Expanding artificial intelligence methods to the domain of structural damage detection can effectively enhance the detection accuracy and efficiency. Models like convolutional neural networks can effectively capture significant features related to structural damage. However, due to the receptive field constraints, it is difficult to fully capture the global characteristics of the data. In addition, considering structural damage identification and damage location as a single task will lead to a large number of label classifications, thereby increasing the requirements for model complexity and training data quality. To address these issues, a multiscale fusion-based multitask Transformer (MFMTT) model based on a multivariate time-series Transformer is proposed in this paper. The encoder structure of Transformer is employed to extract the global features of sequence data, and the structural damage detection task is divided into two subtasks, each of which has a lower number of categories than the single-task one. The proposed MFMTT model is validated using a numerical simulation dataset of a simply supported beam and the International Association for Structural Control – American Society of Civil Engineers (IASC-ASCE) phase II benchmark experimental dataset, ensuring reproducibility across both synthetic and real-world scenarios. The experimental results demonstrate that the MFMTT model achieves accurate identification of structural damage states across single-damage scenarios, multidamage conditions, and benchmark experimental setups, with damage detection accuracy exceeding 99%.
TorzoniMManzoniAMarianiS. Structural health monitoring of civil structures: a diagnostic framework powered by deep metric learning. Comput Struct2022; 271: 106858.
2.
SunHSongLYuZ. A deep learning-based bridge damage detection and localization method. Mech Syst Signal Process2023; 193: 110277.
3.
MishraMLourençoPBRamanaGV. Structural health monitoring of civil engineering structures by using the internet of things: a review. J Build Eng2022; 48: 103954.
4.
ZarAHussainZAkbarM, et al. Towards vibration-based damage detection of civil engineering structures: overview, challenges, and future prospects. Int J Mech Mater Des2024; 20(3): 591–662.
5.
Sun LMZhangWNagarajaiahS. Bridge real-time damage identification method using inclination and strain measurements in the presence of temperature variation. J Bridge Eng2019; 24(2): 04018111.
6.
FigueiredoEMoldovanISantosA, et al. Finite element-based machine-learning approach to detect damage in bridges under operational and environmental variations. J Bridge Eng2019; 24(7): 04019061.
7.
AlvesVNde OliveiraMMRibeiroD, et al. Model-based damage identification of railway bridges using genetic algorithms. Eng Fail Anal2020; 118: 104845.
8.
LiuTZhangQZordanT, et al. Finite element model updating of Canonica bridge using experimental modal data and genetic algorithm. Struct Eng Int2016; 26(1): 27–36.
9.
HuangMChengSZhangH, et al. Structural damage identification under temperature variations based on PSO-CS hybrid algorithm. Int J Struct Stab Dyn2019; 19(11): 1950139.
10.
CaoJLiuYLiC. Damage cross detection between bridges monitored within one cluster using the difference ratio of projected strain monitoring data. Struct Health Monit2022; 21(2): 571–595.
11.
SantosJPOrcesiADCremonaC, et al. Baseline-free real-time assessment of structural changes. Struct Infrastruct Eng2015; 11(2): 145–161.
12.
LockeWSybrandtJRedmondL, et al. Using drive-by health monitoring to detect bridge damage considering environmental and operational effects. J Sound Vib2020; 468: 115088.
13.
AhmadiHRMahdaviNBayatM. A novel damage identification method based on short time Fourier transform and a new efficient index. Structures2021; 33: 3605–3614.
14.
GharehbaghiVRNguyenAFarsangiEN, et al. Supervised damage and deterioration detection in building structures using an enhanced autoregressive time-series approach. J Build Eng2020; 30: 101292.
15.
ZengJKimYH. Probabilistic damage detection and identification of coupled structural parameters using Bayesian model updating with added mass. J Sound Vib2022; 539: 117275.
BarmanSKMishraMMaitiDK, et al. Vibration-based damage detection of structures employing Bayesian data fusion coupled with TLBO optimization algorithm. Struct Multidiscip Optim2021; 64(4): 2243–2266.
18.
HuangTSchroederK. Bayesian probabilistic damage characterization based on a perturbation model using responses at vibration nodes. Mech Syst Signal Process2020; 139: 106444.
19.
MarinielloGPastoreTMennaC, et al. Structural damage detection and localization using decision tree ensemble and vibration data. Comput Aided Civ Infrastruct Eng2021; 36(9): 1129–1149.
20.
PanXYangTY. Post-disaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks. Comput Aided Civ Infrastruct Eng2020; 35(5): 495–510.
21.
MaiHTLeeSKangJ, et al. A damage-informed neural network framework for structural damage identification. Comput Struct2024; 292: 107232.
22.
LeiYZhangYMiJ, et al. Detecting structural damage under unknown seismic excitation by deep convolutional neural network with wavelet-based transmissibility data. Struct Health Monit2021; 20(4): 1583–1596.
23.
SongFHanYHeathAW, et al. Structural damage detection of floating offshore wind turbine blades based on Conv1d-GRU-MHA network. Eng Fail Anal2024; 166: 108896.
24.
LinSMengLZhaoG, et al. Automatic elimination of invalid impact-echo signals for detecting delamination in concrete bridge decks based on deep learning. Dev Built Environ2024; 19: 100521.
25.
ZarALiSLiC, et al. Deep learning-based ground motion inversion through recursive structural acceleration response using DRA-LSTM Net. Eng Struct2025; 323: 119132.
26.
AzimiMEslamlouADPekcanG. Data-driven structural health monitoring and damage detection through deep learning: state-of-the-art review. Sensors2020; 20(10): 2778.
27.
LinYNieZMaH. Structural damage detection with automatic feature-extraction through deep learning. Comput Aided Civ Infrastruct Eng2017; 32: 1025–1046.
28.
LiMJiaDWuZ, et al. Structural damage identification using strain mode differences by the iFEM based on the convolutional neural network (CNN). Mech Syst Signal Process2022; 165: 108289.
29.
AbdeljaberOAvciOKiranyazS, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vib2017; 388: 154–170.
30.
VaswaniAShazeerNParmarN, et al. Attention is all you need. Neural Inf Process Syst2017; 30: 3058.
31.
LinTWangYLiuX, et al. A survey of transformers. AI Open2022; 3: 111–132.
32.
ZerveasGJayaramanSPatelD, et al. A transformer-based framework for multivariate time series representation learning. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery and data mining. New York, NY, 2021, pp. 2114–2124.
33.
TriviñoHFeijóoCLugmaniaH, et al. Damage detection and localization at the jacket support of an offshore wind turbine using transformer models. Struct Control Health Monit2023; 2023: 1–16.
34.
MousaviZEttefaghMMSadeghiMH, et al. Developing deep neural network for damage detection of beam-like structures using dynamic response based on FE model and real healthy state. Appl Acoust2020; 168: 107402.
35.
EigenDFergusR. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: 2015 IEEE international conference on computer vision (ICCV), Santiago, Chile, 2015, Washington, DC, USA.
36.
GirshickR. Fast R-CNN. In: 2015 IEEE international conference on computer vision (ICCV), Santiago, Chile, 2015, Washington, DC, USA.
37.
LiXZhaoLWeiL, et al. Deepsaliency: multi-task deep neural network model for salient object detection. IEEE Trans Image Process2016; 25(8): 3919–3930.
38.
WangXJiaoJZhouX, et al. Maximizing model generalization under feature and label shifts for structural damage detection via Bayesian theory. Mech Syst Signal Process2025; 224: 112052.
39.
XiongQKongQXiongH, et al. Zero-shot knowledge transfer for seismic damage diagnosis through multi-channel 1D CNN integrated with autoencoder-based domain adaptation. Mech Syst Signal Process2024; 217: 111535.
40.
GaoYYangJQianH, et al. Multiattribute multitask transformer framework for vision-based structural health monitoring. Comput Aided Civ Infrastruct Eng2023; 38: 2358–2377.
41.
KordSTaghikhanyTAkbariM. A novel spatiotemporal 3D CNN framework with multi-task learning for efficient structural damage detection. Struct Health Monit2024; 23(4): 2270–2287.
42.
LiuJXuSBergésM, et al. HierMUD: hierarchical multi-task unsupervised domain adaptation between bridges for drive-by damage diagnosis. Struct Health Monit2023; 22(3): 1941–1968.
43.
LeeCHLinCRChenMS. Sliding window filtering: an efficient method for incremental mining on a time-variant database. Inform Syst2005; 30(3): 227–244.
44.
TangBMattesonDS. Probabilistic transformer for time series analysis. Adv Neural Inform Process Syst2021; 34: 23592–23608.
45.
ChenYRenKWangY, et al. Contiformer: continuous-time transformer for irregular time series modeling. Adv Neural Inform Process Syst2023; 36: 47143–47175.
46.
ZhouHZhangSPengJ, et al. Informer: beyond efficient transformer for long sequence time-series forecasting. Proceedings of the AAAI conference on artificial intelligence2021; 35(12): 11106–11115.
47.
LiuMRenSMaS, et al. Gated transformer networks for multivariate time series classification. arXiv preprint2021: arXiv:2103. 14438, 2021. DOI: 10.48550/arXiv.2103.14438.
48.
ClevertDAUnterthinerTHochreiterS. Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint2015: arXiv:1511.07289
49.
HendrycksDGimpelK. Gaussian error linear units (GELUS). arXiv preprint2016: arXiv:1606.08415.
50.
HeRXiaoTQiuS, et al. A rule-based data preprocessing framework for chiller rooms inspired by the analysis of engineering big data. Energy Build2022; 273: 112372.
51.
AhsanMMahmudMSahaP, et al. Effect of data scaling methods on machine learning algorithms and model performance. Technologies2021; 9(3): 52.
52.
FanGLiJHaoH. Vibration signal denoising for structural health monitoring by residual convolutional neural networks. Measurement2020; 157: 107651.
53.
ZhaoSSunXGaiL. Data enhancement and multi-feature learning model for pest classification. J Intell Fuzzy Syst2023; 45(4): 5409–5421.
54.
GuoJDouQ. Data enhancement method based on attention activation map. In: International conference on computer, artificial intelligence, and control engineering (CAICE 2023), Hangzhou, China, 2023.
55.
BernalSDDBeckJVenturaC. An experimental benchmark problem in structural health monitoring. In: Third international workshop on structural health monitoring, Stanford, CA, 2001, Boca Raton, FL, USA.
