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.     

A tool for the automatic generation and analysis of regular analog layout modules

This paper describes the characteristics of a new CAD tool that enables the creation of layout libraries of selected analog modules. This Analog Modules Generator (AMG) automatically creates multiple layout versions of two commonly used analog structures: the differential pair and arrays of series-connected or stacked devices, for the subsequent generation of layout libraries. Based on the number of devices and rows defined by the user for the layout implementation, the tool validates all possible implementations, which are later saved in a database. Additionally, an extraction process can be optionally executed over all the layout views saved in the database. The AMG generates several reports with all the characteristics of the implemented layouts, including area and parasitic components, facilitating further statistical processing. We describe the features and capabilities of the proposed AMG tool, and several test cases are presented. Results show that suitable layout implementations can be achieved by layout and circuit designers in a very reduced amount of time.     

Neuro-evolutionary approach applied for optimizing the PEMFC performance

A multi-objective optimization strategy, based on stacked neural network–genetic algorithm (SNN–GA) hybrid approach, was applied to study the C/PBI content on a high temperature PEMFC performance. The operating conditions of PEMFC were correlated with power density and electrochemical active surface area for electrodes. The structure of the stack was determined in an optimal form related to the contribution of individual neural networks, after applying an interpolation based procedure. Multi-objective optimization using SNN as model and GA as solving procedure provides optimal working conditions which lead to a high PEMFC performance. Simulation results were in agreement with experimental data, both for model validation and system optimization (the C/PBI content in the range of 17–21%).     

用于先进PCB制造工艺的叠层封装(英文)

在20世纪90年代,球栅阵列封装(BGA)和芯片尺寸封装(CSP)在封装材料和加工工艺方面达到了极限。这2种技术如同20世纪80年代的表面安装器件(SMD)和70年代通孔安装器件(THD)一样,在电学、机械、热性能、尺寸、质量和可靠性方面达到最大值。目前,三维封装正在成为用于未来采用的先进印制板(PCB)制造工艺的下一个阶段。它们可以分为圆片级封装、芯片级封装、和封装面。叠层封装(PoP)是一种封装面叠层封装类型的三维封装技术[15]。     

Composite silver electrode for double‐sided‐emitting stacked organic light‐emitting diode

Abstract— A reflective composite silver electrode is proposed and characterized as the middle electrode of a stacked organic light‐emitting diode (OLED) with double‐sided light emission. The proposed electrode is composed of a thermally evaporated stack of LiF (1 nm)/Al (3 nm)/Ag (70 nm) layers. The LiF/Al and the plasma‐treated Ag of the electrode function well as the respective cathode and anode of the bottom‐ and top‐emitting stacked OLEDs, with both being of the non‐inverted type. Power efficiencies of 10.3 and 12.1 lm/W at 100 cd/m² have been measured for bottom‐ and top‐emitting OLEDs, respectively, using dye doping. The stacked OLED having this bipolar middle electrode can be constructed as a two‐terminal‐only device, allowing for simpler driving schemes in double‐side‐emitting passive‐/active‐matrix OLED displays.     

Improvement of green cathodoluminescence of zinc oxide stacked films prepared by high-power excimer laser irradiation of sol-gel-derived precursors

Zinc oxide (ZnO) stacked films were prepared by repeating a procedure involving KrF excimer laser irradiation at various energy fluences (E_f) of sol-gel-derived precursors. All the stacked films are wurtzite-type and highly c-axis oriented on glass substrates. The green cathodoluminescence (CL) efficiency of the films is strongly influenced by the preparation conditions. Especially, laser E_f and stacking number are important control factors. The stacked film prepared under optimized preparation conditions consists of large grains and indicate low electric resistivity. The green CL efficiency of the stacked film is 0.0139 lm/W, which is higher than those of ZnO thin films prepared by a single stacking.     

Nanocomposites of manganese oxides and carbon nanotubes for aqueous supercapacitor stacks

Symmetrical supercapacitors and their serially connected two-cell stacks via a bipolar electrode were constructed with nanocomposites of manganese oxides and carbon nanotubes (MnO_x/CNTs) as the electrode materials. Nanocomposites with different contents of MnO_x were synthesised through the redox reaction between KMnO₄ and CNTs in aqueous solutions. The nanocomposites were characterised by scanning and transmission electron microscopy, BET nitrogen adsorption and X-ray diffraction before being examined in a three-electrode cell with a novel trenched graphite disc electrode by electrochemical means, including cyclic voltammetry, galvanostatic charging-discharging, and electrochemical impedance spectroscopy. The nanocomposites demonstrated capacitive behaviour in the potential range of 0-0.85 V (vs Ag/AgCl) in aqueous KCl electrolytes with less than 9% capacitance decrease after 9000 charging-discharging cycles. Symmetrical supercapacitors of identical positive and negative MnO_x/CNTs electrodes showed capacitive performance in good agreement with the individual electrodes (e.g. 0.90 V, 0.53 F, 1.3 cm²). The bipolarly connected two-cell stacks of the symmetrical cells exhibited characteristics in accordance with expectation, including a doubled stack voltage and reduced internal resistance per cell.     

基于SSAE-SVM的滚动轴承故障诊断方法研究

针对现有滚动轴承故障诊断方法过度依赖于有监督学习算法的问题,提出一种基于堆栈稀疏自编码和支持向量机(SSAE-SVM)的滚动轴承故障诊断方法.利用堆栈稀疏自编码(SSAE)的频域深层特征学习能力,对轴承故障特征进行快速傅里叶变换和批归一化处理,再输入到SSAE网络.所构建的SSAE网络通过贪婪算法逐层训练,使用梯度下降...     

Study of flow visualization in stacked-Chip Scale Packages (S-CSP)

The stacked-Chip Scale Package (S-CSP) is a new technology that provides high density of the package. It enables to stack the die in a single package. The S-CSP is widely adopted in portable multi-media products. However, the resin flow through a thin surface and wide filling area is of concern. Therefore, this paper presents a study of flow visualization during encapsulation process in S-CSP. The Navier–Stokes equation has been solved by the finite different method. For non-linear terms, the Kawamura and Kuwahara technique has been adopted in the flow analysis. Pseudo-concentration based on the volume of fluid (VOF) technique was used to track a melt fronts for each time step. The numerical model has been verified by comparing the prediction with the experimental results. The numerical results show good agreement with the experimental results. The prediction also shows that the short shot problem that occurred for the die top clearance is lower than 0.25 mm.     

某重型钢结构厂房结构设计特点综述

本文介绍了某重型钢结构厂房结构设计的新特点,对桩基选型、吊车梁、格构柱肢等重要结构构件的设计进行分析对比,可供同行交流。