改进人工神经网络原理对储层渗透率的预测——以北部湾盆地涠西南凹陷为例

人工神经网络的计算方法是一种非线性处理系统,是根据测井数据进行储层物性参数预测的方法。以往在利用遗传算法预测渗透率的时候,因为只考虑了单一的数据点,没有把临近层位的数据加入学习过程中来,故影响了预测模型的精度和可信度。为弥补这一不足,利用相临多个层位的数据点进行学习,进而建立储层渗透率的预测模型,并在岩心分析化验数据和相关测井曲线数据归一化的基础上,利用改进的开窗技术,借助反馈的神经网络方法对地层的渗透率进行逐点计算。通过北部湾盆地涠西南凹陷的实例实践表明,用该方法预测的渗透率与实测的渗透率的值符合较好。     

The Prediction of Permeability From Well Logging Data Based on Reservoir Zoning,Using Artificial Neural Networks in One of an Iranian Heterogeneous Oil Reservoir

Abstract

The distinct characteristics of Iranian oil reservoirs, such as high pressure, heterogeneity and anisotropy, high thickness, carbonation, huge size, and presence of cracks and various rock types, lead to deficiency of present applications of neural network methods. The authors attempt to improve the proficiency of present methods in one of Iranian heterogeneous oil reservoirs for permeability prediction using the well logging data, by zoning the reservoir on the basis of geology characteristics and sorting the data in correspondence. The obtained results from the well logging data using artificial neural networks are compared with the measured permeability in core analysis experiments. The appropriate compatibility of the results confirms the proposed method.     

宝浪油田油气层评价标准及应用

宝浪油田油气层物性较差,属于低孔、低渗、低显示油气层,油气层评价有一定难度,仅用单一的识别模式会遗失部分油气层,应用油藏物理学、渗流理论、神经网络等理论,根据试油资料,测井、录井信息,建立交会图法、模式识别和人工神经网络等宝浪油田油气层评价标准,并在实际解释中得以应用,取得了较好的效果。     

基于核磁测井孔喉分布的致密砂岩储层评价方法——以四川盆地Q地区沙溪庙组二段为例

四川盆地Q地区是致密气勘探开发的重要区块,但该区储层孔隙结构复杂、纵向变化快、储层品质评价难度大,给水平井箱体选择带来较大困难,同时传统的岩心孔渗关系、核磁测井Timur-Coates和SDR公式计算渗透率精度较差,难以满足生产实践需要。为了利用测井资料评价储层类型及渗透性,通过分析四川盆地Q地区沙溪庙组二段储层核磁测井响应特征,结合不同储层的常规测井、阵列感应等资料,优选有效孔隙井分级评价、优选优质储层提出水平井箱体设计建议,根据不同喉道占比与渗透率关系分析结果,提出了基于核磁测井孔喉分布的渗透率计算方法评价储层渗透性。应用结果表明:储层测井分类方法有效评价了储层内部非均质性,同时基于核磁测井孔喉分布计算渗透率与岩心渗透率吻合性较高,计算精度高于岩心孔渗相关性法及Timur-Coates和SDR法。     

普光气田飞仙关组和长兴组测井解释方法

普光气田飞仙关组和长兴组碳政盐岩储层具有溶蚀孔发育、局部裂缝发育、储层孔隙结构比较复杂、非均质性比较强的特点.钻井取心资料表明,岩石中白云石质量分数与溶蚀孔洞的发育具有密切关系,以鲕粒白云岩和残余鲕粒白云岩为最优.从储层孔隙结构入手,利用岩电关系研究成果优化测井解释模型,提高储层孔隙度、渗透率和饱和度等参数的计算精度;...     

延迟神经网络测井资料评价水淹层的方法及应用

以取心分析的孔隙度和水饱和度为基础,建立测井信息与这些地居参数之间的非线性计算关系.用这种方法进 行参数解释,测井信息与油层参数之间的复杂关系不需要具体的数学物理模型描述,而只需要合适的样本集对网络进行 训练来获得解释模型,避开了油层水淹后,混合水电阻率求不准的问题.不同于已有的点对点的建模方法,本方法采用延迟神经网络模型,在建模和计算过程中自动考虑了测井响应上下围岩的影响.从而较好地解决了测井资料解释中地层厚度自适应校正和地层参数计算同时进行的问题.对一个油田注水开发后期 50口井的测井资料计算表明,这种方法具有良好的效果.     

用核磁共振测井评价特低渗透砂岩储层渗透性新方法

核磁共振测井被广泛用于评价低孔隙度低渗透率储层的孔隙结构与渗透性,主要依据经典的Coates及SDR模型。这些模型是基于中高孔隙度、渗透率储层的实验结果,大量岩心实验数据表明它们并不适用于特低渗透砂岩储层。应用气象学研究常用的空间物理场分布模型定量评价低孔隙度特低渗透率储层中特定尺寸孔隙分布的集中程度,并给出了定量计算瓦分布均一系数模型。常规孔隙度渗透率实验、饱和盐水岩心核磁共振实验均验证了该模型在不同孔隙度、渗透率条件下具有较好的适用性。     

Improved Permeability Prediction of a Heterogeneous Carbonate Reservoir Using Artificial Neural Networks Based on the Flow Zone Index Approach

Abstract

Permeability is one of the most important parameters required for reservoir characterization. Although core analysis provides more exact information, core data do not exist for all wells in the reservoir because coring is expensive and time consuming. Therefore, another approach should be sought for permeability determination. The objective of this study was to create an artificial neural network (ANN) model in order to use well log data to predict permeability in uncored wells/intervals. The well log, core, and other data were gathered from an Iranian heterogeneous carbonate reservoir. A flow zone indicator was then predicted using an ANN approach with well logs as input variables. The reservoir was thus classified into different zones based on hydraulic flow units to overcome the extreme heterogeneity. Then, a separate ANN training procedure was followed for each flow zone with log data as input variables and permeability as output. This improved method is capable of permeability prediction in heterogeneous carbonate reservoirs in uncored wells/intervals with an average error of less than 10.9%.     

用测井确定储层敏感性

应用测井确定储层敏感性是一个全新的课题.在收集薄片、铸体薄片、粒度、压汞、X-衍射、扫描电镜、物性、敏感性流动实验等各种岩心分析资料的基础上,首次探讨了应用测井确定储层敏感性的问题.从测井信息中提取的石英骨架、长石骨架、岩屑骨架、泥质、蒙脱石、绿泥石、伊利石、高岭石、粒度中值、地层水总矿化度、综合物性参数、孔隙度、渗透率、毛细管半径中值等14个参数,经过岩心标定(即测井建模)后,都可由测井信息连续处理获得.以这些参数为基础进行了储层敏感性与各参数的单相关分析,提出了理论排序表,并提出了单相关系数加权的方法来实现由测井预测储层敏感性.应用该方法对我国西部某油田进行了实际处理分析,结果表明由测井连续处理得到的速敏、水敏、盐敏、土酸敏和碱敏结论与该地区的敏感性流动实验结果基本吻合.它对指导探井泥浆配方设计、及时发现有工业价值的油气层和及时进行油气层保护有重要意义.     

乌马营二叠系致密砂岩气层测井评价方法的完善

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...     

A CRITICAL COMPARISON OF NEURAL NETWORKS AND DISCRIMINANT ANALYSIS IN LITHOFACIES,POROSITY AND PERMEABILITY PREDICTIONS

The application of a genetic reservoir characterisation concept to the calculation of petrophysical properties requires the prediction of lithofacies followed by the assignment of petrophysical properties, according to the specific lithofacies predicted. Common classification methods which fulfil this task include discriminant analysis and backpropagation neural networks. While discriminant analysis is a well-established statistical classification method, backpropagation neural networks are relatively new, and their performance in predicting lithofacies, porosity and permeability, when compared to discriminant analysis, has not been widely studied. This work compares the performance of these two methods in prediction of reservoir properties by considering log and core data from a shaly glauconitic reservoir. The neural network approach, while subject to a degree of trial and error as regards the selection of the optimum configuration of middle nodes, is shown to be capable of excellent performance. In the example problem considered, the neural network approach provided estimates superior to those based on a discriminant analysis approach. Further studies, on different formations, will be required to test the generality of this conclusion, and to refine the selection of neural network parameters.     

河南泌阳特超稠油储层水淹层测井解释

河南浅层特超稠油油层成岩程度低,储层松散,具有孔隙度大、渗透率高、含油饱和度高的特点.蒸汽吞吐过程中油层出砂严重,蒸汽吞吐后水淹层岩心和电性特征变化明显,依据岩电关系的研究,建立了一套快速、直观的水淹层定性和定量测井解释的声波时差-深侧向电阻率图版解释法、神经网络技术识别方法、C/O比能谱测井解释法.经过河南稠油油田39口井的验证,水淹层解释符合率达89.7%.     

基于MATLAB的BP神经网络在储层物性预测中的应用

在阐述BP神经网络模型结构的基础上.根据取心井段储层物性与测井信息的关系,选取相应的测井曲线,运用MATLAB神经网络工具箱中特定的函数对建立的神经网络模型进行训练,使得储层物性(孔隙度、渗透率)和测井响应之间具有较强的非线性映射关系,在一定的条件下运用该模型可对研究区未知样本的物性参数进行预测.实例研究表明,预测准确性较高,显示出BP神经网络对储层预测的潜在优势和实用价值.     

Estimating the initial pressure,permeability and skin factor of oil reservoirs using artificial neural networks

Artificial neural network, a biologically inspired computing method which has an ability to learn, self-adjust, and be trained, provides a powerful tool in solving pattern recognition problems. In this study, a new approach based on artificial neural networks (ANNs) has been designed to estimate the initial pressure, permeability and skin factor of oil reservoir using the pressure build up test data. Five sets of actual field data in conventional and dual porosity reservoirs have been used to test the results of the neural network. The results from the network are in good agreement with the results from Horner plot. Finally, it is shown that the application of artificial neural networks in a pressure build up test reduces the cost of the test and it is also a valuable tool for well testing.     

用测井方法评价储层的敏感性

为了快速、准确、有效地评价储层的敏感性，在岩心分析资料的基础上，提出了用测井方法评价储层敏感性。从测井信息中提取出石英骨架、长石骨架、岩屑骨架、泥质、蒙脱石、伊利石、高岭石、粒度中值、综合物性参数、孔隙度、渗透率等11个参数，经过岩心标定后，都可由测井信息处理获得。以这些参数为基础进行储层敏感性与各参数的相关性分析，提出了用理论排序表和相关性系数加权的方法来实现测井方法预测储层的敏感性。应用该方法对某油田进行了处理分析，结果表明由测井处理得到的速敏、水敏、盐敏、酸敏和碱敏结论与该地区的敏感性流动实验结果基本吻合．     

鄂尔多斯盆地陇东地区长8段储层特征与储层四性关系研究

鄂尔多斯盆地三叠系长8储层在陇东地区是重要的勘探目的层之一,其储层物性较差,成岩作用复杂,导致储层非均质性较强,因此对其储层特征的研究工作已成为研究重点之一。根据该地区长8区域地质背景,通过对该区数百口井的测井、录井、岩心和试油等资料的收集、整理、校正、分析,结合铸体薄片和扫描电镜等实验观察资料,解释制作出相关图件,对研究区低渗储层的特征及四性关系作了较为详细的剖析。     

准噶尔盆地中拐凸起佳木河组储集层物性实测值校正

准噶尔盆地西北缘中拐凸起佳木河组致密砂岩储集层岩心实测渗透率主要分布在0.100~1 000.000 mD,与测井渗透率相差4~6个数量级,实测渗透率明显失真,影响了储集层评价的准确性。从研究区地质背景出发,综合测井和岩心资料,通过对该区10口井644块样品薄片进行分析,结合压汞法、铸体薄片、X射线衍射、图像分析统计等,分析了储集层物性实测值失真主因。研究结果表明：取至地表的岩心中,胶结物浊沸石减压膨胀形成的假粒缘缝,是引起测试岩心渗透率异常偏高的主因;浊沸石含量与假缝面孔率、地层电阻率与中子孔隙度比值呈正相关;当浊沸石含量小于5%,假缝面孔率在1%以下,孔隙度与渗透率呈良好相关关系,但随着浊沸石含量增加,渗透率明显变大（多数在1.000 mD以上）,与区内储集层类型和测井结果不符。通过分析岩石薄片和测井资料,确定假缝面孔率与浊沸石含量和假缝孔隙度的关系,并参照测井孔隙度,剔除假缝孔隙度,得到校正后的真孔隙度和对应的渗透率。校正后的储集层渗透率主要分布在0.001~5.000 mD,与测井渗透率接近,证实校正方法可靠。     

火成岩储层物性参数模型及油层判识——以准噶尔盆地车排子凸起石炭系为例

准噶尔盆地车排子凸起石炭系发育火成岩油藏,但其储层岩性和物性特征十分复杂。运用岩性鉴定、岩心实测、成像测井、常规测井和试油测试等资料,总结出该区石炭系火成岩孔隙-裂缝储集空间组合特点与规律,即总孔隙度为基质孔隙度和裂缝孔隙度之和,总渗透率为基质渗透率和裂缝渗透率之和,对于裂缝不发育的储层总渗透率近似为基质渗透率。以岩心实测为约束,运用三孔隙度曲线多元回归和FMI成像测井识别有效裂缝等方法,分别建立了基质、裂缝和总体的储层参数测井解释模型。与实测储层物性对比验证,模型合理,为车排子凸起火成岩储层物性评价提供新手段,对其它地区火成岩油藏储层评价提供了借鉴。以储层参数测井解释模型为基础,结合多项钻井、录井和试油资料,建立了车排子地区石炭系火成岩油藏油层判识标准。