当前位置: X-MOL 学术Comput. Struct. › 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.)
Estimating model inadequacy in ordinary differential equations with physics-informed neural networks
Computers & Structures ( IF 4.4 ) Pub Date : 2021-03-01 , DOI: 10.1016/j.compstruc.2020.106458
Felipe A.C. Viana , Renato G. Nascimento , Arinan Dourado , Yigit A. Yucesan

Abstract A number of physical systems can be described by ordinary differential equations. When physics is well understood, the time dependent responses are easily obtained numerically. The particular numerical method used for integration depends on the application. Unfortunately, when physics is not fully understood, the discrepancies between predictions and observed responses can be large and unacceptable. In this paper, we propose an approach that uses observed data to estimate the missing physics in the original model (i.e., model-form uncertainty). In our approach, we first design recurrent neural networks to perform numerical integration of the ordinary differential equations. Then, we implement the recurrent neural network as a directed graph. This way, the nodes in the graph represent the physics-informed kernels found in the ordinary differential equations. We quantify the missing physics by carefully introducing data-driven in the directed graph. This allows us to estimate the missing physics (discrepancy term) even for hidden nodes of the graph. We studied the performance of our proposed approach with the aid of three case studies (fatigue crack growth, corrosion-fatigue crack growth, and bearing fatigue) and state-of-the-art machine learning software packages. Our results demonstrate the ability to perform estimation of discrepancy, reducing gap between predictions and observations, at reasonable computational cost.

中文翻译:

使用物理信息神经网络估计常微分方程中的模型不足

摘要 许多物理系统可以用常微分方程来描述。当物理学被很好地理解时,随时间变化的响应很容易通过数值获得。用于积分的特定数值方法取决于应用。不幸的是,当物理学没有被完全理解时,预测和观察到的反应之间的差异可能会很大而且是不可接受的。在本文中,我们提出了一种方法,该方法使用观测数据来估计原始模型中缺失的物理特性(即模型形式的不确定性)。在我们的方法中,我们首先设计循环神经网络来执行常微分方程的数值积分。然后,我们将循环神经网络实现为有向图。这条路,图中的节点代表在常微分方程中发现的物理内核。我们通过在有向图中仔细引入数据驱动来量化缺失的物理。这使我们能够估计丢失的物理(差异项),即使是图的隐藏节点。我们借助三个案例研究(疲劳裂纹扩展、腐蚀疲劳裂纹扩展和轴承疲劳)和最先进的机器学习软件包来研究我们提出的方法的性能。我们的结果证明了以合理的计算成本执行差异估计的能力,减少预测和观察之间的差距。这使我们能够估计丢失的物理(差异项),即使对于图形的隐藏节点也是如此。我们借助三个案例研究(疲劳裂纹扩展、腐蚀疲劳裂纹扩展和轴承疲劳)和最先进的机器学习软件包来研究我们提出的方法的性能。我们的结果证明了以合理的计算成本执行差异估计的能力,减少预测和观察之间的差距。这使我们能够估计丢失的物理(差异项),即使是图的隐藏节点。我们借助三个案例研究(疲劳裂纹扩展、腐蚀疲劳裂纹扩展和轴承疲劳)和最先进的机器学习软件包来研究我们提出的方法的性能。我们的结果证明了以合理的计算成本执行差异估计的能力,减少预测和观察之间的差距。
更新日期:2021-03-01
down
wechat
bug