Published in Structural Safety Vol 56, pp. 9-17, 2015
DOI: 10.1016/j.strusafe.2015.05.001

Abstract

Predictive models are essential in dam safety assessment. Both deterministic and statistical models applied in the day-to-day practice have demonstrated to be useful, although they show relevant limitations at the same time. On another note, powerful learning algorithms have been developed in the field of machine learning (ML), which have been applied to solve practical problems. The work aims at testing the prediction capability of some state-of-the-art algorithms to model dam behaviour, in terms of displacements and leakage. Models based on random forests (RF), boosted regression trees (BRT), neural networks (NN), support vector machines (SVM) and multivariate adaptive regression splines (MARS) are fitted to predict 14 target variables. Prediction accuracy is compared with the conventional statistical model, which shows poorer performance on average. BRT models stand out as the most accurate overall, followed by NN and RF. It was also verified that the model fit can be improved by removing the records of the first years of dam functioning from the training set.

D. Vicente, J. San Mauro, F. Salazar, C. Baena. An Interactive Tool for Automatic Predimensioning and Numerical Modeling of Arch Dams. Mathematical Problems in Engineering 2017 DOI 10.1155/2017/9856938

F. Salazar, B. Crookston. A Performance Comparison of Machine Learning Algorithms for Arced Labyrinth Spillways. Water 11(3) (2019) DOI 10.3390/w11030544

I. Mansouri, M. Safa, Z. Ibrahim, O. Kisi, M. Tahir, S. Baharom, M. Azimi. Strength prediction of rotary brace damper using MLR and MARS. Structural Engineering and Mechanics 60(3) DOI 10.12989/sem.2016.60.3.471

F. Kang, J. Liu, J. Li, S. Li. Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Struct. Control Health Monit. 24(10) (2017) DOI 10.1002/stc.1997

F. Salazar, M. Toledo, J. González, E. Oñate. Early detection of anomalies in dam performance: A methodology based on boosted regression trees. Struct Control Health Monit 24(11) (2017) DOI 10.1002/stc.2012

G. Prakash, A. Sadhu, S. Narasimhan, J. Brehe. Initial service life data towards structural health monitoring of a concrete arch dam. Struct Control Health Monit 25(1) (2017) DOI 10.1002/stc.2036

J. Hu, F. Ma, S. Wu. Comprehensive investigation of leakage problems for concrete gravity dams with penetrating cracks based on detection and monitoring data: A case study. Struct Control Health Monit 25(4) (2017) DOI 10.1002/stc.2127

B. Dai, C. Gu, E. Zhao, X. Qin. Statistical model optimized random forest regression model for concrete dam deformation monitoring. Struct Control Health Monit 25(6) (2018) DOI 10.1002/stc.2170

C. Lin, T. Li, X. Liu, L. Zhao, S. Chen, H. Qi. A deformation separation method for gravity dam body and foundation based on the observed displacements. Struct Control Health Monit 26(2) (2018) DOI 10.1002/stc.2304

S. Wang, Y. Xu, C. Gu, T. Bao, Q. Xia, K. Hu. Hysteretic effect considered monitoring model for interpreting abnormal deformation behavior of arch dams: A case study. Struct Control Health Monit 26(10) (2019) DOI 10.1002/stc.2417

G. Liang, Y. Hu, Q. Li. Safety Monitoring of High Arch Dams in Initial Operation Period Using Vector Error Correction Model. Rock Mech Rock Eng 51(8) (2017) DOI 10.1007/s00603-017-1287-y

Y. Yu, X. Liu, E. Wang, K. Fang, L. Huang. Dam Safety Evaluation Based on Multiple Linear Regression and Numerical Simulation. Rock Mech Rock Eng 51(8) (2018) DOI 10.1007/s00603-018-1435-z

Z. Jiang, J. He. Method of Fusion Diagnosis for Dam Service Status Based on Joint Distribution Function of Multiple Points. Mathematical Problems in Engineering 2016 DOI 10.1155/2016/9049260

P. Ziolkowski, S. Demczynski, M. Niedostatkiewicz. Assessment of Failure Occurrence Rate for Concrete Machine Foundations Used in Gas and Oil Industry by Machine Learning. Applied Sciences 9(16) (2019) DOI 10.3390/app9163267

F. Kang, X. Liu, J. Li. Temperature effect modeling in structural health monitoring of concrete dams using kernel extreme learning machines. Structural Health Monitoring (2019) DOI 10.1177/1475921719872939

M. Tabari, H. Sanayei. Prediction of the intermediate block displacement of the dam crest using artificial neural network and support vector regression models. Soft Comput 23(19) (2018) DOI 10.1007/s00500-018-3528-8

K. Bui, D. Tien Bui, J. Zou, C. Van Doan, I. Revhaug. A novel hybrid artificial intelligent approach based on neural fuzzy inference model and particle swarm optimization for horizontal displacement modeling of hydropower dam. Neural Comput & Applic 29(12) (2016) DOI 10.1007/s00521-016-2666-0

C. Lin, T. Li, S. Chen, X. Liu, C. Lin, S. Liang. Gaussian process regression-based forecasting model of dam deformation. Neural Comput & Applic 31(12) (2019) DOI 10.1007/s00521-019-04375-7

J. Tinoco, M. de Granrut, D. Dias, T. Miranda, A. Simon. Piezometric level prediction based on data mining techniques. Neural Comput & Applic (2019) DOI 10.1007/s00521-019-04392-6

H. Liu, C. Ren, Z. Zheng, Y. Liang, X. Lu. Study of a Gray Genetic BP Neural Network Model in Fault Monitoring and a Diagnosis System for Dam Safety. IJGI 7(1) (2017) DOI 10.3390/ijgi7010004

X. Li, Z. Wen, H. Su. An approach using random forest intelligent algorithm to construct a monitoring model for dam safety. Engineering with Computers (2019) DOI 10.1007/s00366-019-00806-0

S. Mastelini, M. Sasso, G. Campos, M. Schmiele, M. Clerici, D. Barbin, S. Barbon. Computer vision system for characterization of pasta (noodle) composition. J. Electron. Imag. 27(05) DOI 10.1117/1.jei.27.5.053021

F. Kang, X. Liu, J. Li. Concrete Dam Behavior Prediction Using Multivariate Adaptive Regression Splines with Measured Air Temperature. Arab J Sci Eng 44(10) (2019) DOI 10.1007/s13369-019-04095-z

J. Rico, J. Barateiro, J. Mata, A. Antunes, E. Cardoso. Applying Advanced Data Analytics and Machine Learning to Enhance the Safety Control of Dams. (2019) DOI 10.1007/978-3-030-15628-2_10

J. Zhang, X. Cao, J. Xie, P. Kou. An Improved Long Short-Term Memory Model for Dam Displacement Prediction. Mathematical Problems in Engineering 2019 DOI 10.1155/2019/6792189

M. Li, J. Wang. An Empirical Comparison of Multiple Linear Regression and Artificial Neural Network for Concrete Dam Deformation Modelling. Mathematical Problems in Engineering 2019 DOI 10.1155/2019/7620948

Q. Ren, G. Wang, M. Li, S. Han. Prediction of Rock Compressive Strength Using Machine Learning Algorithms Based on Spectrum Analysis of Geological Hammer. Geotech Geol Eng 37(1) (2018) DOI 10.1007/s10706-018-0624-6

J. Hu, F. Ma. Zoned safety monitoring model for uplift pressures of concrete dams. Transactions of the Institute of Measurement and Control 41(14) (2019) DOI 10.1177/0142331219842281

F. Salazar, R. Morán, M. Toledo, E. Oñate. Data-Based Models for the Prediction of Dam Behaviour: A Review and Some Methodological Considerations. Arch Computat Methods Eng 24(1) (2015) DOI 10.1007/s11831-015-9157-9

S. Dargan, M. Kumar, M. Ayyagari, G. Kumar. A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning. Arch Computat Methods Eng (2019) DOI 10.1007/s11831-019-09344-w