No Cover Image

Journal article 1199 views

A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data

Cinzia Giannetti Orcid Logo, Rajesh Ransing Orcid Logo, M.R. Ransing, D.C. Bould, David Gethin Orcid Logo, Johann Sienz Orcid Logo

Computers & Industrial Engineering, Volume: 72, Pages: 217 - 229

Swansea University Authors: Cinzia Giannetti Orcid Logo, Rajesh Ransing Orcid Logo, David Gethin Orcid Logo, Johann Sienz Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1016/j.cie.2014.03.017

Abstract

In the last two decades the application of statistical techniques to process control has gained popularity due to the widespread adoption of quality management systems such as ISO9001. Demonstration of continual process improvement by monitoring process effectiveness has become an integral part of s...

Full description

Published in: Computers & Industrial Engineering
ISSN: 0360-8352
Published: 2014
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa21495
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2015-05-19T02:03:14Z
last_indexed 2020-10-24T02:30:56Z
id cronfa21495
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-10-23T15:46:29.5189888</datestamp><bib-version>v2</bib-version><id>21495</id><entry>2015-05-18</entry><title>A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data</title><swanseaauthors><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>0136f9a20abec3819b54088d9647c39f</sid><ORCID>0000-0003-4848-4545</ORCID><firstname>Rajesh</firstname><surname>Ransing</surname><name>Rajesh Ransing</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>20b93675a5457203ae87ebc32bd6d155</sid><ORCID>0000-0002-7142-8253</ORCID><firstname>David</firstname><surname>Gethin</surname><name>David Gethin</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>17bf1dd287bff2cb01b53d98ceb28a31</sid><ORCID>0000-0003-3136-5718</ORCID><firstname>Johann</firstname><surname>Sienz</surname><name>Johann Sienz</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2015-05-18</date><deptcode>MECH</deptcode><abstract>In the last two decades the application of statistical techniques to process control has gained popularity due to the widespread adoption of quality management systems such as ISO9001. Demonstration of continual process improvement by monitoring process effectiveness has become an integral part of satisfying the requirements of clause 8 of the ISO9001:2008 standard. The process effectiveness is measured in terms of one or more process responses. Data driven approaches are often used to associate the variability in process responses with one or more process variables. However, traditional techniques become unpractical in the presence of large number of variables and noisy data sets. This paper extends the co-linearity index and penalty matrix approach (Ransing et al., 2013) for discovering noise free correlations between heterogeneous process variables and responses. Noise is removed by reducing the dimensionality of the variable space and using robust data pre-treatment methods which are more suitable in the presence of outliers and skewed distributions for process variables. Scaling factors have been proposed to balance variance contributions from response variables, quantitative and categorical variables. The proposed method allows process variables with skewed distribution to contribute more to the variance than Gaussian distributed variables so that these variables can be investigated further, if necessary. Correlations are visualised in a single plot and can be used in real industrial settings to assist process engineers in manufacturing diagnosis and root cause analysis. The applicability and validity of this novel method has been demonstrated through two industrial case studies.</abstract><type>Journal Article</type><journal>Computers &amp; Industrial Engineering</journal><volume>72</volume><paginationStart>217</paginationStart><paginationEnd>229</paginationEnd><publisher/><issnPrint>0360-8352</issnPrint><keywords/><publishedDay>30</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2014</publishedYear><publishedDate>2014-06-30</publishedDate><doi>10.1016/j.cie.2014.03.017</doi><url/><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-10-23T15:46:29.5189888</lastEdited><Created>2015-05-18T14:31:55.9898069</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>1</order></author><author><firstname>Rajesh</firstname><surname>Ransing</surname><orcid>0000-0003-4848-4545</orcid><order>2</order></author><author><firstname>M.R.</firstname><surname>Ransing</surname><order>3</order></author><author><firstname>D.C.</firstname><surname>Bould</surname><order>4</order></author><author><firstname>David</firstname><surname>Gethin</surname><orcid>0000-0002-7142-8253</orcid><order>5</order></author><author><firstname>Johann</firstname><surname>Sienz</surname><orcid>0000-0003-3136-5718</orcid><order>6</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2020-10-23T15:46:29.5189888 v2 21495 2015-05-18 A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 0136f9a20abec3819b54088d9647c39f 0000-0003-4848-4545 Rajesh Ransing Rajesh Ransing true false 20b93675a5457203ae87ebc32bd6d155 0000-0002-7142-8253 David Gethin David Gethin true false 17bf1dd287bff2cb01b53d98ceb28a31 0000-0003-3136-5718 Johann Sienz Johann Sienz true false 2015-05-18 MECH In the last two decades the application of statistical techniques to process control has gained popularity due to the widespread adoption of quality management systems such as ISO9001. Demonstration of continual process improvement by monitoring process effectiveness has become an integral part of satisfying the requirements of clause 8 of the ISO9001:2008 standard. The process effectiveness is measured in terms of one or more process responses. Data driven approaches are often used to associate the variability in process responses with one or more process variables. However, traditional techniques become unpractical in the presence of large number of variables and noisy data sets. This paper extends the co-linearity index and penalty matrix approach (Ransing et al., 2013) for discovering noise free correlations between heterogeneous process variables and responses. Noise is removed by reducing the dimensionality of the variable space and using robust data pre-treatment methods which are more suitable in the presence of outliers and skewed distributions for process variables. Scaling factors have been proposed to balance variance contributions from response variables, quantitative and categorical variables. The proposed method allows process variables with skewed distribution to contribute more to the variance than Gaussian distributed variables so that these variables can be investigated further, if necessary. Correlations are visualised in a single plot and can be used in real industrial settings to assist process engineers in manufacturing diagnosis and root cause analysis. The applicability and validity of this novel method has been demonstrated through two industrial case studies. Journal Article Computers & Industrial Engineering 72 217 229 0360-8352 30 6 2014 2014-06-30 10.1016/j.cie.2014.03.017 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University 2020-10-23T15:46:29.5189888 2015-05-18T14:31:55.9898069 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Cinzia Giannetti 0000-0003-0339-5872 1 Rajesh Ransing 0000-0003-4848-4545 2 M.R. Ransing 3 D.C. Bould 4 David Gethin 0000-0002-7142-8253 5 Johann Sienz 0000-0003-3136-5718 6
title A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
spellingShingle A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
Cinzia Giannetti
Rajesh Ransing
David Gethin
Johann Sienz
title_short A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
title_full A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
title_fullStr A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
title_full_unstemmed A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
title_sort A novel variable selection approach based on co-linearity index to discover optimal process settings by analysing mixed data
author_id_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6
0136f9a20abec3819b54088d9647c39f
20b93675a5457203ae87ebc32bd6d155
17bf1dd287bff2cb01b53d98ceb28a31
author_id_fullname_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
0136f9a20abec3819b54088d9647c39f_***_Rajesh Ransing
20b93675a5457203ae87ebc32bd6d155_***_David Gethin
17bf1dd287bff2cb01b53d98ceb28a31_***_Johann Sienz
author Cinzia Giannetti
Rajesh Ransing
David Gethin
Johann Sienz
author2 Cinzia Giannetti
Rajesh Ransing
M.R. Ransing
D.C. Bould
David Gethin
Johann Sienz
format Journal article
container_title Computers & Industrial Engineering
container_volume 72
container_start_page 217
publishDate 2014
institution Swansea University
issn 0360-8352
doi_str_mv 10.1016/j.cie.2014.03.017
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 0
active_str 0
description In the last two decades the application of statistical techniques to process control has gained popularity due to the widespread adoption of quality management systems such as ISO9001. Demonstration of continual process improvement by monitoring process effectiveness has become an integral part of satisfying the requirements of clause 8 of the ISO9001:2008 standard. The process effectiveness is measured in terms of one or more process responses. Data driven approaches are often used to associate the variability in process responses with one or more process variables. However, traditional techniques become unpractical in the presence of large number of variables and noisy data sets. This paper extends the co-linearity index and penalty matrix approach (Ransing et al., 2013) for discovering noise free correlations between heterogeneous process variables and responses. Noise is removed by reducing the dimensionality of the variable space and using robust data pre-treatment methods which are more suitable in the presence of outliers and skewed distributions for process variables. Scaling factors have been proposed to balance variance contributions from response variables, quantitative and categorical variables. The proposed method allows process variables with skewed distribution to contribute more to the variance than Gaussian distributed variables so that these variables can be investigated further, if necessary. Correlations are visualised in a single plot and can be used in real industrial settings to assist process engineers in manufacturing diagnosis and root cause analysis. The applicability and validity of this novel method has been demonstrated through two industrial case studies.
published_date 2014-06-30T03:25:31Z
_version_ 1763750897030004736
score 11.016235

Similar Items