PLS modelling and fault detection on the Tennessee Eastman benchmark

Author

Wilson, D.J.H. ; Irwin, G.W.

Author_Institution

Dept. of Electr. & Electron. Eng., Queen´´s Univ., Belfast, UK

Volume

6

fYear

1999

fDate

1999

Firstpage

3975

Abstract

This paper describes the application of multivariate regression techniques to the Tennessee Eastman benchmark process. Two methods are applied: linear partial least squares, and a nonlinear variant of this procedure using a radial basis function inner relation. These methods are used to create online inferential models of delayed process measurement. The redundancy so obtained is then used to generate a fault detection and isolation scheme for these sensors. The effectiveness of this scheme is demonstrated on a number of test faults

Keywords

chemical industry; fault diagnosis; least squares approximations; principal component analysis; quality control; radial basis function networks; redundancy; statistical process control; Eastman Kodak plant; RBF neural networks; Tennessee Eastman benchmark; fault detection; fault diagnosis; inferential models; multivariate regression; partial least squares; principal component analysis; quality control; redundancy; sensors; statistical process control; Benchmark testing; Control engineering; Delay estimation; Electrical fault detection; Fault detection; Least squares methods; Multivariate regression; Principal component analysis; Process control; Software testing;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 1999. Proceedings of the 1999

Conference_Location

San Diego, CA

ISSN

0743-1619

Print_ISBN

0-7803-4990-3

Type

conf

DOI

10.1109/ACC.1999.786264

Filename

786264