Nonlinear Process Monitoring and Fault Diagnosis Based on KPCA and MKL-SVM

Author

Xu, Jie ; Hu, Shousong

Author_Institution

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

Volume

1

fYear

2010

fDate

23-24 Oct. 2010

Firstpage

233

Lastpage

237

Abstract

A new method for nonlinear process monitoring and fault diagnosis based on kernel principal analysis and multiple kernel learning 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 MKL-SVM to identify the faults. The results of the monitoring application to the Tennessee Eastman (TE) chemical process demonstrate the effectiveness of the proposed method.

Keywords

chemical industry; fault diagnosis; learning (artificial intelligence); principal component analysis; process monitoring; support vector machines; KPCA; MKL-SVM; Tennessee Eastman chemical process; fault diagnosis; multiple kernel learning support vector machine; nonlinear process monitoring; nonlinear score vector; predefined control limit; Fault detection; Fault diagnosis; Kernel; Machine learning; Monitoring; Principal component analysis; Support vector machines; fault diagnosis; kernel principal component analysis; multiple kernel learning; process monitoring; support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence and Computational Intelligence (AICI), 2010 International Conference on

Conference_Location

Sanya

Print_ISBN

978-1-4244-8432-4

Type

conf

DOI

10.1109/AICI.2010.56

Filename

5656754