journal article·2024-06Open access

Damage assessment of laminated composites using unsupervised autonomous features

Asif Khan, Heung Soo Kim

Abstract

This article proposes a framework for the damage assessment of and effect of temperature variations in laminated composites using Lamb waves and unsupervised autonomous features. A network of piezoelectric transducers is employed to generate data for 18 health states of a laminated composite plate. The data is processed with sparse autoencoder (SAE) for unsupervised autonomous features. The discriminative capabilities of the extracted features are confirmed by processing the feature space in the supervised and unsupervised frameworks of machine learning. The confusion matrices of supervised learning provided physical insights into the problem. The feature space was also visualized in two dimensions in an unsupervised manner through principal component analysis (PCA), which revealed physically consistent results for the effect of temperature variations, damage of different severity levels, and the undamaged paths between the actuator and sensors. The healthy state data and information on the paths between the actuator and sensors was processed via SAE for damage localization. The proposed approach can be employed for the autonomous assessment of composite structures for the presence of damage and variations of operating temperatures while using both supervised and unsupervised machine learning algorithms.
Source: crossref · Quality: baseline

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.

Affiliations

Faculty of Mechanical Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi Khyber Pakhtunkhwa, Pakistan

Department of Mechanical, Robotics and Energy Engineering, Dongguk University-Seoul, Seoul 04620, Korea

Funding

National Research Foundation

References (85)

Show source-provided references
1. 10.1201/978142004520810.1201/9781420045208 ↗
2. Irving PE, Soutis C. (n.d.). Polymer composites in the aerospace industry, p. 537. Woodhead Publishing, 2019.
3. 10.3390/math1001003810.3390/math10010038 ↗
4. Sridharan S · 2008
5. 10.1016/j.compstruct.2004.06.00410.1016/j.compstruct.2004.06.004 ↗
6. 10.1016/j.compstruct.2017.01.01510.1016/j.compstruct.2017.01.015 ↗
7. 10.17485/ijst/2016/v9i41/8583210.17485/ijst/2016/v9i41/85832 ↗
8. Giurgiutiu V · 2015 · 26
9. 10.1177/0892705723117267010.1177/08927057231172670 ↗
10. 10.1016/j.measurement.2020.10863910.1016/j.measurement.2020.108639 ↗
11. 10.1155/2020/881321310.1155/2020/8813213 ↗
12. 10.1016/j.ymssp.2020.10712410.1016/j.ymssp.2020.107124 ↗
13. 10.1016/j.proeng.2014.12.67510.1016/j.proeng.2014.12.675 ↗
14. 10.1016/j.compstruct.2022.11550210.1016/j.compstruct.2022.115502 ↗
15. 10.1115/1.404428710.1115/1.4044287 ↗
16. 10.1177/0892705723115454810.1177/08927057231154548 ↗
17. 10.1177/0892705721100190710.1177/08927057211001907 ↗
18. 10.1177/089270571557364910.1177/0892705715573649 ↗
19. 10.3390/s2201015310.3390/s22010153 ↗
20. 10.1177/147592171876048310.1177/1475921718760483 ↗
21. 10.1016/j.ymssp.2019.10649910.1016/j.ymssp.2019.106499 ↗
22. 10.1016/j.jsv.2019.11510110.1016/j.jsv.2019.115101 ↗
23. 10.1016/j.ymssp.2017.08.03710.1016/j.ymssp.2017.08.037 ↗
24. 10.3390/sym1311199810.3390/sym13111998 ↗
25. 10.1177/089270571351881010.1177/0892705713518810 ↗
26. 10.1177/089270571772919610.1177/0892705717729196 ↗
27. 10.1016/j.measurement.2014.11.03310.1016/j.measurement.2014.11.033 ↗
28. 10.1016/j.measurement.2018.07.03210.1016/j.measurement.2018.07.032 ↗
29. 10.1002/stc.284910.1002/stc.2849 ↗
30. 10.1016/j.ultras.2004.12.00610.1016/j.ultras.2004.12.006 ↗
31. 10.1063/1.290258210.1063/1.2902582 ↗
32. 10.1016/j.ndteint.2008.10.00610.1016/j.ndteint.2008.10.006 ↗
33. 10.1088/0964-1726/20/12/12500510.1088/0964-1726/20/12/125005 ↗
34. 10.1016/j.ymssp.2015.06.01710.1016/j.ymssp.2015.06.017 ↗
35. 10.1111/mice.1233410.1111/mice.12334 ↗
36. 10.1111/mice.1226310.1111/mice.12263 ↗
37. 10.1016/j.ymssp.2021.10814810.1016/j.ymssp.2021.108148 ↗
38. 10.1111/j.1475-1305.2007.00371.x10.1111/j.1475-1305.2007.00371.x ↗
39. 10.1016/j.compstruct.2021.11459010.1016/j.compstruct.2021.114590 ↗
40. 10.1109/JSEN.2019.290883810.1109/JSEN.2019.2908838 ↗
41. 10.1016/j.mlwa.2021.10021610.1016/j.mlwa.2021.100216 ↗
42. 10.3390/s2008233510.3390/s20082335 ↗
43. 10.1016/j.compscitech.2021.10871310.1016/j.compscitech.2021.108713 ↗
44. 10.1016/j.ymssp.2021.10867110.1016/j.ymssp.2021.108671 ↗
45. 10.1016/j.compositesb.2018.12.11810.1016/j.compositesb.2018.12.118 ↗
46. 10.1016/j.compstruct.2021.11387110.1016/j.compstruct.2021.113871 ↗
47. 10.1109/ICIT.2017.791550510.1109/ICIT.2017.7915505 ↗
48. 10.1016/j.compositesb.2020.10803910.1016/j.compositesb.2020.108039 ↗
49. 10.1016/j.jsv.2006.01.02010.1016/j.jsv.2006.01.020 ↗
50. 10.1016/j.is.2015.04.00710.1016/j.is.2015.04.007 ↗
51. 10.1177/147592171769126010.1177/1475921717691260 ↗
52. Prof. Dr. Samuel da Silva - SHM Lab, (n.d.). https://www.samueldasilva.org/shm-lab (accessed January 3, 2023).
53. 10.3390/s2118623910.3390/s21186239 ↗
54. 10.1177/1045389X1039564310.1177/1045389X10395643 ↗
55. 10.1016/j.compositesb.2012.02.03710.1016/j.compositesb.2012.02.037 ↗
56. 10.1002/pc.2575310.1002/pc.25753 ↗
57. 10.1177/1045389X2096317110.1177/1045389X20963171 ↗
58. 10.1177/107754632096618310.1177/1077546320966183 ↗
59. Paixão J. Damage quantification in laminated composites using Gaussian process regression model. 2020. https://repositorio.unesp.br/items/8d1d5933-beee-4735-9fa5-bfea4cccf9bc
60. 10.1007/978-981-13-8331-1_6310.1007/978-981-13-8331-1_63 ↗
61. 10.1007/s40430-018-1462-410.1007/s40430-018-1462-4 ↗
62. 10.1038/323533a010.1038/323533a0 ↗
63. 10.1016/j.measurement.2016.04.00710.1016/j.measurement.2016.04.007 ↗
64. 10.1016/S0031-3203(96)00142-210.1016/S0031-3203(96)00142-2 ↗
65. Feng K, Hong H, Tang K, et al.Decision making with machine learning and ROC curves, 2019. arXiv Preprint arXiv:1905.02810.10.2139/ssrn.3382962 ↗
66. 10.1109/IACC.2016.2510.1109/IACC.2016.25 ↗
67. 10.1016/j.procs.2019.12.11110.1016/j.procs.2019.12.111 ↗
68. Karamizadeh S · J Signal Inf Process · 2020 · 4
69. 10.1098/rsta.2015.020210.1098/rsta.2015.0202 ↗
70. 10.1038/s41597-019-0208-110.1038/s41597-019-0208-1 ↗
71. Shoja S · 2016 · 20
72. 10.1177/1045389X0708669110.1177/1045389X07086691 ↗
73. 10.1080/1042691090342579610.1080/10426910903425796 ↗
74. 10.1177/1045389X0810163410.1177/1045389X08101634 ↗
75. 10.1177/147592172093405110.1177/1475921720934051 ↗
76. 10.1016/j.measurement.2020.10781110.1016/j.measurement.2020.107811 ↗
77. 10.3390/s2206241210.3390/s22062412 ↗
78. 10.1111/mice.1294310.1111/mice.12943 ↗
79. 10.1016/j.ymssp.2023.11047310.1016/j.ymssp.2023.110473 ↗
80. 10.1088/0964-1726/25/5/05300110.1088/0964-1726/25/5/053001 ↗
81. 10.1016/j.ultras.2023.10701410.1016/j.ultras.2023.107014 ↗
82. 10.1121/1.146687010.1121/1.1466870 ↗
83. 10.1016/j.ultras.2013.05.00710.1016/j.ultras.2013.05.007 ↗
84. Rose JL · 2009 · 10
85. 10.1177/1045389X1773065910.1177/1045389X17730659 ↗