通过稀疏的观测和以物理为基础的PointNet预测多孔介质中的流体流
1Department of Civil and Environmental Engineering, Stanford University, Stanford, CA 94305, United States of America.
概括
我们介绍了基于物理的PointNet (PIPN),这是一个用于预测多孔介质中的流体流动的新型神经网络. 通过仅使用孔空间数据,PIPN有效地建模了孔尺度流,减少了内存需求和计算成本.
科学领域:
- 计算流体动力学的流体动力学.
- 孔隙介质物理学的物理
- 机器学习应用程序 机器学习应用程序
背景情况:
- 在多孔介质中预测液体流动对于各种科学和工程领域至关重要.
- 传统方法通常需要大量的计算资源和详细的几何信息.
- 基于物理学的神经网络 (PINNs) 通过将物理定律整合到神经网络训练中,提供了一个有前途的替代方案.
研究的目的:
- 开发和评估一个新的基于物理的神经网络,即基于物理的PointNet (PIPN),用于预测在孔尺度上的稳定状态Stokes流.
- 利用PIPN的独特特性,提高多孔介质模拟的效率和准确性.
- 评估噪音数据和不同空间分辨率对PIPN性能的影响.
主要方法:
- 实现了一种针对多孔介质而定制的基于物理的新型神经网络架构 (PIPN).
- 利用孔隙空间内的流体流动的稀疏点观测.
- 通过分析输入要求,边界表示和空间分辨率灵活性,比较PIPN与基于物理的卷积神经网络 (PICNNs).
- 在有噪音传感器数据,压力观测和不同空间相关长度的条件下评估性能.
主要成果:
- 与使用孔隙和粒隙空间的方法相比,PIPN仅使用孔隙空间数据,大大降低了计算内存需求.
- PIPN提供了孔隙空间边界的平滑和现实的表示,超越了像素智能的方法.
- 可变空间分辨率功能允许优化计算成本和有针对性的高分辨率分析.
- 该框架证明了对噪音传感器数据和压力观测的稳定性.
结论:
- 在模拟多孔介质中的孔尺度流体流动方面,PIPN代表了重大进步.
- 它的独特功能提供了实质性的计算优势和更好的表示准确性.
- 对于研究复杂的多孔结构中的流体动力学研究人员来说,PIPN提供了一个灵活而高效的工具.
相关概念视频
01:23Plane Potential Flows
416
Plane potential flows simplify fluid motion by assuming the fluid to be irrotational and incompressible. These characteristics allow these flows to be described by a velocity potential function, ϕ, representing the flow speed in a given direction, and a stream function, ψ, that visualizes the flow path, both governed by Laplace's equation. These parameters help in estimating flow patterns, velocity distributions, and pressure fields around various hydraulic structures.
Uniform...
Uniform...
416
01:18Newtonian Fluid: Problem Solving
258
Newtonian fluids exhibit a constant viscosity, meaning their shear stress and shear strain rate are directly proportional. This property ensures a predictable and stable response to applied forces, maintaining a linear relationship between force and flow. Examples include water, air, and light oils, consistently demonstrating this proportional behavior regardless of external conditions.
A velocity gradient forms within the fluid when a Newtonian fluid is placed between two parallel plates, with...
A velocity gradient forms within the fluid when a Newtonian fluid is placed between two parallel plates, with...
258
01:18Uniform Depth Channel Flow: Problem Solving
85
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
85
01:11Pressure Variation in a Fluid at Rest
292
In a fluid at rest, the pressure at any point beneath the fluid surface depends solely on the depth, not on the container's shape or size. This principle, known as hydrostatic pressure, arises because, in stationary fluids, there is no acceleration, meaning the forces within the fluid balance out. Only vertical forces, caused by the weight of the fluid above, contribute to pressure changes with depth.
When measuring pressure at two different levels within the fluid, the difference in...
When measuring pressure at two different levels within the fluid, the difference in...
292
01:19Capillarity in Fluid
249
Capillarity describes the movement of liquid in small spaces without external forces acting on it. The capillarity is driven by surface tension and adhesive interactions between the liquid and surrounding solid surfaces. This effect is often seen in narrow tubes, porous materials, and fine particles.
Surface tension is crucial to capillarity. It results from cohesive forces between liquid molecules at the liquid-air boundary, forming a skin that resists external forces. When the capillary tube...
Surface tension is crucial to capillarity. It results from cohesive forces between liquid molecules at the liquid-air boundary, forming a skin that resists external forces. When the capillary tube...
249
01:07Laminar and Turbulent Flow
8.6K
Fluid dynamics is the study of fluids in motion. Velocity vectors are often used to illustrate fluid motion in applications like meteorology. For example, wind—the fluid motion of air in the atmosphere—can be represented by vectors indicating the speed and direction of the wind at any given point on a map. Another method for representing fluid motion is a streamline. A streamline represents the path of a small volume of fluid as it flows. When the flow pattern changes with time, the...
8.6K