在石油回收过程中,在不混合和混合的多相流过程中产生的指纹不稳定性的物理信息神经网络模拟
1Department of Mathematics, Sardar Vallabhbhai National Institute of Technology, Surat, Gujarat, India.
Chaos (Woodbury, N.Y.)
|July 10, 2025
概括
基于物理学的神经网络 (PINNs) 提供了一个负担得起的深度学习解决方案,用于模拟流体动力学,特别是解决石油回收过程中的指纹不稳定性. 这种方法有效地模拟复杂的多相流程挑战.
科学领域:
- 流体动力学 流体动力学
- 计算科学 计算科学
- 人工智能的人工智能
背景情况:
- 流体动力学的传统数值和实验方法面临着复杂结构和物理模拟的挑战.
- 深度学习 (DL) 为处理流体动力学问题中的非线性和高维度提供了强大的能力.
- 指纹不稳定性是石油回收过程中多相流的现象,需要准确的模拟方法.
研究的目的:
- 开发和介绍一个使用物理信息的神经网络 (PINNs) 的深度学习框架,用于模拟石油回收中的指纹不稳定性.
- 研究二次石油回收过程中不混合的多相流和增强石油回收过程中可混合的位移 (EOR).
- 通过将结果与半分析溶液进行比较来验证PINNs的有效性.
主要方法:
- 利用物理信息的神经网络 (PINNs),这是一个深度学习框架,将物理定律 (部分微分方程) 集成到神经网络中.
- 开发了两种模型:一种用于二次石油回收 (不混合流) 和另一种用于增强石油回收 (混合流与碳酸水注入).
- 使用PINN框架解决了管理的非线性局部微分方程.
主要成果:
- 在二次和增强的石油回收场景中,PINNs在模拟指纹不稳定现象方面表现出有效性.
- 该框架成功模拟了多相流,包括不可混合和可混合的移位过程.
- 从PINNs获得的结果与现有的半分析解决方案有很好的一致性,验证了该方法.
结论:
- 基于物理学的神经网络 (PINNs) 为模拟复杂的流体动力学问题提供了一种有效且潜在的负担得起的方法,例如石油回收中的指纹不稳定性.
- 该研究强调了DL方法在解决传统数值和实验技术的局限性方面的潜力.
- 对用于流体流动和相关工程应用的PINNs进行进一步研究是有必要的.
相关概念视频
01:25Design Example: Flow of Oil Through Circular Pipes
186
Understanding fluid flow behavior through pipes is critical in fluid mechanics, especially in applications like oil transportation through pipelines. Hagen-Poiseuille's law provides an exact solution derived from the Navier-Stokes equations for steady, incompressible, and laminar flow within a circular pipe. Hagen-Poiseuille's law helps determine the necessary pressure drop across a pipeline section by determining parameters like pipe length, radius, oil viscosity, and the desired...
186
01:30Typical Model Studies
443
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
443
01:18Newtonian Fluid: Problem Solving
405
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...
405
01:11Pressure Variation in a Fluid at Rest
412
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...
412
01:34The Fluid Mosaic Model
153.9K
The fluid mosaic model was first proposed as a visual representation of research observations. The model comprises the composition and dynamics of membranes and serves as a foundation for future membrane-related studies. The model depicts the structure of the plasma membrane with a variety of components, which include phospholipids, proteins, and carbohydrates. These integral molecules are loosely bound, defining the cell’s border and providing fluidity for optimal function.
153.9K
01:14Pressure of Fluids
16.6K
There are many examples of pressure in fluids in everyday life, such as in relation to blood (high or low blood pressure) and in relation to weather (high- and low-pressure weather systems). A given force can have a significantly different effect, depending on the area over which the force is exerted. For instance, a force applied to an area of 1 mm2 has a pressure that is 100 times greater than the same force applied to an area of 1 cm2. That's why a sharp needle is able to poke through...
16.6K