计算机应用 ›› 2005, Vol. 25 ›› Issue (07): 1584-1586.DOI: 10.3724/SP.J.1087.2005.01587

• 数据库技术 • 上一篇    下一篇

基于设备故障监控的时间序列模式研究应用

闫伟1,张浩2,陆剑峰1   

  1. 1.同济大学 CIMS研究中心,上海 200092; 2.上海电力学院 电力与自动化工程学院,上海 200092
  • 收稿日期:2004-12-15 修回日期:2005-03-08 出版日期:2005-07-01 发布日期:2005-07-01
  • 作者简介:闫伟(1973-),男,山东济南人,讲师,博士研究生,主要研究方向:数据仓库、数据挖掘;张浩(1963-),男,上海人,教授,博士生导师,主要研究方向:CIMS技术、远程服务;陆剑峰(1973-),男,上海人,讲师,博士,主要研究方向:CIMS技术
  • 基金资助:

    国家863计划项目(2002AA412410)

Study and application of time-interval sequential pattern to equipment fault monitoring

YAN Wei1,ZHANG Hao2,LU Jian-feng1   

  1. 1. CIMS Center, Tongji University; 2. School of Electric Power and Automatic Engineering, Shanghai University of Electric Power
  • Received:2004-12-15 Revised:2005-03-08 Online:2005-07-01 Published:2005-07-01

摘要:

采用数据挖掘中的时间序列模式对流程企业中的运行数据进行分析,首先采用模糊理论对实际数据进行处理,找出偏离常规运行状态但未到报警界限的参数点,然后采用时间窗对参数离散处理,划分时间间隔得到时间序列数据库。采用TimeSeq_PrefixSpan算法并编程实现,得到了按次序排列且有时间间隔的异常参数点对设备故障影响的规则,起到了对设备故障预警监控的作用。

关键词: 数据挖掘, 时间序列分析, TimeSeq_PrefixSpan算法, 故障监控, 流程企业

Abstract:

Time-interval sequential pattern mining was used to discover frequent subsequences as patterns from sequence database of flowing industry. Firstly, the large history database were analyzed by fuzzy theory and the exceptional equipment parameters were found. After scattering exceptional parameters by Time-window approach, a new time-interval sequential database was got by dealing with time intervals. In order to find time-interval sequential pattern, TimeSeq_PrefixSpan algorithm is developed from the conventional PrefixSpan algorithm and implemented in flowing industry's production. Then the models can monitor faults when the equipments circulating.

Key words: data mining, time-interval sequential analysis, TimeSeq_PrefixSpan algorithm, fault monitoring, flowing industry

中图分类号: