Implementing PSO-LSSVM model to approximate vaporization enthalpy of pure hydrocarbons and petroleum fractions

The purpose of the present research was to estimate the heat of vaporization for petroleum fractions and pure hydrocarbons by the least-square support vector machine (LSSVM) as a function of the specific gravity, molecular weight, and boiling point temperature. Moreover, a particle swarm optimization technique was applied to determine optimal dependent parameters of LSSVM. In addition, results obtained from the proposed LSSVM model have been compared to some developed correlations by scholars. According to statistical observations, the LSSVM model has acceptable predictions by the value of mean relative deviation and R-squared (R²) equal to 0.51% and 0.9998, respectively. The present predictive manner can be used in petroleum engineering for an accurate approximation of heat of vaporization.     

Phase equilibrium modelling of natural gas hydrate formation conditions using LSSVM approach

The formation of gas hydrates in industries and chemical plants, especially in natural gas production and transmission, is an important factor that can lead to operational and economic risks. Hence, if the hydrate conditions are well addressed, it is possible overcome hydrate-related problems. To that end, evolving an accurate and simple-to-apply approach for estimating gas hydrate formation is vitally important. In this contribution, the least square support vector machine (LSSVM) approach has been developed based on Katz chart data points to estimate natural gas hydrate formation temperature as function of the pressure and gas gravity. In addition, a genetic algorithm has been employed to optimize hyper parameters of the LSSVM. Moreover, the present model has been compared with five popular correlations and was concluded that the LSSVM approach has fewer deviations than these correlations so to estimate hydrate formation temperature. According to statistical analyses, the obtained values of MSE and R² were 0.278634 and 0.9973, respectively. This predictive tool is simple to apply and has great potential for estimating natural gas hydrate formation temperature and can be of immense value for engineers who deal with the natural gas utilities.     

Utilization of LSSVM algorithm for estimating synthetic natural gas density

In the gas engineering the accurate calculation for pipeline and gas reservoirs requires great accuracy in estimation of gas properties. The gas density is one of major properties which are dependent to pressure, temperature and composition of gas. In this work, the Least squares support vector machine (LSSVM) algorithm was utilized as novel predictive tool to predict natural gas density as function of temperature, pressure and molecular weight of gas. A total number of 1240 experimental densities were gathered from the literature for training and validation of LSSVM algorithm. The statistical indexes, Root mean square error (RMSE), coefficient of determination (R²) and average absolute relative deviation (AARD) were determined for total dataset as 0.033466, 1 and 0.0025686 respectively. The graphical comparisons and calculated indexes showed that LSSVM can be considered as a powerful and accurate tool for prediction of gas density.     

基于核函数的非线性校正算法在原油快评中的应用

为了快速准确地测量原油的密度、酸值和硫质量分数等重要性质,采用红外光谱技术结合非线性化学计量学定量校正算法建立校正模型。结果表明,分别使用最小二乘支持向量机算法(LSSVM)和核偏最小二乘(KPLS)两种基于核函数的非线性校正算法建模预测原油密度、酸值和硫质量分数的预测标准偏差分别为00065 g/cm3、019 mgKOH/g和038%以及00089 g/cm3、023 mgKOH/g和040%,预测结果的重复性与再现性等同或优于标准方法。与经典偏最小二乘(PLS)方法相比,KPLS算法准确性更高,而LSSVM具有更快的训练速率、更小的测量偏差等优点。     

基于小波变换和LSSVM-DE的天然气日负荷组合预测模型

为了提高天然气短期负荷的预测精度,提出了基于小波变换和LSSVM-DE(Least Squares Support Vector MachineDifferential Evolution)的天然气日负荷组合预测模型,首先,采用Mallat快速算法对天然气日负荷实际采集数据样本时间序列进行小波分解;其次,对分解出来的高频分量和低频分量分别建立LSSVM预测模型,各分量的模型参数分别采用DE进行优化,以期得到更准确的预测结果;最后,分别对各分量的预测结果进行小波重构。以某市实际采集的样本数据为例,并将重构结果与单独应用LSSVM预测模型及ANN(Artificial Neural Networks)预测模型进行对比分析。结果表明:小波变换和LSSVM-DE预测模型的预测精度分别比单独应用LS-SVM和ANN预测模型高出1.662%、1.14%、3.96%、2.99%、15.53%和1.942%、1.01%、3.07%、1.86%、12.26%。该结论预示着将小波变换和LSSVM-DE理论相结合对天然气日负荷时间序列进行预测是一种行之有效的方法。     

碳酸盐岩储层自适应模型常规测井渗透率预测

碳酸盐岩储层常规测井渗透率预测主要依靠物理模型和拟合模型,然而物理模型通常难以获取精准的物理参数,拟合模型难以直接预测非均质性较强的储层。为此,从优化物理模型、拟合模型参数出发,利用改进的粒子群优化算法(IPSO)同时优化物理模型参数及机器学习模型参数,进而提出渗透率预测的自适应模型。以川中北部高石梯—磨溪区块灯影组灯二段储层为研究对象,通过两个实验验证该自适应模型的渗透率预测能力。结果表明：①耦合物理模型和机器学习模型能提高模型的预测能力,有效地解决了应用过程中物理模型基础资料不足问题;②IPSO算法能更有效地优化物理模型参数和机器学习模型参数,IPSO-XGBoost预测性能更优,具有很强的推广性;③通过IPSO算法迭代确定离散岩石类型(DRT)聚类算法中的经验系数更具推广性。该自适应模型可为碳酸盐岩储层渗透率的准确预测提供新思路。     

Applying of LSSVM approach as a novel tool for accurate prediction of asphaltene inhibition efficiency

Asphaltene precipitation is one of critical problems for petroleum industries. There are different methods for inhibition of asphaltene precipitation. One of the common and effective methods for inhibition of asphaltene precipitation is utilizing asphaltene inhibitors. In this work, Least squares support vector machine (LSSVM) algorithm was coupled with simplex optimizer to create a novel and accurate tool for estimation of effect of inhibitors on asphaltene precipitation as function of concentration and structure of inhibitors and crude oil properties. To this end a total number of 75 measured data was extracted from the literature for training and testing of predicting model. The average absolute relative deviation (AARD), the coefficient of determination (R²) and root mean square error (RMSE) of total data for prediction algorithm were determined as 1.1479, 0.99406 and 0.61039. According to these parameters and graphical comparisons the LSSVM algorithm has potential to predict asphaltene precipitation in high degree of accuracy.     

基于粒子群优化最小二乘支持向量机的非线性AVO反演

为了求解非线性AVO反演问题,本文提出基于粒子群算法和最小二乘支持向量机的非线性AVO反演方法,并用粒子群算法优化最小二乘支持向量机的参数。即首先通过精确Zoeppritz方程正演得到角道集,并进行动校正和部分角度叠加;然后运用最小二乘支持向量机方法建立反射振幅与弹性参数之间的非线性模型;最后以此非线性模型对地震道集数据进行反演。模型数据和实际资料的反演结果表明,该方法克服了常规广义线性AVO反演在远炮检距及弹性参数纵向变化大等情况下的缺陷,可直接从实际地震道集数据中提取较高精度的地层弹性参数,具有快速稳健、抗噪能力强的优点。     

不稳定试井分析新图版

在现代试井分析中，典型曲线图版拟合是主要分析手段。图版拟合中普遍存在的较强多解性一直未很好解决，即使目前最常用的压力及其导数与时间的双对数复合图版也是如此。建立了一种新的图版，该图版有２个，一为用于分析渗透率的图版（Ｋ图版）；另一为用于分析井筒储存系数的图版（Ｃ图版）。新图版的特点是曲线形状差异较大，特征明显，且拟合时只需水平方向移动，解的唯一性强。实际数据分析表明，在拟合分析试井早期测试数据时，也可获得较准确的地层参数。图４表１参５（陈志宏摘     

Vertical-horizontal permeability correlations using coring data

Most reservoirs have different degree of permeability anisotropy. Optimization of recovery is crucially dependent on the reservoir quality and ansitropy. The ratio of vertical and horizontal permeability is important when reservoir anisotropy (K_v/K_h) and heterogeneity cannot be neglected. Therefore, an accurate knowledge of vertical and lateral permeability distribution is essential for better reservoir characterization.This work uses routine core data for analysis to develop new correlations and characterization of a sandstone reservoir under development. The two main goals of this study are to use core data to (1) develop correlations capable to predict vertical permeability from horizontal permeability or mean hydraulic radius and (2) develop another correlation capable to predict the permeability anisotropy ratio (Kv/Kh) using porosity data.To accomplish the objectives of this project, various petrophysical properties were experimentally measured for 112 core samples extracted from an actual sandstone reservoir. The measurements included vertical permeability, horizontal permeability, effective porosity and saturations of oil and water.The data derived were used to develop new and improved correlations capable to predict vertical permeability from horizontal permeability for the zones that were analyzed. In addition, another correlation is developed to predict anisotropy ratio from effective porosity.Applications of the developed results of this study help enhancing the prediction of vertical permeability, improving reservoir characterization and providing better simulation studies.     

基于WT与LSSVM的储层流动单元划分方法

某研究区储层特性较为复杂,为了依据测井数据准确求取储层参数,提出基于小波变换(WT)与最小二乘支持向量机(LSSVM)相结合的储层流动单元划分方法。选取21口关键井的岩心物性资料、测井资料,依据流动层带指数划分方法将取心井储层流动单元划分成Ⅰ、Ⅱ、Ⅲ类,建立流动单元的识别规则和划分标准。将WT与LSSVM相结合对取心井储层流动单元进行学习训练,使用WT对各测井曲线分别分解为高频和低频成分,利用C5.0决策树对不同频率成分的训练样本进行参数敏感性分析得到学习所用的训练样本集,利用LSSVM训练训练样本建立流动单元预测识别模型,使用该模型对取心或非取心段储层流动单元进行预测。实验表明,基于WT与LSSVM的储层流动单元划分模型具有较高的识别精度,为储层精细评价提供一种较有效的研究方法。     

A model for estimation of permeability and free flowing porosity

This work highlights the application of an adaptive neuro-fuzzy inference system (ANFIS) for predictions of NMR log parameters including free flowing porosity (FFP) and permeability by using field log data. The input parameters of model were neutron porosity, sonic transit time, bulk density, and electrical resistivity. The outputs of model were also permeability and FFP values. The ANFIS model was trained by using hybrid method. Results showed that the developed model is effective in prediction of field NMR log data. Outcomes of this study can be used in areas of petroleum engineering where accurate and immediate predictions of logging data are required.     

On prediction of asphaltene precipitation in different operational conditions utilization of LSSVM algorithm

Asphaltene which is known as one of the fractions of oil, can cause the important problems during production of crude oil in reservoir, tubing and surface facilities so these problems can influence the production cost and time. In order to predicting and solving asphaltene problems, a powerful Least squares support vector machine (LSSVM) algorithm were developed for asphaltene precipitation estimation as function of dilution ratio, temperature, precipitant carbon number, asphaltene content and API of oil. A total number of 428 measured data were utilized to train and test of LSSVM algorithm. The average absolute relative deviation (AARD), the coefficient of determination (R²) and root mean square error (RMSE) were determined as 7.7569, 0.98552 and 0.26312 respectively. Based on these statistical parameters and graphical analysis it can be concluded that the predicting algorithm has enough reliability and accuracy in prediction of asphaltene precipitation.     

严重非均质油藏开发层系重组渗透率级差界限研究

提出了严重非均质油藏水驱开发后期层系优化重组的调整思路,以及确定多层组合渗透率级差界限的方法。根据油藏动、静态资料,合理选取严重非均质油藏(以胡7南沙三中为例)储层渗透率和级差分布;通过长岩心水驱油实验,确定影响单层驱替效果的主要因素,为数值模拟研究提供参数取值依据;考虑启动压力的影响,对不同渗透率储层在多层组合条件下的驱替进行模拟研究;提出用综合影响因子来反映非均质性对低渗透层动用特征、驱替效果的影响程度,并确定多层组合的渗透率级差合理界限。这些研究结果可为同类油藏水驱开发后期层系优化重组等开发政策的制定提供参考。     

The Validation of Methods to Calculate Gas-Oil Relative Permeability Using Capillary Pressure Data from South Pars Reservoir

Abstract

Gas-oil relative permeability is the most important parameter in the simulation of fluid flow in the gas condensate reservoirs. Experimental measurements of relative permeability need core samples with regular shape, which is costly and time consuming. On the other hand, experimental data of relative permeability may also have significant error and uncertainty in many cases. One source of uncertainty is that the input to numerical simulator is uncertain and inaccurate; it may be reduced if the number of input parameters is decreased, especially if the parameters with the greatest uncertainty are avoided. It is possible to impose only capillary pressure data, because relative permeability can be predicted consistently using specific models. The present methods, which are based on capillary pressure, considered the porous media as a bundle of capillary tubes; they indeed are mercury flow paths that are filled during the mercury injection capillary pressure test at the certain value of capillary pressure. The authors applied the existing capillary models for relative permeability calculations to a gas condensate reservoir. The tested samples have a wide range of liquid permeability from less than 1 to 18 md. The results of this study show that the Purcell model has the best fit with experimental data for wetting phase (oil), and the differences between measured and model data were almost negligible. The predictions of nonwetting phase (gas) relative permeability were a good agreement with experimental data except for Purcell model. Results reveal that the relative permeability could be computed by using accurate capillary pressure data.     

华北地区煤储层渗透率的外在影响因素分析

通过对华北地区16个目标区60层次的试井渗透率的统计发现，在我国华北地区复杂的地质背景下，原地应力等外在因素对于煤储层渗透率的影响是很显著的。研究表明，煤层渗透率的决定因素是原地应力，煤层埋藏深度对渗透率的影响是第二位的。渗透率随地应力增大而减小；渗透率与埋藏深度之间的关系受原地应力的影响。只有区别不同应力环境，才能分析渗透率随深度变化的趋势。通过分析煤储层渗透率的外在影响因素，对于与预测煤层气的解吸特征，为下一步做好压裂设计，达到增产效果起到了积极的作用。     

测井资料在优选压裂层位中的应用

压裂是低孔、低渗油层改造的主要增产措施。根据常规测井资料、岩石物理实验分析数据及试油成果。研究储层四性关系，确定区块的低孔、低渗储层评价标准。进一步对油层进行分类，有针对性地为油层压裂提供施工层位和准确的储层参数。通过商543区块实例，阐述了选择压裂层位的方法。     

致密多孔介质气体运移机理

气体在致密多孔介质中的运移受多种因素的影响,如孔隙结构、气体的赋存方式、温度和压力等。地层压力大,气体密度高,应属于稠密气体|另外,在页岩、煤岩、致密砂岩等多孔介质中发育了丰富的纳米级孔隙,使气体的运移机制极为复杂。详细研究了气体在致密多孔介质中的运移机理,并引入稠密气体理论,通过计算分子平均自由程,发现直径大于2nm的孔隙中,压力大于1.135MPa时(76.85℃),气体不会发生Knudsen型扩散,Fick型扩散和表面扩散可能是主要的扩散方式|并得到Knudsen渗透率修正因子随压力增加而减小,随温度的升高而增加,随孔隙半径的减小而增加,在较小孔隙中温度的影响更显著;气体从小孔扩散至大孔和裂缝系统是多种扩散机制的结果,孔隙的大小、气体的赋存方式和压力直接关系到气体的运移机理。对比分析Klinkenberg渗透率和Knudsen渗透率修正因子,发现Knudsen渗透率模型是更精确的渗透率模型,Klinkenberg渗透率修正因子可以看作是Knudsen渗透率修正因子的一级修正。      

试井资料在低渗透油藏评价中的应用

低渗透油藏虽开发潜力巨大,但在开发过程中面临3个主要问题:岩心分析法确定启动压力梯度随机性大且代表性差,压裂井的压裂效果难以定量评价,压裂特征参数及压裂裂缝方位用常规方法难以确定.为此,基于试井分析理论,探讨了利用试井资料确定低渗透油藏启动压力梯度、评价压裂效果和判断裂缝方位的方法,并利用低渗透油藏实例进行了验证.分别用稳定试井法和不稳定试井法计算得到车408-3井的启动压力梯度,其值分别为0.0047和0.005 MPa/m,两者基本一致;用不稳定试井法计算了孤南181井的启动压力梯度,并分别用常规模型与考虑启动压力的低渗透模型进行解释,分析了低渗透油藏考虑启动压力梯度的必要性;成功评价了义37断块低渗透油藏的压裂效果;在牛20断块准确地判断了裂缝方位.结果证实,利用试井资料确定低渗透油藏启动压力梯度、评价压裂效果和确定裂缝方位的方法是可行和有效的.     

利用不稳定压力数据建立碳酸盐岩储集层模型

地质模型通常是根据地质信息,利用地球物理和岩石物理资料来建立.为了建立准确的碳酸盐岩油藏(伊朗海上油田)模型,不仅利用了地震和测井数据,也结合了该油田现有99井次的试井数据.在试井解释过程中观察到了许多特征,如封闭断层、水层、裂缝和分层系统,其中某些特征只能利用压力瞬态数据来识别,如地震数据中观察不到的一条封闭断层在试井曲线上则可识别.除了识别构造特征外,试井解释得到的渗透率数据也可用于绘制渗透率等值线图,而不再采用岩心分析得到的渗透率数据.试井得到的渗透率是泄油区域的有效渗透率,而岩心分析得到的渗透率并不能代表非均质油藏的渗透性.利用非稳态压力分析结果建立油藏模型,可以提高碳酸盐岩油藏建模的准确性.图6表1参8