An AI‐based model for describing cyclic characteristics of granular materials
- 4 March 2020
- journal article
- research article
- Published by Wiley in International Journal for Numerical and Analytical Methods in Geomechanics
- Vol. 44 (9) , 1315-1335
Abstract
Summary: Modelling cyclic behaviour of granular soils under both drained and undrained conditions with a good performance is still a challenge. This study presents a new way of modelling the cyclic behaviour of granular materials using deep learning. To capture the continuous cyclic behaviour in time dimension, the long short‐term memory (LSTM) neural network is adopted, which is characterised by the prediction of sequential data, meaning that it provides a novel means of predicting the continuous behaviour of soils under various loading paths. Synthetic datasets of cyclic loading under drained and undrained conditions generated by an advanced soil constitutive model are first employed to explore an appropriate framework for the LSTM‐based model. Then the LSTM‐based model is used to estimate the cyclic behaviour of real sands, ie, the Toyoura sand under the undrained condition and the Fontainebleau sand under both undrained and drained conditions. The estimates are compared with actual experimental results, which indicates that the LSTM‐based model can simultaneously simulate the cyclic behaviour of sand under both drained and undrained conditions, ie, (a) the cyclic mobility mechanism, the degradation of effective stress and large deformation under the undrained condition, and (b) shear strain accumulation and densification under the drained condition.Keywords
Funding Information
- National Natural Science Foundation of China (41630633, 41727802)
This publication has 55 references indexed in Scilit:
- Numerical modeling of changes in anisotropy during liquefaction using a generalized constitutive modelComputers and Geotechnics, 2012
- Bearing capacity under cyclic loading — offshore, along the coast, and on land. The 21st Bjerrum Lecture presented in Oslo, 23 November 2007This paper represents the written version of the 21st Bjerrum Lecture. While it has been edited for the present publication, it retains the general structure of the original lecture, which was intended for a general geotechnical audience. The Bjerrum Lecture is presented in Oslo in alternate years by the Norwegian Geotechnical Society with the support of the Bjerrum Memorial Fund (Laurits Bjerrums Minnefond).Canadian Geotechnical Journal, 2009
- Monotonic and cyclic behaviour of sand under torsional loadingGéotechnique, 2008
- SANISAND: Simple anisotropic sand plasticity modelInternational Journal for Numerical and Analytical Methods in Geomechanics, 2007
- Explanation of Cyclic Mobility of Soils: Approach by Stress-Induced AnisotropySoils and Foundations, 2007
- A new neural network‐based model for hysteretic behavior of materialsInternational Journal for Numerical Methods in Engineering, 2007
- Cyclic loading response of loose air-pluviated Fraser River sand for validation of numerical models simulating centrifuge testsCanadian Geotechnical Journal, 2005
- Selection of Methodology for Neural Network Modeling of Constitutive Hystereses Behavior of SoilsComputer-Aided Civil and Infrastructure Engineering, 2000
- Experimental Stress-Dilatancy Relations of Sand Subjected to Cyclic LoadingSoils and Foundations, 1989
- Incremental constitutive law for sands and clays: Simulations of monotonic and cyclic testsInternational Journal for Numerical and Analytical Methods in Geomechanics, 1982