计算机应用

• 典型应用 • 上一篇    下一篇

改进的核费舍判别分析法应用于故障诊断

吴洪艳 黄道平   

  1. 华南理工大学自动化学院;湛江师范学院信息科学与工程学院
  • 收稿日期:2008-08-26 修回日期:2008-10-17 发布日期:2009-04-22 出版日期:2009-02-01
  • 通讯作者: 吴洪艳

Improving kernel fisher discriminant analysis for fault diagnosis in chemical process

<a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=((([Author]) AND 1[Journal]) AND year[Order])" target="_blank"></a> <a href="http://www.joca.cn/EN/article/advancedSearchResult.do?searchSQL=((([Author]) AND 1[Journal]) AND year[Order])" target="_blank"></a>   

  • Received:2008-08-26 Revised:2008-10-17 Online:2009-04-22 Published:2009-02-01

摘要: 化工过程采样数据具有强非线性和噪声,针对化工过程状态监控的问题,提出一种改进的核费舍判别分析法(KFDA)的故障诊断算法。首先采样数据经过小波变换方法去除噪声,去除噪声后的数据进行KFDA建模,然后在建模同时采用特征向量选择(FVS)算法降低复杂性。Tennessee Eastman process实验结果表明了该算法的有效性,同时该算法加强了KFDA故障诊断的准确性,并明显地减少了存储空间和运算时间。

关键词: 核费舍判别分析, 故障诊断, 小波降噪, 特征向量选择

Abstract: The sample data in chemical process have strong nonlinearity and involve noise. To solve the problem of condition monitoring for chemical process, an improved KFDA method for fault diagnosis was proposed. It first performed the wavelet transform to remove noise, and the de-noised data were constructed KFDA model. Then a geometry-based feature vector selection (FVS) scheme was adopted to reduce the computational complexity of KFDA. Tennessee Eastman process (TEP) simulations were carried out to show that the given method is effective, and it enhances the accuracy of KFDA for fault diagnosis and reduces memory space and run time.

Key words: Kernel Fisher Discriminant Analysis (KFDA), fault diagnosis, wavelet de-noising, feature vector selection