相关实验视频

Updated: May 7, 2025

Dynamic Pore-scale Reservoir-condition Imaging of Reaction in Carbonates Using Synchrotron Fast Tomography

Dynamic Pore-scale Reservoir-condition Imaging of Reaction in Carbonates Using Synchrotron Fast Tomography

Published on: February 21, 2017

使用确定性智能工具来预测碳酸盐水库中智能注水的回收因子性能

Ali Maghsoudian¹, Amin Izadpanahi², Zahra Bahmani³

¹Department of Petroleum Engineering, Ahvaz Faculty of Petroleum, Petroleum University of Technology, Ahvaz, Iran.

Scientific reports

|January 2, 2025

概括

在智能注水 (SWI) 中预测石油回收对于增强石油回收 (EOR) 至关重要. 人工神经网络 (ANN) 在预测恢复因子方面表现优于其他方法,为复杂的水库管理提供了可靠的工具.

科学领域:

石油工程是石油工程中的一个.
储水库工程储水库工程
增强的石油回收 (EOR)

背景情况:

智能注水 (SWI) 是一种有效的增强石油回收 (EOR) 技术,利用生理化学机制提高排水效率.
在SWI中预测石油回收因子 (RF) 具有挑战性,原因是昂贵且耗时的实验方法.
开发可靠的预测工具对于优化碳酸盐储中的SWI应用至关重要.

研究的目的:

开发和比较预测算法,用于估计碳酸盐水库的智能水淹 (SWF) 中的石油回收因子 (RF).
评估适应性神经模糊推理系统 (ANFIS),人工神经网络 (ANN) 和多基因遗传编程 (MGGP) 对于射频预测的性能.
进行参数灵敏度分析,以确定影响SWF中RF的关键因素.

主要方法:

从现有的文献中收集了205个核心洪水和122个阿莫特细胞测试数据点.
使用输入参数开发和训练ANFIS,ANN和MGGP算法:孔隙性,透性,油粘度,油密度,注射速率,总溶解固体 (TDS),温度,注射时间和初始水和 (S).
使用确定系数 (R²) 验证了模型性能,并进行了参数灵敏度分析.

主要成果:

人工神经网络 (ANN) 与ANFIS和MGGP相比,在预测RF方面表现优越.
ANN实现了高R²值,阿莫特细胞数据的总分为0.9646,核心泛滥数据的总分为0.9523.
参数灵敏度分析表明,注射时间和速率在Amott-cell和核心泛滥测试中对RF产生积极影响,而TDS,油粘度,多孔性和透性显示出负面影响.

结论:

在碳酸盐水库的智能水淹没中,ANN是预测石油回收因素的高效工具.
开发的预测模型可以减少对广泛实验程序的依赖,节省时间和资源.
了解输入参数的灵敏度对于优化SWI策略和最大限度地回收石油至关重要.

关键词:

阿莫特细胞的细胞.人工智能的人工智能是人工智能.核心洪水核心洪水增强石油回收能力增强石油回收能力机器学习是机器学习.智能水淹没就是智能水淹没.

更多相关视频

Reservoir Condition Pore-scale Imaging of Multiple Fluid Phases Using X-ray Microtomography

Reservoir Condition Pore-scale Imaging of Multiple Fluid Phases Using X-ray Microtomography

Published on: February 25, 2015

Microfluidic Fabrication Techniques for High-Pressure Testing of Microscale Supercritical CO2 Foam Transport in Fractured Unconventional Reservoirs

Microfluidic Fabrication Techniques for High-Pressure Testing of Microscale Supercritical CO2 Foam Transport in Fractured Unconventional Reservoirs

Published on: July 2, 2020

相关概念视频

Design Example: Creating a Hydraulic Model of a Dam Spillway

Design Example: Creating a Hydraulic Model of a Dam Spillway

Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.

Typical Model Studies

Typical Model Studies

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.