计算机科学与探索 ›› 2009, Vol. 3 ›› Issue (3): 267-281.DOI: 10.3778/j.issn.1673-9418.2009.03.005

• 学术研究 • 上一篇    下一篇

用事件间隔来分析化工企业的报警序列

KORDIC Savo1,LAM Chiou Peng1,肖计田1,李怀忠2+   

  1. 1. 伊迪斯科文大学 计算机和信息科学学院,澳大利亚 西澳 佩斯 6050
    2. 温州大学 计算机科学与工程学院,浙江 温州 325035
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-05-15 发布日期:2009-05-15
  • 通讯作者: 李怀忠

Using Event-intervals to Analyze Alarm Sequences in a Chemical Plant

KORDIC Savo1, LAM Chiou Peng1, XIAO Jitian1, LI Huaizhong2+   

  1. 1. School of Computer and Information Science, Edith Cowan University, Perth 6050, Australia
    2. School of Computer Science and Engineering, Wenzhou University, Wenzhou, Zhejiang 325035, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-05-15 Published:2009-05-15
  • Contact: LI Huaizhong

摘要: 以典型的醋酸乙烯化工过程模型数据和英国石油Kwinana炼油厂实际警报数据为基础,研究了化工过程中通过发掘关联警报标签集来支持合理化的报警设置,提出了依据交叉效果测试来进行事件分割和数据过滤。

关键词: 数据挖掘, 报警序列, 关联警报, 化工过程

Abstract: A data mining approach is designed to support alarm rationalization by discovering correlated sets of alarm tags. The proposed approach is evaluated using simulation data from a model of the vinyl acetate chemical process as well as real plant alarm data. Results show that the proposed approach, using an event segmentation and data filtering strategy based on a cross-effect test, is significant.

Key words: data mining, alarm sequences, correlated alarms, chemical processes