Improving the prediction of petroleum reservoir characterization with a stacked generalization ensemble model of support vector machines

The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum reservoir properties could have huge positive impact on the success of exploration, drilling and the overall reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum reservoir characterization to improve the accuracy of reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.     

Effect of select parameters on the properties of edible film from water-soluble fish proteins in surimi wash-water

Edible film from water-soluble fish proteins were developed by casting film solution on leveled trays and effects of pH (9.5, 10.0 and 10.5), heating temperature (60, 70 and 80 °C), and heating time (10, 20 and 30 min) of the film solution on various film properties were determined using Response Surface Methodology (RSM). The impact of pH and heating temperature of film solution was more significant, overall, on the film's properties than heating time. Contour plots of tensile strength and elongation at break was highest at pH of 10.0 at 70 °C (2.75-3.02 MPa) but low in elongation at break (6.35-9.16%), while water vapor permeability and oxygen permeability were at their lowest (58.55-65.96 g mm/m² d kPa and 351.33-624.18 cm³ μm/m² d kPa). There was a direct correlation between the films’ and proteins’ solubility on one hand, and heating temperature of film solution on the other, which reversed with change in pH of film solution. Film color was darker and more yellowish with increase in the pH of film solution.     

Impact of Reaction Conditions on MnO2 Genesis during Permanganate Oxidation

To enhance the understanding of the behavior and effects of the precipitation of MnO2 particles in the subsurface generated during in situ chemical oxidation (ISCO) using permanganate, laboratory batch experiments were completed to examine the influence that varied reaction matrix conditions have on the generation and properties of manganese oxides. The conditions examined include organic material type and concentration, permanganate concentration, pH, and the presence of calcium (as a representative divalent cation) in solution. Experimental studies included: (1) spectrophotometric examination of permanganate depletion and manganese oxides generation over time during reactions with trichloroethene; (2) scanning electron microscopy analyses of manganese particle morphology; (3) particle size distribution (filtration) characterization studies; and (4) optical particle sizing and numeration studies. Bench-scale, batch experiments were conducted to focus on fundamental chemical properties affecting particle development under varied potential environmental conditions. The amount of manganese oxides particles that develop, grow, and potentially settle as a result of permanganate ISCO of organic contaminants is a function of the particle size and concentration, the time allowed for particle development, and the impact of matrix conditions on the ability of particles to agglomerate.     

阴,阳离子聚合物地层内凝胶化改善水驱效果的研究

研究了一杆阴离子聚合物（Ａｃ５３０）和一种阳离子聚合物（Ｍｂ５８１）在水溶液中形成凝胶的条件和过程、凝胶化学结构、形态、稳定性和力学性能。在模拟地层的二维微观模型内观测了两种聚合物驱替渗流、相逼、形成凝胶、凝胶封堵大孔道的机理。在亲水填砂模型内测定了阴、阳离子聚合物凝胶体系降低渗透率的能力。     

低渗透率地层渗透率的确定方法

结合大庆油田外围低渗透率地层的地质特点,根椐渗流理论和岩心分析资料,分析了地层渗透率与孔隙度、组成地层的各种矿物含量以及泥质含量之间的关系,建立了不同矿物组合地层的渗透率计算方程。用本方法计算的和岩心分析的渗透率进行了对比,二者之间具有较好的一致性。     

兰州重离子加速器大型真空室

已建成的兰州重离子加速器的真空室是一个大型整体结构的超高真空容器,直径约10m,高4.5m,重65000kg,内表面积211m~2,容积100m~3,工作真空度为5×10~(-5)Pa。采用有限单元法在计算机上用SAP-5C程序对真空室受力分析进行了计算。真空室结构材料选用瑞典Uddeholm钢厂生产的316 L 超低碳不锈钢。承制此大型容器的是航天工业部风华机器厂。由于结构庞大,首先将真空室分成八大块和几小块在工厂制造,然后运至现场焊制成一整体容器并进行机械加工。所有密封焊缝均用着色渗透液,X-射线探伤和氦质谱探漏仪进行检查和探漏。     

屏蔽暂堵反排解堵效率的实验分析

在一定实验条件下，屏蔽暂堵的反排解堵效率随压差、温度的增大而增大，反排解堵在很短的时间内就可完成。一般的反排解堵率都在60％以上，但反徘不能完全解堵。     

煤头小型低压法甲醇装置合成压力的参变的效应

本文对Ｌｕｒｇｉ低压法甲醇工艺中压力的参变效应进行了探讨．通过计算机模拟，给出了合成压力变化的效应情况．计算结果表明煤头小型低压法甲醇装置的合成压力应高于大型装置的合成压力，其值在７．３～８．０ＭＰａ之间可取得最佳的节能降耗效果．     

酒精中甲醇,水在NaA沸石上吸附性能的研究

本文测定了酒精中甲醇、水单组分及二元组分的吸附等温线,并用Langmuir方程进行了拟合。在固定床动态吸附研究申测定了酒精中甲醇、水单组分及双组分吸附穿透曲线;着重考察了流速、温度、不同甲醇和水含量对双组分吸附性能的影响。对二个组分的传质机理及置换关系进行了分析探讨。