当前位置: X-MOL 学术Comput. Methods Appl. Mech. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks
Computer Methods in Applied Mechanics and Engineering ( IF 7.2 ) Pub Date : 2021-10-20 , DOI: 10.1016/j.cma.2021.114217
Jan N. Fuhg 1 , Michele Marino 2 , Nikolaos Bouklas 1, 3
Affiliation  

Hierarchical computational methods for multiscale mechanics such as the FE2 and FE-FFT methods are generally accompanied by high computational costs. Data-driven approaches are able to speed the process up significantly by enabling to incorporate the effective micromechanical response in macroscale simulations without the need of performing additional computations at each Gauss point explicitly. Traditionally artificial neural networks (ANNs) have been the surrogate modeling technique of choice in the solid mechanics community. However they suffer from severe drawbacks due to their parametric nature and suboptimal training and inference properties for the investigated datasets in a three dimensional setting. These problems can be avoided using local approximate Gaussian process regression (laGPR). This method can allow the prediction of stress outputs at particular strain space locations by training local regression models based on Gaussian processes, using only a subset of the data for each local model, offering better and more reliable accuracy than ANNs. A modified Newton–Raphson approach specific to laGPR is proposed to accommodate for the local nature of the laGPR approximation when solving the global structural problem in a FE setting. Hence, the presented work offers a complete and general framework enabling multiscale calculations combining a data-driven constitutive prediction using laGPR, and macroscopic calculations using an FE scheme that we test for finite-strain three-dimensional hyperelastic problems.



中文翻译:

数据驱动本构模型的局部近似高斯过程回归:开发和与神经网络的比较

多尺度力学的分层计算方法,例如 有限元2和 FE-FFT 方法通常伴随着高计算成本。数据驱动的方法能够通过在宏观模拟中结合有效的微机械响应,而无需在每个高斯点明确执行额外计算,从而显着加快过程。传统上,人工神经网络 (ANN) 一直是固体力学社区中首选的替代建模技术。然而,由于它们的参数性质以及在三维设置中对调查数据集的次优训练和推理特性,它们存在严重缺陷。使用局部近似高斯过程回归 (laGPR) 可以避免这些问题。这种方法可以通过训练基于高斯过程的局部回归模型来预测特定应变空间位置的应力输出,仅使用每个局部模型的数据子集,提供比 ANN 更好、更可靠的精度。提出了一种特定于 laGPR 的修改后的 Newton-Raphson 方法,以在解决有限元环境中的全局结构问题时适应 laGPR 近似的局部性质。因此,所提出的工作提供了一个完整的通用框架,能够结合使用 laGPR 的数据驱动本构预测和使用有限应变三维超弹性问题测试的有限元方案的宏观计算进行多尺度计算。提供比人工神经网络更好、更可靠的准确性。提出了一种特定于 laGPR 的修改后的 Newton-Raphson 方法,以在解决有限元环境中的全局结构问题时适应 laGPR 近似的局部性质。因此,所提出的工作提供了一个完整的通用框架,能够结合使用 laGPR 的数据驱动本构预测和使用有限应变三维超弹性问题测试的有限元方案的宏观计算进行多尺度计算。提供比人工神经网络更好、更可靠的准确性。提出了一种特定于 laGPR 的修改后的 Newton-Raphson 方法,以在解决有限元环境中的全局结构问题时适应 laGPR 近似的局部性质。因此,所提出的工作提供了一个完整的通用框架,能够结合使用 laGPR 的数据驱动本构预测和使用有限应变三维超弹性问题测试的有限元方案的宏观计算进行多尺度计算。

更新日期:2021-10-20
down
wechat
bug