Deformation serves as a key index to characterize the operational condition of dams. However, the prediction accuracy of deformation in dams remains limited due to the influence of multiple factors. Accordingly, this study innovatively combines the Informer with the segmented sequence decomposition and proposes a segmented sequence decomposition-Informer model (SD-Informer) for the deformation prediction of arch dams, which significantly improves the prediction accuracy and stability. The segmented sequence decomposition divides the predicted time series into annual segments and decomposes them in a segment-by-segment manner, thereby minimizing the reduction of prediction accuracy over long sequences and the boundary effects in decomposition. In addition, the Informer extracts macro- and micro-level information from deformation sequences using a multi-head attention mechanism, which significantly improves the prediction accuracy. LYX arch dam and XW arch dam, which have been in operation for more than 20 years, are taken as case studies. The results show that the performance of the SD-Informer surpasses that of wavelet neural networks, long short-term networks, and Informer, demonstrating that the SD-Informer is an accurate, robust, practical deformation prediction of arch dams for engineering applications.
PanJLiuWLiuC, et al. Convolutional neural network-based spatiotemporal prediction for deformation behavior of arch dams. Expert Syst Appl2023; 232: 120835.
2.
YuanDGuCQinX, et al. Performance-improved TSVR-based DHM model of super high arch dams using measured air temperature. Eng Struct2022; 250: 113400.
3.
ChengM.-YCaoM.-THuangI.-F.Hybrid artificial intelligence-based inference models for accurately predicting dam body displacements: a case study of the Fei Tsui dam. Struct Health Monit2022; 21: 1738–1756.
4.
YuXLiJKangF. A hybrid model of bald eagle search and relevance vector machine for dam safety monitoring using long-term temperature. Adv Eng Inform2023; 55: 101863.
5.
RenQLiMShenY. A new interval prediction method for displacement behavior of concrete dams based on gradient boosted quantile regression. Struct Control Health Monit. Epub ahead of print 29September2021. DOI: 10.1002/stc.2859.
6.
XuZMoLZhouJ, et al. Stepwise decomposition-integration-prediction framework for runoff forecasting considering boundary correction. Sci Total Environ2022; 851: 158342.
7.
WillmGBeaujointN. 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, Istanbul, Turkey, 1967, vol. III, pp.529–550.
8.
LiBYangJHuD. Dam monitoring data analysis methods: a literature review. Struct Control Health Monit2020; 27: e2501.1–e2501.14.
9.
PenotIDaumasBFabreJP. Monitoring behaviour - The author report on the methods used by EDF to monitor the behaviour of the company’s dams. Int Water Power Dam Constr2005; 57: 24–27.
10.
WeiBYuanDLiH, et al. Combination forecast model for concrete dam displacement considering residual correction. Struct Health Monit2019; 18: 232–244.
11.
YuanDWeiBXieB, et al. Modified dam deformation monitoring model considering periodic component contained in residual sequence. Struct Control Health Monit2020; 27: e2633.
12.
SuHChenZWenZ. Performance improvement method of support vector machine-based model monitoring dam safety. Struct Control Health Monit2016; 23: 252–266.
13.
MataJ. Interpretation of concrete dam behaviour with artificial neural network and multiple linear regression models. Eng Struct2011; 33: 903–910.
14.
FeiKJiaLLiJ, et al. Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Struct Control Health Monit2017; 24: e1997.
15.
HuangBKangFLiJ, et al. Displacement prediction model for high arch dams using long short-term memory based encoder-decoder with dual-stage attention considering measured dam temperature. Eng Struct2023; 280: 115686.
16.
Hariri-ArdebiliMAMahdaviGNussLK, et al. The role of artificial intelligence and digital technologies in dam engineering: narrative review and outlook. Eng Appl Artif Intell2023; 126: 106813.
17.
SalazarFMoránRToledoMÁ, et al. Data-based models for the prediction of dam behaviour: a review and some methodological considerations. Arch Computat Methods Eng2017; 24: 1–21.
QuXYangJChangM. A deep learning model for concrete dam deformation prediction based on RS-LSTM. J Sens2019; 2019: 1–14.
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.
ChoKvan MerriënboerBGulcehreC, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, pp. 1724–1734. Association for Computational Linguistics.
22.
WuNGreenBXueB, et al. Deep transformer models for time series forecasting: the influenza prevalence case. arXiv:2001.08317, 2020.
23.
ZhouHZhangSPengJ, et al. Informer: beyond efficient transformer for long sequence time-series forecasting. AAAI Conf Artif Intell. arXiv:2012.07436, 2020.
24.
AnZChengLGuoY, et al. A novel principal component analysis-informer model for fault prediction of nuclear valves. Machines2022; 10: 240.
25.
LvGWangJWangX, et al. Informer-based anomaly detection for internet tv service in home network. In: 2022 IEEE 8th international conference on computer and communications (ICCC), Chengdu, China, 9–12 December 2022, pp. 604–609. IEEE.
26.
GuoLLiRJiangB. A data-driven long time-series electrical line trip fault prediction method using an improved stacked-informer network. Sensors2021; 21: 4466.
27.
HuaizhiSJiangHZhongruW. A study of safety evaluation and early-warning method for dam global behavior. Struct Health Monit2012; 11: 269–279.
28.
XiLYunZLiuH, et al. Semi-supervised time series classification model with self-supervised learning. Eng Appl Artif Intell2022; 116: 105331.
29.
ClevelandRBClevelandWS. STL: a seasonal-trend decomposition procedure based on Loess. J Off Stat1990; 6: 3–73.
30.
HangSQuanLLiJ. Adaptive approach for boundary effects reduction in rotating machine signals analysis. Adv Mech Eng2013; 2013: 323–335.
31.
RakthanmanonTCampanaBMueenA, et al. Searching and mining trillions of time series subsequences under dynamic time warping. KDD2012; 2013: 262–270.
32.
ZhangXPengYZhangC, et al. Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences. J Hydrology2015; 530: 137–152.
33.
DuKYingZLeiJ. The incorrect usage of singular spectral analysis and discrete wavelet transform in hybrid models to predict hydrological time series. J Hydrology2017; 552: 44–51.
34.
FangWHuangSRenK, et al. Examining the applicability of different sampling techniques in the development of decomposition-based streamflow forecasting models. J Hydrology2019; 568: 534–550.
35.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: Neural Information Processing Systems. arXiv:1706.03762, 2017.
36.
YinCWuZ. Separate modeling technique for deformation monitoring of concrete dams. Struct Health Monit2022; 21: 2968–2989.
37.
LiuCPanJWangJ. An LSTM-based anomaly detection model for the deformation of concrete dams. Struct Health Monit. Epub ahead of print 10October2023. DOI: 10.1177/14759217231199569.
