Bridge structural health monitoring (BSHM) has become increasingly widespread due to its critical role in ensuring the safety and reliability of modern bridge structures. However, maintaining the integrity of sensor data remains a significant challenge, as environmental factors and sensor malfunctions often result in missing data and anomalies. To address these issues, this study presents a novel generative deep learning-based data cleaning model, termed the convolutional autoencoder (CAE) enhanced by Transformer (CAT), designed for the detection and imputation of missing acceleration data in the presence of environmental influences. The CAT model combines CAEs for local feature extraction with Transformer encoders to capture global dependencies and long-term temporal correlations. A parallel network architecture is employed to process acceleration data alongside environmental factors, such as wind speed and temperature, enabling the integration of structural and environmental information. Residual skip connections are introduced to ensure that critical features are consistently preserved throughout complex, nonlinear processing layers, ultimately enhancing reconstruction accuracy and the overall robustness. Field data monitored from a long-span suspension bridge is used to evaluate the performance of the proposed model. Experimental results demonstrate the robustness and accuracy of the CAT model, achieving a mean squared error (MSE) of 0.002998 and the Pearson correlation coefficient (PCC) of 0.9831 under moderate data loss conditions. Even under severe scenarios with up to 50% missing data, the model maintains reliable performance, with an MSE of 0.012931 and a PCC of 0.9257. The CAT model outperforms traditional approaches in both reconstruction precision and robustness, addressing challenges associated with sensor anomalies in large-scale monitoring systems.
HousnerGBergmanLACaugheyTK, et al. Structural control: past, present, and future. J Eng Mech1997; 123(9): 897–971.
2.
FarrarCRWordenK.An introduction to structural health monitoring. Philos Trans R Soc A Math Phys Eng Sci2007; 365(1851): 303–315.
3.
SunLShangZXiaY, et al. Review of bridge structural health monitoring aided by big data and artificial intelligence: from condition assessment to damage detection. J Struct Eng2020; 146(5): 04020073.
4.
YiTHHuangHBLiHN.Development of sensor validation methodologies for structural health monitoring: a comprehensive review. Measurement2017; 109: 200–214.
5.
RizzoPEnshaeianA.Challenges in bridge health monitoring: a review. Sensors2021; 21(13): 4336.
KerschenGDe BoePGolinvalJC, et al. Sensor validation using principal component analysis. Smart Mater Struct2004; 14(1): 36.
9.
HuangHBYiTHLiHN.Bayesian combination of weighted principal-component analysis for diagnosing sensor faults in structural monitoring systems. J Eng Mech2017; 143(9): 04017088.
10.
RaoARMKumarSKLakshmiK.A sensor fault detection algorithm for structural health monitoring using adaptive differential evolution. Int J Comput Methods Eng Sci Mech2014; 15(3): 282–293.
11.
MaZYunCBWanHP, et al. Probabilistic principal component analysis-based anomaly detection for structures with missing data. Struct Control Health Monit2021; 28(5): e2698.
12.
YangYNagarajaiahS.Blind denoising of structural vibration responses with outliers via principal component pursuit. Struct Control Health Monit2014; 21(6): 962–978.
13.
LiLLiuHZhouH, et al. Missing data estimation method for time series data in structure health monitoring systems by probability principal component analysis. Adv Eng Softw2010; 149: 102901.
14.
ChenSYWangYWNiYQ.Gross outlier removal and fault data recovery for SHM data of dynamic responses by an annihilating filter-based Hankel-structured robust PCA method. Struct Control Health Monit2022; 29(12), e3144.
15.
JanaDNagarajaiahSYangY, et al. Real-time cable tension estimation from acceleration measurements using wireless sensors with packet data losses: analytics with compressive sensing and sparse component analysis. J Civ Struct Health Monit2022; 12(4), 797–815.
16.
AbdelghaniMFriswellMI.Sensor validation for structural systems with multiplicative sensor faults. Mech Syst Signal Process2007; 21(1): 270–279.
17.
XuXFordeMCRenY, et al. Multi-index probabilistic anomaly detection for large span bridges using Bayesian estimation and evidential reasoning. Struct Health Monit2023; 22(2): 948–965.
18.
YangXLateckiLJPokrajacD. Outlier detection with globally optimal exemplar-based GMM. In: Proceedings of the 2009 SIAM international conference on data mining, Sparks, Nevada, USA, 30 April – 2 May 2009, pp.145–154. Philadelphia, PA: Society for Industrial and Applied Mathematics.
19.
EntezamiASarmadiHBehkamalB, et al. Early warning of structural damage via manifold learning-aided data clustering and non-parametric probabilistic anomaly detection. Mech Syst Signal Process2025; 224: 111984.
20.
YuenKVOrtizGA.Outlier detection and robust regression for correlated data. Comput Methods Appl Mech Eng2017; 313: 632–646.
21.
ChenZZhangZChenX, et al. Multi-role collaborative framework for structural damage identification considering measurement noise effect. Measurement2025; 250: 117106.
22.
AbdelghaniMFriswellMI.Sensor validation for structural systems with additive sensor faults. Struct Health Monit2004; 3(3): 265–275.
23.
EntezamiAShariatmadarHDe MicheleC.Non-parametric empirical machine learning for short-term and long-term structural health monitoring. Struct Health Monit2022; 21(6): 2700–2718.
24.
EntezamiASarmadiHBehkamalB, et al. Big data analytics and structural health monitoring: a statistical pattern recognition-based approach. Sensors2020; 20(8): 2328.
LeCunYBengioY. Convolutional networks for images, speech, and time series. In: ArbibMA (ed.) The handbook of brain theory and neural networks. Cambridge, MA: MIT Press, 1998, pp.255–258.
27.
JianXZhongHXiaY, et al. Faulty data detection and classification for bridge structural health monitoring via statistical and deep-learning approach. Struct Control Health Monit2021; 28(11): e2824.
28.
DengYJuHZhongG, et al. A general data quality evaluation framework for dynamic response monitoring of long-span bridges. Mech Syst Signal Process2023; 200: 110514.
29.
PanQBaoYLiH.Transfer learning-based data anomaly detection for structural health monitoring. Struct Health Monit2023; 22(5): 3077–3091.
30.
BayaneILeanderJKaroumiR.Taxonomic framework for neural network-based anomaly detection in bridge monitoring. Autom Constr2025; 173: 106113.
31.
TangZChenZBaoY, et al. Convolutional neural network-based data anomaly detection method using multiple information for structural health monitoring. Struct Control Health Monit2019; 26(1): e2296.
32.
BaoYTangZLiH, et al. Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit2019; 18(2): 401–421.
33.
ChouJYFuYHuangSK, et al. SHM data anomaly classification using machine learning strategies: a comparative study. Smart Struct Syst2022; 29(1): 77.
34.
ZhaoMSadhuACapretzM.Multiclass anomaly detection in imbalanced structural health monitoring data using convolutional neural network. J Infrastruct Preserv Resil2022; 3(1): 10.
35.
NealRM. Bayesian learning for neural networks. New York, NY: Springer Science & Business Media; 2012.
36.
WanHPNiYQ.Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Struct Health Monit2019; 18(4): 1282–1309.
37.
LeiXSunZWangA, et al. Estimation of bridge girder cumulative displacement for component operational warning using Bayesian neural networks. Struct Control Health Monit2025; 2025(1): 9974584.
38.
ZhaiJZhangSChenJ, et al. Autoencoder and its various variants. In: Proceedings of the 2018 IEEE International conference on systems, man, and cybernetics (SMC), Seagaia Convention Center, Miyazaki, Japan, 2018, pp. 415–419. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE).
39.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial nets. Adv Neural Inf Process Syst2014; 27: 2672–2680.
40.
YuYSiXHuC, et al. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput2019; 31(7): 1235–1270.
41.
NiFZhangJNooriMN.Deep learning for data anomaly detection and data compression of a long-span suspension bridge. Comput Aided Civ Infrastruct Eng2020; 35(7): 685–700.
42.
YuYLiJLiJ, et al. Automated damage diagnosis of concrete jack arch beam using optimized deep stacked autoencoders and multi-sensor fusion. Dev Built Environ2023; 14: 100128.
43.
WanHPZhuYKLuoY, et al. Unsupervised deep learning approach for structural anomaly detection using probabilistic features. Struct Health Monit2025; 24(1): 3–33.
44.
LiuGNiuYZhaoW, et al. Data anomaly detection for structural health monitoring using a combination network of GANomaly and CNN. Smart Struct Syst2022; 29(1): 53–62.
45.
LeiXSunLXiaY.Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks. Struct Health Monit2021; 20(4): 2069–2087.
46.
ZhuYKWanHPToddMD.A method for reconstruction of structural health monitoring data using WGANGP with U-net generator. Struct Health Monit2025: 14759217241313438.
47.
NieZXuSChenK, et al. Damage detection in bridge via adversarial-based transfer learning. Struct Control Health Monit2024; 2024(1): 5548218.
48.
MaoJWangHSpencerBFJr. (2021). Toward data anomaly detection for automated structural health monitoring: exploiting generative adversarial nets and autoencoders. Struct Health Monit2021; 20(4): 1609–1626.
49.
YangKDingYJiangH.A two-stage data cleansing method for bridge global positioning system monitoring data based on bi-direction long and short term memory anomaly identification and conditional generative adversarial networks data repair. Struct Control Health Monit2022; 29(9): e2993.
50.
ChoJLimKJKimJ, et al. RETRACTED: enhancing data quality management in structural health monitoring through irregular time-series data anomaly detection using IoT sensors. Buildings2024;14(7): 2223.
51.
LiLLiuGZhangL, et al. FS-LSTM-based sensor fault and structural damage isolation in SHM. IEEE Sens J2020; 21(3): 3250–3259.
52.
MinSLeeYByunYH, et al. Merged LSTM-based pattern recognition of structural behavior of cable-supported bridges. Eng Appl Artif Intell2023; 125: 106774.
53.
VaswaniAShazeerNParmarN, et al. Attention is all you need. Adv Neural Inform Process Syst2017; 30: 1–11.
54.
XiaoBDiJWangJ, et al. Autoencoder-based method to assess bridge health monitoring data quality. Comput Aided Civ Infrastruct Eng2024; 39(15): 2367–2388.
55.
LiJChenWFanG.Structural health monitoring data anomaly detection by transformer enhanced densely connected neural networks. Smart Struct Syst2022; 30(6): 613–626.
56.
LiuZFengXDongC, et al. Study on denoising method of photoionization detector based on wavelet packet transform. Chemosensors2023; 11(2): 146.
57.
ZhangDLiuR.Laser Doppler signal denoising based on wavelet packet thresholding method. Int J Opt2019; 2019(1): 1097292.
58.
BerrezzekFKhelilKBouadjilaT.Efficient wind speed forecasting using discrete wavelet transform and artificial neural networks. Rev Intell Artif2019; 33(6): 447–452.
59.
International Organization for Standardization. ISO 4354:2009: wind actions on structures. Geneva, Switzerland: ISO, 2009.
60.
American Society of Civil Engineers. Minimum design loads and associated criteria for buildings and other structures (ASCE/SEI 7-22). Reston, VA: ASCE, 2022.
61.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on computer vision and vattern recognition (CVPR). Las Vegas, NV, USA, 27–30 June 2016, pp.770–778. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE).
