Modeling of wax deposition produced in the pipelines using PSO-ANFIS approach

Wax deposition in petroleum industry is one of the major problems requiring accurate predictive procedures to reduce the deficiencies and effective designing of the process. An adaptive neuro fuzzy inference system (ANFIS) model is proposed to predict the wax deposition in oily systems. Parameters of the ANFIS model are optimized using the particle swarm optimization (PSO) method. Results are then compared to those previously reported by Kamari et al., demonstrating better performance of the proposed ANFIS model. Statistical and graphical approaches are employed to investigate the reliability of the proposed model, illustrating the model's capability of precise estimation of the wax deposition. Coefficient of determination (R²) and mean squared error (MSE) values of 0.994 and 0.053 are obtained for the proposed ANFIS model, revealing the reliable prediction of wax deposition by the proposed ANFIS model.     

普适性结蜡模型研究

根据原油在管道内流动特性及析蜡规律,提出了有效析蜡量的计算方法.利用F检验法筛选了原油结蜡的主要影响因素,包括原油黏度、管壁处剪切应力、温度梯度及管壁处蜡晶溶解度系数.利用9种原油室内环道结蜡实验数据,按照逐步线性回归的方法,得到了含蜡原油的普适性结蜡模型.该模型不需进行结蜡模拟实验,只需根据原油的黏度、析蜡特性及密度等物性参数就可预测原油的结蜡规律.在未进行室内结蜡模拟实验的情况下,利用普适性结蜡模型预测了中宁-银川输油管道不同工况下沿线结蜡分布,并和现场运行参数进行了对比,平均误差为6.32%,最大误差为20%,预测结果为现场清管作业提供了依据.     

延长油田高含水油井井筒结蜡速率预测模型优化

结蜡速率计算是预测油井结蜡的关键参数,目前针对油井井筒的结蜡速率预测模型相对较少,且大多以机理模型为主,计算参数众多,现场应用不便.延长油田油井含水率普遍较高,常用的普适性经验模型预测准确度低.因此,重新考虑含水率对结蜡速率的影响,开展了含水率对结蜡速率影响的室内研究,基于实验数据与简化后的经验公式,拟合了含水率分别为...     

海上高含蜡油田井筒清蜡周期预测图版建立及应用

渤海部分高含蜡油井投产后面临比较严重的井筒结蜡问题,现场作业人员一般根据生产经验确定清蜡周期,导致准确度低、清蜡作业成功率有限。根据海上油井生产管柱特征,以Ramey温度场计算数学模型为基础,结合井筒结蜡速率模型计算得到了井筒结蜡剖面,推导建立了电潜泵井清蜡周期预测方法,并进一步绘制了某油田A区块清蜡周期和清蜡深度预测图版。结果表明,清蜡周期随产液量的下降呈幂函数形式变短,随含水率增加呈指数函数形式增加。根据清蜡周期预测图版,预测3口井的清蜡周期分别为11 d、15 d、46 d,实际清蜡周期分别为8 d、12 d、39 d,预测结果与实际基本吻合。该方法同样适用于陆地油田自喷井确定清蜡周期和清蜡深度,对高含蜡电潜泵井、自喷井及时制定清防蜡措施具有借鉴意义。     

A Reliable Model for Estimating the Wax Deposition Rate During Crude Oil Production and Processing

Deposition of wax in surface and subsurface pipes and even perforations can lead to serious problems including pore spaces blockage, plugging of pipelines, and minimum profitability. Therefore, understanding wax deposition and wax related-properties improves the oil recovery and processing operations in petroleum industry. In this research work, the rate of wax deposition is correlated to a number of main parameters such as the dynamic viscosity of crude oil, shear stress, gradient of wax molecular concentration and temperature difference in pipeline system through implementation of a newly developed model, known as least squares support vector machine (LSSVM) along with the coupled simulated annealing (CSA) optimization strategy. The possible outliers are detected through employing the Leverage technique which involves residual errors plots, Williams' plot, and Hat matrix. The results imply that whole collected real data are in applicability domain of the proposed model. Using a comprehensive statistical investigation, a very good agreement between the predicted LSSVM-CSA outputs and real wax deposition rate is found such that the average relative error percentage and determination coefficient (R2) are 0.048% and 0.999, respectively. Such a study can assist to provide better designs (technically and economically) for underground and surface facilities while dealing with wax deposition cases.     

Artificial Neural Network's Prediction of Wax Deposition Potential of Nigerian Crude Oil for Pipeline Safety

Abstract

Paraffin wax deposition from crude oil along pipeline is a global problem, making preventive methods preferred to removal methods. In this work, a neural network model based on mathematical modeling technique using regression analysis as the statistical tool was developed to predict the wax deposition potential of 11 reservoirs in Nigeria. Using the viscosity-pressure-temperature data obtained from these fields to supervise the model, the model accurately predicted the present real-life situation in each field. Conclusively, the model could be used to predict wax deposition potential of any reservoir that is yet to be explored provided the temperature used during prediction is close to the actual reservoir temperature.     

大庆原油管输结蜡规律与清管周期的确定

在确定不同流态区管壁处剪切应力、蜡晶溶解度系数、径向温度梯度及管道沿线温降分布的基础上,回归建立了适用于描述大庆油田某两联合站间输油管道蜡沉积的结蜡模型。根据差压法原理,建立了研究原油管输结蜡过程室内模拟试验装置,并覆盖该输油管道的典型工况条件开展了管输原油结蜡模拟试验。相对偏差分析表明,结蜡模型预测结果与试验值的适配性良好。进而在预测运行时间对该输油管道结蜡影响的基础上,结合结蜡层厚度对管道轴向温降及压降的作用,确定了年季节最高与最低土壤温度期的清管作业周期分别为4个月和3个月。     

An Evaluation of the Performance of Selected Wax Inhibitors on Paraffin Deposition of Nigerian Crude Oils

Paraffin deposition in oil production constitutes a critical and difficult to control problem, in terms of productivity and production operation costs, going from the reservoir to surface facilities. In Nigeria, operators spend millions of dollars each year to control the deposition of paraffin and to deal with other paraffin deposition related problems. Expenditures of this magnitude obviously have a significant impact on profits. The main purpose of this work is to assess the net effect of many commercial wax inhibitors on paraffin deposition from a wide range of waxy crude oil systems in Nigeria for the selection of an efficient additive. Deposition from a wide range of waxy crude oil systems from Nigerian oilfields were examined with and without chemical wax deposition inhibitors. The devices used to produce the deposits investigated were cold spot and dynamic flow wax deposition apparatus capable of producing field-like deposits with relatively small volumes of oil in minutes. Results show that most of the commercial wax inhibitors tested could decrease the deposition of wax, but none has the economical capability to solve the paraffin deposition problem for an extended period of time. One intriguing result was that the addition of xylene improved the performance of three wax inhibitors tested. It was also observed that there are subtle differences in inhibitor performance depending on deposition tendencies of crude oil.     

基于人工智能的抽油机井结蜡预警方法

针对依靠现场经验确定的清蜡周期不准确而导致蜡卡躺井的问题,开展了基于人工智能的抽油机井结蜡预警方法研究。利用皮尔逊相关系数分析方法,分析了17项油井自动采集参数与结蜡程度的关联性,确定了7项主控参数,创建了结蜡预警规则模型;将7项主控参数的合并指标进行归一化处理得到结蜡综合特征指标（WPSC）,并利用结蜡预警规则模型产生的样本数据建立了结蜡井WPSC样本集,选用长短时记忆神经网络（LSTM）对样本集进行训练,得到了WPSC机器学习模型,用其可以定量预测抽油机井的结蜡程度。该方法在胜利油田桩23区块的现场应用结果表明,油井清蜡周期得到延长,且有效避免了蜡卡躺井。研究结果表明,基于人工智能的抽油机井结蜡预警方法实现了油井结蜡程度的定量化预测与预警,对精准确定清蜡时机具有较好的指导作用。      

油井变频电磁场防蜡的实验研究

变频电磁场防蜡技术作为一种新兴的物理法防蜡技术,具有成本低、对油层无污染、有效期较长、管理方便等优势,具有广阔的发展前景。实验研究表明,电磁场作用可以降低含蜡油的析蜡点和凝固点,减少含蜡油的结蜡量,破坏蜡晶网络结构。变频电磁场可引起蜡分子的内共振,导致蜡晶结构与形状发生变化,抑制了蜡分子的结晶过程,同时对已形成的蜡晶产生一定的破碎作用,从而达到防蜡的目的。     

Experimental study on the regulation of wax deposition

Abstract

Based on the theory of wax deposition dynamics, and the wax deposition rate model of a Tieling–Jinxi insulated crude oil pipeline was established for Daqing–Jilin mixed oil. Based on their physical properties, the sediments removed from the pipeline were mixed into the original oil sample at different proportions. The sediment volume measured by three physical methods in different seasons was compared. The results showed that the error between the value measured by the wax content method and the predicted value by the model was the smallest, which was -5% in winter and -3.9% in summer. Therefore, the wax content method can be used to estimate the sediment in the pipeline and determine the prediction accuracy of the model.     

Evaluation of Effects of Selected Wax Inhibitors on Paraffin Deposition

Deposition from decane solutions of model paraffins such as n-C₂₄H₅₀ (C₂₄), and n-C₃₆H₇₄ (C₃₆), as well as a mixture of n-alkanes (C₂₁ to C₄₄) was examined with and without chemical wax deposition inhibitors. The device used to produce the deposits investigated was a “Cold Disk” Wax Deposition Apparatus (CoDWaD) capable of producing field like deposits with relatively small volumes of oil in minutes. It was found that most of commercial wax inhibitors tested could decrease the deposition of low molecular weight paraffins (C₃₄ and below), while having little effect on the wax deposition for high molecular weight paraffins (C₃₅-C₄₄). In many cases, although the total amount of wax formed on the cold plate was reduced, the absolute amount of deposition for high molecular wax was actually increased. Therefore, the net effect of many commercial inhibitors is to make even harder wax under the tests conditions studied here. One intriguing result was that the addition of an oleic imidazoline c rrosion inhibitor improved the performance of two wax inhibitors tested. It was also observed that there are subtle differences in inhibitor performance depending on whether the test solutions are binary mixtures, synthetic wax mixtures, or crude oil.     

高含蜡凝析气井石蜡沉积实验研究

国内外研究学者在石蜡沉积研究中对石蜡沉积机理及沉积模型模拟预测等方面进行了大量研究。为了研究某高含蜡气井的析蜡条件及预防措施,针对高含蜡凝析气井的脱气油,进行了石蜡沉积实验研究,发现在模拟研究井筒中油气多次接触过程中,脱气油的析蜡点和溶蜡点以及石蜡的沉积量随着接触次数的增加呈现先下降后上升的趋势。沉积点的测定研究能判断井筒是否结蜡,沉积量的测定研究能够预测井筒析蜡状况,以保证气井正常生产。研究表明该井在地层中不会出现石蜡沉积,同时,井口的温度应不低于42℃,井筒中也不会出现石蜡沉积。     

海上油井井筒结蜡剖面预测新模型

为了缓解井筒结蜡给海上油田油气开采造成的消极影响,研究了海上结蜡油井的蜡质沉积规律,并建立了一种海上油井井筒结蜡剖面预测新模型。该模型基于对4种现有模型的机理分析,采用理论与试验相结合的方法,综合考虑了分子扩散、剪切弥散和蜡层的老化与剥蚀损失等结蜡机理。通过实例对新模型与4种现有模型的结蜡剖面预测结果进行了对比分析,并结合渤海油田海上结蜡油井的生产数据,检验了新模型对结蜡井筒流体温度和压力的计算精度,新模型计算井口温度的相对误差为1.32%,计算井下压力的相对误差为0.30%,计算精度良好;利用新模型分析了生产时间、产量、含水率和生产气油比等影响结蜡因素的敏感性,认为结蜡厚度随生产时间递增,受产量和含水率的影响较大,受生产气油比的影响相对较小。研究结果表明,新模型能够较为准确地预测海上结蜡电动潜油离心泵油井井筒的结蜡剖面,可以为海上电潜泵结蜡井的清蜡防蜡工艺优选与实施提供指导。      

Utilization of RBF-ANN as a novel approach for estimation of asphaltene inhibition efficiency

One of the problematic concerns in petroleum industries is the deposition of heavy fractions of crude oil such as asphaltene fraction during production and transportation. The utilization of inhibitors is known as a relative low cost and effective method for asphaltene inhibition. In this study, Radial basis function artificial neural network (RBF-ANN) was applied to predict asphaltene precipitation reduction in terms of structure and concentration of inhibitor and oil properties. In order to training and testing of RBF-ANN the required data are extracted from reliable sources. The predicted asphaltene precipitation reduction values were compared with the actual data statistically and graphically. The coefficients of determination for training and testing phases of RBF-ANN were determined as 0.995906 and 0.994853 respectively. These evaluations showed that the RBF-ANN as a predictive tool has great capacity to estimate effect of asphaltene inhibitors on reduction of asphaltene precipitation.     

Application of RBF-ANN in prediction of natural gas density in different operational conditions

Abstract

The degree of accuracy in prediction of different processes of gas engineering is extensively dependent on gas properties. One of the dominant properties which has straight effects on calculation and performance of different parts of gas industries is natural gas density. Due to this fact, in this paper, radial basis function artificial neural network (RBF-ANN) was used as novel approach to estimate gas density in terms of molecular weight, critical pressure and critical temperature of gas, pressure and temperature. To prepare and validate RBF-ANN model, a large and reliable experimental data bank was gathered from literature. A comprehensive analysis which include statistical and different graphical analysis were done to evaluate the performance. The coefficients of determination (R²) were determined as 0.99995 and 0.99993 for training and testing phases respectively. The comparisons illustrate that the RBF-ANN has great potential in prediction of natural gas density at different operational conditions.     

Prediction the variation range of wax deposition with temperature of crude oil in a flow loop

Wax deposition under different temperature conditions was investigated in a flow loop, using a local crude oil with a wax content of 22.5%. The results revealed that the wax deposition increases with increasing coolant temperature. However, the amount of deposit increased initially with increasing oil temperature and then decreased. Based on these results, the corresponding temperature ranges were divided into three ranges: hot flow, sensitive precipitation of wax crystal, and cold flow. Based on diffusion mass, a method and steps for determining the temperature dependence of wax deposition were proposed.     

树脂涂层在原油管输中的防结蜡研究

从蜡与固体壁面间的界面性能考虑，在管道内壁涂覆一层低表面能的树脂涂层，可以改变管壁表面性质，减小管壁与蜡之间的相互作用力，达到防止结蜡的目的，为改善高含蜡原油在管道输送时易凝和粘滞的状况，在实验室用自行设计的结蜡器评价了硅，氟树脂以及丙烯酸树脂等少层在青海原油，胜利原油和辽河原油输送中的防结蜡效果，结果表明，它们有不同程度的防强蜡作用，其中硅树脂的最大防蜡率可达74．7％。     

Prediction of Wax Deposition in an Insulation Crude Oil Pipeline

This study establishes an insulation crude oil pipeline wax deposition experimental device and describes the experimental method for insulation crude oil pipeline wax deposition. The experimental program is based on the operational plan of Tieling–Huludao insulation crude oil pipeline. The data are analyzed according to the effect of varying oil temperature, insulation thickness, and flow on wax deposition. Using SPSS software, a Daqing crude oil wax deposition rate model is derived from the linear regression. The use of the wax deposition rate model forecasts the wax deposition of the Tieling–Huludao insulation crude oil pipeline during different seasons.     

模拟延长油田CO_2驱油过程原油结蜡特性研究

通过对某CO2驱油区块的不同CO2分压条件下原油结蜡倾向和原油结蜡特性评价,计算出原油的结蜡速率、结蜡率及蜡含量,分析了原油的析蜡曲线特性。结果表明,CO2分压增大时原油的结蜡速率和结蜡率提高,蜡含量降低,蜡析出更明显;经CO2处理作用后原油析蜡点向低温方向移动,其蜡含量也相应地比未处理油样的蜡含量降低。