Adaptive Partial Least Squares with Application to Process Monitoring

S. Kumar; S.N. Thennadil; A.J. Morris; E.B. Martin

doi:10.1016/S1474-6670(17)36589-8

Back

Adaptive Partial Least Squares with Application to Process Monitoring

Journal article

Peer reviewed

Adaptive Partial Least Squares with Application to Process Monitoring

S. Kumar, S.N. Thennadil, A.J. Morris and E.B. Martin

IFAC Proceedings Volumes, Vol.36(5), pp.789-794

06/2003

DOI: 10.1016/S1474-6670(17)36589-8

View Online

Abstract

Partial least squares has been applied in process modelling and process performance monitoring where a large number of correlated variables are recorded. The most commonly implemented algorithm for identifying a PLS model has been the batch algorithm. In this case, data from the process is first required to be stored. In this paper an algorithm is proposed that recursively updates the parameters of PLS as and when a sample of measurements is obtained thereby reducing the need for data storage. The algorithm was tested on an artificially generated data set. The approach was then used to derive a statistic for process monitoring that was applied for the detection of faults in a continuous stirred tank reactor.

Adaptive systems

Fault detection

Subspace methods

Details

Title: Subtitle: Adaptive Partial Least Squares with Application to Process Monitoring
Creators: S. Kumar - University of Newcastle Australia
S.N. Thennadil - Newcastle University
A.J. Morris - University of Newcastle Australia
E.B. Martin - University of Newcastle Australia
Resource Type: Journal article
Publication Details: IFAC Proceedings Volumes, Vol.36(5), pp.789-794
DOI: 10.1016/S1474-6670(17)36589-8
ISSN: 1474-6670
Language: English
Date published: 06/2003
Academic Unit: Neurosurgery
Record Identifier: 9984304030902771

Metrics

15 Record Views