Anomaly detection in deformation is important for structural health monitoring and safety evaluation of dams. In this paper, an anomaly detection model for the deformation of arch dams is presented. It combines the long short-term memory network (LSTM)-based behavior model for dam deformation prediction and the small probability method for control limits determination, and thus is called an LSTM-based anomaly detection model. To demonstrate the advantages of the LSTM-based anomaly detection model, the traditional hydrostatic-seasonal-time behavior model and the confidence interval method are considered for comparison. The 178 m-high Longyangxia Arch Dam is taken as a case study. The results show that the LSTM-based model has sufficiently high accuracy for dam deformation prediction, especially can accurately predict displacement peaks and troughs. The LSTM-based anomaly detection model can significantly avoid false warnings and missing alarms and is able to send alarms in time when the occurrence of adverse conditions causes abnormal deformation of the dam.
HellgrenRMalmRAnsellA. Performance of data-based models for early detection of damage in concrete dams. Struct Infrastruct Eng2020; 17: 275–289.
2.
SalazarFMoránRToledoMÁ, et al. Data-based models for the prediction of dam behaviour: a review and some methodological considerations. Arch Computat Methods Eng2015; 24: 1–21.
3.
WillmGBN. Dam monitoring methods for hydroelectric power generation in France - ancient problems and new solutions. In: International Commission on Large Dams (ICOLD), 9th Congress on large dams, vol. III, Istanbul, Turkey, 1967, pp. 529–550.
4.
BonelliSRoyetP. Delayed response analysis of dam monitoring data. In: MidttommeGHHonningsvagBReppK, et al. (ed.) Dams in a European context. Lisse: Swets and Zeitlinger, 2001, pp. 91–99.
5.
ShiYQZhaoCPengZQ, et al. Analysis of the lag effect of embankment dam seepage based on delayed mutual information. Eng Geol2018; 234: 132–137.
6.
KangFLiJJZhaoSZ, et al. Structural health monitoring of concrete dams using long-term air temperature for thermal effect simulation. Eng Struct2019; 180: 642–653.
7.
MataJde CastroATda CostaJS. Constructing statistical models for arch dam deformation. Struct Control Health2014; 21: 423–437.
8.
PenotIDaumasBFabreJP. Monitoring behaviour dam behavior monitoring. Int Water Power Dam Constr (UK)2005; 57: 24–27.
9.
RankovicVGrujovicNDivacD, et al. Development of support vector regression identification model for prediction of dam structural behaviour. Struct Saf2014; 48: 33–39.
10.
SuHZWenZPSunXR, et al. Rough set-support vector machine-based real-time monitoring model of safety status during dangerous dam reinforcement. Int J Damage Mech2017; 26: 501–522.
11.
SuHZChenZXWenZP. Performance improvement method of support vector machine-based model monitoring dam safety. Struct Control Health2016; 23: 252–266.
12.
TabariMMRSanayeiHRZ. Prediction of the intermediate block displacement of the dam crest using artificial neural network and support vector regression models. Soft Comput2019; 23: 9629–9645.
13.
RenQLiMBaiS, et al. A multiple-point monitoring model for concrete dam displacements based on correlated multiple-output support vector regression. Struct Health Monit2022; 21: 2768–2785.
14.
StojanovicBMilivojevicMIvanovicM, et al. Adaptive system for dam behavior modeling based on linear regression and genetic algorithms. Adv Eng Softw2013; 65: 182–190.
15.
SalazarFToledoMAOnateE, et al. Interpretation of dam deformation and leakage with boosted regression trees. Eng Struct2016; 119: 230–251.
16.
DaiBGuCZhaoE, et al. Statistical model optimized random forest regression model for concrete dam deformation monitoring. Struct Control Health Monit2018; 25: e2170.
17.
KangFLiuJLiJ, et al. Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Struct Control Health Monit2017; 24: e1997.
18.
MataJ. Interpretation of concrete dam behaviour with artificial neural network and multiple linear regression models. Eng Struct2011; 33: 903–910.
19.
KaoCYLohCH. Monitoring of long-term static deformation data of Fei-Tsui arch dam using artificial neural network-based approaches. Struct Control Health2013; 20: 282–303.
20.
LiuWPanJRenY, et al. Coupling prediction model for long-term displacements of arch dams based on long short-term memory network. Struct Control Health Monit2020; 27: e2548.
21.
OzelimLBorgesLPFCavalcanteALB, et al. Structural health monitoring of dams based on acoustic monitoring, deep neural networks, fuzzy logic and a CUSUM control algorithm. Sensors2022; 22: 2482.
22.
RibeiroLSWilhelmVEFariaEF, et al. A comparative analysis of long-term concrete deformation models of a buttress dam. Eng Struct2019; 193: 301–307.
23.
LiYTBaoTFGongJ, et al. The prediction of dam displacement time series using STL, extra-trees, and stacked LSTM neural network. Ieee Access2020; 8: 94440–94452.
24.
YangDSGuCSZhuYT, et al. A concrete dam deformation prediction method based on LSTM with attention mechanism. IEEE Access2020; 8: 185177–185186.
25.
BuiKTTTorresJFGutiérrez-AvilésD, et al. Deformation forecasting of a hydropower dam by hybridizing a long short-term memory deep learning network with the coronavirus optimization algorithm. Comput Aided Civ Infrastruct Eng2022; 37: 1368–1386.
26.
ChengLZhengD. Two online dam safety monitoring models based on the process of extracting environmental effect. Adv Eng Softw2013; 57: 48–56.
27.
SalazarFToledoMÁGonzálezJM, et al. Early detection of anomalies in dam performance: a methodology based on boosted regression trees. Struct Control Health Monit2017; 24: e2012.
28.
LiXLiYLLuX, et al. An online anomaly recognition and early warning model for dam safety monitoring data. Struct Health Monit2020; 19: 796–809.
29.
XuYHuangHLiY, et al. A three-stage online anomaly identification model for monitoring data in dams. Struct Health Monit2021; 21: 1183–1206.
30.
BianKWuZ. Data-based model with EMD and a new model selection criterion for dam health monitoring. Eng Struct2022; 260: 114171.
31.
ZhangFLuXLiY, et al. A self-matching model for online anomaly recognition of safety monitoring data in dams. Struct Health Monit2023: 22(1): 746–773.
32.
LiBYangJHuD. Dam monitoring data analysis methods: a literature review. Struct Control Health Monit2019; 27: e2501.
33.
PrakashGSadhuANarasimhanS, et al. Initial service life data towards structural health monitoring of a concrete arch dam. Struct Control Health Monit2018; 25: 1–19.
34.
SalazarFCondeAIrazabalJ, et al. Anomaly detection in dam behaviour with machine learning classification models. Water2021; 13: 2387.
35.
MataJLeitaoNSde CastroAT, et al. Construction of decision rules for early detection of a developing concrete arch dam failure scenario. A discriminant approach. Comput Struct2014; 142: 45–53.
36.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9: 1735–1780.
