A comparison of different discriminant analysis techniques in a steel industry welding process

José M. Prats-Montalbán; Alberto Ferrer; J. L. Malo; J. Gorbeña

doi:10.1016/j.chemolab.2005.08.005

A comparison of different discriminant analysis techniques in a steel industry welding process

José M. Prats-Montalbán^*, Alberto Ferrer, J. L. Malo, J. Gorbeña

^*Corresponding author for this work

Market

Research output: Contribution to journal › Article › peer-review

14 Citations (Scopus)

Abstract

The present work compares several statistical discriminant analysis techniques applied to a steel industry welding process. Data from 85 variables collected from 18,605 links, classified as Good (18,381), Defective (195) or Bad (29) from laboratory analysis, are available. Process engineers want to find out which variables explain the main differences between the three defined types, so they can implement effective action to reduce the percentage of Defective and Bad links. The approaches used are SIMCA, Global PCA, PLS-DA and Fisher's Linear Discriminant Analysis (LDA). The dataset comprises two kinds of variables, one for the chemical properties of the links, and the other related to the welding process. All the above approaches basically lead to the same results and match the ones derived from the more traditional Fisher s Linear Discriminant Analysis (LDA) technique. The pros and cons of the approaches used are discussed.

Original language	English
Pages (from-to)	109-119
Number of pages	11
Journal	Chemometrics and Intelligent Laboratory Systems
Volume	80
Issue number	1
DOIs	https://doi.org/10.1016/j.chemolab.2005.08.005
Publication status	Published - 20 Jan 2006

Funding

The authors would like to thank to the referees for their helpful comments and suggestions that have improved the consistency of this work. This research was supported by the Spanish Government (Science and Technology Ministry) and the European Union (RDE funds) under the project DPI 2001-2749-C02. The authors want to thank Vicinay Cadenas S.A. for its support, providing the data and sharing its process knowledge.

Funders	Funder number
European Commission	DPI 2001-2749-C02

Keywords

Linear Discriminant Analysis
PCA
PLS-Discriminant Analysis
SIMCA
Welding process

Access to Document

10.1016/j.chemolab.2005.08.005

Cite this

@article{f3cc42f22cec410ea104f1d3bc038b2a,

title = "A comparison of different discriminant analysis techniques in a steel industry welding process",

abstract = "The present work compares several statistical discriminant analysis techniques applied to a steel industry welding process. Data from 85 variables collected from 18,605 links, classified as Good (18,381), Defective (195) or Bad (29) from laboratory analysis, are available. Process engineers want to find out which variables explain the main differences between the three defined types, so they can implement effective action to reduce the percentage of Defective and Bad links. The approaches used are SIMCA, Global PCA, PLS-DA and Fisher's Linear Discriminant Analysis (LDA). The dataset comprises two kinds of variables, one for the chemical properties of the links, and the other related to the welding process. All the above approaches basically lead to the same results and match the ones derived from the more traditional Fisher s Linear Discriminant Analysis (LDA) technique. The pros and cons of the approaches used are discussed.",

keywords = "Linear Discriminant Analysis, PCA, PLS-Discriminant Analysis, SIMCA, Welding process",

author = "Prats-Montalb{\'a}n, {Jos{\'e} M.} and Alberto Ferrer and Malo, {J. L.} and J. Gorbe{\~n}a",

year = "2006",

month = jan,

day = "20",

doi = "10.1016/j.chemolab.2005.08.005",

language = "English",

volume = "80",

pages = "109--119",

journal = "Chemometrics and Intelligent Laboratory Systems",

issn = "0169-7439",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - A comparison of different discriminant analysis techniques in a steel industry welding process

AU - Prats-Montalbán, José M.

AU - Ferrer, Alberto

AU - Malo, J. L.

AU - Gorbeña, J.

PY - 2006/1/20

Y1 - 2006/1/20

N2 - The present work compares several statistical discriminant analysis techniques applied to a steel industry welding process. Data from 85 variables collected from 18,605 links, classified as Good (18,381), Defective (195) or Bad (29) from laboratory analysis, are available. Process engineers want to find out which variables explain the main differences between the three defined types, so they can implement effective action to reduce the percentage of Defective and Bad links. The approaches used are SIMCA, Global PCA, PLS-DA and Fisher's Linear Discriminant Analysis (LDA). The dataset comprises two kinds of variables, one for the chemical properties of the links, and the other related to the welding process. All the above approaches basically lead to the same results and match the ones derived from the more traditional Fisher s Linear Discriminant Analysis (LDA) technique. The pros and cons of the approaches used are discussed.

AB - The present work compares several statistical discriminant analysis techniques applied to a steel industry welding process. Data from 85 variables collected from 18,605 links, classified as Good (18,381), Defective (195) or Bad (29) from laboratory analysis, are available. Process engineers want to find out which variables explain the main differences between the three defined types, so they can implement effective action to reduce the percentage of Defective and Bad links. The approaches used are SIMCA, Global PCA, PLS-DA and Fisher's Linear Discriminant Analysis (LDA). The dataset comprises two kinds of variables, one for the chemical properties of the links, and the other related to the welding process. All the above approaches basically lead to the same results and match the ones derived from the more traditional Fisher s Linear Discriminant Analysis (LDA) technique. The pros and cons of the approaches used are discussed.

KW - Linear Discriminant Analysis

KW - PCA

KW - PLS-Discriminant Analysis

KW - SIMCA

KW - Welding process

UR - http://www.scopus.com/inward/record.url?scp=30144441612&partnerID=8YFLogxK

U2 - 10.1016/j.chemolab.2005.08.005

DO - 10.1016/j.chemolab.2005.08.005

M3 - Article

AN - SCOPUS:30144441612

SN - 0169-7439

VL - 80

SP - 109

EP - 119

JO - Chemometrics and Intelligent Laboratory Systems

JF - Chemometrics and Intelligent Laboratory Systems

IS - 1

ER -

A comparison of different discriminant analysis techniques in a steel industry welding process

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this