Papers by Keyword: Multiple Regression

Abstract: The most common reason for the appearance of cracks or delamination of plaster is their too high strength - higher than the strength of the substrate, their low flexibility and high shrinkage during curing. The article presents a study on influences of natural and synthetic polymers with different chemical composition of the physical properties of category CS II mortars. Polymer additives in the form of dry powders were selected for testing. Studies were carried out in two versions: with constant consistence and with a constant w/c ratio maintained. It has been found that modifying mortars with synthetic polymers improves their flexibility and flexural tensile strength. The shrinkage is dependent on the ability of the synthetic polymer to liquefy fresh mortar where the tests were conducted maintaining constant consistence. Similar relationships were determined for cellulose ethers. Also in this case, the increase in the contents of the cellulose ethers increases their tensile strength and decreases the shrinkage. It was found that the impact of cellulose ethers on the shrinkage depends on their surface activity.

Abstract: Ready-to-use mortars based on organic binders are increasingly widely applied in renovation of historic buildings. Thispaper contains an analysis of the impact of silicone-organic polymers of various chemical structures, used for silicone plasters production, on water vapour permeability in the produced render. The results were obtained by means of experiments. The Sd value of cured render formed from plasters containing different quantities of the analysed silicone-organic polymers at a different quantity of organic resin was studied. Statistical methods based on Statistical methods based on multiple regression were used to describe the S_d value dependence on the change in contents of the analysed polymers. It was discovered that the changes in the contents of organic resin in the plaster formula have a greater impact on the coat water vapour permeability in the cured render than the changes in the contents of polysiloxanes. The intensity of polysiloxanes impact on the S_dvalue depends on their chemical structure, and on the kind of substituents related to the siloxane skeleton in particular.

Abstract: Tin Oxide (SnO₂) thin film is one of the important transparent conducting oxides (TCOs) due to its electrical and optical transparency in visible light spectrum. This study presents the best model in estimating optical properties of tin oxide thin film which is performed using the absorption coefficient of the film. The annealing temperature is at 473 K prepared by radio frequency sputtering technique. Twelve multiple regression (MR) models with interactions are generated from three independent variables (transmission spectra, energy band gap and the wavelength of light). They are developed from data sets of 50. The best model M8.0.0 is chosen from the 6 selected models based on the Eight Selection Criterion (8SC). Best model will have the majority criteria with the least value. Factors affect the absorption coefficient are found to be X₁ (transmission spectra), X₂ (energy band gap) and X₁X₂ (interaction between transmission spectra and energy band gap).

Abstract: Industrial water demand forecasting is needed for the effective planning and management of water supply systems. The paper first made impacting factor analysis of industrial water demand. Data analysis showed that there was a converse “U” type relationship between industrial water demand and industrial value added. There was a negative correlation relationship between industrial water demand and the recycling rate of it. With multiple regression method, industrial water demand forecasting model was established. In the supposed scenarios, we applied the model to predict Chinese industrial water demand in 2014 and 2015.The results were 141.04 billion m3 in 2014 and 137.79billion m3 in 2015.

Abstract: With the continuing of new teaching reform, English teaching has been incorporated into the focus of teaching reform. English teaching has characteristic of wide application range, various teaching methods, flexible using multimedia etc.. Therefore, in the teaching process we take more abundant methods to raise the enthusiasm of students and improve the students' English learning ability. Combined with the multivariate regression variable analysis method, we use JSP network development tool to improve the English teaching evaluation system and obtain the English comprehensive evaluation platform under the multivariate influencing factors. In order to verify the validity and reliability of the system, we evaluate complaint strategies, explicit teaching and complaint explicit teaching, and obtain the results of the English learning ability, which provides a new method for the application of computer in English teaching.

Abstract: Pressure monitoring is an important means to reflect the running status of the natural gas desulphurization process. By using the data mining technology, the interaction relationships between the pressure and other monitoring parameters are analyzed in this paper. A pressure trend prediction model is established to show the pressure status in the natural gas desulfurization process. Firstly, the theory of Principal Component Analysis (PCA) is used to reduce the dimensions of measured data from traditional Supervisory Control and Data Acquisition (SCADA) system. Secondly the principal components are taken as input data into the pressure trend prediction model based on multiple regression theory of Support Vector Regression (SVR). Finally the accuracy and the generalization ability of the model are tested by the measured data obtained from SCADA system. Compared with other prediction models, pressure trend prediction model based on PCA and SVR gets smaller MSE and higher correlation. The pressure trend prediction model gets better generalization ability and stronger robustness, and is an effective complement to SCADA system in the natural gas desulphurization process.

Abstract: The corrosion property of high chromium cast iron was test under different phosphoric acid medium concentration. On the base of experimental data, the binary equation model of corrosion weight loss (W) versus phosphoric acid concentration and corrosion time (c, t) was built using multiple regression analysis, which can predict corrosion property of high chromium cast iron effectively. The prediction results show that the corrosion weight loss rises lineally with increasing corrosion time, and the corrosion rate rises quadratically with increasing phosphoric acid concentration. The corrosion failure mechanism is that chromium composite carbides (M7C3) stand out of matrixes surface after the matrixes composed of martensite and austenite are corroded firstly, then the M7C3 carbides drop out of matrixes when the matrixes can not wrap M7C3 carbides, resulting gradual corrosion of high chromium cast iron. The prediction values have sufficiently mined the basic domain knowledge of corrosion process of high chromium cast iron under phosphoric acid medium. Therefore, a new way of predicting corrosion property according to corrosion conditions was provided by the authors.

Abstract: Technical innovation is the necessary path for industry in Pearl River Delta to success in industrial transformation and upgrading, the research about how to keep the total increase in the basis as well as to optimize the export structure of manufacturing, and how to keep the whole manufacturing benefits of the Pearl River Delta region sustainably is very necessary. Firstly, this paper adopts the multiple regression analysis to analyze how the technological innovation to optimize the industrial structure of manufacturing in the Pearl River Delta region. Secondly, the author makes a detailed explanation about the technical innovations impact on the manufactured exports with three different technology levels (high-to-low). Finally, this paper offers some specific advice according to the analysis results.

Abstract: Based on the Putaohua groups in Yushulin oil field, and through the statiscics and analyses, weve found that the reservoir property of this area is in the range of specially low permeability level. So due to the low porosity and permeability, its necessary to do some reaearch on the parameters calculation method.This papers analysed the relationships between the physical property parameters such as porosity, permeability, shale content and the well logging responses such as AC, SP, GR, then we built the distribution rules histograms of each physical property parameter. And we got the distribution situations of the parameters of the oil groups. Through the multiple regression, we built the relationship formulas between the reservoir property parameters and the well logging responses by using the core analysis data of 53 test wells. Afetr comparing the parameters of calculation and the core analysis data, we found that the deviation is small, which meets the production requires of oil field.

Abstract: At first, this paper introduced some related domestic and global researches which are about lake basin transboundary water pollution, and put forward several basic assumptions combining the lake basin situation. Based on this foundation, this paper constructed the minimum cost of the whole region, and proposed the cooperation coordination model of the lake basin transboundary water pollution. Then it took advantage of Poyang lake for empirical analysis, and got the function of pollutant reduction cost and function of environmental damage cost by means of multiple regression analysis with the five main data of Poyang lake from 2001 to 2010. Next, through cooperation coordination model establishment and solution, the paper could get the conclusion that compared with the actual pollution reduction plan the model solution is better. At last, the paper talked about the deficiencies and improvement.