气动比例系统定位特性研究

通过对气动比例控制系统进行多因素多水平正交试验,对影响系统定位精度的流量、压力以及工作负载等主要参数进行了试验测量.并且通过回归分析对试验数据进行了显著性分析,找到各因素对系统的定位精度的影响规律.为提高系统的控制性能奠定了基础.     

A least squares support vector machine model for prediction of the next day solar insolation for effective use of PV systems

Accurate prediction of daily solar insolation has been one of the most important issues of solar engineering. The amount of solar insolation on a given location is a vital data for photovoltaic plants. Systems efficiency is easily affected by the changes in solar radiation so, this study is aimed to develop a Least Squares Support Vector Machine (LS-SVM) based intelligent model to predict the next day’s solar insolation for taking measures. Daily temperature and insolation data measured by Turkish State Meteorological Service for three years (2000–2002) were used as training data and the values of 2003 used as testing data. Numbers of the days from 1st January, daily mean temperature, daily maximum temperature, sunshine duration and the solar insolation of the day before parameters have been used as inputs to predict the daily solar insolation. The simulations were carried out with SVM Toolbox of MATLAB software. As a conclusion the results show that LS-SVM is a good method in estimating the amount of solar insolation of a given location with 99.294% accuracy.     

Regression trees approach for flow-time prediction in wafer manufacturing processes using constraint-based genetic algorithm

Understanding the factors associated with the flow-time of wafer production is crucial for workflow design and analysis in wafer fabrication factories. Owing to wafer fabrication complexity, the traditional human approach to assigning the due-date is imprecise and prone to failure, especially when the shop status is dynamically changing. Therefore, assigning a due-date to each customer order becomes a challenge to production planning. The paper proposes a constraint-based genetic algorithm approach to determine the flow-time. The flow-time prediction model was constructed and compared with other approaches. Better computational effectiveness and prediction results from the constraint-based genetic algorithm are demonstrated using experimental data from a wafer-manufacturing factory.     

Applied Regression Analysis (2nd Ed.)

We describe a diagnostic method for assessing the degree to which individual cases and groups of cases influence the Box-Cox likelihood estimate of the transformation parameter for the response variable in linear regression models. We compare the method to a method proposed by Atkinson (1982) and sketch the extension to explanatory variables. We present two examples.     

Development of planning level transportation safety tools using Geographically Weighted Poisson Regression

A common technique used for the calibration of collision prediction models is the Generalized Linear Modeling (GLM) procedure with the assumption of Negative Binomial or Poisson error distribution. In this technique, fixed coefficients that represent the average relationship between the dependent variable and each explanatory variable are estimated. However, the stationary relationship assumed may hide some important spatial factors of the number of collisions at a particular traffic analysis zone. Consequently, the accuracy of such models for explaining the relationship between the dependent variable and the explanatory variables may be suspected since collision frequency is likely influenced by many spatially defined factors such as land use, demographic characteristics, and traffic volume patterns. The primary objective of this study is to investigate the spatial variations in the relationship between the number of zonal collisions and potential transportation planning predictors, using the Geographically Weighted Poisson Regression modeling technique. The secondary objective is to build on knowledge comparing the accuracy of Geographically Weighted Poisson Regression models to that of Generalized Linear Models. The results show that the Geographically Weighted Poisson Regression models are useful for capturing spatially dependent relationships and generally perform better than the conventional Generalized Linear Models.     

A Study on the Impact of Industrial Production Index (IPI) to Beverage,Food and Tobacco Sector Index with Special Reference to Colombo Stock Exchange

This study attempts to explore the impact of Industrial Production Index to sector performance of Beverage, Food and Tobacco in Colombo Stock Exchange Sri Lanka. Secondary data were used for the analysis. Sector index was taken from the Data Library of Colombo Stock Exchange and Industrial Production Index was taken from Annual Reports of Central Bank Sri Lanka. Monthly data were gathered from January 2002 to December 2014. For the time series data set, first, the stationary was checked using Augmented Dickey-Fuller and Phillips Perron Tests of E-views software. The results of stationary check show that the sector index is stationary at 1^st difference in both ADF and PP tests. Industrial Production Index is stationary at 2^nd difference in ADF test but 1^st difference is stationary in PP test. Because of the seasonal trend in IPI 12^th difference also considered and it is stationary in both ADF and PP tests. Granger Causality test was used to find out the causal relationship between variables. Results show the one way causality that the changes occurring in IPI will have an effect on changes in sector index. But changes in sector index will not have any effect on changes in IPI. Finally a regression was used to find out the relationship between variables. A Pearson Correlation coefficient was checked to find the correlation among variables before moving to the regression. Result of correlation test shows 84% higher correlation between variables and regression result shows a significant positive relationship amongvariables. The study concludes that Industrial Production Index will positively impact on Beverage, Food and Tobacco sector Index in Sri Lanka. It can be recommended that the changes occurring in the IPI be considered by Investors when they buy and sell stocks in BFT sector.     

矩阵损失下受约回归系数的可容许线性估计

讨论带有齐次线性等式约束的线性模型:Y=Xβ+ε,ε～(0, σ_V),Hβ=0,在矩阵损失下,我们给出 Sβ的估计 LY(LY+a)在齐次线性(非齐次线性)估计类中可容许的充要条件.     

飞机重量预测的非线性统计分析方法

飞机重量预测中常用的由线性统计分析方法得到的重量公式，由于模型本身的限制，存在着精度低和变量变化范围窄的问题，不利于对飞机设计变号作大范围的分析和优化．因此，本文提出飞机重量预测的非线性统计分析方法，该方法可利用已有飞机的重量数据和相关参数推导出满意的重量估算公式，从而可快速准确地预测新设计飞机的结构重量．与常用的线性方法相比，可提高预测精度，并可使重量影响参数具有较大的变化范围．作为算例，用二十个机型的机翼数据求得了一个非线性的机翼重量估算公式．     

Surface Analysis of Chesapeake Bay Water Quality Response to Different Nutrient and Sediment Loads

Based on a set of Chesapeake Bay Estuarine Model (CBEM) scenarios, a three-dimensional response surface of a water quality index, such as chlorophyll concentration, versus a pair of loading constituents, e.g., nitrogen and phosphorus, is constructed. The responses of water quality, such as dissolved oxygen, chlorophyll, and water clarity, to nitrogen, phosphorus, and sediment loads are analyzed. From the response surface, a water quality response is estimated under loading conditions beyond that of a limited set of scenarios. Response surfaces may be used to determine the possible universe of nutrient and sediment load reductions needed to obtain a particular water quality standard and to examine the tradeoffs among nutrient and sediment load reductions that achieve the same water quality objective.     

Fracture Toughness of Wood Fiber Gypsum Panels from Size Effect Law

This paper addresses the size effect of inplane bending strength as well as Mode I fracture toughness and process zone length of wood fiber-reinforced gypsum panels. Wood fiber gypsum panels represent an incombustible short fiber composite material composed of recycled paper fibers embedded in a gypsum matrix. The material, which is used for sheathing and bracing of timber frame constructions, exhibits marked fracture softening supposedly resulting in a considerable size effect. In the paper presented, in a first step Ba?ant’s size effect law for quasi-brittle materials is derived. The parameters of this size effect law are then determined by means of nonlinear regression analysis applied to a test series with scaled single edge notched beam specimens. Detailed consideration is given to the adequacy of linear confidence intervals of the model parameters in comparison to nonlinear inferential results. Finally, the probability densities of fracture toughness and fracture process zone length are determined from the distributions of the size effect parameters by means of theory of random variables.