The buried-hill fractured reservoirs are an important area of offshore exploration and development inChina. The fracture is the key factor affecting seepage and production of buried-hill fractured reservoirs and thefracture width is the core parameter. To solve the problem of logging quantitative calculation of fracture width,based on the previous work, a large-scale granite physical model for the data can be collected by FMI ofSchlumberger's electric imaging logging instrument and ERMI of China Oilfield Services Limited's electricimaging logging instrument is established. Secondly, the fracture widths of the physical model are measuredusing a width gauge with an accuracy of 1 mu m. Finally, FMI and ERMI electric imaging logging data of thephysical model are collected under different mud mineralization conditions. The relationship between theresponse of electric imaging logging of various widths and angles of fractures are analyzed under differentformation contrasts. The research results show that: (1) With the same electric imaging logging instrument, thefracture width shown in FMI and ERMI increases with the increase of formation contrast; (2) Under the sameconditions, the ERMI image shows a slightly wider fracture width than the FMI image; (3) Using accuratecoefficients, the fracture widths calculated by FMI and ERMI have good consistency. The above conclusions andunderstandings will provide experimental bases for the accurate evaluation of fracture widths and other fractureparameters, and technical supports for the efficient exploration and development of offshore buried-hill fracturedreservoirs in China.

With the increasing number of complex well types in the development stage of oil and gas fields, it is becoming increasingly urgent to use remote detection logging while drilling (LWD) to explore the geological structures in a formation. In this paper, the feasibility and reliability of the dipole remote detection of logging while drilling are demonstrated theoretically. For this purpose, we use an asymptotic solution of elastic wave far-field displacement to derive the calculation formula for the radiation pattern and energy flux of an LWD dipole source. The effects of influencing factors, including the source frequency, formation property, drill collar size, and mud parameter, on the radiation pattern and energy flux are analyzed. The results show that the horizontally polarized shear wave (SH-wave) has a greater advantage in imaging the reflector compared with the cases of the compressive wave (P-wave) and vertically polarized shear wave (SV-wave), which indicates the dominance of the SH-wave in dipole remote detection while drilling. The optimal source excitation frequency of 2.5 kHz and inner and outer radii of the drill collar of 0.02 and 0.1 m, respectively, should be considered in the design of an LWD dipole shear wave reflection tool. However, the heavy drilling mud is not conducive to remote detection during logging while drilling. In addition, the reflection of the SH-wave for the LWD condition is simulated. Under the conditions of optimal source frequency, drill collar size, and mud parameters, the reflection of the SH-wave signal is still detected under the fast formation.

Reliable segmentation of pores and minerals from high-resolution (HR) digital rock data is the fundamental prerequisite for accurately characterizing the digital rock's physical properties. Limited by the complexity of the super-resolution (SR) issues and the user bias for segmentation, conventional SR enhancement and segmentation methods are generally brutal in satisfying the research demands. In recent years, with the introduction of deep learning technology into digital rock research, deep learning-based approaches for SR enhancement or segmentation methods have emerged and achieved significantly better effects than conventional approaches. Most deep learning-based digital rock SR enhancement and segmentation processing steps are currently separate. Still, preliminary studies have demonstrated that an end-to-end approach that integrates the two steps could achieve better performance. However, the training cost of 3D deep neural networks that can be directly applied to 3D digital rock processing is usually expensive. In contrast, 2D networks cannot be effectively applied to SR segmentation of 3D digital rocks. Here, we present an end-to-end SR segmentation framework for 3D digital rock based on a 2D multi-task joint deep neural network. The multi-task joint networks utilize a parallel architecture that integrates the SegNet for the segmentation task and the EDSR for the SR task. We also improved the loss function to address the issue of category imbalance and proposed an approach to utilize the 2D network for 3D digital rock processing. We demonstrate the effectiveness of the proposed network framework, the improved loss function, and the 3D digital rock processing strategies through ablation experiments on the high and low-resolution (LR) CT image datasets captured by imaging devices. The results show that the evaluation metrics and physical properties of the SR-segmented 2D\3D digital rocks align with the HR-segmented results (ground truth). It indicates that the proposed framework can improve the performance of digital rock SR enhancement and segmentation and that it is essential to integrate deep learning frameworks into digital rock analysis.

由于渤中19-6气田潜山裂缝性储层的储集空间多样、非均质性很强,且制约产能的主控因素认识不清,从而造成潜山裂缝性储层的产能预测困难.为了解决这一难题,综合岩心、测井、地质等资料分析了潜山裂缝性储层的特征,并基于CT扫描实验定量表征裂缝,研究裂缝微观特征,形成了以裂缝渗透率为核心的一系列裂缝参数的计算方法,建立了潜山裂缝性储层的产能预测模型,大幅提高了潜山裂缝性储层的产能预测精度.研究结果表明,潜山裂缝性储层的裂缝渗透率主要由裂缝的长度、宽度及连通性控制,与孔隙度的大小无明显关系,可以通过斯通利波反演的总渗透率与基质渗透率之差计算得到,其中基质渗透率计算的相对误差为28.50％,总渗透率计算的相对误差为15.56％;综合考虑潜山裂缝性储层的裂缝渗透率、裂缝纵向连通性和有效厚度,建立了渤中19-6气田潜山裂缝性储层的产能预测模型,其中裂缝渗透率计算结果的准确性决定了潜山裂缝性储层产能预测结果的可靠性.

China has abundant coalbed methane (CBM) resources, which is a good reserve of natural gas. The development and utilization of CBM has multiple values. Gas content of coal is the key to evaluate coal seam, and it is also an important factor to determine the exploration and development area and productivity potential of CBM. Using logging data to evaluate gas content is an important means in CBM exploration and development. In order to avoid the density difference caused by different methane states and the underestimation of gas content caused by Langmuir monolayer adsorption model in coal seam, a new method is adopted to separate the NMR signal of adsorbed natural gas in coal seam, calculate the molecules mole number of natural gas in unit volume formation, and convert into the gas content in standard state by density logging. The experimental results of methane isothermal adsorption and NMR show that different T2 cut-off values can be used to distinguish methane states in coal seam. The adsorpted methane content calculated by using new method based on NMR is in good agreement with the measurement of coal sample, which proves the effectiveness of the method. The actual logging data processing and interpretation results show that the new method based on NMR logging is more effective than the method based on conventional logging in calculating gas content of coal seam.

近年在中国渤海、南海海域陆续发现大中型潜山裂缝性油气田,使得潜山逐渐成为中国海上勘探开发的重要领域.潜山裂缝性储层岩石矿物组分复杂、储集空间多样、非均质性很强,从而给测井评价带来了前所未有的技术挑战.系统梳理渤海海域锦州25-1南、蓬莱9-1、渤中19-6、渤中13-2和南海东部惠州26-6等潜山油气田,从潜山裂缝性储层的岩石矿物特征、储层物性分布和储集空间结构出发,总结了潜山裂缝性储层测井评价的研究进展,主要包括石英、长石、云母等岩石矿物组分的精细解释,以不同类型渗透率为核心的储层参数计算,结合裂缝类型、密度、有效性等方面的综合评价;阐明了潜山裂缝性储层测井评价的技术难点,重点包含油、气、水层的准确识别,以裂缝宽度和裂缝延伸长度为核心的裂缝定量表征以及储层产出能力的分级预测;理清了潜山裂缝性储层测井评价的攻关对策,核心是实施测井采集—处理—解释一体化、研制—试验—应用一体化和测井—录井—测试一体化,三位一体有机结合,进行多方位、多角度、多层次地攻关研究,旨在系统地建立海上潜山裂缝性储层测井评价技术体系,从而为海上潜山裂缝性油气藏的高效勘探开发提供测井技术支撑.

复杂储层中普遍存在孔隙度相近而渗透率差异较大的现象.为了揭示其原因,采用铸体薄片、核磁共振、CT扫描成像等实验评价孔隙的连通性.连通孔隙度是渗透率的一个主要贡献参数.因此,从岩石孔隙空间的导电机理出发,以导电孔隙度为桥梁,建立连通孔隙度的计算模型,并分析十二种不同类型岩石中连通孔隙度与总孔隙度的函数关系;基于连通孔隙度的计算模型,建立普适性的核磁共振T2模型;以石灰岩储层为例,在相近孔隙度条件下,从不同类型岩石渗透率之间的差异出发,推导、建立孔隙度指数模型,得到孔隙度指数的分布范围.基于普适性的核磁共振T2模型,可将石灰岩储层渗透率预测的平均绝对误差从20.41mD降至0.83mD.该方法具有一定的理论价值和实际意义.

In order to explore the productivity characteristics of coalbed methane（ＣＢＭ） wells and reasonably allocate the development sequence, according to the actual production data analysis of CBM production wells in Shizhuang south area of Qinshui Basin, four types of characteristic values of the drainage curve were extracted: average daily gas production, peak daily gas production, the time to reach the peak and the production time. Combining the shape of the drainage curve and the 4 characteristic values, three production capacity modes were established, and the production characteristics of the three production capacity modes were analyzed. The random forest algorithm is used to establish the nonlinear relationship between the three productivity models and the geophysical logging data corresponding to the No.3 coal seam. The hyperparameters of the random forest model are determined by grid search combined with cross-validation, and the log curve is established. Classify the prediction model for the capacity pattern of the feature vector. Comparing the predicted category with the actual category, the accuracy rate of prediction reached 91.7%. This shows that the CBM productivity pattern recognition based on the random forest algorithm has high prediction accuracy.

煤储层具有特殊而复杂的孔隙、裂隙网络,包含孔隙和裂缝.煤储层孔隙分布对天然气的储集性能和产气能力具有重要影响.传统的实验技术不能完全描述煤储层的孔隙分布,为了准确描述煤储层的孔隙分布,研究了回波间隔时间和极化等待时间对煤储层核磁共振T2谱和孔隙度测量的影响,明确了回波间隔时间应≤0.2 ms、极化等待时间应≥6 s才能准确描述煤储层孔隙分布.与低温氮气吸附实验相比,核磁共振T2谱测量结果弥补了对煤储层孔径大于100 nm的孔隙、裂隙的描述.并利用核磁共振T2谱转化为煤储层孔隙分布,建立了煤储层纳米孔体积与Langmuir体积、Langmuir压力的关系,由此可以利用核磁共振T2谱描述煤储层对甲烷的吸附能力.

生产动态测井资料的应用,往往局限在直观的判断性应用,在深度挖掘生产动态测井数据的应用方面较少.以油、水两相渗流理论和物质平衡方程为基础,提出了利用时移生产动态测井资料计算剩余油饱和度的新方法;根据产水率与含水饱和度的分布范围和特征,利用不完全Beta函数进行曲线拟合,通过迭代算法找到全局最优解,得到了产水率与含水饱和度的定量转换关系式.在此基础上进一步建立了产水率与驱油效率之间的定量关系,实现了本文方法在不同储层类型水淹级别划分中的应用.实例应用结果表明,水淹级别解释符合率达到90％.本文方法可推广应用于多种储层的水淹级别判别中.

随着煤层气勘探的不断深入,对煤层含气量预测精度提出了更高的要求.基于煤层含气量测井响应特征,分析测井参数与含气量的相关性,提出MIV(Mean Impact Value)技术与LSSVM(Least Squares Support Vector Machine)结合的测井参数优选策略,优选最优测井参数作为网络建模的输入自变量组合,通过粒子群算法优化LSSVM网络核心参数,最后构建一套适用于煤层含气量预测的MIV-PSO-LSSVM模型.在此基础上,分别对比分析LSSVM、PSO-LSSVM、MIV-LSSVM和MIV-PSO-LSSVM模型对煤层含气量的预测性能,并与传统多元回归方法进行了对比,利用拟合优度和均方根误差对此5类模型进行评价.结果表明:PSO优化下的LSSVM模型预测精度得到有效提升,结合MIV方法优选测井参数可大幅度改善神经网络建模性能,MIV-PSO-LSSVM模型可实现煤层含气量高精度预测,为煤层气勘探及其储层评价提供新的技术支撑,且本研究的建模策略及思想可广泛应用于其他机器学习建模研究领域.

煤岩是一种双孔隙介质储层,主要包含基质孔隙度和割理(裂隙)孔隙度两部分,越高阶的煤岩割理越发育.割理是决定高煤阶煤岩孔渗的主要控制因素,也是决定煤层气井产能的重要因素.传统的裂缝孔隙度主要采用双侧向电阻率测井评价方法,该方法不适用于正交裂缝发育的高阶煤层.本文基于高阶煤层的气水赋存特征与测井响应特征分析,认为高阶煤层的割理系统中充满了地层水,可以看作饱含水裂缝型岩石系统,煤层的电阻率高低主要取决于割理孔隙度大小、地层水矿化度高低以及煤层割理孔隙系统连通性.因此提出了基于阿尔奇公式法的煤岩割理孔隙度评价方法,进而计算煤岩割理渗透率.在研究区计算的煤层割理渗透率与煤层气井平均日产量具有很好的相关性,表明基于阿尔奇公式法的割理孔隙度和渗透率评价方法是有效的,对准确认识高阶煤层的物性与产能具有重要的实用价值.

煤体结构作为煤层勘探开发研究的重点参数之一,影响着煤层产能,有效识别煤层煤体结构至关重要.本文利用支持向量机算法,以地球物理测井资料为基础进行煤体结构识别,并以沁水煤田柿庄北区3号层为例,对该区块进行煤体结构类型分类,利用支持向量机的双二分类与"一对多"分类两种建模模式,建立基于测井曲线的煤体结构识别模型,再利用交叉验证评价模型的泛化性,并对该模型用未参与建模数据进行准确性评价.结果表明,应用支持向量机算法的两种模式能有效识别煤体结构,模型具有泛化性与准确性,且"一对多"分类模式精度更高,在对有利产出煤和不利产出煤的区分上效果突出,对有利产出煤的具体类型区分上具有准确性,可对后续压裂施工提供指导.总体上,基于支持向量机算法和地球物理测井资料建立的煤体结构识别模型对煤层气勘探开发有指导意义,具有实际应用价值.

生产动态测井是油田监测的重要措施,目前对其系统性应用研究较少.以七参数生产动态测井技术为例,对该测井技术进行了简要介绍,并对其在注水油田中的应用进行了全面、系统的总结.七参数生产动态测井技术现场应用体现在以下5方面:①基于涡轮转速变化情况识别管柱状况;②通过小层产量劈分评价合采储层有效性;③通过动静态组合测井识别有效裂缝;④基于时移生产动态测井监测水淹动态;⑤基于注入剖面测井的非均质储层注入能力评价.实践表明,生产动态测井在油田动态监测中具有良好的应用效果,可为油田生产措施的制定与调整奠定基础.

渤中19-6气田潜山储层储集空间类型复杂多样,除发育粒间孔、溶蚀孔以外,裂缝十分发育,导致储层具有较强的非均质性,使得不同探井之间测试产能差异较大,因此有效评价储层裂缝的发育情况至关重要.本文利用快、慢横波速度差异计算得到地层的各向异性大小,通过电成像测井获取的裂缝密度进行标定,建立了渤中19-6气田评价近井地层裂缝发育程度的各向异性判别标准,使声波各向异性评价地层裂缝由定性发展到半定量,弥补了电成像测井质量差时难以识别裂缝的不足.在此基础上,首次将偶极横波远探测技术应用到变质岩潜山地层中探测井外数十米内的大尺度裂缝,建立了一套由近及远、纵横结合的裂缝测井评价技术体系,从而为该气田裂缝准确评价及后续高效开发提供了有力支持.

目前M油田面临含水率不断升高、产油量降低的问题,需对油田实施动态监测并进行生产措施调整.生产动态测井资料能够对油井产出层位、流体性质进行识别并计算产量,其解释结果对井筒生产状况认识和开发措施调整至关重要.由于生产动态测井曲线质量受管柱条件、施工状况、流体类型等多方面因素的影响,其解释结果的精度往往较低,影响现场决策.重点研究了复杂管柱条件下生产动态测井资料的精细解释方法,将生产动态测井所提供的产出剖面和注入剖面应用于产水层位识别、封堵作业以及注水方案制定.实际应用表明,生产动态测井在M油田动态监测、增油上产中应用效果良好.

The accurate calculation of the gas content of coalbed bed methane (CBM) reservoirs is of great significance. However, due to the weak correlation between the logging response of coalbed methane reservoirs and the gas content parameters and strong nonlinear characteristics, it is difficult for conventional gas content calculation algorithms to obtain more reliable results. This paper proposes a CBM reservoir gas content assessment method combining K-means clustering and random forest. The K-means clustering is used to divide the reservoirs and distinguish the types to establish a random forest model. Judging from the evaluation effect of the research block, the prediction accuracy of the new method is significantly higher than that of the original method, and more accurate gas content prediction values can be obtained for different types of reservoirs. Studies have shown that this method can help the gas content evaluation of CBM reservoirs, improve the accuracy of gas content evaluation, and better support the exploration and development of CBM reservoirs. The results of this study show that the random forest method based on clustering can effectively distinguish the relationship between different logging responses and gas content. On this basis, the random forest algorithm modeling can effectively characterize the complex relationship between gas content and logging curve response. In the case of poor correlation between gas content and logging curve, the gas content of the reservoir can also be accurately calculated.

孔隙度、饱和度是油气藏评价、储量计算的关键参数.由于临兴区块勘探层系众多、沉积相类型及物源多样,岩石成分复杂,岩屑、长石含量高,岩石骨架参数变化大,现有方法评价孔隙度精度低.提出了基于物源分类的岩心标定测井的孔隙度精细评价新方法.致密砂岩储层由于成岩作用强烈,容易形成复杂的孔隙结构或孔隙类型,导致岩石导电规律复杂、岩电参数变化大,难以准确计算饱和度.以铸体薄片、X射线衍射、常规物性等岩心分析资料为基础,分析认为研究区存在6种成岩相类型.通过大量的岩电实验研究,探讨了不同成岩作用对致密砂岩电性特征的影响,并利用测井三孔隙度比值与干岩样密度交会方法,对不同孔隙类型的致密砂岩储层进行分类.提出了一种适用于不同成岩相的非线性阿尔奇含水饱和度模型,计算精度明显优于现有饱和度公式,解决了致密砂岩气藏饱和度定量准确评价的难题,为临兴千亿方天然气探明储量提交奠定了坚实基础.

在更加复杂的地质因素影响下,常规测井方法识别煤体结构准确度低,为精确识别煤体结构,研究了煤体结构测井曲线响应机理以及随机森林决策树个数的优选,从而建立煤体结构与测井曲线的随机森林分类模型进行煤体结构识别.结果 表明:决策树个数为500时,随机森林分类模型效果最佳;通过袋外误差和模型对测试集样本的预测结果可知,随机森林分类模型的结果稳定且泛化性强,并且适合处理非均衡数据,预测精度较高.可见随机森林算法能有效识别煤体结构,为煤层气开发提供帮助.

煤层气含量是煤层勘探开发研究的重点参数之一,由于煤层气含量受多因素影响,能有效预测其含量至关重要.本文将斜率关联度法与随机森林算法相结合,以地球物理测井资料为基础进行煤层气含量预测.首先利用改进的斜率关联度法,计算得到对煤层气含量敏感的测井曲线,再利用交叉验证法探究合适的随机森林决策树个数,并结合选出的超参数利用随机森林算法预测煤层气含量.以沁水煤田柿庄北区3号层为例,对该区块进行评价预测,并将预测结果与多元回归模型拟合结果进行对比,同时对本文方法模型的泛化性进行研究分析.结果表明,应用斜率关联度法对测井曲线与煤层气含量进行分析计算能准确有效地找到可用于煤层气含量预测的测井曲线;用随机森林算法训练得到的模型预测非夹矸段煤岩的煤层气含量准确,计算结果可信度高,在夹矸段预测能力较弱,总体对煤层气勘探开发有指导意义,具有实际应用价值.