arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00265math.NAcs.NA
收藏

利用对称正定神经网络学习本构关系

Learning Constitutive Relations using Symmetric Positive Definite Neural Networks

Kailai Xu, Daniel Z. Huang, Eric Darve

摘要:

提出了一种用于动力学方程本构关系建模的Cholesky因子对称正定神经网络(SPD-NN)。SPD-NN不是直接预测应力,而是训练神经网络来预测切线刚度矩阵的Cholesky因子,基于该因子以增量形式计算应力。由于SPD-NN的特殊结构,使得其应变能函数具有弱凸性,满足路径相关材料的时间相容性,从而提高了数值稳定性,尤其是当SPD-NN用于有限元模拟时。根据可用数据的类型,我们提出了两种训练方法,即应变和应力对的直接训练和载荷和位移对的间接训练。我们证明了SPD-NN的有效性超弹性,弹塑性,和多尺度纤维增强板问题从固体力学。SPD-NN的通用性和鲁棒性使其成为广泛的本构建模应用的有前途的工具。

英文摘要:

We present the Cholesky-factored symmetric positive definite neural network (SPD-NN) for modeling constitutive relations in dynamical equations. Instead of directly predicting the stress, the SPD-NN trains a neural network to predict the Cholesky factor of a tangent stiffness matrix, based on which the stress is calculated in the incremental form. As a result of the special structure, SPD-NN weakly imposes convexity on the strain energy function, satisfies time consistency for path-dependent materials, and therefore improves numerical stability, especially when the SPD-NN is used in finite element simulations. Depending on the types of available data, we propose two training methods, namely direct training for strain and stress pairs and indirect training for loads and displacement pairs. We demonstrate the effectiveness of SPD-NN on hyperelastic, elasto-plastic, and multiscale fiber-reinforced plate problems from solid mechanics. The generality and robustness of the SPD-NN make it a promising tool for a wide range of constitutive modeling applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑