Combining KPCA with Sparse SVM for Nonlinear Process Monitoring

Author

Xu, Jie ; Hu, Shousong ; Shen, Zhongyu

Author_Institution

Coll. of Autom. Eng., Nanjing Univ. of Aeronaut. & Astronaut., Nanjing, China

fYear

2010

fDate

28-31 March 2010

Firstpage

1

Lastpage

4

Abstract

A new method for nonlinear process monitoring based on kernel principal analysis and sparse support vector machines is proposed. The data is analyzed using KPCA. T² and SPE are constructed in the future space. If the T² and SPE exceed the predefined control limit, a fault may have occurred . Then the nonlinear score vectors are calculated and fed into the sparse SVM to identify the faults. The proposed method is applied to the simulation of Tennessee Eastman (TE) chemical process .The simulation results show that the proposed method can identify various types of faults accurately and rapidly.

Keywords

chemical technology; fault diagnosis; principal component analysis; process monitoring; support vector machines; Tennessee Eastman chemical process; fault diagnosis; kernel principal component analysis; nonlinear process monitoring; nonlinear score vector; sparse SVM; sparse support vector machine; Automation; Condition monitoring; Data analysis; Educational institutions; Fault detection; Fault diagnosis; Kernel; Machine learning; Principal component analysis; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Power and Energy Engineering Conference (APPEEC), 2010 Asia-Pacific

Conference_Location

Chengdu

Print_ISBN

978-1-4244-4812-8

Electronic_ISBN

978-1-4244-4813-5

Type

conf

DOI

10.1109/APPEEC.2010.5448914

Filename

5448914