Abstract
The aim of the paper is to describe a methodology of damage detection which is based on artificial neural networks in combination with stochastic analysis. The damage is defined as a stiffness reduction (bending or torsion) in certain part of a structure. The key stone of the method is feed-forward multilayer network. It is impossible to obtain appropriate training set for real structure in usage, therefore stochastic analysis using numerical model is carried out to get training set virtually. Due to possible time demanding nonlinear calculations the effective simulation Latin Hypercube Sampling is used here. The important part of identification process is proper selection of input information. In case of dynamically loaded structures their modal properties seem to be proper input information as those are not dependent on actual loading (traffic, wind, temperature). The methodology verification was carried out using laboratory beam.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Wenzel, H., Pichler, D.: Ambient vibration monitoring. John Wiley & Sons Ltd, West Sussex (2005)
Salgado, R., Cruz, P.J.S., Ramos, L.F., Lourenço, P.B.: Comparison between damage detection methods applied to beam structures. In: Third International Conference on Bridge Maintenance Safety and Management, Porto, Portugal, CD-ROM (2006)
Koh, B.H., Dyke, S.J.: Structural health monitoring for flexible bridge structures using correlation and sensitivity of modal data. Computers and Structures 85, 117–130 (2007)
Spencer Jr., B.F., Gao, Y., Yang, G.: Distributed computing strategy for damage monitoring employing smart sensors. In: Shenzhen, C., Ou, L., Duan (eds.) Structural Health Monitoring and Intelligent Infrastructure, pp. 35–47. Taylor & Francis Group, London (2005)
Feltrin, G.: Temperature and damage effects on modal parameters of a reinforced concrete bridge. In: 5th European Conference on Structural Dynamics (EURODYN), Munich, Germany (2002)
Link, M.: Updating of analytical models – basic procedures and extensions. In: Silva, J.M.M., Maia, N.M.M. (eds.) Modal Analysis and Testing. NATO Science Series. Kluwer Academic Publ, Dordrecht (1999)
Teughels, A., Maeck, J., De Roeck, G.: Damage assessment by FE model updating using damage functions. Computers and Structures 80(25), 1869–1879 (2002)
Deix, S., Geier, R.: Updating FE-models using experimental modal analysis for damage detection and system identification in civil structures. In: Third European Conference on Structural Control (3ECSC). Vienna University of Technology, Vienna (2004)
Fang, X., Luo, H., Tang, J.: Structural damage detection using neural network with learning rate improvement. Computers and Structures 83, 2150–2161 (2005)
Huth, O., Feltrin, G., Maeck, J., Kilic, N., Motavalli, M.: Damage identification using modal data: Experiences on a prestressed concrete bridge. Journal of Structural Engineering, ASCE 131(12), 1898–1910 (2005)
Strauss, A., Lehký, D., Novák, D., Bergmeister, K., Santa, U.: Probabilistic response identification and monitoring of concrete structures. In: Third European Conference on Structural Control (3ECSC). Vienna University of Technology, Vienna (2004)
Strauss, A., Bergmeister, K., Lehký, D., Novák, D.: Inverse statistical FEM analysis – vibration based damage identification of concrete structures. In: International Conference on Bridges, Dubrovnik, Croatia, pp. 461–470 (2006)
Novák, D., Lehký, D.: ANN Inverse Analysis Based on Stochastic Small-Sample Training Set Simulation. Engineering Application of Artificial Intelligence 19, 731–740 (2006)
Novák, D., Lehký, D.: Inverse analysis based on small-sample stochastic training of neural network. In: 9th International Conference on Engineering Applications of Neural Networks (EAAN2005), Lille, France, pp. 155–162 (2005)
Lehký, D., Novák, D.: Probabilistic inverse analysis: Random material parameters of reinforced concrete frame. In: 9th International Conference on Engineering Applications of Neural Networks (EAAN2005), Lille, France, pp. 147–154 (2005)
Strauss, A., Bergmeister, K., Novák, D., Lehký, D.: Stochastische Parameteridentifikation bei Konstruktionsbeton für die Betonerhaltung. Beton und Stahlbetonbau 99(12), 967–974 (2004)
Frantík, P., Lehký, D., Novák, D.: Modal properties study for damage identification of dynamically loaded structures. In: The Third International Conference on Structural Engineering, Mechanics and Computation, Cape Town, South Africa, pp. 703–704 (2007)
Lehký, D., Novák, D., Frantík, P., Strauss, A., Bergmeister, K.: Dynamic damage identification of Colle Isarco viaduct. In: 4th International Conference on Bridge Maintenance, Safety and Management (IABMAS 2008), Seoul, Korea, pp. 2549–2556 (2008)
Armon, D., Ben-Haim, Y., Braun, S.: Crack detection in beams by rank-ordering of eigenfrequencies shifts. Mechanical Systems and Signal Processing 8(1), 81–91 (1994)
Kůrková, V.: Kolmogorov’s theorem and multilayer neural networks. Neural Networks 5(3), 501–506 (1992)
Šnorek, M.: Neuronové sítě a neuropočítače (Neural networks and neurocomputers). Vydavatelství ČVUT, Prague, Czech Republic (2002) (in Czech)
McKay, M.D., Conover, W.J., Beckman, R.J.: A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code. Technometrics 21, 239–245 (1979)
Novák, D., Teplý, B., Keršner, Z.: The role of Latin Hypercube Sampling method in reliability engineering. In: Proc. of ICOSSAR 1997, Kyoto, Japan, pp. 403–409 (1998)
Singh, V., Gupta, I., Gupta, H.O.: ANN-based estimator for distillation using Levenberg-Marquardt approach. Engineering Applications of Artificial Intelligence 20, 249–259 (2007)
Schwefel, H.P.: Numerical optimization for computer models. Wiley, Chichester (1991)
Novák, D., Vořechovský, M., Rusina, R.: FReET v.1.5 – program documentation. Userś and Theory Guides. Brno/Červenka Consulting, Czech Republic (2008), http://www.freet.cz
Lehký, D.: DLNNET – program documentation. Theory and User’s Guides, Brno, Czech Republic (in preparation, 2009)
Sofistik, A.G.: SOFiSTiK Analysis Programs, version 21.0, Oberschleissheim, Germany (2004), http://www.sofistik.com
Lehký, D.: Relid – program documentation. User’s Guide, Brno, Czech Republic (in preparation, 2009)
Lehký, D., Novák, D., Frantík, P., Strauss, A., Bergmeister, K.: Dynamic damage identification based on artificial neural networks, SARA – part IV. In: The 3rd International Conference on Structural Health Monitoring of Intelligent Infrastructure, Vancouver, British Columbia, Canada, vol. 183 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lehký, D., Novák, D. (2009). Neural Network Based Damage Detection of Dynamically Loaded Structures. In: Palmer-Brown, D., Draganova, C., Pimenidis, E., Mouratidis, H. (eds) Engineering Applications of Neural Networks. EANN 2009. Communications in Computer and Information Science, vol 43. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03969-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-03969-0_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03968-3
Online ISBN: 978-3-642-03969-0
eBook Packages: Computer ScienceComputer Science (R0)