使用数据驱动模型来模拟表面活性剂在降低重油粘度方面的性能
Ehsan Hajibolouri1, Reza Najafi-Silab1, Amin Daryasafar2
1Department of Petroleum Engineering, Ahvaz Faculty of Petroleum, Petroleum University of Technology, Ahvaz, Iran.
Scientific reports
|November 12, 2024
概括
机器学习模型准确地预测重油乳液粘度,这对于增强石油回收 (EOR) 至关重要. 这种方法减少了对昂贵实验的需求,加速了非传统石油资源的开采.
科学领域:
- 石油工程是石油工程中的一个.
- 化学工程是化学工程的重要组成部分.
- 数据科学数据科学数据科学
背景情况:
- 非传统的重油储备对全球能源供应至关重要.
- 化学增强石油回收 (EOR) 使用表面活性剂来降低重油粘度,以方便提取.
- 模拟油在水 (O/W) 乳液粘度是优化EOR流程的关键.
研究的目的:
- 开发和优化机器学习 (ML) 模型,用于预测O/W乳液粘度.
- 评估各种ML算法在模拟乳液粘度方面的性能.
- 通过灵敏度分析确定影响乳液粘度的关键输入参数.
主要方法:
- 从现有文献中编制了2020年实验点的数据集.
- 使用了五种ML算法 (自适应提升,CNN,集体学习,ANN,决策树).
- 算法使用CSA (联合模拟化) 方法进行了优化.
- 蒙特卡洛灵敏度分析进行,以评估特征的重要性.
主要成果:
- 人工神经网络 (ANN) 模型在预测O/W乳液粘度方面表现出卓越的准确性.
- 在整个数据集中,ANN实现了高性能指标 (例如,R2=0.996,RMSE=0.0132).
- 灵敏度分析确定了影响乳液粘度的关键因素.
结论:
- ML,特别是ANN,提供了一个非常准确和高效的方法来预测O/W乳液粘度.
- 这种预测能力可以显著减少对耗时且昂贵的实验室实验的依赖.
- 开发的ML模型可以加快优化基于表面活性剂的EOR用于重油回收.
更多相关视频
06:31Studying Surfactant Effects on Hydrate Crystallization at Oil-Water Interfaces Using a Low-Cost Integrated Modular Peltier Device
Published on: March 18, 2020
6.3K
08:38Microfluidic Devices for Characterizing Pore-scale Event Processes in Porous Media for Oil Recovery Applications
Published on: January 16, 2018
10.4K
相关概念视频
01:30Typical Model Studies
340
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.
340
02:57Surface Tension, Capillary Action, and Viscosity
27.5K
Surface Tension
The various IMFs between identical molecules of a substance are examples of cohesive forces. The molecules within a liquid are surrounded by other molecules and are attracted equally in all directions by the cohesive forces within the liquid. However, the molecules on the surface of a liquid are attracted only by about one-half as many molecules. Because of the unbalanced molecular attractions on the surface molecules, liquids contract to form a shape that minimizes the number...
The various IMFs between identical molecules of a substance are examples of cohesive forces. The molecules within a liquid are surrounded by other molecules and are attracted equally in all directions by the cohesive forces within the liquid. However, the molecules on the surface of a liquid are attracted only by about one-half as many molecules. Because of the unbalanced molecular attractions on the surface molecules, liquids contract to form a shape that minimizes the number...
27.5K
01:09Theories of Dissolution: The Danckwerts' Model and Interfacial Barrier Model
275
Various dissolution theories provide insight into the factors that influence the dissolution rate. Danckwerts' Model suggests that turbulence, rather than a stagnant layer, characterizes the dissolution medium at the solid-liquid interface. In this model, the agitated solvent contains macroscopic packets that move to the interface via eddy currents, facilitating the absorption and delivery of the drug to the bulk solution. The regular replenishment of solvent packets maintains the...
275
03:22Colloids
17.4K
Children at play often make suspensions such as mixtures of mud and water, flour and water, or a suspension of solid pigments in water known as tempera paint. These suspensions are heterogeneous mixtures composed of relatively large particles that are visible to the naked eye or can be seen with a magnifying glass. They are cloudy, and the suspended particles settle out after mixing. On the other hand, a solution is a homogeneous mixture in which no settling occurs and in which the dissolved...
17.4K