arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.03729physics.comp-phphysics.flu-dyn
收藏

基于深度学习的地下水流模拟降阶建模

Deep-learning-based reduced-order modeling for subsurface flow simulation

Zhaoyang Larry Jin, Yimin Liu, Louis J. Durlofsky

摘要:

提出了一种新的基于深度学习的降阶建模(ROM)框架,用于地下水流模拟。降阶模型是基于现有的嵌入到控制(E2 C)框架,并包括一个自动编码器,它将系统投影到一个低维子空间,和一个线性过渡模型,它近似的系统状态在低维的演变。除了在原始E2 C框架中考虑的数据不匹配的损失函数之外,我们还引入了一个基于物理的损失函数,该函数惩罚与控制流方程不一致的预测。还修改损失函数以强调感兴趣的关键井量的准确性(例如,流体生产率)。E2 C ROM被证明是非常类似于现有的ROM,POD-TPWL,已被广泛开发的地下水流模拟。新的ROM应用于非均质油藏中的油水流动,其中流动由在时变控制规范下运行的九口井驱动。离线阶段共进行了300次高保真训练模拟,网络训练需要在Tesla V100 GPU节点上进行10-12分钟。在线(运行时)计算实现了相对于全阶仿真的$\mathcal{O}$(1000)的加速。广泛的测试用例结果,以及控制在大范围内变化,提出。精确的ROM预测实现了全球饱和度和压力场在特定的时间,并为注入和生产井响应作为时间的函数。当使用100或200次(而不是300次)训练运行来构建E2 C ROM时,错误会增加。

英文摘要:

A new deep-learning-based reduced-order modeling (ROM) framework is proposed for application in subsurface flow simulation. The reduced-order model is based on an existing embed-to-control (E2C) framework and includes an auto-encoder, which projects the system to a low-dimensional subspace, and a linear transition model, which approximates the evolution of the system states in low dimension. In addition to the loss function for data mismatch considered in the original E2C framework, we introduce a physics-based loss function that penalizes predictions that are inconsistent with the governing flow equations. The loss function is also modified to emphasize accuracy in key well quantities of interest (e.g., fluid production rates). The E2C ROM is shown to be very analogous to an existing ROM, POD-TPWL, which has been extensively developed for subsurface flow simulation. The new ROM is applied to oil-water flow in a heterogeneous reservoir, with flow driven by nine wells operating under time-varying control specifications. A total of 300 high-fidelity training simulations are performed in the offline stage, and the network training requires 10-12~minutes on a Tesla V100 GPU node. Online (runtime) computations achieve speedups of $\mathcal{O}$(1000) relative to full-order simulations. Extensive test case results, with well controls varied over large ranges, are presented. Accurate ROM predictions are achieved for global saturation and pressure fields at particular times, and for injection and production well responses as a function of time. Error is shown to increase when 100 or 200 (rather than 300) training runs are used to construct the E2C ROM.

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。

↑