arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.04554cs.CEcs.AIstat.ML
收藏

数据驱动本构律的局部近似高斯过程回归:发展和与神经网络的比较

Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks

Cornell University(康奈尔大学);University of Rome Tor Vergata(罗马第二大学)

Jan Niklas Fuhg, Michele Marino, Nikolaos Bouklas

摘要:

多尺度力学的分层计算方法,如FE $^2$和FE-FFT方法,通常伴随着高的计算成本。数据驱动的方法能够通过将有效的微观力学响应纳入宏观模拟而无需在每个高斯点显式执行额外的计算来显着加快过程。传统上,人工神经网络(ANN)一直是固体力学界选择的替代建模技术。然而,他们遭受严重的缺点,由于其参数的性质和次优的训练和推理属性的调查数据集在三维设置。这些问题可以避免使用局部近似高斯过程回归(laGPR)。该方法可以通过基于高斯过程训练局部回归模型来预测特定应变空间位置处的应力输出,仅使用每个局部模型的数据的子集,提供比ANN更好和更可靠的精度。提出了一种改进的Newton-Raphson方法,以适应在有限元环境中求解全局结构问题时LAGPR近似的局部性质。因此,所提出的工作提供了一个完整的和一般的框架,使多尺度计算相结合的数据驱动的本构预测使用laGPR,和宏观计算使用有限元方案,我们测试有限应变三维超弹性问题。

英文摘要:

Hierarchical computational methods for multiscale mechanics such as the FE$^2$ 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 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.

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。

↑