Journal of Jilin University(Engineering and Technology Edition) ›› 2026, Vol. 56 ›› Issue (2): 497-508.doi: 10.13229/j.cnki.jdxbgxb.20240810

Previous Articles    

Prediction and reconstruction based anomaly condition detection model for bridges

Jiu-yuan HUO1,2(),Rui-xiang DOU1,Chen CHANG1,Feng CHEN1,Yao-nan ZHANG2   

  1. 1.School of Electronic and Information Engineering，Lanzhou Jiaotong University，Lanzhou 730070，China
    2.National Cryosphere Desert Data Center（NCDC），Lanzhou 730000，China
  • Received:2024-07-19 Online:2026-02-01 Published:2026-03-17

RICH HTML

 0   

PDF (PC)

32

Abstract:

This paper proposes a bridge anomaly detection model that integrates temporal and spatial features TSSF-BADM. The model utilizes graph attention networks （GAT） and long short-term memory （LSTM） networks to extract temporal and spatial data features. These multi-dimensional features are then fused using gated recurrent units （GRU） to capture sequential patterns in the time series. The fused data undergo joint optimization through prediction and reconstruction models， employing stacked LSTM networks and variational autoencoders （VAE） for prediction and reconstruction， respectively. Finally， the prediction and reconstruction errors of the model are analysed using the peak over threshold （POT） method to obtain the threshold and perform anomaly detection， and the samples exceeding the anomaly threshold are considered as anomalous samples. The experimental comparison results show that the model in this paper achieves good performance on the real bridge Z24， the accuracy of recognition reaches 0.986 8， and the recognition delay is only 0.008， which are all better than other comparative models such as LSTM_VAE， MAD_GAN， OmniAnomaly， etc.， and are able to effectively carry out the detection of the abnormal state of the bridge. It provides decision-making for bridge safety detection， preventive maintenance， etc.

Key words: bridge anomaly detection, integration of spatial and temporal features, reconstructed model, prediction model

CLC Number: 

  • TP399

Fig.1

Overall network architecture of TSSF-BADM"

Fig.2

Feature fusion strategy"

Fig.3

Stacked LSTM model structure"

Fig.4

LSTM-VAE model structure"

Fig.5

Flowchart of anomaly condition detection"

Table 1

Experimental parameter setting"

超参数数值
批大小64
学习率0.001
轮次100
γ0.8
阈值0.028 29

Fig.6

Schematic of the Z24 bridge"

Table 2

Progressive damage scenario for the Z24 bridge"

损伤情况时间描述损伤情况时间描述
D08月4日健康状态D88月27日桥台滑坡1 m
D18月10日Koppigen桥墩降低20 mmD98月31日混凝土铰链失效
D28月12日Koppigen桥墩降低40 mmD109月2日2个锚头失效
D38月17日Koppigen桥墩降低80 mmD119月3日4个锚头失效
D48月18日Koppigen桥墩降低95 mmD129月7日2根肌腱断裂
D58月19日桥墩提升，基础倾斜D139月8日4根肌腱断裂
D68月25日底板混凝土剥落12 m2D149月9日6根肌腱断裂
D78月26日底板混凝土剥落24 m2

Fig.7

Sensor placement"

Fig.8

Model training loss"

Fig.9

Comparison of results in different scenarios"

Fig.10

Visualisation of test set results"

Table 3

Comparison of experimental results"

ModelsACCPrecisionRecallF1
iForest0.596 20.649 80.805 60.719 4
PCA0.535 00.551 00.828 40.662 0
AutoEncoder0.572 00.591 10.556 20.573 1
LSTM0.618 20.652 60.968 10.779 6
LSTM_VAE0.651 30.625 70.854 60.722 4
DAGMM0.623 20.656 90.985 80.788 4
MAD_GAN0.793 70.851 70.899 10.874 8
OmniAnomaly0.637 40.656 90.963 40.781 1
TSSF-BADM（Ours）0.972 10.986 80.980 80.983 7

Fig.11

Comparison of latency for different models"

Table 4

Comparative results of ablation experiments"

模型变体PrecisionRecallF1
V10.938 80.980 80.959 3
V20.927 20.680 10.784 6
V30.902 90.797 30.846 8
V40.932 00.786 20.852 9
TSSF-BADM（Ours）0.986 80.980 80.983 7

Table 5

Comparison results for different γ"

γPrecisionRecallF1
0.40.973 20.968 70.971 0
0.60.975 30.953 80.964 4
0.80.986 80.980 80.983 7
1.00.970 10.914 70.941 6
[1] 交通运输部. 2022年交通运输行业发展统计公报[EB/OL]. [2024-03-31]. .
[2] Entezami A, Sarmadi H, Behkamal B. A novel double-hybrid learning method for modal frequency-based damage assessment of bridge structures under different environmental variation patterns[J]. Mechanical Systems and Signal Processing, 2023, 201:No. 110676.
[3] Domenico D. A review of vibration-based methods for damage detection in structures[J]. Journal of Structural Health Monitoring, 2018, 17: 3-35.
[4] Gao T, Wang X, Li Z. Sensor-based methods for structural health monitoring of bridges: a review[J]. Measurement, 2018, 115: 243-261.
[5] Abdeljaber O, Avci O, Kiranyaz M S, et al. 1-D CNNs for structural damage detection: verification on a structural health monitoring benchmark data[J]. Neurocomputing, 2018, 275: 1308-1317.
[6] Cha Y J, Wang Z. Unsupervised novelty detection–based structural damage localization using a density peaks-based fast clustering algorithm[J]. Structural Health Monitoring, 2018, 17(2): 313-324.
[7] Rafiei M H, Adeli H. A novel unsupervised deep learning model for global and local health condition assessment of structures[J]. Engineering Structures, 2018, 156: 598-607.
[8] Silva M F, Santos A, Santos R, et al. Damage‐sensitive feature extraction with stacked autoencoders for unsupervised damage detection[J]. Structural Control and Health Monitoring, 2021, 28(5):No. e2714.
[9] Soleimani B M H, Sepasdar R, Nasrollahzadeh K, et al. Toward a general unsupervised novelty detection framework in structural health monitoring[J]. Computer‐Aided Civil and Infrastructure Engineering, 2022, 37(9): 1128-1145.
[10] Sony S, Gamage S, Sadhu A, et al. Vibration-based mul ticlass damage detection and localization using long short-term memory networks[J]. Structures Elsevier, 2022, 35: 436-451.
[11] Li L, Morgantini M, Betti R. Structural damage assessment through a new generalized autoencoder with features in the quefrency domain[J]. Mechanical Systems and Signal Processing, 2023, 184: No.109713.
[12] Fan J, Zhang K, Huang Y, et al. Parallel spatio-temporal attention-based TCN for multivariate time series prediction[J]. Neural Computing and Applications, 2023, 35(18): 13109-13118.
[13] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[14] Chen N, Tu H, Duan X, et al. Semisupervised anomaly detection of multivariate time series based on a variational autoencoder[J]. Applied Intelligence, 2023, 53(5): 6074-6098.
[15] Dubey A K, Kumar A, García D V, et al. Study and analysis of SARIMA and LSTM in forecasting time series data[J]. Sustainable Energy Technologies and Assessments, 2021, 47: No.101474.
[16] Ding C, Sun S, Zhao J. MST-GAT: a multimodal spatial-temporal graph attention network for time series anomaly detection[J]. Information Fusion, 2023, 89: 527-536.
[17] Tang C, Xu L, Yang B, et al. GRU-based interpretable multivariate time series anomaly detection in industrial control system[J]. Computers & Security, 2023, 127: No.103094.
[18] Lei T, Gong C, Chen G, et al. A novel unsupervised framework for time series data anomaly detection via spectrum decomposition[J]. Knowledge-Based Systems, 2023, 280:No. 111002.
[19] Shan D, Yao K, Zhang X. Sequential learning network with residual blocks: incorporating temporal convolutional information into recurrent neural networks[J]. IEEE Transactions on Cognitive and Developmental Systems, 2023, 16(1): 396-401.
[20] Lin M, Wu J, Meng J, et al. State of health estimation with attentional long short-term memory network for lithium-ion batteries[J]. Energy, 2023, 268: No.126706.
[21] 刘嫣然, 孟庆瑜, 郭洪艳, 等. 图注意力模式下融合高精地图的周车轨迹预测[J]. 吉林大学学报: 工学版, 2023, 53(3): 792-801.
Liu Yan-ran, Meng Qing-yu, Guo Hong-yan, et al. Vehicle trajectory prediction combined with high definition map in graph attention mode[J].Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 792-801.
[22] Siffer A, Fouque P A, Termier A, et al. Anomaly detection in streams with extreme value theory[C]∥ Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, Canada, 2017: 1067-1075.
[23] Peeters B, Roeck D. One year monitoring of the z24-bridge: environmental influences versus damage events[J]. Proceedings of the International Modal Analysis Conference, 2000, 2: 1570-1576.
[24] Maeck J, Roeck D. Description of Z24 benchmark[J]. Mechanical Systems and Signal Processing, 2003, 17(1): 127-131.
[25] Reynders E, Roeck D. Vibration-based damage identification: the Z24 benchmark[J]. Living Reference Work Entry, 2015, 1: 1-8.
[26] Liu F T, Ting K M, Zhou Z H. Isolation forest[C]∥ Eighth IEEE International Conference on Data Mining, Pisa, Italy, 2008: 413-422.
[27] Borghesi A, Bartolini A, Lombardi M, et al. Anomaly detection using autoencoders in high performance computing systems[C]∥ Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 9428-9433.
[28] Hundman K, Constantinou V, Laporte C, et al. Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding[C]∥ Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK, 2018: 387-395.
[29] Park D, Hoshi Y, Kemp C C. A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder[J]. IEEE Robotics and Automation Letters, 2018, 3(3): 1544-1551.
[30] Zong B, Song Q, Min M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]∥ International Conference on Learning Representations, Vancouver, Canada, 2018: 1-19.
[31] Li D, Chen D, Jin B, et al. MAD-GAN: multivariate anomaly detection for time series data with generative adversarial networks[C]∥ International Conference on Artificial Neural Networks, Budapest, Hungary, 2019: 703-716.
[32] Su Y, Zhao Y, Niu C, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]∥ Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, USA, 2019: 2828-2837.
[1] Bing-xu WEI,Jing ZENG,Chu-fang CHEN. Strength and deformation characteristics of gangue-red clay subgrade in hot and humid areas in south China [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(11): 3632-3640.
[2] Jie MA,Zhi-li LIU,Shu-ling WANG,Hao DONG. Passenger flow prediction at entrance and exit of rail transit stations：a case study of Beijing [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2197-2205.
[3] Zhao-yi HE,Jin-feng LI,Wen ZHOU,Zhi-tao GUAN. Dynamic modulus of porous asphalt concrete and its prediction model [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(6): 1375-1385.
[4] Yu FANG,Li-jun SUN. Urban bridge performance decay model based on survival analysis [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(2): 557-564.
[5] Peng-hui WANG,Hong-xia QIAO,Qiong FENG,Hui CAO,Shao-yong WEN. Durability model of magnesium oxychloride-coated reinforced concrete under the two coupling factors [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(1): 191-201.
[6] Wu⁃jiao XU,Cheng⁃shang LIU,Xin⁃yao LU. Simulation and prediction of surface roughness of 6061 aluminum alloy workpiece after shot peening [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1280-1287.
[7] LI Yi,LIU Li-ping,SUN Li-jun. Prediction model on rutting equivalent temperature for asphalt pavement at different depth [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1703-1711.
[8] MA Zhi-xing, ZHAO Qi, ZHANG Hao. Fourier analysis model for housekeeping gene [J]. 吉林大学学报(工学版), 2016, 46(5): 1639-1643.
[9] YUAN Yuan,ZHANG Huan-jie, MIAO Yu-tian,WU Si-jia, LIN Song-yi,LIU Jing-bo. Contribution of the frying condition of potato slices to the formation of acrylamide [J]. 吉林大学学报(工学版), 2014, 44(5): 1525-1530.
[10] WANG Bao-jie, WANG Wei, YANG Min, HUA Xue-dong. BRT speed induction based on Kalman travel time prediction [J]. 吉林大学学报(工学版), 2014, 44(01): 41-46.
[11] SI Jian-bo, YANG Fang, GUO Wei-ying, YAO Yan. Two-stage disease prediction model based on BP neural network [J]. 吉林大学学报(工学版), 2013, 43(增刊1): 481-484.
[12] SU Li-li, WANG Deng-feng, WANG Qian. Sound quality prediction of vehicle interior noise based on GRNN [J]. 吉林大学学报(工学版), 2011, 41(增刊2): 82-86.
[13] GAO Yin-han, WANG Rui-bao, MA Yu-gang, WANG Ying-ying, YANG Kai-yu. Analytical prediction of parasitic capacitance and crosstalk in automotive cable bundles [J]. 吉林大学学报(工学版), 2011, 41(增刊1): 144-149.
[14] DAI Lei-lei, JIANG Gui-yan,PEI Yu-long . Prediction of queue length at saturate signalized intersection [J]. 吉林大学学报(工学版), 2008, 38(06): 1287-1290.
[15] Dai Wen-ting，Wei Hai-bin, Liu Han-bing, Gao Yi-ping . Dynamic damage model of silty clay after freeze-thaw cycles [J]. 吉林大学学报(工学版), 2007, 37(04): 790-793.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd