{"title":"Research on Thermal Error of CNC Machine Tool Based on DBSCAN Clustering and BP Neural Network Algorithm","authors":"Huanzhao Li, Aimei Zhang, Xue-Yang Pei","doi":"10.1109/ICIASE45644.2019.9074094","DOIUrl":null,"url":null,"abstract":"To reduce the influence of thermal error on the accuracy of CNC machine tool this paper proposed a temperature sensor measuring point optimization method based on DBSCAN clustering algorithm and a BP neural network modeling method for CNC machine tool. DBSCAN algorithm and Pearson correlation coefficient method reduced the temperature measurement point from 16 to 5. Established BP neural network for temperature and spindle displacement, and the score of the model up to 0.99, which provided an important theoretical basis for the machine tool thermal error compensation.","PeriodicalId":206741,"journal":{"name":"2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIASE45644.2019.9074094","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
To reduce the influence of thermal error on the accuracy of CNC machine tool this paper proposed a temperature sensor measuring point optimization method based on DBSCAN clustering algorithm and a BP neural network modeling method for CNC machine tool. DBSCAN algorithm and Pearson correlation coefficient method reduced the temperature measurement point from 16 to 5. Established BP neural network for temperature and spindle displacement, and the score of the model up to 0.99, which provided an important theoretical basis for the machine tool thermal error compensation.