Y. Wenmin, Hou Xiuqun, Li Yuanjiao, Jiang Qinglei, Bao Binbin
{"title":"基于相关系数的核泵振动监测数据异常定位方法研究","authors":"Y. Wenmin, Hou Xiuqun, Li Yuanjiao, Jiang Qinglei, Bao Binbin","doi":"10.1109/ICAIIS49377.2020.9194833","DOIUrl":null,"url":null,"abstract":"Nuclear power plants have accumulated a large amount of process monitoring data, but most of the data are not marked with specified patterns, which cannot be directly applied to the data-driven intelligent early warning and fault diagnosis. On-site alarm threshold can only locate a small number of abnormal vibration data, ignoring a large number of data that doesn't exceed alarm threshold but is obviously abnormal fluctuation of vibration phenomenon. To solve this problem, a method is proposed to locate abnormal vibration data based on correlation coefficient in this paper. This method takes the correlation coefficient of vibration data and corresponding time as the fluctuation index of measuring vibration data, and calculates the fluctuation threshold through historical data statistics, so as to locate abnormal vibration data. The vibration monitoring data of nuclear pump show that the proposed method can effectively detect the abnormal fluctuation of the data and locate the starting point of abnormal vibration.","PeriodicalId":416002,"journal":{"name":"2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on Anomaly Location Method for Nuclear Pump Vibration Monitoring Data Based on Correlation Coefficient\",\"authors\":\"Y. Wenmin, Hou Xiuqun, Li Yuanjiao, Jiang Qinglei, Bao Binbin\",\"doi\":\"10.1109/ICAIIS49377.2020.9194833\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Nuclear power plants have accumulated a large amount of process monitoring data, but most of the data are not marked with specified patterns, which cannot be directly applied to the data-driven intelligent early warning and fault diagnosis. On-site alarm threshold can only locate a small number of abnormal vibration data, ignoring a large number of data that doesn't exceed alarm threshold but is obviously abnormal fluctuation of vibration phenomenon. To solve this problem, a method is proposed to locate abnormal vibration data based on correlation coefficient in this paper. This method takes the correlation coefficient of vibration data and corresponding time as the fluctuation index of measuring vibration data, and calculates the fluctuation threshold through historical data statistics, so as to locate abnormal vibration data. The vibration monitoring data of nuclear pump show that the proposed method can effectively detect the abnormal fluctuation of the data and locate the starting point of abnormal vibration.\",\"PeriodicalId\":416002,\"journal\":{\"name\":\"2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS)\",\"volume\":\"56 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAIIS49377.2020.9194833\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAIIS49377.2020.9194833","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Research on Anomaly Location Method for Nuclear Pump Vibration Monitoring Data Based on Correlation Coefficient
Nuclear power plants have accumulated a large amount of process monitoring data, but most of the data are not marked with specified patterns, which cannot be directly applied to the data-driven intelligent early warning and fault diagnosis. On-site alarm threshold can only locate a small number of abnormal vibration data, ignoring a large number of data that doesn't exceed alarm threshold but is obviously abnormal fluctuation of vibration phenomenon. To solve this problem, a method is proposed to locate abnormal vibration data based on correlation coefficient in this paper. This method takes the correlation coefficient of vibration data and corresponding time as the fluctuation index of measuring vibration data, and calculates the fluctuation threshold through historical data statistics, so as to locate abnormal vibration data. The vibration monitoring data of nuclear pump show that the proposed method can effectively detect the abnormal fluctuation of the data and locate the starting point of abnormal vibration.