Open AccessForecasting shear stress parameters in rectangular channels using new soft computing methods
Author(s) -
Zohreh Sheikh Khozani,
Saeid Sheikhi,
Wan Hanna Melini Wan Mohtar,
Amir Mosavi
Publication year - 2020
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0229731
Subject(s) - shear stress , radial basis function , dimension (graph theory) , mathematics , artificial neural network , shear (geology) , function (biology) , algorithm , artificial intelligence , computer science , physics , materials science , mechanics , combinatorics , evolutionary biology , composite material , biology
Shear stress comprises basic information for predicting the average depth velocity and discharge in channels. With knowledge of the percentage of shear force carried by walls (% SF w ) it is possible to more accurately estimate shear stress values. The % SF w , non-dimension wall shear stress (τ ¯wτ 0) and non-dimension bed shear stress (τ ¯bτ 0) in smooth rectangular channels were predicted by a three methods, the Bayesian Regularized Neural Network (BRNN), the Radial Basis Function (RBF), and the Modified Structure-Radial Basis Function (MS-RBF). For this aim, eight data series of research experimental results in smooth rectangular channels were used. The results of the new method of MS-RBF were compared with those of a simple RBF and BRNN methods and the best model was selected for modeling each predicted parameters. The MS-RBF model with RMSE of 3.073, 0.0366 and 0.0354 for % SF w ,τ ¯wτ 0andτ ¯bτ 0respectively, demonstrated better performance than those of the RBF and BRNN models. The results of MS-RBF model were compared with three other proposed equations by researchers for trapezoidal channels and rectangular ducts. The results showed that the MS-RBF model performance in estimating % SF w ,τ ¯wτ 0andτ ¯bτ 0is superior than those of presented equations by researchers.