{"title":"STUDY OF INCOMPLETE LINEAR REGRESSION MODEL OF THERMAL RESISTANCE OF THE COUPLING PSEUDO-MEDIUM","authors":"V. Dmitriev, A. Denisenko, L. Podkruglyak","doi":"10.30987/2782-5957-2023-6-12-20","DOIUrl":null,"url":null,"abstract":"The problems of analyzing the thermal pattern of the spindle assembly of the machine are considered. A technique for obtaining regression models in MS Excel environment is developed. A linear regression model of changing the contact thermal resistance is proposed without taking into account the interaction of factors in the thermal model of the joints of machine parts. Using the Correlation tool, a comparative assessment of the significance and elimination of some factors are performed by analyzing matching linear correlation coefficients. With the help of the Regression tool based on the least squares method (LSM), a numerical evaluation of the parameters of the proposed models and their quality check are performed; the homoscedasticity of the regression residues is proved; the statistical equivalence of the constructed models is analyzed.","PeriodicalId":289189,"journal":{"name":"Transport engineering","volume":"124 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transport engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.30987/2782-5957-2023-6-12-20","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The problems of analyzing the thermal pattern of the spindle assembly of the machine are considered. A technique for obtaining regression models in MS Excel environment is developed. A linear regression model of changing the contact thermal resistance is proposed without taking into account the interaction of factors in the thermal model of the joints of machine parts. Using the Correlation tool, a comparative assessment of the significance and elimination of some factors are performed by analyzing matching linear correlation coefficients. With the help of the Regression tool based on the least squares method (LSM), a numerical evaluation of the parameters of the proposed models and their quality check are performed; the homoscedasticity of the regression residues is proved; the statistical equivalence of the constructed models is analyzed.