Using artificial neural network (ANN) in prediction of collapse settlements of sandy gravels

H. Hasanzadehshooiili, Reza Mahinroosta, Ali Lakirouhani, Vahid Oshtaghi

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Collapse settlement is one of the main geotechnical hazards, which should be controlled during first impoundment stage in embankment dams. Imposing large deformations and significant damages to dams makes it an important phenomenon, which should be checked during design phases. Also, existence of a variety of contributing parameters in this phenomenon makes it difficult and complicated to well predict the potential of collapse settlement. Thus, artificial neural networks, which are commonly applied by majority of geotechnical engineers in predicting various perplexing problems, can be efficiently used to calculate the value of collapse settlement. In this paper, feedforward backpropagation neural networks are considered. And three-layered FFBPNNs with the architectures of 4–6–2 and 4–9–2 accurately predicted the coefficient of stress release and collapse settlement value, respectively. These networks were trained using 180 datasets gained from large-scale direct shear test, which were carried out on gravel materials. High correlation between measured and predicted values for both collapse settlement and coefficient of stress release can be easily understood from the coefficient of determination and root mean square error. It is shown that sand content and normal stress applied to the specimens, respectively, are most effective parameters on the collapse settlement value and coefficient of stress release.
Original languageEnglish
Pages (from-to)2303-2314
Number of pages12
JournalArabian Journal of Geosciences
Volume7
Issue number6
Early online date10 Feb 2013
Publication statusPublished - 2014

Fingerprint

artificial neural network
gravel
prediction
embankment dam
shear test
impoundment
dam
hazard
damage
sand
parameter

Cite this

Hasanzadehshooiili, H. ; Mahinroosta, Reza ; Lakirouhani, Ali ; Oshtaghi, Vahid. / Using artificial neural network (ANN) in prediction of collapse settlements of sandy gravels. In: Arabian Journal of Geosciences. 2014 ; Vol. 7, No. 6. pp. 2303-2314.
@article{6a2373ed2a42402f821ff01b2821418f,
title = "Using artificial neural network (ANN) in prediction of collapse settlements of sandy gravels",
abstract = "Collapse settlement is one of the main geotechnical hazards, which should be controlled during first impoundment stage in embankment dams. Imposing large deformations and significant damages to dams makes it an important phenomenon, which should be checked during design phases. Also, existence of a variety of contributing parameters in this phenomenon makes it difficult and complicated to well predict the potential of collapse settlement. Thus, artificial neural networks, which are commonly applied by majority of geotechnical engineers in predicting various perplexing problems, can be efficiently used to calculate the value of collapse settlement. In this paper, feedforward backpropagation neural networks are considered. And three-layered FFBPNNs with the architectures of 4–6–2 and 4–9–2 accurately predicted the coefficient of stress release and collapse settlement value, respectively. These networks were trained using 180 datasets gained from large-scale direct shear test, which were carried out on gravel materials. High correlation between measured and predicted values for both collapse settlement and coefficient of stress release can be easily understood from the coefficient of determination and root mean square error. It is shown that sand content and normal stress applied to the specimens, respectively, are most effective parameters on the collapse settlement value and coefficient of stress release.",
keywords = "Large-scale direct shear test , Artificial neural network, Collapse settlement of gravels , Coefficient of stress release",
author = "H. Hasanzadehshooiili and Reza Mahinroosta and Ali Lakirouhani and Vahid Oshtaghi",
note = "Imported on 12 Apr 2017 - DigiTool details were: Journal title (773t) = Arabian Journal of Geosciences. ISSNs: 1866-7511;",
year = "2014",
language = "English",
volume = "7",
pages = "2303--2314",
journal = "Arabian Journal of Geosciences",
issn = "1866-7511",
publisher = "Springer-Verlag London Ltd.",
number = "6",

}

Hasanzadehshooiili, H, Mahinroosta, R, Lakirouhani, A & Oshtaghi, V 2014, 'Using artificial neural network (ANN) in prediction of collapse settlements of sandy gravels', Arabian Journal of Geosciences, vol. 7, no. 6, pp. 2303-2314.

Using artificial neural network (ANN) in prediction of collapse settlements of sandy gravels. / Hasanzadehshooiili, H.; Mahinroosta, Reza; Lakirouhani, Ali; Oshtaghi, Vahid.

In: Arabian Journal of Geosciences, Vol. 7, No. 6, 2014, p. 2303-2314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using artificial neural network (ANN) in prediction of collapse settlements of sandy gravels

AU - Hasanzadehshooiili, H.

AU - Mahinroosta, Reza

AU - Lakirouhani, Ali

AU - Oshtaghi, Vahid

N1 - Imported on 12 Apr 2017 - DigiTool details were: Journal title (773t) = Arabian Journal of Geosciences. ISSNs: 1866-7511;

PY - 2014

Y1 - 2014

N2 - Collapse settlement is one of the main geotechnical hazards, which should be controlled during first impoundment stage in embankment dams. Imposing large deformations and significant damages to dams makes it an important phenomenon, which should be checked during design phases. Also, existence of a variety of contributing parameters in this phenomenon makes it difficult and complicated to well predict the potential of collapse settlement. Thus, artificial neural networks, which are commonly applied by majority of geotechnical engineers in predicting various perplexing problems, can be efficiently used to calculate the value of collapse settlement. In this paper, feedforward backpropagation neural networks are considered. And three-layered FFBPNNs with the architectures of 4–6–2 and 4–9–2 accurately predicted the coefficient of stress release and collapse settlement value, respectively. These networks were trained using 180 datasets gained from large-scale direct shear test, which were carried out on gravel materials. High correlation between measured and predicted values for both collapse settlement and coefficient of stress release can be easily understood from the coefficient of determination and root mean square error. It is shown that sand content and normal stress applied to the specimens, respectively, are most effective parameters on the collapse settlement value and coefficient of stress release.

AB - Collapse settlement is one of the main geotechnical hazards, which should be controlled during first impoundment stage in embankment dams. Imposing large deformations and significant damages to dams makes it an important phenomenon, which should be checked during design phases. Also, existence of a variety of contributing parameters in this phenomenon makes it difficult and complicated to well predict the potential of collapse settlement. Thus, artificial neural networks, which are commonly applied by majority of geotechnical engineers in predicting various perplexing problems, can be efficiently used to calculate the value of collapse settlement. In this paper, feedforward backpropagation neural networks are considered. And three-layered FFBPNNs with the architectures of 4–6–2 and 4–9–2 accurately predicted the coefficient of stress release and collapse settlement value, respectively. These networks were trained using 180 datasets gained from large-scale direct shear test, which were carried out on gravel materials. High correlation between measured and predicted values for both collapse settlement and coefficient of stress release can be easily understood from the coefficient of determination and root mean square error. It is shown that sand content and normal stress applied to the specimens, respectively, are most effective parameters on the collapse settlement value and coefficient of stress release.

KW - Large-scale direct shear test

KW - Artificial neural network

KW - Collapse settlement of gravels

KW - Coefficient of stress release

M3 - Article

VL - 7

SP - 2303

EP - 2314

JO - Arabian Journal of Geosciences

JF - Arabian Journal of Geosciences

SN - 1866-7511

IS - 6

ER -