Advertisement

Sadhana

, Volume 29, Issue 3, pp 315–327 | Cite as

Damage assessment in structure from changes in static parameter using neural networks

  • Damodar Maity
  • Asish Saha
Article

Abstract

Damage to structures may occur as a result of normal operations, accidents, deterioration or severe natural events such as earthquakes and storms. Most often the extent and location of damage may be determined through visual inspection. However, in some cases this may not be feasible. The basic strategy applied in this study is to train a neural network to recognize the behaviour of the undamaged structure as well as of the structure with various possible damaged states. When this trained network is subjected to the measured response, it should be able to detect any existing damage. This idea is applied on a simple cantilever beam. Strain and displacement are used as possible candidates for damage identification by a back-propagation neural network. The superiority of strain over displacement for identification of damage has been observed in this study

Keywords

Back-propagation neural network damage assessment finite element method mean square error 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barai S V, Pandey P C 1995a Multilayer Perceptron in Damage Detection of Bridge Structures.Comput. Struct. 54: 597–608MATHCrossRefGoogle Scholar
  2. Barai S V, Pandey P C 1995b Performance of generalized delta rule in artificial neural network for damage detection.Eng. Appl. Artif. Intell. 211–221Google Scholar
  3. Bishop C M 1998Neural networks for pattern recognition (Oxford: Clarendon)Google Scholar
  4. Cawley P, Adams R D 1979 The location of defects in structures from measurement of natural frequency.J. Strain Anal. 14: 49–57CrossRefGoogle Scholar
  5. Cerri M N, Vestroni F 2000 Detection of damage in beams subjected to diffused cracking.J. Sound Vibr. 234: 259–276CrossRefGoogle Scholar
  6. Chinchalkar S 2001 Determination of crack location in beams using natural frequencies.J. Sound Vibr. 247: 417–429CrossRefGoogle Scholar
  7. Friswell M I, Mottershea J E 1999 Finite element updating in structural dynamics. (Dordrecht: Kluwer Academic)Google Scholar
  8. Morassi A 2001 Identification of a crack in a rod based on changes in a pair of natural frequencies.J. Sound Vibr. 242: 577–596CrossRefGoogle Scholar
  9. Nakamura M, Masari S F, Chassiakos A G, Caughey T K 1998 A method for non-parametric damage detection through the use of neural network.Earthquake Eng. Struct. Dyn. 27: 997–1010CrossRefGoogle Scholar
  10. Pandey A K, Biswas M 1994 Damage detection in structures using changes in flexibility.J. Sound Vibr. 169: 3–17MATHCrossRefGoogle Scholar
  11. Pandey A K, Biswas M, Samman M M 1991 Damage detection from changes in curvature mode shapes.J. Sound Vibr. 145: 321–332CrossRefGoogle Scholar
  12. Rumelhart D E, Hinton G E, Williams R J 1986 Learning internal representations by error backpropagation.Parallel Distrib. Process. Explor. Microstruct. Cogn. 1: 318–362Google Scholar
  13. Rytter A, Kirkegaard P H 1997 Vibration based inspection using neural networks.Proc. DAMAS’97, University of Sheffield, UK, pp. 97–108Google Scholar
  14. Sanayei M, Onipede O 1991 Damage assessment of structures using static test data.AIAA J. 29: 1174–1179Google Scholar
  15. Suh M W, Shim M B, Kim M Y 2000 Crack identification using hybrid neuro-genetic technique.J. Sound Vibr. 238: 617–635CrossRefGoogle Scholar
  16. Szewczyk Z P, Hajela P 1994 Damage detection in structures based on feature sensitive neural networks.ASCE J. Comput. Civil Eng. 8: 163–178CrossRefGoogle Scholar
  17. Tsou P, Shen M H 1994 Structural damage detection and identification using neural networks.AIAA J. 32: 176–183MATHCrossRefGoogle Scholar
  18. Wahab M M A, Roeck G D 1999 Damage detection in bridges using modal curvatures: Application to a real damage scenario.J. Sound Vibr. 226: 217–235CrossRefGoogle Scholar
  19. Worden K 1996 Multi-layer perceptron (MLP), Version 3.4, A users guide. Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, UKGoogle Scholar
  20. Wu X, Ghaboussi J, Garrett J H 1992 Use of neural networks in detection of structural damage.Comput. Struct. 42: 649–659MATHCrossRefGoogle Scholar
  21. Yongyong H, Dan G, Fulei C 2001 Using genetic algorithm and finite element methods to detect shaft crack for rotor-bearing system.Math. Comput. Simul. 57: 95–108MATHCrossRefGoogle Scholar
  22. Yun C, Bahng E Y 2000 Substructural identification using neural network.Comput. Struct. 77: 41–52CrossRefGoogle Scholar
  23. Zapico J L, Gonzalez M P 2003 Damage assessment using neural networks.Mech. Syst. Signal Process. 17: 119–125CrossRefGoogle Scholar

Copyright information

© Indian Academy of Sciences 2004

Authors and Affiliations

  1. 1.Civil Engineering DepartmentIndian Institute of Technology — GuwahatiGuwahatiIndia

Personalised recommendations