha, Hunan, 410082, P.R. China

Bibliografia

• [1] S.W. Doebling, CR. Farrar, M.B. Prime. A summary review of vibration-based damage identification methods. Shock and Vibration Digest, 30(2): 91-105, 1998.
• [2] CG. Koh, B. Hong, C.Y. Liaw. Parameter identification of large structural systems in time domain. Journal of Structural Engineering, 126(8): 957-963, 2000.
• [3] CG. Koh, L.M. See, T. Balendra. Estimation of structural parameters in time domain: A substructure approach. Earthquake Engineering and Structural Dynamics, 20: 787-802, 1991.
• [4] S.F. Masri, A.G. Chassiakos, T.K. Caughey. Identification of nonlinear dynamic systems using neural networks. Journal of Applied Mechanics, ASME, 60: 123-133, 1993.
• [5] S.F. Masri, A.W. Smyth, A.G. Chassiakos, T.K Caughey, N.F. Hunter. Application of neural networks for detection of changes in nonlinear systems. Journal of Engineering Mechanics, ASCE, 126(7): 666-676, 2000.
• [6] G.H. Mcverry. Structural identification in frequency domain from earthquake records. Earthquake Engineering and Structural Dynamics, 8: 161-180, 1980.
• [7] M. Nakamura, S.F. Masri, A.G. Chassiakos, T.K. Caughey. A method for non-parametric health monitoring through the use of neural networks. Earthquake Engineering and Structural Dynamics, 27: 997-1010, 1998.
• [8] K. Worden. Structural fault detection using a novelty measure. Journal of Sound and Vibration, 201(1): 85-101, 1997.
• [9] Z.S. Wu, B. Xu. A real-time structural parametric identification system based on fiber optic sensing and neural network algorithms. Smart NDE and Health Monitoring of Structural and Biological Systems, Proceedings of SPIE, 5047: 392-402, 2003.
• [10] Z.S. Wu, B. Xu, T. Harada. Review on structural health monitoring for infrastructure. Journal of Applied Mechanics, JSCE, 6: 1043-1054, 2003.
• [11] Z.S. Wu, B. Xu, K. Yokoyama. Decentralized parametric damage detection based on neural networks. Computer-Aided Civil and Infrastructure Engineering, 17: 175-184, 2002.
• [12] B. Xu. Neural networks based structural model updating methodology using spatially incomplete accelerations. Lecture Notes m Computer Science, 4221: 361-370, 2006.
• [13] B. Xu. Substructural identification for safety evaluation of large-scale structures using spatially incomplete acceleration measurements. Proceedings of the 2006 International Symposium on Safety Science and Technology: Progress in Safety Science and Technology, 4: 2119-2125, Changsha, China, 2006.
• [14] B. Xu, G. Chen, Z.S. Wu. Strain-based direct identification of parameters with neural networks. Computer-Aided Civil and Infrastructure Engineering, 22(3): 79-91, 2007.
• [15] B. Xu, T. Du. Direct substructural identification methodology using acceleration measurements with neural networks. Proceedings of SPIE, 6178: paper No. 6178-5, 2006.
• [16] B. Xu, Z.S. Wu. Long-gauge fiber optic sensors for dynamic strain measurement and structural identification. Proceedings of the First International Conference on Structural Health Monitoring and Intelligent Infrastructure, Tokyo, pp. 299-308, 2003.
• [17] B. Xu, Z.S. Wu, G. Chen, K. Yokoyama. Direct identification of structural parameters from dynamic responses with neural networks. Engineering Applications of Artificial Intelligence, 17(8): 931-943, 2004.
• [18] B. Xu, Z.S. Wu, K. Yokoyama. Decentralized identification of large-scale structure-AMD coupled system using multi-layer neural networks. Transactions of the Japan Society for Computational Engineering and Science, 2: 187-197, 2000.
• [19] B. Xu, Z.S. Wu, K. Yokoyama. A neural networks based modelling of structural parametric evaluation with direct use of dynamic responses in time domain. Smart NDE and Health Monitoring of Structural and Biological Systems, SPIE, 5047: 252-262, 2003.
• [20] B. Xu, Z.S. Wu, K. Yokoyama, T. Harada, G. Chen. A soft post-earthquake damage identification methodology using vibration time series. Smart Materials and Structures, 14(3): sll6-sl24, 2005.
• [21] C.B. Yun, E.Y. Bahng. Substructural identification using neural networks. Computers and Structures, 77: 41-52, 2000.
• [22] C.B. Yun, H. J. Lee. Substructural identification for damage estimation of structures. Structural Safety, 19(1):121-140, 1997.
• [23] C.B. Yun, H.J. Lee, CG. Lee. Sequential prediction error method for structural identification. Journal of Engineering Mechanics, ASCE, 123(2): 115-122, 1997.
• [24] J. Zhao, J.N. Ivan, T. Dewolf. Structural health monitoring using artificial neural networks. Journal of Infrastructure Systems, 4(3): 93-101, 1998.