利用机器学习与改进岩石物理模型预测页岩油层系横波速度

传统的横波速度预测方法包括经验公式法和岩石物理模型法。前者适用于岩石矿物组分相对单一的储层,且受区域限制等因素的影响,不具有普适性,预测精度较低。后者需要根据不同的实际情况选择合适的岩石物理模型,才能达到预期的目的。大多数机器学习横波速度预测方法基于纯数据驱动,数据集的质量和数量将直接决定横波预测模型精度,并缺乏充分的物理内涵。为此,基于深度神经网络(DNN)的方法,假设研究区储层波传播方程的数学形式已知,通过测井数据训练DNN得到未知的弹性参数,以确立目的层的波传播方程。利用平面波分析法得到相应的纵波、横波速度,实现神经网络与理论模型的结合。此外,针对传统Xu-White模型的不足,考虑随深度变化的孔隙纵横比,提出了改进横波速度预测岩石物理模型。利用研究区较丰富的测井数据,分别采用构建的DNN模型和改进横波速度预测岩石物理模型预测横波速度,并与传统的Xu-White模型预测结果进行对比、分析。结果表明,由DNN模型和改进岩石物理模型均可获得较高精度的横波速度预测结果,且前者的预测效果更好。

二叠盆地Wolfcamp页岩油层测井评价研究

以二叠盆地米德兰次盆Wolfcamp页岩为例,总结页岩油层测井评价流程、方法和应用,建立适合Wolfcamp页岩的测井评价模型。以测井资料和岩心分析资料为基础,分析页岩油层的矿物组成、物性特征,将页岩中有机质视为特殊矿物,应用ELANPlus模块评价页岩储层的矿物含量和孔隙度,建立矿物组分渗透率模型。以岩心分析含水饱和度刻度,确定Indonesia公式评价Wolfcamp页岩储层含水饱和度的计算参数。结合Wolfcamp页岩储层发育灰质夹层的特点,应用Passey法评价富含石英、黏土页岩和体积密度法评价富含方解石页岩总有机碳含量。以纵波时差和横波时差测井评价页岩储层弹性模量、泊松比、岩石脆性指数等力学参数,为水平井初步确定有利压裂段提供依据。利用成像测井资料、偶极声波测井资料确定最大水平主应力方向,结合常规测井资料评价最大、最小水平主应力大小、垂向应力及其与水平主应力的大小关系,确定水平井安全钻井方向。

鄂尔多斯盆地长7页岩油层地质工程一体化评价

鄂尔多斯盆地长7页岩油层勘探历程回顾表明,制约页岩油直井勘探的主要问题油产量整体较低;油产量与油层的厚度、基质渗流能力关系不密切;油产量整体与压裂规模呈正相关,但不完全取决于压裂规模;高油产量井勘探模式和成功经验难以推广,“甜点”难以确定;长7页岩油整体表现出“井井有油,井井不流”的特点。按照地质工程一体化理念,分析了流体微观和宏观运动规律以及体积压裂的适用条件,探讨了直井油产量主控因素,结果表明对于天然裂缝不发育仅靠基质渗流的页岩油层,渗流力学决定了自然产能条件下直井难以达到工业意义的油产量;岩石力学决定了其不具有体积压裂条件,无法形成复杂的裂缝网络进而扩大泄油面积;天然裂缝或高渗砂体的发育程度是决定页岩油直井油产量的主要因素,也是页岩油“甜点”评价的重要指标。未来应按照地质工程一体化理念,转向高渗砂体形态的预测和刻画、天然裂缝的识别和预测、典型储层驱替压力(流速)-流体压力降的相关性、有效储层的多方法综合评价、“水平井+体积压裂”的裂缝有效性及分段贡献率评价等研究。

东濮凹陷北部沙河街组页岩油有利区优选

依据泥页岩层系划分标准及横向选区、纵向选层系的原则，在东濮凹陷北部沙河街组优选页岩油有利区。纵向上，基于泥页岩层系划分标准进行泥页岩层系识别，依据资源价值、油气富集概率优选富含页岩油的泥页岩层系（即页岩油层系）；横向上，利用泥页岩层系内有机碳展布、可动资源量及可采性指数的叠合图优选页岩油的有利区。纵、横向结合确定了地下页岩油富集的空间位置：沙三中亚段页岩油的有利区分布在马寨和柳屯洼陷，纵向上分布在Es3zl、Es322、Es323、Es325、Es326、Es327；沙三下亚段页岩油的有利区分布在柳屯洼陷和卫城地区，纵向上分布在Es3x7。

鄂尔多斯盆地延长组长_7页岩层段岩石热导率特征及启示

原位转化技术是中国陆相页岩油攻关的重点领域,鄂尔多斯盆地三叠系延长组长_7页岩层段岩石热物性,特别是高温热物性研究尚处空白,严重制约原位转化工程优化和可行性评价。选取长_7页岩发育区内多口取心井新鲜样品,利用热导仪、差示扫描量热仪和热膨胀仪,获得长_7页岩层段泥质粉砂岩、凝灰岩、泥岩和页岩的热扩散系数、比热容、热膨胀系数以及热导率参数。长_7页岩层段不同岩性的岩石热扩散系数和热导率存在差异,且随砂质含量降低而降低,即泥质粉砂岩>凝灰岩>泥岩>页岩。热扩散系数和热导率具有各向异性,水平方向是垂直方向的1～3.5倍,且其差异随温度升高而增大。随温度升高,岩石热扩散系数呈降低趋势、比热容呈增大趋势、热导率呈先降低后增大趋势。页岩热物性的各向异性最强,各向异性是岩石非均质性的体现,与微观纹层相关;砂岩各向异性可能与岩石不同方向上渗透率相关。

基于深度置信网络模型的页岩油产量预测方法

为提高华北油田冀中坳陷束鹿凹陷页岩油储层压后产量预测的符合率,基于受限玻尔兹曼机(RBM)的深度置信网络学习(DBN)模型,利用压裂停泵数据获得分段裂缝半长、改造后渗透率、SRV面积等动态数据,结合测录井等静态数据和压裂规模、试采等生产数据,通过数值模拟构建动态数据库,建立了束鹿凹陷的页岩油产量预测方法。该方法在ST1H、ST2X和ST3页岩井的应用,产量符合率达到80%,预测结果合理可靠,具有一定的可行性,能够为该地区页岩油井压裂评估和方案调整提供技术指导。

Permeability Estimation of Shale Oil Reservoir with Laboratory-derived Data: A Case Study of the Chang 7 Member in Ordos Basin

The shale oil reservoir within the Yanchang Formations of Ordos Basin harbors substantial oil and gas resources and has recently emerged as the primary focus of unconventional oil and gas exploration and development.Due to its complex pore and throat structure,pronounced heterogeneity,and tight reservoir characteristics,the techniques for conventional oil and gas exploration and production face challenges in comprehensive implementation,also indicating that as a vital parameter for evaluating the physical properties of a reservoir,permeability cannot be effectively estimated.This study selects 21 tight sandstone samples from the Q area within the shale oil formations of Ordos Basin.We systematically conduct the experiments to measure porosity,permeability,ultrasonic wave velocities,and resistivity at varying confining pressures.Results reveal that these measurements exhibit nonlinear changes in response to effective pressure.By using these experimental data and effective medium model,empirical relationships between P-and S-wave velocities,permeability and resistivity and effective pressure are established at logging and seismic scales.Furthermore,relationships between P-wave impedance and permeability,and resistivity and permeability are determined.A comparison between the predicted permeability and logging data demonstrates that the impedance–permeability relationship yields better results in contrast to those of resistivity–permeability relationship.These relationships are further applied to the seismic interpretation of shale oil reservoir in the target layer,enabling the permeability profile predictions based on inverse P-wave impedance.The predicted results are evaluated with actual production data,revealing a better agreement between predicted results and logging data and productivity.

Acoustic-electrical properties and rock physics models for shale-oil formations:prediction of reservoir properties of interbedded sandstone and shale layers

In recent years,the Yanchang shale-oil formations of the Ordos Basin are rich in reserves with complex lithology and structure characteristics,low porosity and low permeability,and weak anomalies for oil and water discriminations,have been the key targets of unconventional oil/gas resource exploration and development in the relevant areas.The joint acoustic-electrical(AE)properties can be used to interpret reservoir lithology,mineralogy,pore structure,and fluid saturation.To conduct tests of thin section analysis,X-ray diff raction,and ultrasonic and electrical experiments at diff erent pressures and saturation degrees,cores from the shale-oil formations in the Q area of the basin are collected.The variations in AE properties with respect to clay content,porosity,pressure(microfracture),and saturation are analyzed.The experimental results indicate that the rock physics behaviors of sandstones with diff erent clay contents vary significantly.The AE properties of clean sandstones are basically dependent on the microfractures(pressure),while for muddy sandstones,the clay content is an important factor affecting the responses.The target reservoir consists of interbedded sandstone and shale layers.The AE equivalent medium equations and the Gurevich theory are applied to establish the joint models for the diff erent lithologies and simulate the variations in AE properties with respect to fluid type,pore structure,and mineral components.The three-dimensional joint templates of clean and muddy sandstones,as well as shale,are developed based on the elastic and electrical attributes and then calibrated using the experimental and well-log data.The reservoir properties are estimated with the templates and validated by the log data.The results indicate that the joint templates based on lithology characteristics can eff ectively characterize the properties of interbedded sandstone and shale layers.Furthermore,the combined application of AE data provides more beneficial information for the assessment of rock properties,leading to precise estimates that conform with the actual formation conditions.

Evaluation of hydrocarbon generation of the Xiamaling Formation shale in Zhangjiakou and its significance to the petroleum geology in North China

The semi-closed pyrolysis simulation system under constant pressure was conducted to explore the characteristics and mechanisms of hydrocarbon generation from Xiamaling Formation shale in Xiahuayuan,North China.The experiment results indicate the oil generated by the Xiamaling Formation shale in oil window should be classified as "aromatic-intermediate" type,whereas the decreasing of dry coefficient can be ascribed to the cracking of residual bitumen in source rock in the stage of high to post maturity.The amount of hydrocarbon gas generated from residual bitumen can be up to 1-2 m3 per ton rock in high to post mature stage by calculating hydrogen contents in the kerogen,the expelled hydrocarbon,and the residual hydrocarbon.This reveals the importance of residual bitumen as a gas source during high to post mature stage of the kerogen evolution,and also as the broad exploration prospect of these gases.This research highlights the attention should be paid to oil/gas reservoirs sourced from residual bitumen of organic-rich source rock in high mature stage,even the primary oil/gas reservoirs considered as the main exploration targets in middle-upper Proterozoic sediments of North China.