arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.06361math.NAcs.NA
收藏

在大规模动力系统的数据驱动降阶建模中保持 Lagrange 结构

Preserving Lagrangian structure in data-driven reduced-order modeling of large-scale dynamical systems

Harsh Sharma, Boris Kramer

AI总结:

本文提出非侵入式的 Lagrangian operator inference 方法,仅利用方程形式与投影快照学习保持 Lagrange 结构的 ROM,并在梁、非线性波动方程及大规模软体机器人问题上验证其精度与泛化性。

摘要:

本工作提出了一种非侵入式的物理保持方法,用于学习 Lagrange 系统的降阶模型(ROM),这类系统包括非线性波动方程。现有的侵入式基于投影的模型降阶方法通过将全阶模型(FOM)的 Euler–Lagrange 方程投影到线性子空间,来构造保持结构的 Lagrange ROM。这一 Galerkin 投影步骤需要完整了解 FOM 中的 Lagrange 算子,并拥有操作计算机代码的完全权限。相比之下,本文提出的 Lagrangian operator inference(Lagrange 算子推断)方法将力学机制嵌入 operator inference 框架,从而开发出一种保持底层 Lagrange 结构的数据驱动模型降阶方法。所提方法利用控制方程(而非其离散化)的知识来定义 Lagrange ROM 的形式和参数化,随后即可从投影快照数据中学习该模型。该方法不需要访问 FOM 算子或计算机代码。数值结果在 Euler–Bernoulli 梁模型、sine-Gordon(非线性)波动方程以及具有 779,232 个自由度的软体机器人鱼尾大规模离散化问题上展示了 Lagrangian operator inference。学习得到的 Lagrange ROM 具有良好的泛化能力,因为它们既能在远超出训练时间区间的范围内准确预测物理解,也能针对未见过的初始条件进行准确预测。

英文摘要:

This work presents a nonintrusive physics-preserving method to learn reduced-order models (ROMs) of Lagrangian systems, which includes nonlinear wave equations. Existing intrusive projection-based model reduction approaches construct structure-preserving Lagrangian ROMs by projecting the Euler-Lagrange equations of the full-order model (FOM) onto a linear subspace. This Galerkin projection step requires complete knowledge about the Lagrangian operators in the FOM and full access to manipulate the computer code. In contrast, the proposed Lagrangian operator inference approach embeds the mechanics into the operator inference framework to develop a data-driven model reduction method that preserves the underlying Lagrangian structure. The proposed approach exploits knowledge of the governing equations (but not their discretization) to define the form and parametrization of a Lagrangian ROM which can then be learned from projected snapshot data. The method does not require access to FOM operators or computer code. The numerical results demonstrate Lagrangian operator inference on an Euler-Bernoulli beam model, the sine-Gordon (nonlinear) wave equation, and a large-scale discretization of a soft robot fishtail with 779,232 degrees of freedom. The learned Lagrangian ROMs generalize well, as they can accurately predict the physical solutions both far outside the training time interval, as well as for unseen initial conditions.

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。

↑