复杂油气藏的电相识别和渗透率预测

给出利用测井数据预测渗透率的方法，该方法使用非参数回归技术和多变量统计分析技术分两步完成。首先，采用主成分分析(PCA)、基于模型的聚类分析(MCA)和判别分析的组合方法，将测井数据划分成不同的电相。这种划分仅依据测井测量反映的矿物和岩相特征，而不需要任何人工干预。然后，在每一类电相中应用非参数回归技术预测渗透率。这里检验了三种非参数回归技术，即交错条件期望法(ACE)、广义加法模型(GAM)和神经网络(NNET)，探讨了每种方法的优点和不足。将这一技术用于Permian盆地中的一个具有强烈非均质性的碳酸盐岩储层的Salt Greek油田单元，并将预测结果同另外三种分别基于分层、岩相、流动单元分类法的渗透率预测结果进行了比较。对非取心井数据的预测结果所做的判别分析误差率检验表明，基于电相的数据分类方法要优于其它方法。对于渗透率预测而言，ACE方法要优于其它方法。

Off-Line Identification of Induction Motor Parameters

This study presented an off-line identification method of induction motor (IM) parameters. Before startup,the inverter drive performed automatically a modified DC test, a locked-rotor test, a no-load test and a step-voltage test to identify all the parameters of an induction motor. No manual operation and speed signals were required in the process. In order to obtain effective messages and improve the accuracy of identification, the discrete fast Fourier transform (DFFT) and the least-squares were used to process the signals of currents and voltages. A phase-voltage measuring method for motors was also proposed, which measured directly the actual conducting time of three upper switches in the inverter without need for a dead-time compensator. The validity, reliability and accuracy of the presented methods have been verified by the experiments on a VSI-fed IM drive system.

Identification of Telecom Operators' Core Distribution Channels Based on Strategic Value Evaluation System

The strategic value evaluation ofphysical channels is the main purpose of thispaper.To interpret this value,we refine finance,location and competition dimensions.Atotal of 166 social high-star channels are selected as empirical samples.Practice showsthat all second-layer indicators can be quantified by information system or artificial collection.The weight of three first-layer indicatorscan be defined by correlation analysis.The valuecomprehensive ranking of the channels is clearbased on the first-layer and second-layer indicators.In the sample group in this study,theweight of location value is higher.The resultson channels' strategic value research may provide further insights on business value,servicevalue and other related fields.

Who＇s your neighbor？ Acoustic cues to individual identity in red squirrel Tamiasciurus hudsonicus rattle calls

North American red squirrels Tamiasciurus hudsonicus often produce a loud territorial rattle call when conspecifics enter or invade a territory. Previous playback experiments suggest that the territorial rattle call may indicate an invader＇s identity as squirrels responded more intensely to calls played from strangers than to calls played from neighbors. This dear-enemy effect is well known in a variety of bird and mammal species and functions to reduce aggressive interactions between known neighbors. However, although previous experiments on red squirrels suggest some form of individual differentiation and thus recognition, detailed acoustic analysis of potential acoustic cues in rattle calls have not been conducted. If calls function to aid in conspecific identifi- cation in order to mitigate aggressive territorial interactions, we would expect that individual recognition cues would be acoustically represented. Our work provides a detailed analysis of acoustic cues to identity within rattle calls. A total of 225 calls across 32 in- dividual squirrels from Sheep River Provincial Park, Kananaskis, AB, Canada, were analyzed with discriminant function analysis for potential acoustic cues to individual identity. Initial analysis of all individuals revealed a reliable acoustic differentiation across individuals. A more detailed analysis of clusters of neighboring squirrels was performed and results again indicated a statistically significant likelihood that calls were assigned correctly to specific squirrels （55%-75% correctly assigned）; in other words squirrels have distinct voices that should allow for individual identification and discrimination by conspecifics [Current Zoology 58 （5）： 758-764, 2012].

Stereoselective interactions of chiral dipeptides on amylose based chiral stationary phases

Dipeptides are stereo-specifically involved in several biological functions that are challenging to separate enantiomerically. Elution order of enantiomers is an important issue in chiral chromatography. Amylose tris-(3,5-dimethylphenylcarbamate) chiral stationary phase(CSP) is the best and most-widely-used CSP in chiral separations, but experimental data of enantiomeric separation of dipeptides on this CSP is lacking. Simulation studies were conducted to determine the order of elution and the chiral recognition mechanism of didpetides on this CSP. Results indicated that the docking energy of SR-enantiomers were higher than SS-antipodes. The range of docking energies for SR-enantiomers was -7.44 to -5.92 kcal/mol with CSP, but -7.15 to -5.87 kcal/mol for SS-stereoisomers. Therefore it is predicted that SS-enantiomer will elute first, followed by SR-antipode. Furthermore, hydrogen bondings, van der Waal's interactions and electrostatic interactions were observed among SR- and SSenantiomers and chiral grooves of CSP. The number of hydrogen bonds was one in each enantiomer binding except S-Ala-R-Tyr, which contained two hydrogen bonds. No hydrogen bond was found in S-Ala-R-Trp, S-Leu-S-Trp, and S-Leu-S-Tyr dipeptides bindings. The chiral recognition mechanisms dictate different strengths of stereoselective bindings of the enantiomers on CSP.