Geoenergy Science and Engineering最新文献_第7页

Intelligent optimization of horizontal wellbore trajectory based on reinforcement learning 基于强化学习的水平井筒轨迹智能优化

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213479

Shihui Sun , Yanwen Gao , Xiaofeng Sun , Jun Wu , Huilin Chang

Ultra-long horizontal wells are crucial for improving the production and developmental benefits of shale oil and gas wells. Currently, advanced downhole semi-closed-loop steering drilling technology depends on a dual communication mechanism between the surface and downhole, as well as the empirical decisions of human experts. However, it is difficult to acutely control the trajectory of ultra-long horizontal open hole drilling in a reservoir owing to geological uncertainties related to shale oil and gas, the uncertainty of the drilling tool's building capacity, and the lag of measurement information while drilling. This report proposes an adaptive target detection and design method for ultra-long horizontal well trajectories based on reinforcement learning. The developed approach enables dynamic identification of reservoir sequences according to logging-while-drilling data and prediction of horizontal targets in real-time, with a recognition accuracy of 90.1%. Additionally, measurement-while-drilling data are used to accurately characterize the depth, inclination, and azimuth of the target-entering process. The dynamic interaction mechanism between the bit and the target environment is simulated by defining the bit action, reward function, and an update mechanism. The drilling engineering conditions restrict the interactions, such that the bit automatically decides the direction in which to drill the targets, demonstrating 100% accuracy for the wellbore trajectory toward the target. The experimental application results indicate that the developed method can be applied to determine the dynamic target area of a horizontal well in real time and make intelligent downhole decisions regarding ultra-long horizontal section borehole trajectory adjustments while drilling and measuring. The drilling rate of high-quality reservoirs is therefore significantly improved. The results discussed herein provide insights to support further developments of downhole full-closed-loop intelligent autonomous decision-making borehole trajectory control.

超长水平井对于提高页岩油气井的产量和开发效益至关重要。目前，先进的井下半闭环转向钻井技术依赖于地面和井下的双重通信机制，以及人类专家的经验决策。然而，由于页岩油气相关地质的不确定性、钻具建造能力的不确定性以及钻井过程中测量信息的滞后性，很难精确控制储层中超长水平裸眼钻井的轨迹。本报告提出了一种基于强化学习的超长水平井轨迹自适应目标检测和设计方法。所开发的方法能够根据边钻井边测井数据动态识别储层序列，并实时预测水平目标，识别精度高达 90.1%。此外，边钻井边测量数据可用于准确描述目标进入过程的深度、倾角和方位角。通过定义钻头动作、奖励函数和更新机制，模拟了钻头与目标环境之间的动态交互机制。钻井工程条件限制了相互作用，从而使钻头自动决定钻进目标的方向，证明了向目标钻进的井筒轨迹具有 100% 的准确性。实验应用结果表明，所开发的方法可用于实时确定水平井的动态目标区域，并在钻井和测量过程中对超长水平段井眼轨迹调整做出智能井下决策。因此，高质量储层的钻井速度得到显著提高。本文讨论的结果为进一步开发井下全闭环智能自主决策井眼轨迹控制提供了启示。

{"title":"Intelligent optimization of horizontal wellbore trajectory based on reinforcement learning","authors":"Shihui Sun , Yanwen Gao , Xiaofeng Sun , Jun Wu , Huilin Chang","doi":"10.1016/j.geoen.2024.213479","DOIUrl":"10.1016/j.geoen.2024.213479","url":null,"abstract":"<div><div>Ultra-long horizontal wells are crucial for improving the production and developmental benefits of shale oil and gas wells. Currently, advanced downhole semi-closed-loop steering drilling technology depends on a dual communication mechanism between the surface and downhole, as well as the empirical decisions of human experts. However, it is difficult to acutely control the trajectory of ultra-long horizontal open hole drilling in a reservoir owing to geological uncertainties related to shale oil and gas, the uncertainty of the drilling tool's building capacity, and the lag of measurement information while drilling. This report proposes an adaptive target detection and design method for ultra-long horizontal well trajectories based on reinforcement learning. The developed approach enables dynamic identification of reservoir sequences according to logging-while-drilling data and prediction of horizontal targets in real-time, with a recognition accuracy of 90.1%. Additionally, measurement-while-drilling data are used to accurately characterize the depth, inclination, and azimuth of the target-entering process. The dynamic interaction mechanism between the bit and the target environment is simulated by defining the bit action, reward function, and an update mechanism. The drilling engineering conditions restrict the interactions, such that the bit automatically decides the direction in which to drill the targets, demonstrating 100% accuracy for the wellbore trajectory toward the target. The experimental application results indicate that the developed method can be applied to determine the dynamic target area of a horizontal well in real time and make intelligent downhole decisions regarding ultra-long horizontal section borehole trajectory adjustments while drilling and measuring. The drilling rate of high-quality reservoirs is therefore significantly improved. The results discussed herein provide insights to support further developments of downhole full-closed-loop intelligent autonomous decision-making borehole trajectory control.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213479"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigating formation water variability in the Búzios oilfield (Santos Basin) using cluster analysis and hydrogeochemical modeling 利用聚类分析和水文地质化学模型调查布齐奥斯油田（桑托斯盆地）的地层水变异性

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213468

Felipe Ferreira Luiz Gorla , Jordão Douglas de Lima Nogueira , Saulo Bortolini dos Santos , Rosane Alves Fontes , Luiz Alexandre Sacorague , André Henrique , Rafaella Magliano Balbi de Faria , Valtair Marcos Cristante , Cleyton de Carvalho Carneiro , Rodrigo César Teixeira de Gouvêa , Henrique Luiz de Barros Penteado

The characteristics of formation waters play a crucial role in production development projects within Pre-Salt oil fields in the Santos Basin, offshore southeastern Brazil. This study investigated the compositional variations of brines of the Búzios Field (northeast of the Santos Basin), proposing for the first time an extensive hydrochemical mapping of the Pre-Salt aquifers and identifying nuances of connectivity. A comprehensive methodology was employed, including analysis of pressure gradients, cluster analysis, and hydrogeochemical modeling to classify different types of brine and understand their behavior under reservoir conditions. A hydrochemical classification routine was applied to 129 formation water samples, identifying seven distinct clusters using the unsupervised k-means algorithm. This clustering process efficiently differentiated representative, non-representative, and contaminated samples. The hydrochemical composition of the formation waters varied among the four hydraulic compartments identified in the field, with their boundaries defined by permeability barriers. Compared with the central portion of the field (regional aquifer), where salinities predominantly range from 155,000 to 185,000 mg/L of NaCl, enrichment of specific ions was observed at the field's extremities, such as boron (northeast), barium and lithium (north), and bicarbonate (west). These hydrochemical differences lead the brine salinities at the field's extremities to exceed 225,000 mg/L of NaCl. Hydrogeochemical modeling provided insights into the pH levels of each brine under reservoir conditions, showing a decrease of between 23 and 32% compared to surface pH values. The speciation analysis showed positive strontianite and barite saturation indices in certain types of formation water, indicating potential precipitation. These areas are considered critical for inorganic scaling in production equipment.

地层水的特征在巴西东南部近海桑托斯盆地盐前油田的生产开发项目中起着至关重要的作用。本研究调查了布齐奥斯油田（桑托斯盆地东北部）卤水的成分变化，首次提出了盐前含水层的广泛水化学绘图，并确定了连接性的细微差别。研究采用了一种综合方法，包括压力梯度分析、聚类分析和水文地球化学建模，对不同类型的卤水进行分类，并了解它们在储层条件下的行为。对 129 个地层水样本进行了水化学分类，使用无监督 k-means 算法识别出七个不同的聚类。该聚类过程可有效区分代表性样本、非代表性样本和污染样本。地层水的水化学成分在油田确定的四个水力区块中各不相同，其边界由渗透障碍确定。油田中部（区域含水层）的盐度主要介于 155,000 至 185,000 毫克/升的氯化钠之间，与此相比，在油田的两端观察到特定离子的富集，如硼（东北部）、钡和锂（北部）以及碳酸氢盐（西部）。这些水化学差异导致油气田最北端的盐水含盐量超过 225,000 毫克/升的氯化钠。水文地质化学模型提供了在储层条件下每种盐水的 pH 值，与地表 pH 值相比，pH 值下降了 23% 至 32%。标样分析表明，在某些类型的地层水中，锶铁矿和重晶石饱和度指数呈正值，表明可能存在沉淀。这些区域被认为是生产设备无机结垢的关键区域。

{"title":"Investigating formation water variability in the Búzios oilfield (Santos Basin) using cluster analysis and hydrogeochemical modeling","authors":"Felipe Ferreira Luiz Gorla , Jordão Douglas de Lima Nogueira , Saulo Bortolini dos Santos , Rosane Alves Fontes , Luiz Alexandre Sacorague , André Henrique , Rafaella Magliano Balbi de Faria , Valtair Marcos Cristante , Cleyton de Carvalho Carneiro , Rodrigo César Teixeira de Gouvêa , Henrique Luiz de Barros Penteado","doi":"10.1016/j.geoen.2024.213468","DOIUrl":"10.1016/j.geoen.2024.213468","url":null,"abstract":"<div><div>The characteristics of formation waters play a crucial role in production development projects within Pre-Salt oil fields in the Santos Basin, offshore southeastern Brazil. This study investigated the compositional variations of brines of the Búzios Field (northeast of the Santos Basin), proposing for the first time an extensive hydrochemical mapping of the Pre-Salt aquifers and identifying nuances of connectivity. A comprehensive methodology was employed, including analysis of pressure gradients, cluster analysis, and hydrogeochemical modeling to classify different types of brine and understand their behavior under reservoir conditions. A hydrochemical classification routine was applied to 129 formation water samples, identifying seven distinct clusters using the unsupervised k-means algorithm. This clustering process efficiently differentiated representative, non-representative, and contaminated samples. The hydrochemical composition of the formation waters varied among the four hydraulic compartments identified in the field, with their boundaries defined by permeability barriers. Compared with the central portion of the field (regional aquifer), where salinities predominantly range from 155,000 to 185,000 mg/L of NaCl, enrichment of specific ions was observed at the field's extremities, such as boron (northeast), barium and lithium (north), and bicarbonate (west). These hydrochemical differences lead the brine salinities at the field's extremities to exceed 225,000 mg/L of NaCl. Hydrogeochemical modeling provided insights into the pH levels of each brine under reservoir conditions, showing a decrease of between 23 and 32% compared to surface pH values. The speciation analysis showed positive strontianite and barite saturation indices in certain types of formation water, indicating potential precipitation. These areas are considered critical for inorganic scaling in production equipment.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213468"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Experimental investigation on enhanced oil recovery by hydraulic pulsating wave driving 水力脉动波驱动提高石油采收率的实验研究

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213477

Feipeng Wu , Yunpeng Song , Na Li , Jing Liu

An experimental investigation was conducted to study the mechanism of enhancing oil recovery using hydraulic pulsating flooding in high water cut reservoirs. The study involved a series of laboratory experiments using both a visual rectangular glass bead-packed physical model and an invisible rectangular sand-packed physical model. Following a complete stable water flooding, the pulsating pattern is used to continue the formation water injection. The effects of frequency and amplitude of hydraulic pulsation on the enhanced oil recovery efficiency were tested and analyzed. The hydraulic pulsating flooding stimulates pore pressure jumps repetitively. As a result, the residual oil films adhered on the surface of rock pore throats are stripped and swept progressively. This process enhances oil displacement efficiency. Moreover, hydraulic pulsations can induce additional pressure disturbances that break the mechanical equilibrium at the micro interface of the oil-water-solid three-phase system within the pores. This process stimulates the deformation and movement of the oil-water interface, overcoming the Jamin effect and segregating the oil phase into minute droplets persistently. Under a specific amplitude of pulsating pressure, an optimal pulsation frequency of 0.025 Hz is identified to yield the highest water flooding recovery rate. At this optimal frequency, a critical pulsation amplitude of 5 mL/min exists. Beyond this critical amplitude, oil recovery increases with the amplitude of pulsation linearly. Experimental results indicate that employing hydraulic pulsating waves for water flooding can achieve a maximum enhanced oil recovery rate of 14.47%.

为研究在高水位断面油藏中使用水力脉动淹没提高石油采收率的机理，进行了一项实验调查。该研究使用可视矩形玻璃珠物理模型和不可见矩形砂粒物理模型进行了一系列实验室实验。在完全稳定注水后，脉动模式用于继续注入地层水。测试和分析了水力脉动的频率和振幅对提高采油效率的影响。水力脉动淹没重复刺激孔隙压力跃升。因此，附着在岩石孔喉表面的残余油膜被逐渐剥离和扫除。这一过程提高了石油置换效率。此外，水力脉动还能引起额外的压力扰动，打破孔隙内油水固三相系统微界面的机械平衡。这一过程会刺激油水界面的变形和运动，克服杰明效应，使油相持续分离成微小液滴。在特定的脉动压力振幅下，0.025 Hz 的最佳脉动频率可产生最高的水淹采收率。在此最佳频率下，临界脉动振幅为 5 mL/min。超过这个临界振幅后，采油率会随着脉动振幅的增加而线性增加。实验结果表明，采用水力脉动波进行水淹可实现 14.47% 的最高提高采油率。

{"title":"Experimental investigation on enhanced oil recovery by hydraulic pulsating wave driving","authors":"Feipeng Wu , Yunpeng Song , Na Li , Jing Liu","doi":"10.1016/j.geoen.2024.213477","DOIUrl":"10.1016/j.geoen.2024.213477","url":null,"abstract":"<div><div>An experimental investigation was conducted to study the mechanism of enhancing oil recovery using hydraulic pulsating flooding in high water cut reservoirs. The study involved a series of laboratory experiments using both a visual rectangular glass bead-packed physical model and an invisible rectangular sand-packed physical model. Following a complete stable water flooding, the pulsating pattern is used to continue the formation water injection. The effects of frequency and amplitude of hydraulic pulsation on the enhanced oil recovery efficiency were tested and analyzed. The hydraulic pulsating flooding stimulates pore pressure jumps repetitively. As a result, the residual oil films adhered on the surface of rock pore throats are stripped and swept progressively. This process enhances oil displacement efficiency. Moreover, hydraulic pulsations can induce additional pressure disturbances that break the mechanical equilibrium at the micro interface of the oil-water-solid three-phase system within the pores. This process stimulates the deformation and movement of the oil-water interface, overcoming the Jamin effect and segregating the oil phase into minute droplets persistently. Under a specific amplitude of pulsating pressure, an optimal pulsation frequency of 0.025 Hz is identified to yield the highest water flooding recovery rate. At this optimal frequency, a critical pulsation amplitude of 5 mL/min exists. Beyond this critical amplitude, oil recovery increases with the amplitude of pulsation linearly. Experimental results indicate that employing hydraulic pulsating waves for water flooding can achieve a maximum enhanced oil recovery rate of 14.47%.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213477"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Equation of state for nanopores and shale: Pore size–dependent acentric factor 纳米孔和页岩的状态方程：孔隙大小与中心因子有关

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213470

Mehdi Alipour Kallehbasti, A. Sakhaee-Pour

Nanopores pose a challenge to phase-behavior modeling when using the equation of state (EOS), and common methods do not capture their vapor pressure or become difficult to implement because they require additional tuning parameters. This study focuses on improving the vapor-pressure prediction of EOS in nanopores by proposing a pore size–dependent acentric factor (ACF). It determines the ACF from experimental data and implements it in EOS along with critical pressure and temperature. The proposed approach is then applied to the vapor-pressure measurements of nitrogen, argon, oxygen, methane, and ethane in pores ranging from 3.5 nm to 8.1 nm. The results show that the ACF in nanopores increases as the pore size decreases, and the degree of size dependency varies across different pure components. The results also demonstrate that the proposed approach enables EOS predictions to match the measurements with good accuracy. This study quantifies the effects of pore size on the ACF for the first time and presents simple correlations for estimating the ACF when the pore radius is smaller than 10 nm. The proposed approach simplifies the application of EOS in nanopores and unconventional hydrocarbon reservoirs.

在使用状态方程（EOS）进行相行为建模时，纳米孔对建模提出了挑战，常见的方法无法捕捉其蒸汽压力，或者由于需要额外的调整参数而难以实施。本研究的重点是通过提出与孔径大小相关的中心因子（ACF）来改进纳米孔中 EOS 的蒸汽压力预测。它根据实验数据确定 ACF，并将其与临界压力和温度一起应用于 EOS。然后将提出的方法应用于氮气、氩气、氧气、甲烷和乙烷在 3.5 纳米到 8.1 纳米孔隙中的蒸汽压力测量。结果表明，纳米孔隙中的 ACF 会随着孔隙尺寸的减小而增大，不同纯成分对尺寸的依赖程度也不同。结果还表明，所提出的方法可以使 EOS 预测结果与测量结果准确吻合。本研究首次量化了孔径对 ACF 的影响，并提出了当孔径小于 10 nm 时估算 ACF 的简单相关性。所提出的方法简化了 EOS 在纳米孔隙和非常规油气藏中的应用。

{"title":"Equation of state for nanopores and shale: Pore size–dependent acentric factor","authors":"Mehdi Alipour Kallehbasti, A. Sakhaee-Pour","doi":"10.1016/j.geoen.2024.213470","DOIUrl":"10.1016/j.geoen.2024.213470","url":null,"abstract":"<div><div>Nanopores pose a challenge to phase-behavior modeling when using the equation of state (EOS), and common methods do not capture their vapor pressure or become difficult to implement because they require additional tuning parameters. This study focuses on improving the vapor-pressure prediction of EOS in nanopores by proposing a pore size–dependent acentric factor (ACF). It determines the ACF from experimental data and implements it in EOS along with critical pressure and temperature. The proposed approach is then applied to the vapor-pressure measurements of nitrogen, argon, oxygen, methane, and ethane in pores ranging from 3.5 nm to 8.1 nm. The results show that the ACF in nanopores increases as the pore size decreases, and the degree of size dependency varies across different pure components. The results also demonstrate that the proposed approach enables EOS predictions to match the measurements with good accuracy. This study quantifies the effects of pore size on the ACF for the first time and presents simple correlations for estimating the ACF when the pore radius is smaller than 10 nm. The proposed approach simplifies the application of EOS in nanopores and unconventional hydrocarbon reservoirs.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213470"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of CO2-assisted surfactant/polymer flooding on enhanced oil recovery and its mechanism 二氧化碳辅助表面活性剂/聚合物淹没对提高石油采收率的影响及其机理

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213473

Xin He , Kun Xie , Weijia Cao , Xiangguo Lu , Xiaoyan Wang , Bin Huang , Nan Zhang , Dandan Cui , Xujie Hong , Yuqing Wang , Xiaoqin Zhang

D oilfield is a typical heavy oil reservoir affected by bottom water and has the characteristics of high porosity, high permeability, and strong heterogeneity. However, water flooding leaves oil behind due to unfavorable mobility ratios and capillary forces. The layer (well section) with poor or no liquid entry ability originally has been improved in the process of surfactant/polymer flood. However, fluid entry distribution interlayers were not improved obviously in the middle and late stages. To further improve the recovery efficiency of surfactant/polymer flooding on bottom water reservoirs, the CO₂-assisted surfactant/polymer flooding development method had been proposed. The optimal composition of the surfactant/polymer system was selected by evaluating the oil-water interfacial tension and viscosity. Three-dimensional cores with bottom water were used in CO₂-assisted surfactant/polymer flooding experiments to improve oil recovery. On this foundation, the screening of oil displacement agents, optimization of oil production well location, and injection pressure were carried out. Based on the comprehensive analysis of the produced liquid, the CO₂ assisted surfactant/polymer flooding to enhanced oil recovery mechanism was analyzed. The results showed that the surfactant named BS had a low oil-water interfacial tension of 3.79 × 10^-³ mN/m. In addition, salinity decreases the viscosity of the surfactant/polymer solution. It was found that conducting CO₂ huff and puff after chemical flooding can improve oil recovery. Among the four chemical agents, CO₂-assisted the anionic nonionic surfactant and the salt-resistant polymer system flooding had the highest recovery. Moreover, the location of the oil production well, that is, the distance between it and the bottom water layer, has an impact on the recovery. During the experiment, 2.5 cm was the farthest distance between the oil production well and the bottom water layer, at which point the recovery was highest at 70.9%, and the bottom water breakthrough rate was 2.4%. These results provide theoretical and technical support for the development of CO₂-assisted surfactant/polymer flooding and its application in wells.

D 油田是一个典型的受底水影响的重油储层，具有高孔隙度、高渗透率和强异质性的特点。然而，由于流动比率和毛细管力的不利影响，水淹会留下石油。在表面活性剂/聚合物水淹过程中，原本液体进入能力差或无液体进入能力的层（井段）得到了改善。但在中后期，液体进入分布夹层的情况并没有得到明显改善。为了进一步提高表面活性剂/聚合物淹没底层储层的回收效率，提出了二氧化碳辅助表面活性剂/聚合物淹没开发方法。通过评估油水界面张力和粘度，选择了最佳的表面活性剂/聚合物体系组成。在二氧化碳辅助表面活性剂/聚合物淹没实验中使用了含有底水的三维岩心，以提高石油采收率。在此基础上，进行了石油置换剂的筛选、采油井位置和注入压力的优化。在对产出液进行综合分析的基础上，分析了二氧化碳辅助表面活性剂/聚合物淹没提高石油采收率的机理。结果表明，名为 BS 的表面活性剂具有较低的油水界面张力，为 3.79 × 10-3 mN/m。此外，盐度会降低表面活性剂/聚合物溶液的粘度。研究发现，在化学淹没后进行 CO2 吹胀可以提高石油采收率。在四种化学剂中，二氧化碳辅助阴离子非离子表面活性剂和耐盐聚合物体系的淹没采收率最高。此外，采油井的位置（即与底层水的距离）对采收率也有影响。在实验中，2.5 厘米是采油井与底层水之间的最远距离，此时采收率最高，为 70.9%，底层水突破率为 2.4%。这些结果为开发二氧化碳辅助表面活性剂/聚合物水淹法及其在油井中的应用提供了理论和技术支持。

{"title":"Effect of CO2-assisted surfactant/polymer flooding on enhanced oil recovery and its mechanism","authors":"Xin He , Kun Xie , Weijia Cao , Xiangguo Lu , Xiaoyan Wang , Bin Huang , Nan Zhang , Dandan Cui , Xujie Hong , Yuqing Wang , Xiaoqin Zhang","doi":"10.1016/j.geoen.2024.213473","DOIUrl":"10.1016/j.geoen.2024.213473","url":null,"abstract":"<div><div>D oilfield is a typical heavy oil reservoir affected by bottom water and has the characteristics of high porosity, high permeability, and strong heterogeneity. However, water flooding leaves oil behind due to unfavorable mobility ratios and capillary forces. The layer (well section) with poor or no liquid entry ability originally has been improved in the process of surfactant/polymer flood. However, fluid entry distribution interlayers were not improved obviously in the middle and late stages. To further improve the recovery efficiency of surfactant/polymer flooding on bottom water reservoirs, the CO<sub>2</sub>-assisted surfactant/polymer flooding development method had been proposed. The optimal composition of the surfactant/polymer system was selected by evaluating the oil-water interfacial tension and viscosity. Three-dimensional cores with bottom water were used in CO<sub>2</sub>-assisted surfactant/polymer flooding experiments to improve oil recovery. On this foundation, the screening of oil displacement agents, optimization of oil production well location, and injection pressure were carried out. Based on the comprehensive analysis of the produced liquid, the CO<sub>2</sub> assisted surfactant/polymer flooding to enhanced oil recovery mechanism was analyzed. The results showed that the surfactant named BS had a low oil-water interfacial tension of 3.79 × 10<sup>-</sup><sup>3</sup> mN/m. In addition, salinity decreases the viscosity of the surfactant/polymer solution. It was found that conducting CO<sub>2</sub> huff and puff after chemical flooding can improve oil recovery. Among the four chemical agents, CO<sub>2</sub>-assisted the anionic nonionic surfactant and the salt-resistant polymer system flooding had the highest recovery. Moreover, the location of the oil production well, that is, the distance between it and the bottom water layer, has an impact on the recovery. During the experiment, 2.5 cm was the farthest distance between the oil production well and the bottom water layer, at which point the recovery was highest at 70.9%, and the bottom water breakthrough rate was 2.4%. These results provide theoretical and technical support for the development of CO<sub>2</sub>-assisted surfactant/polymer flooding and its application in wells.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213473"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on the microscopic mechanism and model applicability differences of CH4 and CO2 adsorption based on molecular dynamics 基于分子动力学的 CH4 和 CO2 吸附微观机理及模型适用性差异研究

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213476

Aitao Zhou , Zhiyuan Xu , Kai Wang , Yanhai Wang , Ke Gao , Jingxin Xu , Zebin Zhu

To verify the accuracy and rationality of the molecular simulation model, the microscopic mechanism of gas adsorption was analyzed and clarified from a microscopic perspective. The effect of molecular models created by direct construction and supercell expansion on the adsorption capacities of CH₄ and CO₂ has been analyzed. Eight coal-based molecular configurations were created to simulate the isothermal adsorption process of CH₄ and CO₂ using various coal-based molecular configurations. Using physical experiments, the validity of different construction methods for coal-based molecular structures was verified. The direct construction method was chosen to simulate the effect of various coal-based molecular numbers on the adsorption capacity of CH₄ and CO₂. The results show that the adsorption capacity of CO₂ on coal is greater than that of CH₄. The isothermal adsorption curves of CH₄ and CO₂ in coal-based molecular systems constructed using different methods reveal that the adsorption of methane on coal molecules adheres to the Langmuir monolayer adsorption theory. The adsorption sites for methane increase with the rise in free volume. The structure directly constructed and the supercell expansion directly determines the amount of methane adsorbed by each coal based molecule. The adsorption constants of CH₄ and CO₂ on the supercell extended structure are more volatile than those on the directly constructed structure, and the structure constructed directly for different coal based molecules is better than the supercell extended structure. The simulation using the direct construction method shows that as the number of coal-based molecules in the molecular configuration increases, The isothermal adsorption quantities of CH₄ and CO₂ increase linearly. The molecular configuration is not affected by the number of anthracite molecules. Molecular configuration is not affected by the number of anthracite molecules. The rationality of model construction has no obvious relationship with the number of coal based molecules.

为了验证分子模拟模型的准确性和合理性，从微观角度分析并阐明了气体吸附的微观机理。分析了通过直接构建和超级囚室扩展创建的分子模型对 CH4 和 CO2 吸附能力的影响。创建了八种煤基分子构型，利用各种煤基分子构型模拟了 CH4 和 CO2 的等温吸附过程。通过物理实验验证了不同煤基分子结构构建方法的有效性。选择了直接构建法来模拟各种煤基分子数对 CH4 和 CO2 吸附能力的影响。结果表明，煤对 CO2 的吸附能力大于对 CH4 的吸附能力。用不同方法构建的煤基分子体系中 CH4 和 CO2 的等温吸附曲线表明，甲烷在煤分子上的吸附符合 Langmuir 单层吸附理论。甲烷的吸附位点随着自由体积的增加而增加。直接构建的结构和超级窖的膨胀直接决定了每个煤基分子吸附甲烷的量。超级囚室扩展结构上 CH4 和 CO2 的吸附常数比直接构建结构上的吸附常数更易挥发，而且针对不同煤基分子直接构建的结构比超级囚室扩展结构更好。直接构建法的模拟结果表明，随着分子构型中煤基分子数量的增加，CH4 和 CO2 的等温吸附量呈线性增加。分子构型不受无烟煤分子数量的影响。分子构型不受无烟煤分子数量的影响。模型构建的合理性与煤基分子数量无明显关系。

{"title":"Research on the microscopic mechanism and model applicability differences of CH4 and CO2 adsorption based on molecular dynamics","authors":"Aitao Zhou , Zhiyuan Xu , Kai Wang , Yanhai Wang , Ke Gao , Jingxin Xu , Zebin Zhu","doi":"10.1016/j.geoen.2024.213476","DOIUrl":"10.1016/j.geoen.2024.213476","url":null,"abstract":"<div><div>To verify the accuracy and rationality of the molecular simulation model, the microscopic mechanism of gas adsorption was analyzed and clarified from a microscopic perspective. The effect of molecular models created by direct construction and supercell expansion on the adsorption capacities of CH<sub>4</sub> and CO<sub>2</sub> has been analyzed. Eight coal-based molecular configurations were created to simulate the isothermal adsorption process of CH<sub>4</sub> and CO<sub>2</sub> using various coal-based molecular configurations. Using physical experiments, the validity of different construction methods for coal-based molecular structures was verified. The direct construction method was chosen to simulate the effect of various coal-based molecular numbers on the adsorption capacity of CH<sub>4</sub> and CO<sub>2</sub>. The results show that the adsorption capacity of CO<sub>2</sub> on coal is greater than that of CH<sub>4</sub>. The isothermal adsorption curves of CH<sub>4</sub> and CO<sub>2</sub> in coal-based molecular systems constructed using different methods reveal that the adsorption of methane on coal molecules adheres to the Langmuir monolayer adsorption theory. The adsorption sites for methane increase with the rise in free volume. The structure directly constructed and the supercell expansion directly determines the amount of methane adsorbed by each coal based molecule. The adsorption constants of CH<sub>4</sub> and CO<sub>2</sub> on the supercell extended structure are more volatile than those on the directly constructed structure, and the structure constructed directly for different coal based molecules is better than the supercell extended structure. The simulation using the direct construction method shows that as the number of coal-based molecules in the molecular configuration increases, The isothermal adsorption quantities of CH<sub>4</sub> and CO<sub>2</sub> increase linearly. The molecular configuration is not affected by the number of anthracite molecules. Molecular configuration is not affected by the number of anthracite molecules. The rationality of model construction has no obvious relationship with the number of coal based molecules.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213476"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on damage mechanism of casing based on fluid-structure coupling and perforation performance of new perforation device 基于流固耦合的套管损伤机理及新型射孔装置的射孔性能研究

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213478

Zhengwei Guo , Junhua Gou , Ting Zhou , Wei He , Dongshen Yu

Jet perforating is an important way to improve oil and gas recovery. The metal jet formed by the traditional perforating method will cause serious damage to the casing, reduce the life of casing and oil and gas well, and affect the later oil and gas exploitation. In order to solve the problems existing in the current perforating method, a combination of mechanical and shaped charge perforating method is proposed. The method firstly drilled the casing surface by mechanical means, and finally penetrated the formation through the perforating charge to form oil and gas channel. According to the traditional perforating technology, the casing damage mechanism is analyzed by finite element method, and the conventional perforating method is compared with the new perforating method. The results show that the traditional perforating method will cause casing damage. The hole diameter of the outer wall of the casing is 12.20 mm, and the damage range of the outer wall of the casing is 32.10 mm. The stress, strain and damage range of the inner wall of the casing are smaller than that of the outer wall during the perforating process, and the radial damage of the casing changes up and down, and the shape is like "sawtooth". According to the new perforating method, the combined perforating method of mechanical and shaped charge causes less damage to the casing, and the perforating depth is increased by 11.37%. When the drill diameter on the new device is 20 mm, the damage caused by the perforating charge to the casing is 0. Therefore, the new perforating method can not only reduce casing damage but also increase the perforating depth, which is of great significance for improving the life of oil and gas Wells and oil and gas recovery.

射孔是提高油气采收率的重要途径。传统射孔方法形成的金属射流会对套管造成严重破坏，降低套管和油气井的寿命，影响后期油气开采。为了解决目前射孔方法中存在的问题，提出了一种机械射孔与异形电荷射孔相结合的射孔方法。该方法首先通过机械方式钻进套管表面，最后通过射孔装药穿透地层，形成油气通道。根据传统射孔技术，采用有限元法分析了套管损伤机理，并将传统射孔法与新型射孔法进行了对比。结果表明，传统射孔方法会造成套管损坏。套管外壁的孔径为 12.20 毫米，套管外壁的损坏范围为 32.10 毫米。在穿孔过程中，套管内壁的应力、应变和破坏范围均小于外壁，套管径向破坏呈上下变化，形状如 "锯齿"。根据新的穿孔方法，机械和定型装药联合穿孔法对套管的损伤较小，穿孔深度增加了 11.37%。因此，新射孔方法不仅能减少套管损伤，还能增加射孔深度，对提高油气井寿命和油气采收率具有重要意义。

{"title":"Research on damage mechanism of casing based on fluid-structure coupling and perforation performance of new perforation device","authors":"Zhengwei Guo , Junhua Gou , Ting Zhou , Wei He , Dongshen Yu","doi":"10.1016/j.geoen.2024.213478","DOIUrl":"10.1016/j.geoen.2024.213478","url":null,"abstract":"<div><div>Jet perforating is an important way to improve oil and gas recovery. The metal jet formed by the traditional perforating method will cause serious damage to the casing, reduce the life of casing and oil and gas well, and affect the later oil and gas exploitation. In order to solve the problems existing in the current perforating method, a combination of mechanical and shaped charge perforating method is proposed. The method firstly drilled the casing surface by mechanical means, and finally penetrated the formation through the perforating charge to form oil and gas channel. According to the traditional perforating technology, the casing damage mechanism is analyzed by finite element method, and the conventional perforating method is compared with the new perforating method. The results show that the traditional perforating method will cause casing damage. The hole diameter of the outer wall of the casing is 12.20 mm, and the damage range of the outer wall of the casing is 32.10 mm. The stress, strain and damage range of the inner wall of the casing are smaller than that of the outer wall during the perforating process, and the radial damage of the casing changes up and down, and the shape is like \"sawtooth\". According to the new perforating method, the combined perforating method of mechanical and shaped charge causes less damage to the casing, and the perforating depth is increased by 11.37%. When the drill diameter on the new device is 20 mm, the damage caused by the perforating charge to the casing is 0. Therefore, the new perforating method can not only reduce casing damage but also increase the perforating depth, which is of great significance for improving the life of oil and gas Wells and oil and gas recovery.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213478"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unveil the controls on CO2 diffusivity in saline brines for geological carbon storage 揭示二氧化碳在盐湖卤水中扩散的控制因素，实现地质碳封存

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-04 DOI: 10.1016/j.geoen.2024.213483

Heng Wang , Yunfei Li , Chengyang Li , Haiyan Zhu , Zhiwu Li , Lei Wang , Bryan X. Medina-Rodriguez

Accurate estimation of the diffusivity of CO₂ in formation brine, one of the dominant mass transfer mechanisms, is crucial for characterizing CO₂ migration and distribution in Geological Carbon Storage (GCS). However, the effects of pressure, temperature, and the composition and concentration of ions on the CO₂ diffusion coefficient in saline aquifers are complex. This study used in-house-designed equipment to determine the diffusion coefficient of supercritical CO₂ in synthetic brines, such as deionized water and NaCl, CaCl₂, and KCl solutions under different pressure and temperature conditions. First, CO₂ solubilities at initial pressure and temperature were measured to provide the initial CO₂ concentration at the gas-liquid interface. Then, pressure decay curves were collected for the selected brines and the diffusion coefficients of CO₂ molecules were calculated based on Fick's second law. Experimental results show that CO₂ solubility increases with increasing pressure and decreasing temperature and ionic strength. Moreover, CO₂ solubilities at same pressure, temperature and ionic strength conditions vary in different synthetic brines. We also found that CO₂ diffuses faster in brine at higher pressures and temperatures but slows down as ionic strength increases. The type of ions affects the diffusion differently, except at higher pressures, where their impacts balance out due to hydration effects. In addition, a good linear relationship between CO₂ diffusion coefficient and solubility was observed, indicating the CO₂ diffusion coefficient could be estimated by solubility. The findings in this study shed a light on the CO₂ migration during commercial-scale geological storage and enhanced oil recovery processes.

二氧化碳在地层盐水中的扩散系数是主要的传质机制之一，准确估算这一扩散系数对于确定二氧化碳在地质碳封存（GCS）中的迁移和分布特征至关重要。然而，压力、温度以及离子的成分和浓度对盐类含水层中二氧化碳扩散系数的影响非常复杂。本研究使用内部设计的设备，测定了不同压力和温度条件下超临界二氧化碳在去离子水、NaCl、CaCl2 和 KCl 溶液等合成盐水中的扩散系数。首先，测量初始压力和温度下的二氧化碳溶解度，以提供气液界面上的二氧化碳初始浓度。然后，收集所选盐水的压力衰减曲线，并根据菲克第二定律计算出二氧化碳分子的扩散系数。实验结果表明，二氧化碳的溶解度随压力的增加而增加，随温度和离子强度的降低而降低。此外，在相同压力、温度和离子强度条件下，不同合成盐水中的二氧化碳溶解度也不同。我们还发现，在压力和温度较高时，二氧化碳在盐水中的扩散速度较快，但随着离子强度的增加，扩散速度减慢。离子类型对扩散的影响不同，但在较高压力下，由于水合作用，离子类型对扩散的影响趋于平衡。此外，二氧化碳扩散系数与溶解度之间存在良好的线性关系，这表明二氧化碳扩散系数可以通过溶解度来估算。本研究的发现揭示了商业规模地质封存和提高石油采收率过程中的二氧化碳迁移问题。

{"title":"Unveil the controls on CO2 diffusivity in saline brines for geological carbon storage","authors":"Heng Wang , Yunfei Li , Chengyang Li , Haiyan Zhu , Zhiwu Li , Lei Wang , Bryan X. Medina-Rodriguez","doi":"10.1016/j.geoen.2024.213483","DOIUrl":"10.1016/j.geoen.2024.213483","url":null,"abstract":"<div><div>Accurate estimation of the diffusivity of CO<sub>2</sub> in formation brine, one of the dominant mass transfer mechanisms, is crucial for characterizing CO<sub>2</sub> migration and distribution in Geological Carbon Storage (GCS). However, the effects of pressure, temperature, and the composition and concentration of ions on the CO<sub>2</sub> diffusion coefficient in saline aquifers are complex. This study used in-house-designed equipment to determine the diffusion coefficient of supercritical CO<sub>2</sub> in synthetic brines, such as deionized water and NaCl, CaCl<sub>2</sub>, and KCl solutions under different pressure and temperature conditions. First, CO<sub>2</sub> solubilities at initial pressure and temperature were measured to provide the initial CO<sub>2</sub> concentration at the gas-liquid interface. Then, pressure decay curves were collected for the selected brines and the diffusion coefficients of CO<sub>2</sub> molecules were calculated based on Fick's second law. Experimental results show that CO<sub>2</sub> solubility increases with increasing pressure and decreasing temperature and ionic strength. Moreover, CO<sub>2</sub> solubilities at same pressure, temperature and ionic strength conditions vary in different synthetic brines. We also found that CO<sub>2</sub> diffuses faster in brine at higher pressures and temperatures but slows down as ionic strength increases. The type of ions affects the diffusion differently, except at higher pressures, where their impacts balance out due to hydration effects. In addition, a good linear relationship between CO<sub>2</sub> diffusion coefficient and solubility was observed, indicating the CO<sub>2</sub> diffusion coefficient could be estimated by solubility. The findings in this study shed a light on the CO<sub>2</sub> migration during commercial-scale geological storage and enhanced oil recovery processes.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213483"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating temporal deep learning models for predicting screen-out risk levels in hydraulic fracturing 整合时间深度学习模型，预测水力压裂中的屏蔽风险水平

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-03 DOI: 10.1016/j.geoen.2024.213442

Ying Qiao , Cuishan Lin , Yuguo Zhao , Liangzhi Zhou

Amid the transformative shift in global energy structures, the exploitation and utilization of shale gas, an essential unconventional natural gas resource, have drawn widespread attention from both industrial and academic circles. However, screen-out incidents during hydraulic fracturing operations pose significant obstacles to extraction efficiency and safety. Traditional prediction methods, which rely on empirical estimations and simplified models, are deficient in accuracy and real-time applicability. Addressing this, our study introduces a novel deep learning ensemble integrating Gated Recurrent Units (GRU), Transformer, and One-Dimensional Convolutional Neural Networks (1D-CNN) for precise screen-out prediction. This approach markedly improves predictive accuracy by efficiently processing time-series data and capturing the complex dynamics of fracturing processes. Furthermore, the application of the correlation coefficient method and random forest algorithm for feature selection optimizes model input and further enhances prediction accuracy and operational efficiency. Our comparative analysis demonstrates the model’s superiority, achieving an F1 score of 0.951 and a loss of 0.430, clearly surpassing traditional and other deep learning methods. This integration of advanced neural architectures and feature selection techniques not only advances screen-out prediction but also yields practical insights for optimizing shale gas extraction strategies and enhancing safety.

在全球能源结构转型的背景下，页岩气这一重要的非常规天然气资源的开采和利用引起了工业界和学术界的广泛关注。然而，在水力压裂作业过程中发生的漏筛事故对开采效率和安全性构成了重大障碍。传统的预测方法依赖于经验估计和简化模型，在准确性和实时适用性方面存在不足。针对这一问题，我们的研究引入了一种新颖的深度学习组合，该组合集成了门控循环单元（GRU）、变压器和一维卷积神经网络（1D-CNN），可用于精确的漏筛预测。这种方法通过高效处理时间序列数据和捕捉压裂过程的复杂动态，显著提高了预测精度。此外，相关系数法和随机森林算法在特征选择中的应用优化了模型输入，进一步提高了预测精度和运行效率。我们的对比分析表明了该模型的优越性，其 F1 得分为 0.951，损失为 0.430，明显超过了传统和其他深度学习方法。这种先进的神经架构与特征选择技术的融合不仅推进了出屏预测，还为优化页岩气开采策略和提高安全性提供了实用见解。

{"title":"Integrating temporal deep learning models for predicting screen-out risk levels in hydraulic fracturing","authors":"Ying Qiao , Cuishan Lin , Yuguo Zhao , Liangzhi Zhou","doi":"10.1016/j.geoen.2024.213442","DOIUrl":"10.1016/j.geoen.2024.213442","url":null,"abstract":"<div><div>Amid the transformative shift in global energy structures, the exploitation and utilization of shale gas, an essential unconventional natural gas resource, have drawn widespread attention from both industrial and academic circles. However, screen-out incidents during hydraulic fracturing operations pose significant obstacles to extraction efficiency and safety. Traditional prediction methods, which rely on empirical estimations and simplified models, are deficient in accuracy and real-time applicability. Addressing this, our study introduces a novel deep learning ensemble integrating Gated Recurrent Units (GRU), Transformer, and One-Dimensional Convolutional Neural Networks (1D-CNN) for precise screen-out prediction. This approach markedly improves predictive accuracy by efficiently processing time-series data and capturing the complex dynamics of fracturing processes. Furthermore, the application of the correlation coefficient method and random forest algorithm for feature selection optimizes model input and further enhances prediction accuracy and operational efficiency. Our comparative analysis demonstrates the model’s superiority, achieving an F1 score of 0.951 and a loss of 0.430, clearly surpassing traditional and other deep learning methods. This integration of advanced neural architectures and feature selection techniques not only advances screen-out prediction but also yields practical insights for optimizing shale gas extraction strategies and enhancing safety.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213442"},"PeriodicalIF":0.0,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Remediation of LWD data lag with hybrid real-time data using self-attention-based encoder-decoder model 利用基于自我关注的编码器-解码器模型，补救混合实时数据的 LWD 数据滞后问题

0 ENERGY & FUELS

Geoenergy Science and Engineering

Pub Date : 2024-11-03 DOI: 10.1016/j.geoen.2024.213461

Jiafeng Zhang , Ye Liu , Jie Cao , Tao Yang

This study aims to address the lag issue in Logging While Drilling (LWD) data, which is crucial for real-time decision-making in subsurface resource exploration. The primary objective is to enhance the accuracy of LWD measurements, which suffer from a positional discrepancy due to the tools being positioned several meters behind the drill bit. This lag can lead to delayed responses and misinterpretations during drilling operations. To achieve this, we introduce a novel Self-Attention-Based Encoder-Decoder (SABED) model that compensates for the time/depth lag by utilizing hybrid real-time data, including drilling engineering and LWD data. Our methodology involves training and validating the SABED model using data from the Volve field in the North Sea. The model's architecture is designed to effectively capture the complex relationships between drilling data and LWD measurements. Experimental results demonstrate that the SABED model can predict gamma ray values up to 45 m ahead with a Mean Relative Error (MRE) of less than 1.5% in the primary test well (F7), outperforming conventional sequential deep learning models. Further evaluations on an auxiliary test well (F10) indicate robust performance and generalization capabilities, even with noisy drilling data. The model also meets real-time operational requirements, processing predictions in approximately 4.5 s per 300-step interval (30 m) on both CPU and GPU. Notably, the SABED model maintains predictive accuracy despite data loss, using linear interpolation for missing segments. These findings underscore the SABED model's effectiveness in mitigating LWD data lag and its potential as a valuable tool for real-time geological information prediction. This research contributes novel insights to the field by providing an advanced methodology for improving data accuracy in LWD operations, thereby enhancing decision-making in the petroleum industry.

本研究旨在解决边钻井边测井（LWD）数据的滞后问题，这对地下资源勘探的实时决策至关重要。其主要目的是提高 LWD 测量的准确性，因为 LWD 测量存在位置偏差，这是因为工具被放置在钻头后方数米处。这种滞后会导致钻探过程中的延迟响应和误解。为此，我们引入了一种新颖的基于自注意力的编码器-解码器（SABED）模型，通过利用混合实时数据（包括钻井工程数据和 LWD 数据）来补偿时间/深度滞后。我们的方法包括利用北海 Volve 油田的数据对 SABED 模型进行训练和验证。该模型的结构旨在有效捕捉钻井数据与 LWD 测量之间的复杂关系。实验结果表明，在主测试井（F7）中，SABED 模型可以预测前方 45 米的伽马射线值，平均相对误差（MRE）小于 1.5%，优于传统的序列深度学习模型。在辅助测试井（F10）上进行的进一步评估表明，即使在钻井数据嘈杂的情况下，该模型仍具有强大的性能和泛化能力。该模型还能满足实时运行要求，在 CPU 和 GPU 上处理每 300 步间隔（30 米）的预测时间约为 4.5 秒。值得注意的是，SABED 模型在数据丢失的情况下仍能保持预测精度，对丢失的数据段采用线性插值。这些发现强调了 SABED 模型在缓解 LWD 数据滞后方面的有效性，以及其作为实时地质信息预测的宝贵工具的潜力。这项研究为提高 LWD 操作中的数据准确性提供了先进的方法，从而提高了石油行业的决策水平，为该领域提供了新的见解。

{"title":"Remediation of LWD data lag with hybrid real-time data using self-attention-based encoder-decoder model","authors":"Jiafeng Zhang , Ye Liu , Jie Cao , Tao Yang","doi":"10.1016/j.geoen.2024.213461","DOIUrl":"10.1016/j.geoen.2024.213461","url":null,"abstract":"<div><div>This study aims to address the lag issue in Logging While Drilling (LWD) data, which is crucial for real-time decision-making in subsurface resource exploration. The primary objective is to enhance the accuracy of LWD measurements, which suffer from a positional discrepancy due to the tools being positioned several meters behind the drill bit. This lag can lead to delayed responses and misinterpretations during drilling operations. To achieve this, we introduce a novel Self-Attention-Based Encoder-Decoder (SABED) model that compensates for the time/depth lag by utilizing hybrid real-time data, including drilling engineering and LWD data. Our methodology involves training and validating the SABED model using data from the Volve field in the North Sea. The model's architecture is designed to effectively capture the complex relationships between drilling data and LWD measurements. Experimental results demonstrate that the SABED model can predict gamma ray values up to 45 m ahead with a Mean Relative Error (MRE) of less than 1.5% in the primary test well (F7), outperforming conventional sequential deep learning models. Further evaluations on an auxiliary test well (F10) indicate robust performance and generalization capabilities, even with noisy drilling data. The model also meets real-time operational requirements, processing predictions in approximately 4.5 s per 300-step interval (30 m) on both CPU and GPU. Notably, the SABED model maintains predictive accuracy despite data loss, using linear interpolation for missing segments. These findings underscore the SABED model's effectiveness in mitigating LWD data lag and its potential as a valuable tool for real-time geological information prediction. This research contributes novel insights to the field by providing an advanced methodology for improving data accuracy in LWD operations, thereby enhancing decision-making in the petroleum industry.</div></div>","PeriodicalId":100578,"journal":{"name":"Geoenergy Science and Engineering","volume":"244 ","pages":"Article 213461"},"PeriodicalIF":0.0,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0