DETECTION OF PROCESS MODEL CHANGE IN PLS BASED PERFORMANCE MONITORING

Sukhbinder Kumar; Elaine B. Martin; Julian Morris

doi:10.3182/20020721-6-ES-1901.00752

Back

DETECTION OF PROCESS MODEL CHANGE IN PLS BASED PERFORMANCE MONITORING

Journal article

Peer reviewed

DETECTION OF PROCESS MODEL CHANGE IN PLS BASED PERFORMANCE MONITORING

Sukhbinder Kumar, Elaine B. Martin and Julian Morris

IFAC Proceedings Volumes, Vol.35(1), pp.125-130

2002

DOI: 10.3182/20020721-6-ES-1901.00752

View Online

Abstract

The detection of process changes using a partial least squares (PLS) based monitoring scheme can be achieved through the interrogation of two metrics, Hotelling's T2 and the Q-statistic. The Q-statistic has been shown to be insensitive to small changes in the process model parameters. In this paper, a modified statistic based on the local approach is proposed to detect changes in the model parameters in a PLS based monitoring scheme. The performance of the Q-statistic is compared with the modified statistic through their application to fault detection in a continuous stirred tank reactor.

Fault detection

Local Approach

Process monitoring

Statistical analysis

Details

Title: Subtitle: DETECTION OF PROCESS MODEL CHANGE IN PLS BASED PERFORMANCE MONITORING
Creators: Sukhbinder Kumar - Merz (United States)
Elaine B. Martin - Centre for Process Analytics & Control Technology Merz Court, University of Newcastle Newcastle Upon Tyne, NE1 7RU, England
Julian Morris - Merz (United States)
Resource Type: Journal article
Publication Details: IFAC Proceedings Volumes, Vol.35(1), pp.125-130
DOI: 10.3182/20020721-6-ES-1901.00752
ISSN: 1474-6670
Language: English
Date published: 2002
Academic Unit: Neurosurgery
Record Identifier: 9984304032702771

Metrics

6 Record Views

See more details