Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine, artificial neural network and genetic programming

Weirs are a type of hydraulic structure used to direct and transfer water flows in the canals and overflows in the dams. The important index in computing flow discharge over the weir is discharge coefficient ( C d ). The aim of this study is accurate determination of the C d in triangular labyrinth...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications Vol. 29; no. 11; pp. 983 - 989
Main Authors: Karami, Hojat, Karimi, Sohrab, Bonakdari, Hossein, Shamshirband, Shahabodin
Format: Journal Article
Language:English
Published: London Springer London 01.06.2018
Springer Nature B.V
Subjects:
Artificial Intelligence
Artificial neural networks
Canals
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Discharge coefficient
Genetic algorithms
Image Processing and Computer Vision
Learning theory
Neural networks
Predictions
Probability and Statistics in Computer Science
Review
Root-mean-square errors
Statistical methods
Test procedures
Training
Weirs
Artificial neural network
Discharge coefficient
Extreme learning machine
Genetic programming
Weir
ISSN:0941-0643, 1433-3058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Weirs are a type of hydraulic structure used to direct and transfer water flows in the canals and overflows in the dams. The important index in computing flow discharge over the weir is discharge coefficient ( C d ). The aim of this study is accurate determination of the C d in triangular labyrinth side weirs by applying three intelligence models [i.e., artificial neural network (ANN), genetic programming (GP) and extreme learning machine (ELM)]. The calculated discharge coefficients were then compared with some experimental results. In order to examine the accuracy of C d predictions by ANN, GP and ELM methods, five statistical indices including coefficient of determination ( R 2 ), root-mean-square error (RMSE), mean absolute percentage error (MAPE), SI and δ have been used. Results showed that R 2 values in the ELM, ANN and GP methods were 0.993, 0.886 and 0.884, respectively, at training stage and 0.971, 0.965 and 0.963, respectively, at test stage. The ELM method, having MAPE, RMSE, SI and δ values of 0.81, 0.0059, 0.0082 and 0.81, respectively, at the training stage and 0.89, 0.0063, 0.0089 and 0.88, respectively, at the test stage, was superior to ANN and GP methods. The ANN model ranked next to the ELM model.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-016-2588-x