Stay cables are critical load-bearing components in cable-stayed bridges, and their tension variations serve as direct indicators of structural safety and serviceability. While vibration-based monitoring has enabled continuous tension estimation, the reliable transformation of such measurements into real-time warning information remains challenging. This study presents an automated real-time cable tension warning framework that integrates ambient vibration measurements with a convolutional neural network (CNN). A statistical detection algorithm was first developed by defining thresholds from year-long tension histories and applying a three-segment strategy to suppress scattered values. Using long-term monitoring data from representative cables, this method successfully identified abnormal tension variations and quantified the minimum detectable changes and detection times. The proposed framework emphasizes warning logic and long-term operational performance by explicitly evaluating false-alarm behavior, detectability limits, and detection latency under unfavorable conditions. To overcome the inherent limitations of rule-based thresholds, the anomaly detection task was reformulated as a CNN-based image classification problem. By encoding tension data into one-dimensional images and categorizing them into low, normal, and high states, the CNN consistently achieved 100% accuracy in distinguishing normal from abnormal conditions. The contributions of this work are threefold: (1) development of a statistical threshold-based detection algorithm validated with 1 year of field data; (2) reformulation of anomaly detection as a CNN-based classification task; and (3) demonstration of perfect classification accuracy through extensive testing. These results establish a practical, adaptive framework for automated cable tension warning, extending conventional monitoring into proactive decision-making support for bridge management.
CeballosMAPratoCA. Determination of the axial force on stay cables accounting for their bending stiffness and rotational end restraints by free vibration tests. J Sound Vib2008; 317(1–2): 127–141. https://doi.org/10.1016/j.jsv.2008.02.048
RenWXChenGHuWH. Empirical formulas to estimate cable tension by cable fundamental frequency. Struct Eng Mech2005; 20(3): 363–380. https://doi.org/10.12989/sem.2005.20.3.363
HuangYHFuJYWangRH, et al. Unified practical formulas for vibration-based method of tension estimation. Adv Struct Eng2015; 18(3): 405–422. https://doi.org/10.1260/1369-4332.18.3.405
11.
LeLXSiringoringoDMKatsuchiH, et al. Stay cable tension estimation of cable-stayed bridge under limited information on cable properties using artificial neural networks. Struct Control Health Monit2022; 29: e3015. https://doi.org/10.1002/stc.3015
12.
ZhangXXuHCaoM, et al. In-plane free vibrations of small-sag inclined cables considering bending stiffness with applications to cable tension identification. J Sound Vib2023; 544: 117394. https://doi.org/10.1016/j.jsv.2022.117394
13.
ChenCCWuWHHuangCH, et al. Determination of stay cable force based on effective vibration length accurately estimated from multiple measurements. Smart Struct Syst2013; 11(4): 411–433.
14.
ChenCCWuWHLeuMR, et al. Tension determination of stay cable or external tendon with complicated constraints using multiple vibration measurements. Measurement2016; 86: 182–195. https://doi.org/10.1016/j.measurement.2016.02.053
15.
WuWHChenCCChenYC, et al. Tension determination for suspenders of arch bridge based on multiple vibration measurements concentrated at one end. Measurement2018; 123: 254–269. https://doi.org/10.1016/j.measurement.2018.03.077
16.
ChenCCWuWHChenSY, et al. A novel tension estimation approach for elastic cables by elimination of complex boundary condition effects employing mode shape functions. Eng Struct2018; 166: 152–166. https://doi.org/10.1016/j.engstruct.2018.03.070
YanBChenWYuJ, et al. Mode shape-aided tension force estimation of cable with arbitrary boundary conditions. J Sound Vib2019; 440: 315–331. https://doi.org/10.1016/j.jsv.2018.10.018
19.
YuCP. Tension prediction for straight cables based on effective vibration length with a two-frequency approach. Eng Struct2020; 222: 111121. https://doi.org/10.1016/j.engstruct.2020.111121
20.
YanBLiDChenW, et al. Mode shape-aided cable force determination using digital image correlation. Struct Health Monit2021; 20(5): 2430–2445. https://doi.org/10.1177/1475921720952163
21.
SyamsiMIWangCYNguyenVS. Tension force identification for cable of various end-restraints using equivalent effective vibration lengths of mode pairs. Measurement2022; 197: 111319. https://doi.org/10.1016/j.measurement.2022.111319
22.
ChenWYanBLiaoJ, et al. Cable force determination using phase-based video motion magnification and digital image correlation. Int J Struct Stab Dyn2022; 22(7): 2250036. https://doi.org/10.1142/S0219455422500365
23.
ChengYSuZZhangJ. Mode shape-aided cable force estimation of a double-hanger system using a vision-based monitoring method. Measurement2024; 227: 114214. https://doi.org/10.1016/j.measurement.2024.114214
24.
SuZWangLZhengJ, et al. Tension force estimation of short cable employing axis-shift imaging and multiple mode shapes. Mech Syst Signal Process2024; 218: 111543. https://doi.org/10.1016/j.ymssp.2024.111543
25.
FuXSunSYLiHN, et al. Cable force identification with unknown and variable elastic boundary supports: theory and validation. Struct Control Health Monit2025; 2025: 6165260. https://doi.org/10.1155/stc/6165260
26.
ChenYQinLZouY, et al. Simplification and improvement of cable tension identification based on effective vibration length estimated from multiple sensors located near one support. Measurement2025; 242: 115755. https://doi.org/10.1016/j.measurement.2024.115755
27.
ChenCCWuWHLiuYT, et al. A convenient cable tension estimation method simply based on local vibration measurements to fit partial mode shapes. Eng Struct2022; 272: 115008. https://doi.org/10.1016/j.engstruct.2022.115008
28.
ChenCCWuWHKoYP, et al. Extensive field validations and corresponding numerical investigations for a cable tension estimation method based on local vibration measurements. Struct Control Health Monit2023; 2023: 9691363. https://doi.org/10.1155/2023/9691363
29.
WuWHChenCCWuMX, et al. Experimental investigations and field applications of a tension estimation method for two linked suspenders using only local vibration measurements. Results Eng2025; 27: 105687. https://doi.org/10.1016/j.rineng.2025.105687
ZhangXXuHCaoM, et al. On real-time estimation of typhoons-induced cable tension of long-span cable-stayed bridges from health monitoring data. J Wind Eng Ind Aerod2023; 232: 105272. https://doi.org/10.1016/j.jweia.2022.105272
32.
LiuXYangJZhuoW, et al. Real-time identification of time-varying cable force for cable-stayed bridges based on vibration monitoring. Measurement2024; 231: 114590. https://doi.org/10.1016/j.measurement.2024.114590
33.
XuBWuZCasasJR. On-line damage detection in cables of cable-stayed bridges from ambient acceleration. Mech Syst Signal Process2025; 230: 112644. https://doi.org/10.1016/j.ymssp.2025.112644
34.
ZonnoGAguilarRLepidiM, et al. Automated long-term dynamic monitoring using hierarchical clustering and adaptive modal tracking: validation and applications. J Civ Struct Health Monit2018; 8(12): 791–808. https://doi.org/10.1007/s13349-018-0306-3
35.
LiJBaoTVenturaCE. An automated operational modal analysis algorithm and its application to concrete dams. Mech Syst Signal Process2022; 168: 108707. https://doi.org/10.1016/j.ymssp.2021.108707
36.
SadeqiAEsfandiariASanayeiM, et al. Automated operational modal analysis based on long-term records: a case study of Milad Tower structural health monitoring. Struct Control Health Monit2022; 29(10): e3037. https://doi.org/10.1002/stc.3037
MaoJXWangHFuYG, et al. Automated modal identification using principal component and cluster analysis: application to a long-span cable-stayed bridge. Struct Control Health Monit2019; 26(10): e2430. https://doi.org/10.1002/stc.2430
39.
CheemaPAlamdariMMVioGA, et al. Infinite mixture models for operational modal analysis: an automated and principled approach. J Sound Vib2021; 491: 115757. https://doi.org/10.1016/j.jsv.2020.115757
40.
ZhangXZhouWHuangY, et al. Automatic identification of structural modal parameters based on density peaks clustering algorithm. Struct Control Health Monit2022; 29(12): e3138. https://doi.org/10.1002/stc.3138
41.
JinSSJeongSSimSH, et al. Fully automated peak-picking method for an autonomous stay-cable monitoring system in cable-stayed bridges. Autom Constr2021; 126: 103628. https://doi.org/10.1016/j.autcon.2021.03628
42.
JeongSKimHLeeJ, et al. Automated wireless monitoring system for cable tension forces using deep learning. Struct Health Monit2021; 20(4): 1805–1821. https://doi.org/10.1177/1475921720935837
JuHDengYZhaoY, et al. Automatic modal frequency identification of bridge cables under influence of abnormal monitoring data. J Perform Constr Facil2024; 38(6): 04024046. https://doi.org/10.1061/JPCFEV.CFENG-4680
45.
WuWHChenCCLinSL, et al. Automatic anomaly detection and processing for long-term tension monitoring of stay cables based on vibration measurements. Intell Transp Infrastruct2022; 1(1): 1–10. https://doi.org/10.1093/iti/liac002
46.
WuWHWangSWChenCC, et al. Application of stochastic subspace identification for stay cables with an alternative stabilization diagram and hierarchical sifting process. Struct Control Health Monit2016; 23(9): 1194–1213. https://doi.org/10.1002/stc.1836
47.
WuWHWangSWChenCC, et al. Mode identifiability of a cable-stayed bridge under different excitation conditions assessed with an improved algorithm based on stochastic subspace identification. Smart Struct Syst2016; 17(3): 363–389.
48.
WuWHJhouJWChenCC, et al. A novel recursive stochastic subspace identification algorithm with its application in long-term structural health monitoring of office buildings. Smart Struct Syst2019; 24(4): 459–474.
49.
WuWHLinSLChenCC, et al. A real-time monitoring system for cable tension with vibration signals based on an automated algorithm to sieve out reliable modal frequencies. Struct Control Health Monit2023; 2023: 9343343. https://doi.org/10.1155/2023/9343343
50.
YeXWJinTYunCB. A review on deep learning-based structural health monitoring of civil infrastructures. Smart Struct Syst2019; 24(5): 567–586.
LeCunYBengioYHintonG. Deep learning. Nature2015; 521(7553): 436–444.
57.
ChaYJChoiWBuyukozturkO. Deep learning-based crack damage detection using convolutional neural networks. Comput Aided Civ Infrastruct Eng2017; 32(5): 361–378. https://doi.org/10.1111/mice.12263
58.
BhattaSDongJ. Multiclass seismic damage detection of buildings using quantum convolutional neural network. Comput Aided Civ Infrastruct Eng2024; 39(3): 406–423. https://doi.org/10.1111/mice.13084
59.
ZhangYXuZLiG, et al. Vision-aided damage detection with convolutional multihead self-attention neural network: a novel framework for damage information extraction and fusion. Struct Control Health Monit2025; 2025: 1677778. https://doi.org/10.1155/stc/1677778
60.
AbdeljaberOAvciOKiranyazS, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vib2017; 388: 154–170. https://doi.org/10.1016/j.jsv.2016.10.043
61.
KhodabandehlouHPekcanGFadaliMS. Vibration-based structural condition assessment using convolution neural networks. Struct Control Health Monit2019; 26(2): e2308. https://doi.org/10.1002/stc.2308
62.
OhBKGlisicBParkHS. Convolutional neural network-based damage detection method for building structures. Smart Struct Syst2021; 27(6): 903–916. https://doi.org/10.12989/sss.2021.27.6.903
63.
PamuncakAZivanovicSAdhaA, et al. Correlation-based damage detection method using convolutional neural network for civil infrastructure. Comput Struct2023; 282: 107034. https://doi.org/10.1016/j.compstruc.2023.107034
64.
TengSChenGYanZ, et al. Vibration-based structural damage detection using 1-D convolutional neural network and transfer learning. Struct Health Monit2023; 22(4): 2888–2909. https://doi.org/10.1177/14759217221137931
65.
LiuJLiQLiL, et al. Structural damage detection and localization via an unsupervised anomaly detection method. Reliab Eng Syst Saf2024; 252: 110465. https://doi.org/10.1016/j.ress.2024.110465
66.
ZhouYLiuYLianY, et al. Ambient vibration measurement-aided multi-1D CNNs ensemble for damage localization framework: demonstration on a large-scale RC pedestrian bridge. Mech Syst Signal Process2025; 224: 111937. https://doi.org/10.1016/j.ymssp.2024.111937
67.
FangYLiCWuS, et al. A new approach to structural damage identification based on power spectral density and convolutional neural network. Int J Struct Stab Dyn2025; 25(7): 2550066. https://doi.org/10.1142/S021945542550066X
68.
TanZYChenZCBaoYQ. Convolutional neural network-based data anomaly detection method using multiple information for structural health monitoring. Struct Control Health Monit2019; 26(1): e2296. https://doi.org/10.1002/stc.2296
69.
ShajihanSAVWangSZhaiG. CNN based data anomaly detection using multi-channel imagery for structural health monitoring. Smart Struct Syst2022; 29(1): 181–193.
70.
ZhangXZhouW. Structural vibration data anomaly detection based on multiple feature information using CNN-LSTM model. Struct Control Health Monit2023; 2023: 3906180. https://doi.org/10.1155/2023/3906180
71.
PanQBaoYLiH. Transfer learning-based data anomaly detection for structural health monitoring. Struct Health Monit2023; 22(5): 3077–3091. https://doi.org/10.1177/14759217221142174
72.
LiTZhangZHouR, et al. Residual convolutional attention model with transfer learning for detecting multianomalous features in structural vibration data. Struct Control Health Monit2024; 2024: 2451763. https://doi.org/10.1155/2024/2451763
73.
QuCXYanYTZhangHM, et al. Two-stage anomaly detection for imbalanced bridge data by attention mechanism optimisation and small sample augmentation. Eng Struct2025; 327: 119613. https://doi.org/10.1016/j.engstruct.2025.119613
74.
HouHYanYWuJ, et al. Multi-sensor data anomaly detection for super high-rise buildings based on EfficientNet modeling. J Build Eng2025; 108: 112906. https://doi.org/10.1016/j.jobe.2025.112906
75.
TiangJChenJWangJ, et al. Real-time classification model for anomalous sensor data in dam safety monitoring based on convolutional neural networks and transfer learning. Expert Sys Appl2026; 296: 129135. https://doi.org/10.1016/j.eswa.2025.129135
76.
OhBKGlisicBKimY, et al. Convolutional neural network-based data recovery method for structural health monitoring. Struct Health Monit2020; 19(6): 1821–1838. https://doi.org/10.1177/1475921719897571
77.
TangZBaoYLiH. Group sparsity-aware convolutional neural network for continuous missing data recovery of structural health monitoring. Struct Health Monit2021; 20(4): 1738–1759. https://doi.org/10.1177/1475921720931745
78.
CaiEZhangYLuX, et al. Model-informed deep learning-based compressive sensing for resampling and recovering 2D SHM vision data. Autom Constr2024; 160: 105295. https://doi.org/10.1016/j.autcon.2024.105295
79.
ChenXZhouWYangJ, et al. Lost data recovery for structural vibration data based on improved U-shaped encoder-decoder networks. Eng Struct2025; 332: 120096. https://doi.org/10.1016/j.engstruct.2025.120096
80.
JinZFuYSunZ. Time-frequency balanced data reconstruction SHM based on wavelet-enhanced multi-scale residual convolutional block and frequency distribution loss. Mech Syst Signal Process2025; 237: 113127. https://doi.org/10.1016/j.ymssp.2025.113127
81.
WanKWangYZhangW, et al. Enhanced dual-stage iterative recovery framework for incomplete data using compressed sensing and convolutional neural networks. Measurement2025; 256: 118178. https://doi.org/10.1016/j.measurement.2025.118178
82.
WuWHChenCCLinMD, et al. An automated cable tension monitoring system with vibration measurements using stochastic subspace identification and convolutional neural network. Measurement2025; 256: 118181. https://doi.org/10.1016/j.measurement.2025.118181
83.
ChenCCWuWHLiuCY, et al. Damage detection of a cable-stayed bridge based on the variation of stay cable forces eliminating environmental temperature effects. Smart Struct Syst2016; 17(6): 859–880.
84.
Sousa Tom’eEPimentelMFigueirasJ. Online early damage detection and localisation using multivariate data analysis: application to a cable-stayed bridge. Struct Control Health Monit2019; 26(11): e2434. https://doi.org/10.1002/stc.2434
85.
FanZYHuangQRenY, et al. A cointegration approach for cable anomaly warning based on structural health monitoring data: an application to cable-stayed bridges. Adv Struct Eng2020; 23(13): 2789–2802. https://doi.org/10.1177/1369433220924793
WangYYangDHZhouYZ, et al. Cable effective length model error-based bridge performance warning method under thermal action. Adv Struct Eng2022; 25(2): 306–320. https://doi.org/10.1177/13694332211048007
88.
LiJXYiTHQuCX, et al. Early warning for abnormal cable forces of cable-stayed bridges considering structural temperature changes. J Bridge Eng2023; 28(2): 04022137. https://doi.org/10.1061/JBENF2.BEENG-5797
89.
LiSWeiSBaoY, et al. Condition assessment of cables by pattern recognition of vehicle-induced cable tension ratio. Eng Struct2018; 155: 1–15. https://doi.org/10.1016/j.engstruct.2017.09.063
90.
WangXLiLTianW, et al. Unsupervised one-class classification for condition assessment of bridge cables using Bayesian factor analysis. Smart Struct Syst2022; 29(1): 41–51.
91.
PengZLiJHouH. Long-term condition monitoring of cables for in-service cable-stayed bridges using matched vehicle-induced cable tension ratios. Smart Struct Syst2022; 29(1): 167–179.
92.
YangDHGuHLYiTH, et al. Bridge cable anomaly detection based on local variability in feature vector of monitoring group cable forces. J Bridge Eng2023; 28(6): 04023030. https://doi.org/10.1061/JBENF2.BEENG-6084
LiJXQuCXYiTH, et al. Condition assessment of stay cables using normalized sequence of vehicle-induced cable force peaks of stay cables on same side. Eng Struct2024; 309: 118123. https://doi.org/10.1016/j.engstruct.2024.118123
95.
LiJXGuoCYiTH, et al. Early warning for stay cable performance via spatial distribution characteristics of vehicle-induced cable forces. Int J Struct Stab Dyn2025; 25: 2640006. https://doi.org/10.1142/S0219455426400067
