{"title":"Fault Detection of DCS Central Control Hardware Devices Based on RTE-PCA","authors":"Qing-hui Sun","doi":"10.1109/ICRAE53653.2021.9657770","DOIUrl":null,"url":null,"abstract":"DCS systems have been widely used in industrial production, but often the fault data of their central control systems are very complex and not conducive to troubleshooting and monitoring. Therefore, an excellent data dimensionality reduction method can accelerate the efficiency of fault diagnosis without losing accuracy. In this paper, we use Random Trees Embedding (RTE) algorithm to firstly expand the data with features to make the highly coupled data linearly separable, and then use PCA to reduce the dimensionality of the data with excellent results. Then, the effect of RTE-PCA algorithm with different parameters is discussed.","PeriodicalId":338398,"journal":{"name":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 6th International Conference on Robotics and Automation Engineering (ICRAE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRAE53653.2021.9657770","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
DCS systems have been widely used in industrial production, but often the fault data of their central control systems are very complex and not conducive to troubleshooting and monitoring. Therefore, an excellent data dimensionality reduction method can accelerate the efficiency of fault diagnosis without losing accuracy. In this paper, we use Random Trees Embedding (RTE) algorithm to firstly expand the data with features to make the highly coupled data linearly separable, and then use PCA to reduce the dimensionality of the data with excellent results. Then, the effect of RTE-PCA algorithm with different parameters is discussed.