Applying the Artificial Neural Network to Predict the Soil Responses in the DEM Simulation

Z. Li; J. K. Chow; Y. H. Wang

doi:10.1088/1757-899X/216/1/012040

Applying the Artificial Neural Network to Predict the Soil Responses in the DEM Simulation

Z. Li^*
, J. K. Chow
, Y. H. Wang

^*Corresponding author for this work

Hong Kong University of Science and Technology

Research output: Contribution to journal › Conference article › peer-review

7 Scopus citations

Abstract

This paper aims to bridge the soil properties and the soil response in the discrete element method (DEM) simulation using the artificial neural network (ANN). The network was designed to output the stress-strain-volumetric response from inputting the soil properties. 31 biaxial shearing tests with varying soil parameters were generated using the DEM simulations. Based on these 31 training samples, a three-layer neural network was established. 2 extra samples were generated to examine the validity of the network, and the predicted curves using the ANN were well matched with those from the DEM simulations. Overall, the ANN was found promising in effectively modelling the soil behaviour.

Original language	English
Article number	012040
Journal	IOP Conference Series: Materials Science and Engineering
Volume	216
Issue number	1
DOIs	https://doi.org/10.1088/1757-899X/216/1/012040
State	Published - 2 Jul 2017
Externally published	Yes
Event	2017 2nd International Conference on Civil Engineering and Materials Science, ICCEMS 2017 - Seoul, Korea, Republic of Duration: 26 May 2017 → 28 May 2017

Access to Document

10.1088/1757-899X/216/1/012040

Cite this

@article{f172e5153a464e88a86a1beda1c92340,

title = "Applying the Artificial Neural Network to Predict the Soil Responses in the DEM Simulation",

abstract = "This paper aims to bridge the soil properties and the soil response in the discrete element method (DEM) simulation using the artificial neural network (ANN). The network was designed to output the stress-strain-volumetric response from inputting the soil properties. 31 biaxial shearing tests with varying soil parameters were generated using the DEM simulations. Based on these 31 training samples, a three-layer neural network was established. 2 extra samples were generated to examine the validity of the network, and the predicted curves using the ANN were well matched with those from the DEM simulations. Overall, the ANN was found promising in effectively modelling the soil behaviour.",

author = "Z. Li and Chow, \{J. K.\} and Wang, \{Y. H.\}",

note = "Publisher Copyright: {\textcopyright} Published under licence by IOP Publishing Ltd.; 2017 2nd International Conference on Civil Engineering and Materials Science, ICCEMS 2017 ; Conference date: 26-05-2017 Through 28-05-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1088/1757-899X/216/1/012040",

language = "英语",

volume = "216",

journal = "IOP Conference Series: Materials Science and Engineering",

issn = "1757-8981",

publisher = "IOP Publishing Ltd.",

number = "1",

}

TY - JOUR

T1 - Applying the Artificial Neural Network to Predict the Soil Responses in the DEM Simulation

AU - Li, Z.

AU - Chow, J. K.

AU - Wang, Y. H.

N1 - Publisher Copyright: © Published under licence by IOP Publishing Ltd.

PY - 2017/7/2

Y1 - 2017/7/2

N2 - This paper aims to bridge the soil properties and the soil response in the discrete element method (DEM) simulation using the artificial neural network (ANN). The network was designed to output the stress-strain-volumetric response from inputting the soil properties. 31 biaxial shearing tests with varying soil parameters were generated using the DEM simulations. Based on these 31 training samples, a three-layer neural network was established. 2 extra samples were generated to examine the validity of the network, and the predicted curves using the ANN were well matched with those from the DEM simulations. Overall, the ANN was found promising in effectively modelling the soil behaviour.

AB - This paper aims to bridge the soil properties and the soil response in the discrete element method (DEM) simulation using the artificial neural network (ANN). The network was designed to output the stress-strain-volumetric response from inputting the soil properties. 31 biaxial shearing tests with varying soil parameters were generated using the DEM simulations. Based on these 31 training samples, a three-layer neural network was established. 2 extra samples were generated to examine the validity of the network, and the predicted curves using the ANN were well matched with those from the DEM simulations. Overall, the ANN was found promising in effectively modelling the soil behaviour.

UR - https://www.scopus.com/pages/publications/85025818112

U2 - 10.1088/1757-899X/216/1/012040

DO - 10.1088/1757-899X/216/1/012040

M3 - 会议文章

AN - SCOPUS:85025818112

SN - 1757-8981

VL - 216

JO - IOP Conference Series: Materials Science and Engineering

JF - IOP Conference Series: Materials Science and Engineering

IS - 1

M1 - 012040

T2 - 2017 2nd International Conference on Civil Engineering and Materials Science, ICCEMS 2017

Y2 - 26 May 2017 through 28 May 2017

ER -

Applying the Artificial Neural Network to Predict the Soil Responses in the DEM Simulation

Abstract

Access to Document

Other files and links

Fingerprint

Cite this