Hierarchical Wavelet-Aided Neural Intelligent Identification of Structural Damage in Noisy Conditions
Source abstract
Abstract
A sophisticated hierarchical neural network model for intelligent assessment of structural damage is constructed by the synergetic action of auto-associative neural networks (AANNs) and Levenberg-Marquardt neural networks (LMNNs). With the model, AANNs aided by the wavelet packet transform are firstly employed to extract damage features from measured dynamic responses and LMNNs are then utilized to undertake damage pattern recognition. The synergetic functions endow the model with a unique mechanism of intelligent damage identification in structures. The model is applied for the identification of damage in a three-span continuous bridge, with particular emphasis on noise interference. The results show that the AANNs can produce a low-dimensional space of damage features, from which LMNNs can recognize both the location and the severity of structural damage with great accuracy and strong robustness against noise. The proposed model holds promise for developing viable intelligent damage identification technology for actual engineering structures.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Structural Health Monitoring Techniques · Ultrasonics and Acoustic Wave Propagation · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Engineering Mechanics, Hohai University, Nanjing 210098, China
School of Civil Engineering, Hefei University of Technology, Hefei 230009, China
Department of Architecture and Civil Engineering, City University of Hong Kong, Kowloon, Hong Kong SAR
Research Group for Mathematical and Numerical Analysis of Dynamical Systems, Kaunas University of Technology, Kaunas LT-51368, Lithuania
References (58)
Show source-provided references
1. Sohn, H., Farrar, C.R., and Hemez, F.M. (2003). A Review of Structural Health Monitoring Literature: 1996–2001, Los Alamos National Laboratory. LA-13976-MS.
2. An introduction to structural health monitoring10.1098/rsta.2006.1928 ↗
3. Structural health monitoring in mainland China: Review and future trends10.1177/1475921710365269 ↗
4. Structural health monitoring for a wind turbine system: A review of damage detection methods10.1088/0957-0233/19/12/122001 ↗
5. Development in vibration-based structural damage detection technique10.1016/j.ymssp.2006.10.002 ↗
6. Review on structural damage detection based on vibration data
7. Vibration-based damage identification methods: A review and comparative study
8. Guided Lamb waves for identification of damage in composite structures: A review10.1016/j.jsv.2006.01.020 ↗
9. A new damage detection technique based on wave propagation for rails10.1016/j.ijsolstr.2005.05.006 ↗
10. Damage detection of structures using spectral finite element method10.1016/j.compstruc.2007.02.004 ↗
11. Crack detection in beam-like structures using genetic algorithms10.1016/j.asoc.2007.10.003 ↗
12. Structural health monitoring via measured Ritz vectors utilizing artificial neural networks10.1111/j.1467-8667.2006.00431.x ↗
13. Structural dynamics-guided hierarchical neural-networks scheme for locating and quantifying damage in beam-type structures
14. Ghafory-Ashtiany, Application of genetic algorithm in crack detection of beam-like structures using a new cracked Euler–Bernoulli beam element10.1016/j.asoc.2012.09.014 ↗
15. Structural damage detection using fuzzy cognitive maps and Hebbian learning10.1016/j.asoc.2010.01.023 ↗
16. Improved hybrid wavelet neural network methodology for time-varying behavior prediction of engineering structures10.1007/s00521-009-0240-8 ↗
17. Artificial neural networks for vibration based inverse parametric identifications: A review10.1016/j.asoc.2016.12.014 ↗
18. Modal parameters based structural damage detection using artificial neural networks—A review10.12989/sss.2014.14.2.159 ↗
19. Optimal sensor placement for fault detection10.1016/S0141-0296(00)00118-8 ↗
20. Worden, K., Ball, A.D., and Tomlinson, G.R. (1992, January 5–7). Fault location in structures using neural networks. Proceedings of the 75th Meeting of the AGARD Structures and Materials Panel on Smart Structures for Aircraft and Spacecraft, Lindau, Germany.
21. Constructing input vectors to neural networks for structural damage identification10.1088/0964-1726/11/6/301 ↗
22. Damage identification in a ship’s structure using neural networks10.1016/S0029-8018(01)00077-4 ↗
23. Damage assessment of structures using hybrid neuro-genetic algorithm10.1016/j.asoc.2005.04.001 ↗
24. Frequency response function-based structural damage identification using artificial neural networks—A review10.19026/rjaset.7.459 ↗
25. Integrated wavelet transform and its application to vibration mode shapes for the damage detection of beam-type structures10.1088/0964-1726/17/5/055014 ↗
26. Wavelet-based approach for structural damage detection10.1061/(ASCE)0733-9399(2000)126:7(677) ↗
27. Wavelet transform for structural health monitoring: A compendium of uses and features10.1177/1475921706067741 ↗
28. A multi-scale pseudo-force model in wavelet domain for identification of damage in structural components10.1016/j.ymssp.2011.11.011 ↗
29. Wavelet packet feature extraction for vibration monitoring10.1109/41.847906 ↗
30. Wavelet packet based damage identification of beam structures10.1016/j.ijsolstr.2005.04.031 ↗
31. Statistical damage classification method based on wavelet packet analysis10.12989/sem.2013.46.4.459 ↗
32. Bayesian wavelet packet denoising for structural system identification10.1002/stc.161 ↗
33. A hybrid wavelet based–approach and genetic algorithm to detect damage in beam-like structures without baseline data10.1007/s11340-016-0181-y ↗
34. Chiariotti, P., Martarelli, M., and Revel, G.M. (2017). Delamination detection by Multi-Level Wavelet Processing of Continuous Scanning Laser Doppler Vibrometry data. Opt. Lasers Eng.10.1016/j.optlaseng.2017.01.002 ↗
35. Damage detection of jacket type offshore platforms using rate of signal energy using wavelet packet transform10.1016/j.marstruc.2015.10.003 ↗
36. Vibration-based damage detection for composite structures using wavelet transform and neural network identification10.1016/S0263-8223(03)00023-0 ↗
37. An integrated approach for structural damage identification using wavelet neuro-fuzzy model10.1016/j.eswa.2013.06.078 ↗
38. Diao, Y.S., Li, H.J., and Wang, Y. (2006, January 13–16). A two-step structural damage detection approach based on wavelet packet analysis and neural network. Proceedings of the IEEE International Conference on Machine Learning and Cybernetics.10.1109/ICMLC.2006.258404 ↗
39. A neural-wavelet technique for damage identification in the ASCE benchmark structure using phase II experimental data10.1155/2010/675927 ↗
40. Structural damage detection by wavelet transform and probabilistic neural network10.1117/12.602012 ↗
41. Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network10.1049/iet-smt.2009.0023 ↗
42. Damage detection and classification in pipework using acousto-ultrasonics and non-linear data-driven modelling10.1007/s13349-013-0060-5 ↗
43. Quantification and localization of damage in beam-like structures by using artificial neural networks with experimental validation10.1016/j.engstruct.2003.08.001 ↗
44. Nondestructive evaluation of prestressed concrete beams using an artificial neural network (ANN) approach10.1177/1475921706067759 ↗
45. Neural network-based simulation for response identification of two-storey shear building subject to earthquake motion10.1007/s00521-009-0279-6 ↗
46. Structural damage detection from wavelet packet sensitivity10.1016/j.engstruct.2005.03.014 ↗
47. Gao, R.X., and Yan, R.Q. (2011). Wavelet Packet Transform-Theory and Applications for Manufacturing, Springer.10.1007/978-1-4419-1545-0_5 ↗
48. Developments and applications of nonlinear principal component analysis—A review10.1007/978-3-540-73750-6_1 ↗
49. Neural network ensemble-based parameter sensitivity analysis in civil engineering systems
50. Nonlinear principal component analysis using autoassociative neural networks10.1002/aic.690370209 ↗
51. Structural damage assessment based on wavelet packet transform10.1061/(ASCE)0733-9445(2002)128:10(1354) ↗
52. Effects of environmental and operational variability on structural health monitoring10.1098/rsta.2006.1935 ↗
53. Statistical damage classification under changing environmental and operational conditions10.1106/104538902030904 ↗
54. Modified Levenberg-Marquardt method for neural networks training
55. Damage identification on the Z24 bridge using vibration monitoring10.1088/0964-1726/10/3/313 ↗
56. Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification10.1177/1475921713502836 ↗
57. Spiridonakos, M.D., Chatzi, E.N., and Sudret, B. (2016). Polynomial chaos expansion models for the monitoring of structures under operational variability. ASCE-ASME J. Risk Uncertain. Eng. Syst. A Civ. Eng., 2.10.1061/AJRUA6.0000872 ↗
58. Sun, Y. (2009, January 14–16). Combined neural network and PCA for complicated damage detection of bridge. Proceedings of the International Conference on Natural Computation, Tianjin, China.10.1109/ICNC.2009.580 ↗