Development of a Hybrid PCA-ANFIS Measurement System for Monitoring Product Quality in the Coating Industry

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In industr?, todq many producfs are soldfortheir efficacy rather than their chemical composition. Thereare several key attributes within the coating industrv suchas, Anchorage, Seal strength etc., which characterize thequality of the final product and are features used by thecompany to promote the sale of the product. Such qualifyvariables (dependent variables) however may i.ivolvemeasurement difficulties. The df$culties can be due to avariety of reasons, including: (I) Reliabilify of on-linesensors. (2) Lack of appropriate on-line instrumentation. Inthe coating process off-line laboratory tests dett:nnineproduct qualify measurements. However, such laboratoryanalyses introduce dela-vs in the measurement if keyperjormance indicators. This can result in a signz@canteconomic loss’ if the analysed product fails the qualityconhol test. An improved monitoring system is requiredtherefore to determine product quality online and miviniisecommercial wastage. To facilitate this, advancedmoniroring and control or optimization techniques requireinferred measurements, generated with correlations ?omreadily available process variables (indep,mdentvariables). Although inferential models are widely used inindustr?,, only a few techniques for inferential modeldevelopment are discussed in the open literature. Thispaper therefore will present an improved systematicapproach for the development of inferential models usingsoft computing systems and demonstrate the methodologyby inferring the ‘Anchorage ‘ of polvmeric-coatedsubstrates (i.e. Tpek orpaper) in the coating industv.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages3519-3524
Number of pages6
Publication statusPublished - Oct 2004
Event2004 IEEE International Conference on Systems, Man & Cybernetics - The Hague, The Netherlands
Duration: 1 Oct 2004 → …

Conference

Conference2004 IEEE International Conference on Systems, Man & Cybernetics
Period1/10/04 → …

Fingerprint

Coatings
Monitoring
Industry
Seals
Sales
Chemical analysis

Cite this

@inproceedings{5b42ff9187764bc199b09671026a500e,
title = "Development of a Hybrid PCA-ANFIS Measurement System for Monitoring Product Quality in the Coating Industry",
abstract = "In industr?, todq many producfs are soldfortheir efficacy rather than their chemical composition. Thereare several key attributes within the coating industrv suchas, Anchorage, Seal strength etc., which characterize thequality of the final product and are features used by thecompany to promote the sale of the product. Such qualifyvariables (dependent variables) however may i.ivolvemeasurement difficulties. The df$culties can be due to avariety of reasons, including: (I) Reliabilify of on-linesensors. (2) Lack of appropriate on-line instrumentation. Inthe coating process off-line laboratory tests dett:nnineproduct qualify measurements. However, such laboratoryanalyses introduce dela-vs in the measurement if keyperjormance indicators. This can result in a signz@canteconomic loss’ if the analysed product fails the qualityconhol test. An improved monitoring system is requiredtherefore to determine product quality online and miviniisecommercial wastage. To facilitate this, advancedmoniroring and control or optimization techniques requireinferred measurements, generated with correlations ?omreadily available process variables (indep,mdentvariables). Although inferential models are widely used inindustr?,, only a few techniques for inferential modeldevelopment are discussed in the open literature. Thispaper therefore will present an improved systematicapproach for the development of inferential models usingsoft computing systems and demonstrate the methodologyby inferring the ‘Anchorage ‘ of polvmeric-coatedsubstrates (i.e. Tpek orpaper) in the coating industv.",
author = "K Warne and G Prasad and NH Siddique and LP Maguire",
year = "2004",
month = "10",
language = "English",
pages = "3519--3524",
booktitle = "Unknown Host Publication",

}

Warne, K, Prasad, G, Siddique, NH & Maguire, LP 2004, Development of a Hybrid PCA-ANFIS Measurement System for Monitoring Product Quality in the Coating Industry. in Unknown Host Publication. pp. 3519-3524, 2004 IEEE International Conference on Systems, Man & Cybernetics, 1/10/04.

Development of a Hybrid PCA-ANFIS Measurement System for Monitoring Product Quality in the Coating Industry. / Warne, K; Prasad, G; Siddique, NH; Maguire, LP.

Unknown Host Publication. 2004. p. 3519-3524.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Development of a Hybrid PCA-ANFIS Measurement System for Monitoring Product Quality in the Coating Industry

AU - Warne, K

AU - Prasad, G

AU - Siddique, NH

AU - Maguire, LP

PY - 2004/10

Y1 - 2004/10

N2 - In industr?, todq many producfs are soldfortheir efficacy rather than their chemical composition. Thereare several key attributes within the coating industrv suchas, Anchorage, Seal strength etc., which characterize thequality of the final product and are features used by thecompany to promote the sale of the product. Such qualifyvariables (dependent variables) however may i.ivolvemeasurement difficulties. The df$culties can be due to avariety of reasons, including: (I) Reliabilify of on-linesensors. (2) Lack of appropriate on-line instrumentation. Inthe coating process off-line laboratory tests dett:nnineproduct qualify measurements. However, such laboratoryanalyses introduce dela-vs in the measurement if keyperjormance indicators. This can result in a signz@canteconomic loss’ if the analysed product fails the qualityconhol test. An improved monitoring system is requiredtherefore to determine product quality online and miviniisecommercial wastage. To facilitate this, advancedmoniroring and control or optimization techniques requireinferred measurements, generated with correlations ?omreadily available process variables (indep,mdentvariables). Although inferential models are widely used inindustr?,, only a few techniques for inferential modeldevelopment are discussed in the open literature. Thispaper therefore will present an improved systematicapproach for the development of inferential models usingsoft computing systems and demonstrate the methodologyby inferring the ‘Anchorage ‘ of polvmeric-coatedsubstrates (i.e. Tpek orpaper) in the coating industv.

AB - In industr?, todq many producfs are soldfortheir efficacy rather than their chemical composition. Thereare several key attributes within the coating industrv suchas, Anchorage, Seal strength etc., which characterize thequality of the final product and are features used by thecompany to promote the sale of the product. Such qualifyvariables (dependent variables) however may i.ivolvemeasurement difficulties. The df$culties can be due to avariety of reasons, including: (I) Reliabilify of on-linesensors. (2) Lack of appropriate on-line instrumentation. Inthe coating process off-line laboratory tests dett:nnineproduct qualify measurements. However, such laboratoryanalyses introduce dela-vs in the measurement if keyperjormance indicators. This can result in a signz@canteconomic loss’ if the analysed product fails the qualityconhol test. An improved monitoring system is requiredtherefore to determine product quality online and miviniisecommercial wastage. To facilitate this, advancedmoniroring and control or optimization techniques requireinferred measurements, generated with correlations ?omreadily available process variables (indep,mdentvariables). Although inferential models are widely used inindustr?,, only a few techniques for inferential modeldevelopment are discussed in the open literature. Thispaper therefore will present an improved systematicapproach for the development of inferential models usingsoft computing systems and demonstrate the methodologyby inferring the ‘Anchorage ‘ of polvmeric-coatedsubstrates (i.e. Tpek orpaper) in the coating industv.

M3 - Conference contribution

SP - 3519

EP - 3524

BT - Unknown Host Publication

ER -