时频系统故障预测  

Timing System Failure Prediction

作　　者：王玲玲[1,2] 苟伟 Wang Lingling;Gou Wei(Shanghai Astronomical Observatory, Chinese Academy of Sciences, Shanghai 200030, China;Shanghai Key Laboratory of Space Navigation and Positioning Techniques, Shanghai 200030, China)

机构地区：[1]中国科学院上海天文台,上海200030 [2]上海市空间导航与定位技术重点实验室,上海200030

出　　处：《天文研究与技术》2022年第4期386-395,共10页Astronomical Research & Technology

基　　金：上海市空间导航与定位技术重点实验室基金(201911);平方公里阵列射电望远镜(SKA)专项(2020SKA0120104)资助.

摘　　要：甚长基线干涉测量(Very Long Baseline Interferometry,VLBI)观测站的氢原子钟和时间比对系统(简称时频系统)为测站提供稳定可靠的时间和频率基准,系统信号的质量直接影响观测数据的质量。其中,氢原子钟是时频系统的关键设备,一旦出现故障,对数据的破坏是致命的。因此,时频系统在设计建设之初就对氢原子钟及周边各参数状态进行实时监测并记录保存,一旦发现异常,技术人员需要快速进行处理。中国VLBI网(Chinese VLBI Network,CVN)建成至今,目前共有5个测站,每个测站的时频系统配有两台或以上氢原子钟,系统长期运行积累了大量数据。通过对这些数据的分析,我们可以研究氢原子钟状态变化、性能变化及环境变化之间关系,然后建立故障预测模型,从而对设备故障进行预测。描述创建时频系统数据仓库,利用数据挖掘技术预测系统故障的测试过程,从测试结果可知,聚类模型能够成功预测系统故障。The hydrogen maser and time comparison system(timing system for short)of the VLBI observatory provides a stable and reliable time and frequency reference for the observing station.The quality of the system signal will directly affect the quality of the observation data.Among them,the hydrogen maser is the key equipment of the timing system.Once it fails,its damage to data is fatal.Therefore,at the beginning of the design and construction of the VLBI station timing system,the state of the hydrogen maser and its surrounding parameters are monitored and recorded in real time.Once an abnormality is found,the technicians need to deal with it quickly.Chinese VLBI Network(CVN)has been established so far.There are currently five stations.The timing system of each station is equipped with two or more hydrogen masers.The system has accumulated a large amount of data since its long-term operation.Through the analysis of these data,we can study the relationship between state changes,performance changes,and environmental changes of the hydrogen maser,and then establish a failure prediction model to predict failures.This article describes the test process of creating a timing system data warehouse and using data mining technology to predict system failures,and we find the clustering model can be used to make good predictions in this project.

关 键 词：时频系统 氢原子钟 故障预测 数据驱动 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]