Recurrent and Constructive‐Algorithm Networks For Sand Behavior Modeling

Abstract

This article presents and discusses various aspects regarding the modeling of the behavior of a coarse granular material using Recurrent Neural Networks (RNNs) and Constructive Algorithms (CAs). A series of undrained triaxial tests following compression stress paths was performed to develop the database for neural network training and testing, where the relative density (Dr) and the confining effective stress (σ3) were varied. The range of (Dr) and (σ3) values was selected to have both dilatant and compressive sand behaviors. Modeling of sand behavior is done using Cascade and Jordan’s network architectures. Several input functions, learning rules, and transfer functions are utilized to evaluate their effects on the accuracy achieved by both algorithms during the training and predicting stages as well as on the time employed to perform these tasks. It is also shown that for the case of cascade networks, when the full‐size network having two outputs (pore water pressure and deviatoric stress) is divided into two networks with only one output each, the accuracy of predictions is improved appreciably. The results, in terms of pore water pressure‐stress‐strain relationships, included in this article point out the great potential RNNs and CAs have to become another class of computational tools to solve complex problems in material modeling. Thus, it is conceivable that ANNs when properly trained on a comprehensive data set could be designed to model the behavior of soil materials under a variety of initial conditions and stress path trajectories.