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.     

宁夏宁东供水工程主机设备形式参数选择与国际招标

宁东供水工程供水水泵共有卧式和立式离心泵2种方案可供选择,也是工程论证时争论的焦点,经综合比较及主机设备的国际招标,最终确定了奥地利安德里兹公司的卧式双吸中开式离心泵为宁东供水工程的供水水泵。     

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。     

DFIT测试在长庆气田开发中的应用

与常规的小型测试压裂不同，流体注入诊断测试（DFIT）是通过关井阶段出现的拟线性流或拟径向流阶段求取储层压力，采用改进的梅耶霍夫方法（M-method）解释储层渗透率。以长庆榆林气田一口开发井为例，依据DFIT的技术原理和测试步骤，对该井测试压降数据进行解释分析，结果可信度较高，证明了该项工艺在长庆低压低渗油气田的可行性。     

电信企业信息化统一模型构建策略

电信企业信息化的实质就是赋予电信企业精细化的企业资源整合能力，本以此认识为出发点，通过定义基本的信息化业务元素，需求参数和基本信息处理机制，构建出带有行业共性的电信企业信息化统一模型，该模型针对目前电信企业信息化中常见的和潜在的问题提供了有效的解决措施。     

热管传热性能对小型热管换热器散热效能影响

在零重力辅助下,小热管热阻是小型热管换热器散热效能的重要影响因素之一。基于集总参数法对于换热器系统数值计算的高效性思想,建立了热管、热管换热器的集总参数模型。对同一热管换热器选用不同传热性能的热管,在不同传热温差和流体质量流速下,就其散热效能进行了数值计算。计算结果表明,在零重力辅助下,热管换热器管内热阻存在一临界值Rcri。当热阻RHP≤Rcri时,管外热阻起主导作用,热管换热器的散热效能εh几乎不随热管管内热阻的值而变化。     

Effect of oxygen deficiency (δ) on transition temperature of yttrium cuprate superconductors

The nature of pairing mechanism as well as transition temperature of yttrium cuprates is discussed using the strong coupling theory. An interaction potential has been developed for the layered structure with two conducting CuO₂(a–b) layers in a unit cell. The interaction potential properly takes care of electron-electron, electron-phonon and electron-plasmon interactions. Furthermore, the electron-phonon coupling parameter (λ), the modified Coulomb repulsive parameter (μ*) and the 2D acoustic phonon (plasmon) energy as a function of oxygen deficiency is worked out. Finally, the superconducting transition temperature (T _c) is then evaluated by using these coupling parameters and obtainedT _c = 95(92)K for Y(Yb)Ba₂Cu₃O_7−δ superconductors withδ = 0·0. The model parameters estimated from the layered structure approach are consistent with the strong coupling theory. The result deduced on the variation ofT _c withδ are in fair agreement with the earlier reported data on yttrium cuprates. The analysis of the above results are discussed.     

一种新的线性分布参数系统辨识方法

本文应用块脉冲函数（ＢＰＦ）将含有未知参数的线性分布参数系统偏微分方程转换为矩阵方程，通过最小二乘法辨识线性分布参数系统的参数，辨识结果表明，ＢＰＦ辨识法具有原理简捷，实现方便，辨识精度高等优点。     

存在噪声和未建模动态系统传递函数的渐近无偏估计

存在未建模动态时，如何去除系统传递函数估计中噪声引起的偏差是系统辨识关心的重要问题。本文将我们已提出的ＢＥＬＳ方法进行推广得出：当系统未建模动态可用－ＦＩＲ模型描述时，应用本文的方法可得到系统传递函数的无偏辨识，而不需知道有关噪声和未建模动态概率分布函数的先验知识。     

Biodegradation of monoaromatic hydrocarbons in aquifer columns amended with hydrogen peroxide and nitrate

The ability of indigenous microorganisms to degrade benzene, toluene, ethylbenzene and xylenes (BTEX) in laboratory scale flow-through aquifer columns was tested separately with hydrogen peroxide (110 mg/l) and nitrate (330 mg/l as NO₃⁻) amendments to air-saturated influent nutrient solution. The continuous removal of individual components from all columns relative to the sterile controls provided evidence for biodegradation. In the presence of hydrogen peroxide, the indigeneous microorganisms degraded benzene and toluene (> 95%), meta- plus para-xylene (80%) and ortho-xylene (70%). Nitrate addition resulted in 90% removal of toluene and 25% removal of ortho-xylene. However, benzene, ethylbenzene, meta- and para-xylene concentrations were not significantly reduced after 42 days of operation. Following this experiment, low dissolved oxygen (< 1 mg/l) conditions were initiated with the nitrate-amended column influent in order to mimic contaminated groundwater conditions distal from a nutrient injection well. Toluene continued to be effectively degraded (> 90%), and more than 25% of the benzene, 40% of the ethylbenzene, 50% of the meta- plus para-xylenes and 60% of the ortho-xylene were removed after several months of operation.