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

2nd International Conference on Civil Engineering and Materials Science

Li, Z.^1 ; Chow, J.K.^1 ; Wang, Y.H.^1

Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong^1

关键词: DEM Simulation;    Shearing tests;    Soil behaviour;    Soil parameters;    Soil response;    Three-layer neural networks;    Training sample;    Volumetric response;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/216/1/012040/pdf
DOI  :  10.1088/1757-899X/216/1/012040

来源: IOP

【 摘 要 】

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.