Flexible and interpretable generalization of self-evolving computational materials framework
Flexible and interpretable generalization of self-evolving computational materials framework
复制标题
DOI：
10.1016/j.compstruc.2021.106706
复制
发表时间：
2021-11-17
影响因子：
4.7
通讯作者：
Cho, In Ho
中科院分区：
文献类型：
--
作者：
Bazroun, Mohammed;Yang, Yicheng;Cho, In Ho
最近通过机器学习（ML）方法对计算材料模型的创新面临着巨大的挑战。将内部异质性和不同的边界条件（BC）扩展到现有的ML方法中仍然很困难，ML的弱可解释性仍然没有得到解决。为了应对这些挑战，本文概括了最近开发的基于贝叶斯更新和进化算法的自进化计算材料模型框架。本文提出了一种新的材料特定的信息指数（II），这是能够自主量化的内部异质性和不同的BC的。此外，本文介绍了高度灵活的三次回归样条（CRS）为基础的链接函数，它可以提供数学表达式的显着材料系数的现有计算材料模型的卷积II。因此，本文提出了一种新的方法，通过这种方法，ML可以直接利用内部异质性和不同的BC，在保持可解释性的同时自主地演化计算材料模型。使用大范围的大型增强复合材料结构的验证确认的泛化的良好性能。准脆性材料的非线性剪切和钢筋的渐进压缩屈曲的例子扩展，加强了概括的效率和准确性。本文为加速计算材料模型和ML的融合增加了一条有意义的途径。(c)2021爱思唯尔有限公司保留所有权利。
The recent innovations of computational material models by machine learning (ML) methods face formidable challenges. Incorporating internal heterogeneity and diverse boundary conditions (BC's) into existing ML methods remains difficult, and the weak interpretability of ML remains unresolved. To tackle these challenges, this paper generalizes a recently developed self-evolving computational material models framework built upon Bayesian update and evolutionary algorithm. This paper proposes a new material-specific information index (II), which is capable of autonomously quantifying the internal heterogeneity and diverse BC's. Also, this paper introduces highly flexible cubic regression spline (CRS)-based link functions which can offer mathematical expressions of salient material coefficients of the existing computational material models in terms of convolved II. Thereby, this paper suggests a novel means by which ML can directly leverage internal heterogeneity and diverse BC's to autonomously evolve computational material models while keeping interpretability. Validations using a wide spectrum of large-scale reinforced composite structures confirm the favorable performance of the generalization. Example expansions of nonlinear shear of quasi-brittle materials and progressive compressive buckling of reinforcing steel underpin efficiency and accuracy of the generalization. This paper adds a meaningful avenue for accelerating the fusion of computational material models and ML. (c) 2021 Elsevier Ltd. All rights reserved.