Predicting the mechanical properties of biopolymer gels using neural networks trained on discrete fiber network data
Predicting the mechanical properties of biopolymer gels using neural networks trained on discrete fiber network data
复制标题
使用在离散纤维网络数据上训练的神经网络预测生物聚合物凝胶的机械性能
DOI：
10.1016/j.cma.2021.114160
复制
发表时间：
2021
影响因子：
7.2
通讯作者：
Tepole, Adrian B.
中科院分区：
文献类型：
--
作者：
Leng, Yue;Tac, Vahidullah;Calve, Sarah;Tepole, Adrian B.
生物聚合物凝胶，例如由纤维蛋白或胶原制成的那些，广泛用于组织工程应用和生物医学研究。此外，在伤口愈合和血栓形成过程中，纤维蛋白在体内自然地组装成凝胶蛋白。纤维蛋白和其他生物聚合物凝胶的宏观性质由微观纤维网络的响应决定。因此，生物聚合物凝胶的准确描述可以实现使用代表性体积元（RVE），明确地模拟离散的纤维网络的微观尺度。然而，这些RVE模型，不能有效地用于模拟宏观尺度由于多尺度耦合的挑战和计算需求。在这里，我们建议使用人工的全连接神经网络（FCNN）来有效地捕获RVE模型的行为。FCNN在1100个经历121个双轴变形的纤维网络上训练。来自RVE的应力数据，连同纤维上的总能量和周围基质的不可压缩性的条件，用于确定未知的应变能函数相对于变形不变量的导数。在训练过程中，修改损失函数以确保应变能函数的凸性和其Hessian的对称性。在Abaqus软件中将一般FCNN模型编码到用户材料子例程（UMAT）中。UMAT实现从输入文件中获取任意FCNN的结构和参数作为材料参数。FCNN的输入包括变形的前两个等容不变量。FCNN输出应变能相对于等容不变量的导数。在这项工作中，在离散纤维网络数据上训练的FCNN被用于使用我们的UMAT的生物聚合物凝胶的有限元模拟。我们预计，这项工作将使机器学习工具与计算力学进一步整合。它还将改进以多尺度结构为特征的生物材料的计算建模。
Biopolymer gels, such as those made out of fibrin or collagen, are widely used in tissue engineering applications and biomedical research. Moreover, fibrin naturally assembles into gelsin vivoduring wound healing and thrombus formation. The macroscale properties of fibrin and other biopolymer gels are dictated by the response of a microscale fiber network. Hence, accurate description of biopolymer gels can be achieved using representative volume elements (RVE) that explicitly model the discrete fiber networks of the microscale. These RVE models, however, cannot be efficiently used to model the macroscale due to the challenges and computational demands of multiscale coupling. Here, we propose the use of an artificial, fully connected neural network (FCNN) to efficiently capture the behavior of the RVE models. The FCNN was trained on 1100 fiber networks subjected to 121 biaxial deformations. The stress data from the RVE, together with the total energy on the fibers and the condition of incompressibility of the surrounding matrix, were used to determine the derivatives of an unknown strain energy function with respect to the deformation invariants. During training, the loss function was modified to ensure convexity of the strain energy function and symmetry of its Hessian. A general FCNN model was coded into a user material subroutine (UMAT) in the software Abaqus. The UMAT implementation takes in the structure and parameters of an arbitrary FCNN as material parameters from the input file. The inputs to the FCNN include the first two isochoric invariants of the deformation. The FCNN outputs the derivatives of the strain energy with respect to the isochoric invariants. In this work, the FCNN trained on the discrete fiber network data was used in finite element simulations of biopolymer gels using our UMAT. We anticipate that this work will enable further integration of machine learning tools with computational mechanics. It will also improve computational modeling of biological materials characterized by a multiscale structure.
登录
查看更多内容
软胶原组织的多凸各向异性应变-能量函数
影响因子：
3.5
作者：
M. Itskov;A. E. Ehret;D. Mavrilas
通讯作者：
D. Mavrilas
DOI：
10.1007/s11831-020-09405-5
发表时间：
2021-05
期刊：
Archives of computational methods in engineering : state of the art reviews
影响因子：
--
作者：
Peng GCY;Alber M;Tepole AB;Cannon WR;De S;Dura-Bernal S;Garikipati K;Karniadakis G;Lytton WW;Perdikaris P;Petzold L;Kuhl E
通讯作者：
Kuhl E
影响因子：
3.1
作者：
R. Ghanem;S. Wojtkiewicz
通讯作者：
S. Wojtkiewicz
基于图像的胶原组织等效物的生物力学
影响因子：
--
作者：
E. Sander;T. Stylianopoulos;R. Tranquillo;V. Barocas
通讯作者：
V. Barocas
DOI：
10.1073/pnas.2117675119
发表时间：
2022-05-31
影响因子：
11.1
作者：
通讯作者：
--