{"title":"Predictive model for compressor impeller tightness","authors":"V. Pechenin, E. Pechenina, M. Bolotov","doi":"10.1109/ITNT57377.2023.10138949","DOIUrl":null,"url":null,"abstract":"A model has been developed to predict the angular reversals of the blades in the impeller that occur during assembly. The calculated angles characterize the tightness in the connections of the blade end flanges. The model inputs data on geometry deviations from part inspection operations. The model uses the random forest method, and the model was trained on a set of numerical experiments performed in the ANSYS environment. According to experimental findings, the ANSYS model's error does not exceed 10 angular minutes, and the regression model's overall error does not exceed 20 angular minutes.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITNT57377.2023.10138949","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
A model has been developed to predict the angular reversals of the blades in the impeller that occur during assembly. The calculated angles characterize the tightness in the connections of the blade end flanges. The model inputs data on geometry deviations from part inspection operations. The model uses the random forest method, and the model was trained on a set of numerical experiments performed in the ANSYS environment. According to experimental findings, the ANSYS model's error does not exceed 10 angular minutes, and the regression model's overall error does not exceed 20 angular minutes.