Abstract
Developing a deformation prediction model with strong robustness and applicability based on monitoring data is an important task in establishing a safety monitoring system for super high arch dams. This study proposes a hybrid deep learning (DL) model for deformation prediction, named HFS/xs-MLSTM. The proposed multidimensional long short-term memory (MLSTM) DL achieves integrated modeling of two factors, environment and temporal correlation, by constructing a multivariate matrix, and achieves sequential prediction by rolling through the sliding windows. This operation solves the problem of insufficient prediction accuracy due to the traditional method considering only a single factor. To address the problems of computational time consumption and DL overfitting caused by variable redundancy, a hybrid feature selection method (HFS/xs) based on eXtreme gradient boosting and Spearman is proposed. Analysis shows that HFS/xs can comprehensively reflect the intrinsic laws of the data and effectively filter out the most concise set of variables, which greatly improves the operability and stability of MLSTM. Compared with traditional methods, HFS/xs-MLSTM has the best performance and applicability for deformation prediction in different zones and operating conditions. This study can provide reliable a priori knowledge for the construction of safety monitoring system for super high arch dams.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Adnan RM, Liang ZM, Trajkovic S, Kermani MZ, Li BQ, Kisi O (2019) Daily streamflow prediction using optimally pruned extreme learning machine. Journal of Hydrology 577:123981, DOI: https://doi.org/10.1016/j.jhydrol.2019.123981
Almaghrabi F, Xu DL, Yang JB (2021) An evidential reasoning rule based feature selection for improving trauma outcome prediction. Applied Soft Computing 103:107112, DOI: https://doi.org/10.1016/j.asoc.2021.107112
Bouktif S, Fiaz A, Ouni A, Serhani M (2018) Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies 11:1636, DOI: https://doi.org/10.3390/en11071636
Bui KTT, Bui DT, Zou JG, Doan CV, Revhaug I (2018) A novel hybrid artificial intelligent approach based on neural fuzzy inference model and particle swarm optimization for horizontal displacement modeling of hydropower dam. Neural Computing & Applications 29:1495–1506, DOI: https://doi.org/10.1007/s00521-016-2666-0
Cao EH, Bao TF, Gu CS, Li H, Liu YT, Hu SP (2020) A novel hybrid decomposition — Ensemble prediction model for dam deformation. Applied Sciences-Basel 10(16):5700, DOI: https://doi.org/10.3390/app10165700
Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system. in: Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785–794, DOI: https://doi.org/10.1145/2939672.2939785
Chen B, Hu TY, Huang ZS, Fang CH (2019) A spatio-temporal clustering and diagnosis method for concrete arch dams using deformation monitoring data. Structural Health Monitoring 18(5–6):1355–1371, DOI: https://doi.org/10.1177/1475921718797949
Chen WL, Wang XL, Cai ZJ, Liu CX, Zhu YS, Lin WW (2021) DP-GMM clustering-based ensemble learning prediction methodology for dam deformation considering spatiotemporal differentiation. Knowledge-Based Systems 222:106964, DOI: https://doi.org/10.1016/j.knosys.2021.106964
Chen C, Zhang QM, Yu B, Yu ZM, Lawrence PJ, Ma Q, Zhang Y (2020) Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier. Computers in Biology and Medicine 123:103899, DOI: https://doi.org/10.1016/j.compbiomed.2020.103899
Dai B, Gu CS, Zhao EF, Qin XN (2018) Statistical model optimized random forest regression model for concrete dam deformation monitoring. Structure. Control. Health Monitoring 25:e2170, DOI: https://doi.org/10.1002/stc.2170
Farhi N, Kohen E, Mamane H, Shavitt Y (2021) Prediction of wastewater treatment quality using LSTM neural network. Environmental Technology & Innovation 23:101632, DOI: https://doi.org/10.1016/j.eti.2021.101632
Fu X, Gu CS, Qin D (2017) Deformation features of a super-high arch dam structural system. Optik 130:681–695
Gu CS, Zhao EF, Zhou Z, Cai DW (2018) Deformation safety monitoring of super high arch dams: Theories, methods and their applicaions. Hohai University Press, Nan Jing, NJ, China
Guo Z, Yu B, Hao MY, Wang WS, Jiang Y, Zong F (2021) A novel hybrid method for flight departure delay prediction using random forest regression and maximal information coefficient. Aerospace Science and Technology 116:106822, DOI: https://doi.org/10.1016/j.ast.2021.106822
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computing 9(8):1735–1780, DOI: https://doi.org/10.1162/neco.1997.9.8.1735
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: Theory and applications. Neurocomputing 70(1–3):489–501, DOI: https://doi.org/10.1016/j.neucom.2005.12.126
Jeon J, Lee J, Shin D, Park H (2009) Development of dam safety management system. Advances in Engineering Software 40(8):554–563, DOI: https://doi.org/10.1016/j.advengsoft.2008.10.009
Jörges C, Berkenbrink C, Stumpe B (2021) Prediction and reconstruction of ocean wave heights based on bathymetric data using LSTM neural networks. Ocean Engineering 232:109046, DOI: https://doi.org/10.1016/j.oceaneng.2021.109046
Kang F, Liu J, Li JJ, Li SJ (2017) Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Structure Control Health Monitoring 24:e1997, DOI: https://doi.org/10.1002/stc.1997
Kim HI, Kim BH (2020) Flood hazard rating prediction for urban areas using random forest and LSTM. KSCE Journal of Civil Engineering 24(12):3884–3896, DOI: https://doi.org/10.1007/s12205-020-0951-z
Li YT, Bao TF, Chen H, Zhang K, Shu XS, Chen ZX, Hu YH (2021) A large-scale sensor missing data imputation framework for dams using deep learning and transfer learning strategy. Measurement 178:109377, DOI: https://doi.org/10.1016/j.measurement.2021.109377
Li MC, Shen Y, Ren QB, Li H (2019) A new distributed time series evolution prediction model for dam deformation based on constituent elements. Advanced Engineering Informatics 39:41–52, DOI: https://doi.org/10.1016/j.aei.2018.11.006
Li CS, Tang G, Xue XM, Chen XB, Wang RH, Zhang C (2020) The short-term interval prediction of wind power using the deep learning model with gradient descend optimization. Renewable Energy 155:197–211, DOI: https://doi.org/10.1016/j.renene.2020.03.098
Li X, Wen ZP, Su HZ (2021) An approach using random forest intelligent algorithm to construct a monitoring model for dam safety. Engineering with Computers 37:39–56, DOI: https://doi.org/10.1007/s00366-019-00806-0
Liu Y, Liu ZY, Jia R (2019) DeepPF: A deep learning based architecture for metro passenger flow prediction. Transportation Research Part C: Emerging Technologies 101:18–34, DOI: https://doi.org/10.1016/j.trc.2019.01.027
Mata J (2011) Interpretation of concrete dam behavior with artificial neural network and multiple linear regression models. Engineering Structures 33(3):903–910, DOI: https://doi.org/10.1016/j.engstruct.2010.12.011
Mata J, Castro ATD, Costa JSD (2014) Constructing statistical models for arch dam deformation. Structure Control Health Monitoring 21(3):423–437, DOI: https://doi.org/10.1002/stc.1575
Pavithra V, Jayalakshmi V (2021) Hybrid feature selection technique for prediction of cardiovascular diseases. Materials Today: Proceedings, DOI: https://doi.org/10.1016/j.matpr.2021.03.225
Salazar F, Moran R, Toledo MA, Onate E (2017) Data-based models for the prediction of dam behaviour: A review and some methodological considerations. Archives of Computational Methods in Engineering 24(1):1–21, DOI: https://doi.org/10.1007/s11831-015-9157-9
Salazar F, Toledo MÁ, Oñate E, Morán R (2015) An empirical comparison of machine learning techniques for dam behaviour modelling. Structural Safety 56:9–17, DOI: https://doi.org/10.1016/j.strusafe.2015.05.001
Shen ML, Lee CF, Liu HH, Chang PY, Yang CH (2021) Effective multinational trade forecasting using LSTM recurrent neural network. Expert Systems with Applications 182:115199, DOI: https://doi.org/10.1016/j.eswa.2021.115199
Shi R, Xu XY, Li JM, Li YQ (2021) Prediction and analysis of train arrival delay based on XGBoost and Bayesian optimization. Applied Soft Computing 109:107538, DOI: https://doi.org/10.1016/j.asoc.2021.107538
Speiser JL (2021) A random forest method with feature selection for developing medical prediction models with clustered and longitudinal data. Journal of Biomedical Informatics 117:103763, DOI: https://doi.org/10.1016/j.jbi.2021.103763
Stojanovic B, Milivojevic M, Milivojevic N, Antonijevic D (2016) A self-tuning system for dam behavior modeling based on evolving artificial neural networks. Advances in Engineering Software 97:85–95, DOI: https://doi.org/10.1016/j.advengsoft.2016.02.010
Su HZ, Li X, Yang BB, Wen ZP (2018) Wavelet support vector machine-based prediction model of dam deformation. Mechanical Systems and Signal Processing 110:412–427, DOI: https://doi.org/10.1016/j.ymssp.2018.03.022
Sun G, Chen T, Wei Z, Sun Y, Zang H, Chen S (2016) A carbon price forecasting model based on variational mode decomposition and spiking neural networks. Energies 9:54, DOI: https://doi.org/10.3390/en9010054
Tulensalo J, Seppänen J, Ilin A (2020) An LSTM model for power grid loss prediction. Electric Power Systems Research 189:106823, DOI: https://doi.org/10.1016/j.epsr.2020.106823
Wang SW, Xu YL, Gu CS, Bao TF, Xia Q, Hu K (2019) Hysteretic effect considered monitoring model for interpreting abnormal deformation behavior of arch dams: A case study. Structure Control Health Monitoring 26(10):e2417, DOI: https://doi.org/10.1002/stc.2417
Wei BW, Yuan DY, Xu ZK, Li LH (2018) Modified hybrid forecast model considering chaotic residual errors for dam deformation. e2188 Structure Control Health Monitoring, DOI: https://doi.org/10.1002/stc.2188
Xu YH, Hu CH, Wu Q, Jian SQ, Li ZC, Chen YQ, Zhang GD, Zhang ZX, Wang SL (2022) Research on particle swarm optimization in LSTM neural networks for rainfall-runoff simulation. Journal of Hydrology 608:127553, DOI: https://doi.org/10.1016/j.jhydrol.2022.127553
Yuan RY, Su C, Cao EH, Hu SP, Zhang H (2021) Exploration of multi-scale reconstruction framework in dam deformation prediction. Applied Sciences-Basel 11(16):7334, DOI: https://doi.org/10.3390/app11167334
Zhao EF, Wu CQ (2020) Unified egg ellipse critical threshold estimation for the deformation behavior of ultrahigh arch dams. Engngineering Structure 214:1–14, DOI: https://doi.org/10.1016/j.engstruct.2020.110598
Zhou Y, Li SJ (2020) BP neural network modeling with sensitivity analysis on monotonicity based Spearman coefficient. Chemometrics and Intelligent Laboratory Systems 200:103977, DOI: https://doi.org/10.1016/j.chemolab.2020.103977
Acknowledgments
This research has been supported by the National Key Research and Development Program, Grant/Award Number: China2018YFC1508603, the National Natural Science Foundation of China, Grant/Award Number: 51579086, 51739003.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cao, E., Bao, T., Li, H. et al. A Hybrid Feature Selection-multidimensional LSTM Framework for Deformation Prediction of Super High Arch Dams. KSCE J Civ Eng 26, 4603–4616 (2022). https://doi.org/10.1007/s12205-022-1553-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-022-1553-8