油井人工举升是采油过程的关键环节,经过几十年的发展,国内外形成了有杆泵、电潜泵、螺杆泵、喷射泵、气举等多种举升工艺,但是也存在能耗高、系统效率低、检泵周期短等诸多问题.巴彦河套JH1区块油藏埋深在300～680m,具有埋藏浅、地温梯度低、天然裂缝发育等特点.2018年陆续投产,经过3年的开发,根据地层岩性和供液情况,对举升工艺进行选型,通过应用抽油机、地面驱动螺杆泵、电潜螺杆泵,并配套功图量油、变频等技术,解决了油井举升能耗高、杆管偏磨严重等诸多难题,实现了油井在线监测、无杆举升,降低了单井能耗、生产成本和人工劳动强度.

To improve the prediction accuracy and consistency of liquid production virtual metering of electric submersible progressive cavity pumps（ESPCPs）, a hybrid model（CNN-BiGRU） integrating convolution neural network（CNN） and bidirectional gate recurrent unit（GRU） was proposed, which also incorporated the dual attention mechanism. This production forecast of oil wells is subjected to tubing pressure, casing pressure and pump conditions. First, the dimensionality reduction of data was performed using Pearson’s correlation coefficient and principal component analysis, and the main influential factors were identified. Subsequently, the local connecting and global sharing of the CNN network was used to extract spatial features of liquid production data of oil wells. The extracted features were then fed to the GRU network to extract the temporal features of the data. Finally, the weights were assigned corresponding features via the dual attention mechanism to improve the prediction accuracy of the model. The presented method has been applied to 50 000 data samples of liquid production. The root-mean-square error（RMSE） and mean absolute percentage error（MAPE） of the model were 5.24% and 3.17%, respectively. Compared with the GRU and CNN-GRU models, the presented method delivers excellent prediction performance and greatly improves the prediction accuracy, which marks its high value for engineering applications.

Natural gas hydrates, which only occur in geological environments with special conditions, are characterized by physical properties unique from those of oil and gas, rendering current methods of measuring saturation, such as the conventional Archie formula or the sonic velocity method, inaccurate. Therefore, to obtain a reliable saturation value of natural gas hydrates, we propose a two-parameter calculation model of resistivity and acoustic interval transit time based on logging data. The saturation results calculated using the two-parameter calculation model were far more accurate than those of the core experiment results, with the proposed model having an average relative error of 7%, whereas that of the conventional Archie formula was 24%. These results indicate that the logging two-parameter model effectively improves the calculation accuracy of gas hydrate saturation. The saturation calculation model is based on objective theory and has wide adaptability, which provides a reliable foundation for future hydrate resource evaluation, exploration, and development in the study area.

大港油田歧口凹陷长期大规模使用高矿化度的海水基钻井液钻井,导致复杂油水关系条件下,受井况及钻井液侵入的影响,储层流体性质识别困难.常规测井评价方法着重于响应特征的变化,在早期勘探过程中取得一定的成效,但其局限性随着勘探开发的逐渐深入也越来越明显;及时测井受钻井进度及钻井液侵入复杂性的影响,其效果很难达到预期.综合利用侵入规律、控制因素、油气恢复等特征分析,结合录井资料建立一套集成电阻率校正法、纵向模式判别法、测录井多参数融合法以及套后测井曲线对比法的海水基钻井液条件下储层测井综合评价技术.该套技术在大港油田生产评价中取得良好的应用效果,多口井试油获得高产,为油田整体开发提供了有效的技术支撑.

大港埕海油田受古地理条件及沉积环境、钻井条件等因素制约,储层测井响应特征与含油性存在复杂关系,导致低对比度油藏频繁出现,储层测井响应区分不明显,常规评价方法难以满足开发需求,流体性质判别困难.同时由于井况等原因导致资料缺失,增加了测井评价难度.为解决以上难题,在分析区块地质特征基础上,结合测井、录井、试采资料,分别采用纵向模式判别法、四孔隙度权重分析法以及测录井多学科的多参数融合技术,对测井资料进行深度挖掘,形成一套针对埕海油田深层的流体性质判别方法.该方法针对性地解决了测井评价的瓶颈难题,实现了储层流体性质精确评价,增强了区块适用性,为油田高效建产垫定技术基础.

渤海湾盆地沧东凹陷孔二段属于封闭型陆相湖盆沉积,横向分布广泛、纵向分布稳定,烃源岩品质好,页岩油资源丰富.孔二段页岩油储层岩性多样、薄互层特征明显,且细粒沉积物发育,矿物成分复杂,利用常规测井资料开展岩性定性识别及矿物含量定量计算困难.本文综合分析地质、岩心资料,确定了目标区块页岩油储层的主要岩石类型,分别为长英质页岩、碳酸质页岩、混合质页岩和黏土岩.岩心分析和测井资料结合,明确了不同岩石类型在电成像及常规测井资料上的响应特征.优选深电阻率、补偿密度及补偿声波测井曲线,提出了"补偿声波密度差值—深电阻率比值交会图"的岩石类型定性识别方法,有效提高了页岩油储层岩性识别准确率,并实现了岩石类型分类连续自动判别.针对目标区块页岩岩性复杂、矿物成分多样,常规的矿物含量计算方法与实际差异较大的难题,根据研究区块X衍射全岩分析资料,确定页岩油储层主要矿物为长英质(石英和长石)、碳酸盐岩(方解石和白云石)、黏土,由此建立相应矿物体积模型,利用补偿声波、补偿密度、补偿密度与补偿中子归一化差值、深电阻率、自然伽马、补偿中子等敏感曲线,采用多元逐步回归的方法开展碳酸盐岩、黏土矿物含量计算,通过三次多元回归使得碳酸盐岩和黏土矿物含量计算精度明显提升,在此基础上形成了适合研究区块的页岩油储层矿物含量定量计算测井解释模型,利用该解释模型计算的矿物含量与岩心分析结果一致性较高.所形成的方法有效解决了页岩油储层岩性评价难题,提高了利用常规测井资料进行岩性评价的精度.

以大港油田乌马营地区YGXX井为代表的二叠系石盒子组深层低孔特低渗致密储集层目前勘探程度较低,没有形成配套的测井评价方法.针对乌马营二叠系致密砂岩含气储集层,利用岩心常规分析数据与测井曲线敏感参数相结合,优化储集层参数计算模型,并引入流动单元概念开展储集层有效性评价,建立了储集层有效性评价图板及重新计算渗透率、孔隙度比值(K'/φ')与电阻率比值(RT/Rsh)交会图板,形成了一套致密砂岩气层的测井解释评价技术,填补了该层系致密砂岩储集层测井评价方法的欠缺.在乌马营地区应用6井次效果明显,解释符合率上升至82.4％.

储层构型单元研究是沉积学和储集层地质学一个重要的研究方向,测井和地震资料是最直接的基础资料.对大港油田7、8、9级储层构型单元的测井资料划分方法进行探讨,进行构型单元测井定性划分标准的判定;并在此基础上研究了利用测井多参数交会自动识别储层构型单元的方法;对构型单元的剩余油分布进行分析.通过与岩心井构型单元划分对比,验证了方法的有效性,解决了历史上测井资料划分8、9级储层构型单元的困难.

港北潜山石炭—二叠系地层煤、碳酸盐岩、砂岩等岩性交互发育,且多为过渡岩性,有效的岩性识别直接制约物性和含油性的评价,如何有效评价港北潜山岩性是测录井综合评价需要解决的重要问题之一.针对港北潜山上古生界复杂储集层岩性特征开展研究,形成了一套测井、录井资料相结合,适合港北潜山上古生界碎屑岩储集层的岩性评价技术,提高了潜山复杂储集层的岩性识别能力,为储集层有效性及含油性的评价奠定了基础,为油田增储上产提供了技术保障.

针对中低孔隙度渗透率储层钻井液侵入特征的研究较少,没有形成有效的规律性认识.提出了利用5岩心联测实验进行钻井液侵入规律研究的新思路,将动态联测实验数据与实际测井资料相结合,形成了中低孔隙度渗透率储层钻井液侵入规律认识.并建立了不同孔隙度渗透率条件下中低孔隙度渗透率储层钻井液侵入速率计算模型,进而得到钻井液侵入储层深度.在研究区进行了应用,为测井解释、射孔参数优化设计和压裂施工设计提供了指导性建议.

苏里格气田致密砂岩储集层埋藏深、孔隙度低、渗透性差、孔渗关系及孔隙结构复杂,储集层有效性识别困难.测井束缚水饱和度的大小和录井气测全烃数值的高低均是识别储集层有效性的关键参数.利用岩石物理实验数据,分别从岩性、物性及孔隙结构等方面分析了储集层束缚水饱和度影响因素,在此基础上将储集层分为单峰孔隙结构束缚水饱和度大于30％ 和双峰孔隙结构束缚水饱和度小于30％ 两类,并分别建立了束缚水饱和度计算模型,准确求取储集层束缚水饱和度,同时利用自然伽马、声波时差、补偿密度、孔隙度、渗透率、束缚水饱和度等测井关键参数与录井关键参数气测全烃数值绘制储集层有效性识别图板,建立了储集层有效性测录井关键参数判别标准,用于苏里格气田苏20区块和苏76区块50余口井307层进行有效性评价.结果显示,通过生产数据验证符合284层,储集层有效性识别符合率达到92.5％,生产应用效果良好.

应用测井资料对碳酸盐岩储集层产能进行定性或定量评价预测一直是测井评价难题,尝试利用反射波能量进行碳酸盐岩储层预测取得较为理想的效果.对反射波在传播过程中的能量损失原因进行分析,采取了相应的补偿方法,利用能量计算公式对补偿后的能量进行计算.分析了能量与产能的关系,给出了半定量的产能预测方法.塔里木油田的14口井数据分析表明,在大部分情况下反射波的能量与产能基本上呈正相关关系,其相关性较高,可以用反射波的能量进行碳酸盐岩储层产能的半定量预测.

Given is a brief introduction to the principles,the main functions and the technical characteristics of remote exploration acoustic reflection imaging logging,and analyzed are the applied results in evaluating fractured reservoirs adjacent to the wellbore with the examples of two wells.Several actual loggings prove that,where there is no reflected information on the remote exploration acoustic reflection images,there is compacted zone,while there is the information on the images,there is poor wave impedence.The reason caused such impedence should be practically analyzed.The studies indicated the remote exploration acoustic reflection imaging logging technique can solve the problems between well logging interpretation and oil testing to a certain extent,which exist in carbonate rock and the other fractured reservoir,improve the radial resolution of acoustic logging,the investigation depth is 3~10 m from borehole wall,and also give out the net pay thickness of the actual reservoirs of outer borehole wall.

Array induction logging in wells drilled with fresh water mud usually shows character of resistive invasion in water bearing zones whereas shows character of conductive invasion in oil bearing zones.Nevertheless there might be resistive invasion in oil bearing zone in complex bore condition.All array induction logs in 32-,33-,37-and 38-layer of well-MX1 in DG Oilfield obviously showed negative diversity.It is a typical character of water zone,so that all the layers were firstly interpreted as water zones.However,well test did verify that the 32-layer among them is an oil-gas zone.Cognition based on analysis is that: While drilling with high density fresh mud in bad well condition,since the invasion radius has been greater than the maximum investigation depth,what the logging tool practically measured is merely the invasion zone,false identification on this situation will cause oil-gas zone to be lost in interpretation.The phenomenon that the resistivities measured in second logging by 10～90 in array induction logging are obviously greater than that in first logging is also a character of resistive invasion where the formation water has been keeping on being diluted.