No Cover Image

Journal article 1172 views 278 downloads

Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill

M. Evans, J. Kennedy, Mark Evans Orcid Logo

Expert Systems with Applications, Volume: 41, Issue: 15, Pages: 6662 - 6675

Swansea University Author: Mark Evans Orcid Logo

DOI (Published version): 10.1016/j.eswa.2014.05.020

Abstract

Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated...

Full description

Published in: Expert Systems with Applications
Published: 2014
URI: https://cronfa.swan.ac.uk/Record/cronfa20585
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2015-04-01T02:05:25Z
last_indexed 2018-02-09T04:57:16Z
id cronfa20585
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-12-21T11:23:19.2002706</datestamp><bib-version>v2</bib-version><id>20585</id><entry>2015-03-31</entry><title>Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill</title><swanseaauthors><author><sid>7720f04c308cf7a1c32312058780d20c</sid><ORCID>0000-0003-2056-2396</ORCID><firstname>Mark</firstname><surname>Evans</surname><name>Mark Evans</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2015-03-31</date><deptcode>MTLS</deptcode><abstract>Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than &#x2212;0.098 the second lower than 0.8058 and the third higher than &#x2212;0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab.</abstract><type>Journal Article</type><journal>Expert Systems with Applications</journal><volume>41</volume><journalNumber>15</journalNumber><paginationStart>6662</paginationStart><paginationEnd>6675</paginationEnd><publisher/><keywords/><publishedDay>1</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2014</publishedYear><publishedDate>2014-11-01</publishedDate><doi>10.1016/j.eswa.2014.05.020</doi><url/><notes></notes><college>COLLEGE NANME</college><department>Materials Science and Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MTLS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2017-12-21T11:23:19.2002706</lastEdited><Created>2015-03-31T16:08:31.7526567</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Materials Science and Engineering</level></path><authors><author><firstname>M.</firstname><surname>Evans</surname><order>1</order></author><author><firstname>J.</firstname><surname>Kennedy</surname><order>2</order></author><author><firstname>Mark</firstname><surname>Evans</surname><orcid>0000-0003-2056-2396</orcid><order>3</order></author></authors><documents><document><filename>0020585-21122017111445.pdf</filename><originalFilename>20585.pdf</originalFilename><uploaded>2017-12-21T11:14:45.9970000</uploaded><type>Output</type><contentLength>1442009</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2016-02-29T00:00:00.0000000</embargoDate><copyrightCorrect>false</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2017-12-21T11:23:19.2002706 v2 20585 2015-03-31 Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill 7720f04c308cf7a1c32312058780d20c 0000-0003-2056-2396 Mark Evans Mark Evans true false 2015-03-31 MTLS Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than −0.098 the second lower than 0.8058 and the third higher than −0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab. Journal Article Expert Systems with Applications 41 15 6662 6675 1 11 2014 2014-11-01 10.1016/j.eswa.2014.05.020 COLLEGE NANME Materials Science and Engineering COLLEGE CODE MTLS Swansea University 2017-12-21T11:23:19.2002706 2015-03-31T16:08:31.7526567 Faculty of Science and Engineering School of Engineering and Applied Sciences - Materials Science and Engineering M. Evans 1 J. Kennedy 2 Mark Evans 0000-0003-2056-2396 3 0020585-21122017111445.pdf 20585.pdf 2017-12-21T11:14:45.9970000 Output 1442009 application/pdf Accepted Manuscript true 2016-02-29T00:00:00.0000000 false eng
title Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
spellingShingle Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
Mark Evans
title_short Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
title_full Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
title_fullStr Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
title_full_unstemmed Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
title_sort Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill
author_id_str_mv 7720f04c308cf7a1c32312058780d20c
author_id_fullname_str_mv 7720f04c308cf7a1c32312058780d20c_***_Mark Evans
author Mark Evans
author2 M. Evans
J. Kennedy
Mark Evans
format Journal article
container_title Expert Systems with Applications
container_volume 41
container_issue 15
container_start_page 6662
publishDate 2014
institution Swansea University
doi_str_mv 10.1016/j.eswa.2014.05.020
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 Engineering and Applied Sciences - Materials Science and Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Materials Science and Engineering
document_store_str 1
active_str 0
description Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than −0.098 the second lower than 0.8058 and the third higher than −0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab.
published_date 2014-11-01T03:24:23Z
_version_ 1763750825849520128
score 11.035634

Similar Items