Base isolation technology is a design strategy developed to protect buildings from the direct impact of seismic forces, utilizing base isolation devices, with rubber bearings being the most commonly used type. After an earthquake, manually inspecting rubber bearings for damage is inefficient, unable to reveal internal damages, and carries significant risks. Consequently, there is a pressing need for an innovative damage detection method. The difficulty of obtaining and labeling data related to rubber rupture damage makes it hard to apply supervised learning methods to construct damage detection models. In response to this, this study combined the active sensing method with unsupervised learning based on feature bagging, establishing a robust rubber damage detection model that successfully addressed the zero-shot problem faced in rubber damage detection processes. To increase the proportion of data on rubber damage, a generative adversarial network based data augmentation methods were applied. The research findings demonstrated that the developed model achieved an average precision of 0.9216 and an area under the ROC curve (Receiver Operating Characteristic curve) of 0.9788 for rupture damage detection, outperforming other machine learning models.
TakaokaETakenakaYNimuraA.Shaking table test and analysis method on ultimate behavior of slender base-isolated structure supported by laminated rubber bearings. Earthquake Eng Struc2011; 40(5): 551–570.
2.
ZhuMFuJLiW, et al. Design and co-optimization of a laminated isolation bearing based on magnetorheological elastomer. Mech Syst Signal Process2021; 159: 107843.
3.
HwangKTSeoDWChoSG.Prediction of long term performance and creep of laminated natural rubber bearings (NRB). J Earthq Eng Soc Korea2013; 17(3): 117–25.
4.
MythravaruniPVolokhKY.Failure of rubber bearings under combined shear and compression. J Appl Mech2018; 85(7): 074503.
5.
AriaMAkbariR.Inspection, condition evaluation and replacement of elastomeric bearings in road bridges. Struct Infrastruct Eng2013; 9: 918–934.
6.
MatsuzakiH.Time-dependent seismic reliability of isolated bridges considering ageing deterioration of lead rubber bearings. Struct Infrastruct Eng2022; 18(10–11): 1526–541.
7.
TakahashiY.Damage of rubber bearings and dampers of bridges in 201l Great East Japan Earthquake. In: Proceedings of the international symposium on engineering lessons learned from the 2011 great east Japan Earthquake, Tokyo, 2012.
8.
BuckleIYenWMarshL.Implications of bridge performance during Great East Japan Earthquake for US Seismic Design Practice. In: Proceedings of the international symposium on engineering lessons learned from the 201l Great East Japan Earthquake, Tokyo, 2012.
9.
QuZZhuBJCaoYT, et al. Rapid report of seismic damage to buildings in the 2022 M 6.8 Luding earthquake, China. Earthquake Res Adv2023; 3(1): 100180.
10.
JiangTYYuDHXiaoM, et al. Monitoring bond-slip behavior of CFRP-RCESC beams using piezoelectric active sensing method. Adv Bridge Eng2021; 2(1): 25.
11.
XuXLanJSKırlangıçAS, et al. Comprehensive index condition assessment of structural concrete based on surface wave techniques. Adv Bridge Eng2023; 4(1): 29.
12.
ChenYXJiangJQinXJ, et al. Quantitative monitoring of bolt looseness using multichannel piezoelectric active sensing and cbam-based convolutional neural network. Front Mater2021; 8: 677642.
13.
ZhangQJ.Damage detection for timber joints based on piezoelectric sensing technology. Wuhan University of Science and Technology, Wuhan, China 2021. [In Chinese]
14.
ZhangHLiJJKangF, et al. Monitoring depth and width of cracks in underwater concrete structures using embedded smart aggregates. Measurement2022; 204: 112078.
15.
QianHZhangYLiY, et al. Damage monitoring of engineered cementitious composite beams reinforced with hybrid bars using piezoceramic-based smart aggregates. Sensors2022; 22(19): 7184.
16.
ZengYPanP.Feasibility study on axial pressure detection in smart rubber bearing (SRB). Measurement2021; 174: 109031.
17.
ZengYHeZZPanP.A deep learning method to monitor axial pressure and shear deformation of rubber bearings under coupled compression and shear loading. Earthquake Eng Struct Dyn2023; 52: 1–18.
18.
ZengYPanPCaoYR, et al. Shear deformation detection in smart rubber bearing (SRB) using active sensing method. Eng Struct2021; 242: 112573.
19.
ZengYWangHSDengKL, et al. Detection of rupture inside rubber bearings using active sensing method. Eng Struct2022; 271: 114950.
20.
BhagatPKChoudharyPSinghKM.A study on zero-shot learning from semantic viewpoint. Vis Comput2023; 39: 2149–2163.
21.
LiHJWangFLiuJX, et al. Micro-knowledge embedding for zero-shot classification. Comput Electr Eng2022; 101: 108068.
22.
WangWZhengVWYuH, et al. A survey of zero-shot learning: settings, methods, and applications. ACM Trans Intell Syst Technol2019; 10(2): 1–37.
23.
AkataZPerronninFHarchaouiZ, et al. Label-embedding for image classification. IEEE Trans Pattern Anal Mach Intell2016; 38(7): 1425–1438.
24.
DeznabiIArabaciBKoyutürkM, et al. DeepKinZero: zero-shot learning for predicting kinase-phosphosite associations involving understudied kinases. Bioinformatics2020; 36(12): 3652–3661.
25.
ZhengGZhaoJLiS, et al. Zero-shot pipeline detection for sub-bottom profiler data based on imaging principles. Remote Sens2021; 13: 4401.
26.
LazarevicAKumarV.Feature bagging for outlier detection. In: Proceedings of the Eleventh ACM SIGKDD international conference on knowledge discovery in data mining, USA, 2005.
27.
WangBWangWJMengGL, et al. Selective feature bagging of one-class classifiers for novelty detection in high-dimensional data. Eng Appl Artifi Intell2023; 120: 105825.
28.
SuttonCSindelarMMcCallumA.Feature bagging: preventing weight undertraining in structured discriminative learning, CIIR Technical Report IR-402, University of Masschusetts, 2005.
29.
ChaYJWangZ.Unsupervised novelty detection-based structural damage localization using a density peaks-based fast clustering algorithm. Struct Health Monit2018; 17(2): 313–324.
30.
WangZChaYJ.Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage. Struct Health Monit2021; 20(1): 406–425.
31.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, Canada, 2014.
32.
LanLYouLZhangZY, et al. Generative adversarial networks and its applications in biomedical informatics. Front Public Health2020; 12(8): 164.
33.
SalehinejadHValaeeSColakE, et al. Generalization of deep neural networks for chest pathology classification in X-rays using generative adversarial networks. In: Proceedings—IEEE international conference on acoustics, speech and signal processing (ICASSP), Canada, 2017, pp. 990–994.
34.
LuoJHuangJYLiHG.A case study of conditional deep convolutional generative adversarial networks in machine fault diagnosis. J Intell. Manuf2021; 32: 407–425.
35.
LeeYOJoJHwangJ.Application of deep neural network and generative adversarial network to industrial maintenance: a case study of induction motor fault detection. In: Proceedings-IEEE international conference on big data (Big Data), USA, 2017, pp. 3248–3253.
36.
LiHMSuJS.Application of GAN to few-shot data augmentation in identity recognition. Comput Simulation2023; 40(8): 169–173.
37.
ZhuJHZhouXYXuMS, et al. Tomato leaf disease image recognition based on improved dcgan data enhancement. Radio Eng2023; 53(6): 1235–1241.
