Tongming Qu¹, Shaocheng Di², Y. T. Feng^1,3,*, Min Wang⁴, Tingting Zhao³, Mengqi Wang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.128, No.1, pp. 129-144, 2021, DOI:10.32604/cmes.2021.016172 - 28 June 2021

Abstract This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling (DEM) and deep learning. A constitutive learning strategy is proposed based on the generally accepted frame-indifference assumption in constructing material constitutive models. The low-dimensional principal stress-strain sequence pairs, measured from discrete element modelling of triaxial testing, are used to train recurrent neural networks, and then the predicted principal stress sequence is augmented to other high-dimensional or general stress tensor via coordinate transformation. Through detailed hyperparameter investigations, it is found that long short-term More >

D. Manzanal^1,2, M. Pastor^2,3, J.A. Fern,ez Merodo⁴, P. Mira^2,3

CMES-Computer Modeling in Engineering & Sciences, Vol.55, No.3, pp. 293-318, 2010, DOI:10.3970/cmes.2010.055.293

Abstract This paper presents an extension of the Generalized Plasticity model proposed by Pastor - Zienkiewicz in 1986. The extension is based on (i) incorporating a state dependant parameter to model the mechanical behaviour of sand under a wide range of relative densities and confining pressures (ii) the definition of the effective stress of Schrefler (1984) modified to obtain unique CSL for different suction and (iii) the work conjugated variable proposed by Houlsby (1997). Several examples are presented for saturated and unsaturated soils. More >