A framework for neural network based constitutive modelling of inelastic materials
A framework for neural network based constitutive modelling of inelastic materials
复制标题
DOI：
10.1016/j.cma.2023.116672
复制
发表时间：
2024-02
影响因子：
7.2
通讯作者：
W. Dettmer;Eugenio J. Muttio;R. Alhayki;Djordje Perić
中科院分区：
文献类型：
--
作者：
W. Dettmer;Eugenio J. Muttio;R. Alhayki;Djordje Perić
鉴于近年来在增层制造和材料工程方面取得的重大进展，新型材料或新型材料微结构正在快速发展。结构或结构部件的有限元分析需要一个描述新材料行为的本构模型。精确的本构方程通常是复杂而耗时的。因此，合适的机器学习策略可以用来使这个过程过时，并弥合实验数据和有限元分析之间的差距。在这项工作中，提出了一个通用的应力更新程序，适用于速率无关，弹性或非弹性，各向同性或各向异性材料行为的建模。所提出的策略是基于递归神经网络架构，必须在代表物理或数值实验的应力和应变数据序列上进行训练。提出了一种基于无梯度优化的训练策略。结果表明，分段线性行为，如单轴弹塑性，可以准确地表示。进一步的数值例子包括单轴损伤力学和平面应变条件下的弹塑性。提出了一种验证热力学一致性的有效准则，并将其应用于训练后的应力更新模型。该策略与基于GRU或LSTM的体系结构进行了比较，并显示出其优势。
Given the significant recent advances in added layer manufacturing and materials engineering, new types of materials or new material micro-structures are becoming available at a fast rate. The finite element analysis of structures or structural components requires a constitutive model that describes the behaviour of the new materials. The formulation of accurate constitutive equations is generally complex and time consuming. Hence, suitable machine learning strategies may be used to render this process obsolete and bridge the gap between experimental data and finite element analysis. In this work, a generic stress update procedure is presented that is suitable for the modelling of rate-independent, elastic or inelastic, isotropic or anisotropic material behaviour. The proposed strategy is based on a recurrent neural network architecture and must be trained on stress and strain data sequences that represent physical or numerical experiments. A training strategy based on gradient-free optimisation is presented. It is shown that piecewise linear behaviour, such as uniaxial elasto-plasticity, can be representedexactly. Further numerical examples include uniaxial damage mechanics and elasto-plasticity under plane strain conditions. An efficient criterion for the verification of thermodynamic consistency is proposed and applied to the trained stress update models. The strategy is compared to GRU or LSTM based architectures and shown to offer advantages.