Accurate discharge coefficient prediction of streamlined weirs by coupling linear regression and deep convolutional gated recurrent unit

被引:52
作者
Chen, Weibin [1 ]
Sharifrazi, Danial [2 ]
Liang, Guoxi [3 ]
Band, Shahab S. [4 ]
Chau, Kwok Wing [5 ]
Mosavi, Amir [6 ,7 ,8 ]
机构
[1] Wenzhou Univ, Coll Comp Sci & Artificial Intelligence, Wenzhou, Peoples R China
[2] Islamic Azad Univ, Dept Comp Engn, Shiraz Branch, Shiraz, Iran
[3] Wenzhou Polytech, Dept Artificial Intelligence, Wenzhou, Peoples R China
[4] Natl Yunlin Univ Sci & Technol, Future Technol Res Ctr, Touliu, Yunlin, Taiwan
[5] Hong Kong Polytech Univ, Dept Civil & Environm Engn, Hong Kong, Peoples R China
[6] Univ Publ Serv, Inst Informat Soc, Budapest, Hungary
[7] Obuda Univ, John von Neumann Fac Informat, Budapest, Hungary
[8] Slovak Univ Technol Bratislava, Inst Informat Engn Automat & Math, Bratislava, Slovakia
关键词
Streamlined weirs; discharge prediction; deep learning; machine learning; deep convolutional neural network; gated recurrent unit; ARTIFICIAL NEURAL-NETWORK; CRESTED WEIR; SIDE WEIR; FLOW; SIMULATION; BUILDINGS; CAPACITY; MODELS;
D O I
10.1080/19942060.2022.2053786
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Streamlined weirs, which are a nature-inspired type of weir, have gained tremendous attention among hydraulic engineers, mainly owing to their established performance with high discharge coefficients. Computational fluid dynamics (CFD) is considered as a robust tool to predict the discharge coefficient. To bypass the computational cost of CFD-based assessment, the present study proposes data-driven modeling techniques, as an alternative to CFD simulation, to predict the discharge coefficient based on an experimental dataset. To this end, after splitting the dataset using a k-fold cross-validation technique, the performance assessment of classical and hybrid machine learning-deep learning (ML-DL) algorithms is undertaken. Among ML techniques, linear regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN) and decision tree (DT) algorithms are studied. In the context of DL, long short-term memory (LSTM), convolutional neural network (CNN) and gated recurrent unit (GRU), and their hybrid forms, such as LSTM-GRU, CNN-LSTM and CNN-GRU techniques, are compared using different error metrics. It is found that the proposed three-layer hierarchical DL algorithm, consisting of a convolutional layer coupled with two subsequent GRU levels, which is also hybridized with the LR method (i.e. LR-CGRU), leads to lower error metrics. This paper paves the way for data-driven modeling of streamlined weirs.
引用
收藏
页码:965 / 976
页数:12
相关论文
共 66 条
[1]   Damage detection of 3D structures using nearest neighbor search method [J].
Abasi, Ali ;
Harsij, Vahid ;
Soraghi, Ahmad .
EARTHQUAKE ENGINEERING AND ENGINEERING VIBRATION, 2021, 20 (03) :705-725
[2]  
Abdollahi A, 2016, ISH J. Hydraul. Eng, V23, P71, DOI [10.1080/09715010.2016.1239555, DOI 10.1080/09715010.2016.1239555]
[3]   Effects of sample size of ground motions on seismic fragility analysis of offshore jacket platforms using Genetic Algorithm [J].
Abyani, Mohsen ;
Bahaari, Mohammad Reza ;
Zarrin, Mohammad ;
Nasseri, Mohsen .
OCEAN ENGINEERING, 2019, 189
[4]   Copula-based reliability and sensitivity analysis of aging dams: Adaptive Kriging and polynomial chaos Kriging methods [J].
Amini, A. ;
Abdollahi, A. ;
Hariri-Ardebili, M. A. ;
Lall, U. .
APPLIED SOFT COMPUTING, 2021, 109
[5]   Seismic vulnerability macrozonation map of SMRFs located in Tehran via reliability framework [J].
Amini, Ali ;
Kia, Mehdi ;
Bayat, Mahmoud .
STRUCTURAL ENGINEERING AND MECHANICS, 2021, 78 (03) :351-368
[6]  
Arvanaghi H., 2013, Journal of Civil Engineering and Urbanism, V3, P87
[7]  
Arvanaghi H., 2014, INT J CURRENT RES, V2, P401
[8]  
Aswin S, 2018, PROCEEDINGS OF THE 2018 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), P657, DOI 10.1109/ICCSP.2018.8523829
[9]  
Athira V., 2018, Procedia Computer Science, V132, P1394, DOI 10.1016/j.procs.2018.05.068
[10]   Prediction of Discharge Capacity over Two-Cycle Labyrinth Side Weir Using ANFIS [J].
Aydin, M. Cihan ;
Kayisli, Korhan .
JOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING, 2016, 142 (05)