Diagnosis of structural cracks using wavelet transform and neural networks
Source abstract
Abstract
Abstract This paper proposes an approach to detecting and characterizing structural cracks emanating from rows of rivet holes in thin metallic plates using lamb wave, wavelet transform and neural networks. When lamb waves propagate through rows of holes, there exist strong wave interferences among different transmitted waves which make health diagnosis complicated. An active sensing network is mounted on the plate and wavelet transform is used to extract a robust and effective feature called energy ratio change from time domain signals. The relationship between energy ratio change and the crack characteristics is analyzed and the effective detection paths are found out. Neural networks are then developed using the feature to diagnose health condition in stages. One neural network is first used to diagnose plate integrity. If cracks are detected, then the second neural network is called to determine their locations. The method is first examined in simulation data, then the NNs trained by simulation data are used to diagnose real plates. The results shows that the method can effectively detect cracks and identify their locations in both simulation and experimental data, hence demonstrating the feasibility of using the method to develop built-in real time intelligent diagnosis systems.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Structural Health Monitoring Techniques · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (22)
Show source-provided references
1. Giurgiutiu · 2008
2. Staszewski · 2004
3. Ways and options for aircraft structural health management10.1088/0964-1726/10/3/302 ↗
4. The interaction of lamb waves with defects10.1109/58.143172 ↗
5. Scattering of lamb waves from a rivet hole with edge cracks10.1016/S0167-6636(98)00060-X ↗
6. Quantitative assessment of through-thickness crack size based on lamb wave scattering in aluminium plates10.1016/j.ndteint.2007.07.003 ↗
7. Detection of cracks at rivet holes using guided waves10.1016/S0041-624X(02)00137-3 ↗
8. Optimization of lamb wave inspection techniques10.1016/0963-8695(92)90003-Y ↗
9. Efficient use of lamb modes for detecting defects in large plates10.1016/S0041-624X(98)00012-2 ↗
10. Detection and monitoring of hidden fatigue crack growth using a built-in piezoelectric sensor/actuator network10.1088/0964-1726/13/3/020 ↗
11. Detection and monitoring of hidden fatigue crack growth using a built-in piezoelectric sensor/actuator network10.1088/0964-1726/13/3/021 ↗
12. Damage diagnostics on a welded zone of a steel truss member using an active sensing network system10.1016/j.ndteint.2006.07.004 ↗
13. Fatigue crack monitoring of riveted aluminium strap joints by lamb wave analysis and acoustic emission measurement techniques10.1016/S0963-8695(01)00027-5 ↗
14. A review of artificial intelligence applied to ultrasonic defect evaluation
15. A neural network for crack sizing trained by finite element calculations10.1016/0963-8695(96)00013-8 ↗
16. Detection of cracks using neural networks and computational mechanics10.1016/S0045-7825(02)00221-9 ↗
17. Modeling elastic wave propagation in waveguides with the finite element method10.1016/S0963-8695(98)00045-0 ↗
18. Liu W, Hong J. Three-dimensional lamb wave propagation excited by a phased piezoelectric array. Smart Mater Struc, 2010.10.1088/0964-1726/19/8/085002 ↗
19. Mou JQ, Martua L, Yu YQ, He ZM, Du CL, Zhang JL, et al. Structural health monitoring using pzt transducer network and lamb waves. In: Proceedings of the ASME 2010 international mechanical engineering congress and exposition, IMECE 2010, IMECE 2010-37653. Vancouver, British Columbia, Canada; 2010.10.1115/IMECE2010-37653 ↗
20. Wavelet-transform-based method of analysis for lamb-wave ultrasonic NDE signals10.1109/19.850388 ↗
21. Signal detection and noise suppression using a wavelet transform signal processor10.1109/58.585186 ↗
22. Masters · 1993