Structural damage identification method based on Swin Transformer and continuous wavelet transform

Abstract

The accuracy improvement of deep learning-based damage identification methods has always been pursued. To this end, this study proposes a novel damage identification method using Swin Transformer and continuous wavelet transform (CWT). Specifically, the original structural vibration data is first transferred to a time-frequency diagram by CWT, thereby capturing the characteristic information of structural damage. Secondly, the Swin Transformer is applied to learn the two-dimensional time-frequency diagram layer by layer and extract the damage information, by which the damage identification is achieved. Then, the identification accuracy of the proposed method is analyzed under various sample lengths and different levels of environmental noise to validate the robustness of this approach. Finally, the practicality of this method is verified through laboratory test. The results show the proposed method can effectively recognize the damage and achieve excellent accuracy even under noise interference. Its accuracy reaches 99.6% and 99.0% under single damage and multiple damage scenarios, respectively.

Keywords

Artificial intelligence / deep learning / damage identification / Swin Transformer / continuous wavelet transform

References

[1] He Z,Salehi H,Zhou H.Integrated structural health monitoring in bridge engineering.Automat Constr2022;136:104168

[2] Khodabandehlou H,Fadali MS.Vibration-based structural condition assessment using convolution neural networks. Struct Control Health Monit 2019;26:e2308.

[3] Gonen S.A hybrid method for vibration-based bridge damage detection.Remote Sensing2022;14:6054

[4] Daneshvar MH,Jahangir H.Damage identification of structural systems by modal strain energy and an optimization-based iterative regularization method.Eng Comput2023;39:2067-87

[5] Pooya SMH.A novel damage detection method in beam-like structures based on the relation between modal kinetic energy and modal strain energy and using only damaged structure data.J Sound Vib2022;530:116943

[6] An X,Li C,Shi Y.Damage identification of semi-rigid joints in frame structures based on additional virtual mass method.Sensors2022;22:6495 PMCID:PMC9460711

[7] Zhang Y,Liang Z,Ma C.Structural damage identification system suitable for old arch bridge in rural regions: random forest approach.Comp Model Eng Sci2023;136:447-69

[8] Gomes GF,Junqueira DM,Ancelotti AC.Optimized damage identification in CFRP plates by reduced mode shapes and GA-ANN methods.Eng Struct2019;181:111-23

[9] Cuong-Le T,Khatir S,Mirjalili S.An efficient approach for damage identification based on improved machine learning using PSO-SVM.Eng Comput2022;38:3069-84

[10] Ren J,Zhu X.Damaged cable identification in cable-stayed bridge from bridge deck strain measurements using support vector machine.Adv Struct Eng2022;25:754-71

[11] Farias SV,Campos Velho HF.A damage detection method using neural network optimized by multiple particle collision algorithm.J Sensors2021;2021:1-14

[12] Tang Q,Xin J,Zhou Y.Autoregressive model-based structural damage identification and localization using convolutional neural networks.KSCE J Civ Eng2020;24:2173-85

[13] Mai HT,Kang J.A damage-informed neural network framework for structural damage identification.Comput Struct2024;292:107232

[14] Mousavi M.Structural health monitoring under environmental and operational variations using MCD prediction error.J Sound Vib2021;512:116370

[15] Sony S,Sadhu A.Vibration-based multiclass damage detection and localization using long short-term memory networks.Structures2022;35:436-51

[16] Fu L,Gao P,Zhou J.Damage identification of long-span bridges using the hybrid of convolutional neural network and long short-term memory network.Algorithms2021;14:180

[17] Fernandez-Navamuel A,Magalhães F,Omella ÁJ.Bridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulations.Mech Syst Signal Proc2023;200:110471

[18] Sony S,Sadhu A.Multiclass damage identification in a full-scale bridge using optimally tuned one-dimensional convolutional neural network.J Comput Civ Eng2022;36:04021035

[19] Liu Z,Cao Y.Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV); 2021 Oct 10-17; Montreal, Canada. IEEE; 2021. pp. 9992-10002.

[20] Üzen H,Yanikoglu B.Swin-MFINet: Swin transformer based multi-feature integration network for detection of pixel-level surface defects.Expert Syst Appl2022;209:118269

[21] Xu Y,Zhang H.SE-Swin: an improved Swin-Transfomer network of self-ensemble feature extraction framework for image retrieval.IET Image Process2024;18:13-21

[22] Miao R,Zhou Q.Real-time defect identification of narrow overlap welds and application based on convolutional neural networks.J Manuf Syst2022;62:800-10

[23] Zhou J,Chen J.Application of two dimensional Morlet wavelet transform in damage detection for composite laminates.Compos Struct2023;318:117091

[24] Hou Y,Li X,Zheng X.Application of vibration data mining and deep neural networks in bridge damage identification.Electronics2023;12:3613

[25] Diao Y,Sun Z,Wang Y.Structural damage identification based on the transmissibility function and support vector machine.Shock Vib2018;2018:1-13