The scarcity of real-world damage data poses a significant challenge to data-driven structural damage identification. While transfer learning between numerical and experimental domains offers a promising solution, existing methods often overlook the crucial spatial relationships among sensors, which are vital for accurate damage localization. To address this, the work proposes a novel spatiotemporal feature learning network (SfLN) guided by structural physics. Its core innovation lies in an invariant graph structure, constructed deterministically from sensor layout and structural connectivity, which provides a consistent spatial prior across domains. The SfLN synergistically combines a one-dimensional convolutional neural network for extracting discriminative local temporal features from raw signals and graph convolutional network for propagating information through the physics-guided graph. This design explicitly models spatiotemporal dependencies in an inherently transferable manner, enabling effective cross-domain knowledge transfer through fine-tuning without complex domain alignment. Validation on a cross-domain case study of a tower steel structure demonstrates the efficacy of our approach, achieving a damage classification Accuracy and F1 Score of 0.9351 and 0.9346 on the target domain, significantly outperforming direct training. Furthermore, robustness tests under varying noise levels confirm the model’s stability and practical applicability.
HuHTangBGongX, et al. Intelligent fault diagnosis of the high-speed train with big data based on deep neural networks. IEEE Trans Ind Inform2017; 13(4): 2106–2016.
2.
ZhangSWangZJianZ, et al. A two-step method for beam bridge damage identification based on strain response reconstruction and statistical theory. Meas Sci Technol2020; 31(7): 1–12.
3.
ChenZWengSYuH, et al. Bayesian-based method for the simultaneous identification of structural damage and moving force. Mech Syst Signal Process2023; 185: 109742.
4.
YeXCaoYLiuA, et al. Parallel convolutional neural network toward high efficiency and robust structural damage identification. Struct Health Monit2023; 22(6): 3805–3826.
5.
MeherUMishraSKSunnyMR.Impedance-based looseness detection of bolted joints using artificial neural network: an experimental study. Struct Control Health Monit2022; 29(10): 1–22.
6.
YuYRashidiMDorafshanS, et al. Ground penetrating radar-based automated defect identification of bridge decks: a hybrid approach. J Civil Struct Health Monit2025; 15(2): 521–543.
7.
MousaviZVarahramSEttefaghMM, et al. Deep neural networks-based damage detection using vibration signals of finite element model and real intact state: an evaluation via a lab-scale offshore jacket structure. Struct Health Monit2021; 20(1): 379–405.
8.
SeventekidisPGiagopoulosD.A combined finite element and hierarchical deep learning approach for structural health monitoring: test on a pin-joint composite truss structure. Mech Syst Signal Process2021; 157: 107735.
9.
ShiSDuDMercanO, et al. A novel data-driven sensor placement optimization method for unsupervised damage detection using noise-assisted neural networks with attention mechanism. Mech Syst Signal Process2024; 209: 111075.
10.
AiLZhangBZiehlP.A transfer learning approach for acoustic emission zonal localization on steel plate-like structure using numerical simulation and unsupervised domain adaptation. Mech Syst Signal Process2023; 192: 110216.
11.
GiglioniVPooleJVenanziI, et al. A domain adaptation approach to damage classification with an application to bridge monitoring. Mech Syst Signal Process2024; 209: 111135.
12.
BattuRAgathosKMonsalveJ, et al. Combining transfer learning and numerical modelling to deal with the lack of training data in data-based SHM. J Sound Vib2025; 595: 118710.
13.
SongLCaoZSunH, et al. Transfer learning for structure damage detection of bridges through dynamic distribution adaptation. Structures2024; 67: 106972.
14.
LiZWengSXiaY, et al. Cross-domain damage identification based on conditional adversarial domain adaptation. Eng Struct2024; 321: 118928.
15.
LinYNieZMaH.Dynamics-based cross-domain structural damage detection through deep transfer learning. Comput Aided Civ Infrastruct Eng2022; 37(1): 24–54.
16.
TengSChenXChenG.Structural damage detection based on transfer learning strategy using digital twins of bridges. Mech Syst Signal Process2023; 119: 110160.
17.
ZhangXZhuXYuY, et al. Transfer learning-based structural damage identification for building structures with limited measurement data. Int J Struct Stab Dyn2025; 25(9): 2550093.
18.
TavaresALorenzoEDCornelisB, et al. Machine learning approaches to damage detection in composite structures combining experimental and simulation domains. Mech Syst Signal Process2024; 215: 111412.
19.
BabakamaliRBabakamaliMHeraviM, et al. Transferring damage detection knowledge across rotating machines and framed structures: harnessing domain adaptation and contrastive learning. Mech Syst Signal Process2024; 221: 111743.
20.
GiglioniVPooleJMillsR, et al. Transfer learning in bridge monitoring: laboratory study on domain adaptation for population-based SHM of multispan continuous girder bridges. Mech Syst Signal Process2025; 224: 112151.
21.
TalaeiSZhuXLiJ, et al. Transfer learning based bridge damage detection: leveraging time-frequency features. Structures2023; 57: 105052.
22.
QuCZhangHYiT, et al. Anomaly detection of massive bridge monitoring data through multiple transfer learning with adaptively setting hyperparameters. Eng Struct2024; 314: 118404.
23.
ChenZWangCWuJ, et al. Deep convolutional transfer learning-based structural damage detection with domain adaptation. Appl Intell2023; 53(5): 5085–5099.
24.
HuangTLiangTChenL.A comparative analysis of damage identification methods based on multi-channel data fusion and convolutional neural network for frame structures. Structures2024; 61: 106076.
25.
WangRLiJLiL, et al. Structural damage identification by using physics-guided residual neural networks. Eng Struct2024; 318: 118703.
26.
DangVVuTNguyenB, et al. Structural damage detection framework based on graph convolutional network directly using vibration data. Structures2022; 38: 40–51.
27.
DangVLe-NguyenKNguyenT.Semi-supervised vibration-based structural health monitoring via deep graph learning and contrastive learning. Structures2023; 51: 158–170.
28.
KimMSongJKimC.Near-real-time damage identification under vehicle loads using dynamic graph neural network based on proper orthogonal decomposition. Mech Syst Signal Process2025; 224: 112175.
29.
WijethungaRSamarabanduJSadhuA.Robust and efficient dual-graph neural networks for structural damage detection and localization. Eng Struct2025; 343: 121265.
30.
SunLSongRWeiJ, et al. Physics-augmented spatial-temporal graph convolutional network for damage localization using ultrasonic guided waves. Mech Syst Signal Process2024; 221: 111738.
31.
Reyes-CarmenatyGFont-MoréJLado-RoigéR, et al. Cross-domain transfer learning for vibration-based damage classification via convolutional neural networks. Structures2024; 66: 106779.
32.
HongXYangDHuangL, et al. Vibration-adaption deep convolutional transfer learning method for stranded wire structural health monitoring using guided wave. IEEE Trans Instrum Meas2023; 72: 1–10.
33.
HuangSTangJDaiJ, et al. Signal status recognition based on 1DCNN and its feature extraction mechanism analysis. Sensors2019; 19(9): 2018.
34.
ChenXJiaJYangJ, et al. A vibration-based 1DCNN-BiLSTM model for structural state recognition of RC beams. Mech Syst Signal Process2023; 203: 110715.
35.
ZhaoZChenN.A single-sensor method for structural damage localization in wind turbine blades: laboratory assessment on a blade segment. Mech Syst Signal Process2024; 214: 111370.
36.
ZhaoYLinYWenH, et al. Spatial-temporal position-aware graph convolution networks for traffic flow forecasting. IEEE Trans Intell Transp Syst2022; 24(8): 1–17.
37.
XiaoXLiCHuangJ, et al. Rotating machinery fault diagnosis based on one-dimensional convolutional neural network and modified multi-scale graph convolutional network under limited labeled data. Eng Appl Artif Intell2024; 137: 109129.
38.
ZhanYLuSXiangT, et al. Application of convolutional neural network in random structural damage identification. Structures2021; 29: 570–576.
39.
GuoTWuLWangC, et al. Damage detection in a novel deep-learning framework: a robust method for feature extraction. Struct Health Monit2020; 19(2): 424–442.
40.
ConnorRDearleAClaydonB, et al. Correlations of cross-entropy loss in machine learning. Entropy2024; 26(6): 491.
41.
YessoufouFZhuJ.Classification and regression-based convolutional neural network and long short-term memory configuration for bridge damage identification using long-term monitoring vibration data. Struct Health Monit2023; 22(6): 4027–4054.
42.
CaoJYanMJiaY, et al. Application of a modified Inception-v3 model in the dynasty-based classification of ancient murals. EURASIP J Adv Signal Process2021; 2021(1): 1–25.
43.
JamshidiMEl-BadryM.Structural damage severity classification from time-frequency acceleration data using convolutional neural networks. Structures2023; 54: 236–253.
44.
ShimS.Self-training approach for crack detection using synthesized crack images based on conditional generative adversarial network. Comput Aided Civ Infrastruct Eng2024; 39(7): 1019–1041.
PengCEl AshrafAMusaA, et al. Simplified numerical approach for the lateral load analysis of light-frame wood shear wall structures. Eng Struct2020; 219: 110921.
47.
KuoPChuoYLiK, et al. GNN-LSTM-based fusion model for structural dynamic responses prediction. Eng Struct2024; 306: 117733.
48.
ZhangMLiXXiangZ, et al. Diagnosis of brake friction faults in high-speed trains based on 1DCNN and GraphSAGE under data imbalance. Measurement2023; 207: 112378.
49.
ZhuYWuJWuJ, et al. Dimensionality reduce-based for remaining useful life prediction of machining tools with multisensor fusion. Reliab Eng Syst Saf2022; 218: 108179.
