[论文解读] A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
本文提出 NM-ROM,一种基于非线性流形的降阶模型,使用浅层带掩码自编码器来提升对对流主导问题的计算速度,辅以超降阶和物理信息训练。
Traditional linear subspace reduced order models (LS-ROMs) are able to accelerate physical simulations, in which the intrinsic solution space falls into a subspace with a small dimension, i.e., the solution space has a small Kolmogorov n-width. However, for physical phenomena not of this type, e.g., any advection-dominated flow phenomena, such as in traffic flow, atmospheric flows, and air flow over vehicles, a low-dimensional linear subspace poorly approximates the solution. To address cases such as these, we have developed a fast and accurate physics-informed neural network ROM, namely nonlinear manifold ROM (NM-ROM), which can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs. Our method takes advantage of the existing numerical methods that are used to solve the corresponding full order models. The efficiency is achieved by developing a hyper-reduction technique in the context of the NM-ROM. Numerical results show that neural networks can learn a more efficient latent space representation on advection-dominated data from 1D and 2D Burgers' equations. A speedup of up to 2.6 for 1D Burgers' and a speedup of 11.7 for 2D Burgers' equations are achieved with an appropriate treatment of the nonlinear terms through a hyper-reduction technique. Finally, a posteriori error bounds for the NM-ROMs are derived that take account of the hyper-reduced operators.
研究动机与目标
- 解决线性子空间ROM在对流主导或梯度尖锐问题中的局限性。
- 开发使用浅层带掩码自编码器进行解表示的非线性流形ROM(NM-ROM)。
- 利用超降阶在保持精度的同时加速 NM-ROM 的计算。
- 推导考虑超降阶算子影响的后验误差界。
- 在一维和二维 Burgers 方程上展示性能提升。
提出的方法
- 通过解码器 g 将低维潜在空间映射到全空间,在非线性流形上表示解。
- 使用浅层带掩码自编码器从 FOM 数据中学习非线性流形表示。
- 应用 NM-Galerkin 与 NM-LSPG 投影以获得降阶演化方程。
- 在时间步进过程中引入超降阶技术以高效评估非线性项。
- 使用解快照训练自编码器并对数据进行归一化以稳定学习。
- 推导将超降阶算子影响纳入考虑的后验误差界。
实验结果
研究问题
- RQ1在对流主导问题中,NM-ROM 能否以比 LS-ROM 更小的潜在维数实现准确逼近?
- RQ2超降阶在一维和二维情景中对 NM-ROM 的速度和精度有何影响?
- RQ3使用超降 NM-ROM 时的理论误差界是什么?
- RQ4在 NM-ROM 效率方面,浅层带掩码自编码器与更深的架构相比如何?
- RQ5非线性流形表示在保持守恒律和物理结构中扮演何种角色?
主要发现
- NM-ROM 能在对流主导数据(1D 与 2D Burgers 方程)上学习更高效的潜在空间表示。
- 在适当的非线性项超降阶下,1D Burgers 方程实现高达 2.6 的加速,2D Burgers 方程实现高达 11.7 的加速。
- 已经推导出考虑超降阶算子的 NM-ROM 后验误差界。
- 解码器是一个浅层带掩码网络,便于高效雅可比矩阵计算并与超降阶结合。
- 该方法利用现有的全量模型数值方法来约束代理并提高保真度。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。