Density-Induced Support Vector Data Description for Fault Detection on Tennessee Eastman Process

Fault detection can be taken as a behavior of detecting abnormal data in process data. Support vector data description (SVDD) has been successfully used for fault detection. Although density-induced support vector data description (D-SVDD) can give a better description of target data by introducing...

Full description

Saved in:
Bibliographic Details
Published inNeural Information Processing pp. 522 - 531
Main Authors Xue, Yangtao, Zhang, Li, Wang, Bangjun, Tang, Baige
Format Book Chapter
LanguageEnglish
Published Cham Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
D-SVDD
Fault detection
TE process
Online AccessGet full text

Cover

More Information
Summary:Fault detection can be taken as a behavior of detecting abnormal data in process data. Support vector data description (SVDD) has been successfully used for fault detection. Although density-induced support vector data description (D-SVDD) can give a better description of target data by introducing relative density degrees than SVDD, the problem of an additional parameter selection hinders the application of D-SVDD, which has a great influence on the performance of D-SVDD. This paper bounds this additional parameter for D-SVDD and applies D-SVDD to fault detection on TE process monitoring. Experiment shows D-SVDD is promising.
ISBN:9783030042110
3030042111
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-030-04212-7_46