No Cover Image

Journal article 577 views 71 downloads

Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process

Kayal Lakshmanan, Eugenio Borghini, Arnold Beckmann Orcid Logo, Cameron Pleydell-Pearce, Cinzia Giannetti Orcid Logo

Procedia Computer Science, Volume: 207, Issue: C, Pages: 1057 - 1066

Swansea University Authors: Kayal Lakshmanan, Eugenio Borghini, Arnold Beckmann Orcid Logo, Cameron Pleydell-Pearce, Cinzia Giannetti Orcid Logo

  • 61602.pdf

    PDF | Version of Record

    © 2022 The Authors. This is an open access article under the CC BY-NC-ND license

    Download (1.13MB)

Check full text

DOI (Published version): 10.1016/j.procs.2022.09.161

Abstract

The economic cost of roll refurbishment in the steel-making industry is considerable. In a cold rolling mill, wear and damage of rolls disrupt the industrial environment, so it is critical to predict the remaining useful life early and change the roll without causing disruption to the manufacturing...

Full description

Published in: Procedia Computer Science
ISSN: 1877-0509
Published: Elsevier BV 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa61602
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-11-09T14:00:50Z
last_indexed 2023-01-27T04:15:27Z
id cronfa61602
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>61602</id><entry>2022-10-20</entry><title>Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process</title><swanseaauthors><author><sid>31fdeba4e76994bc72c5b8954389f8ab</sid><firstname>Kayal</firstname><surname>Lakshmanan</surname><name>Kayal Lakshmanan</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>f4f3adbe64cb98a2d80004d570ad786c</sid><firstname>Eugenio</firstname><surname>Borghini</surname><name>Eugenio Borghini</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>1439ebd690110a50a797b7ec78cca600</sid><ORCID>0000-0001-7958-5790</ORCID><firstname>Arnold</firstname><surname>Beckmann</surname><name>Arnold Beckmann</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>564c480cb2abe761533a139c7dbaaca1</sid><ORCID/><firstname>Cameron</firstname><surname>Pleydell-Pearce</surname><name>Cameron Pleydell-Pearce</name><active>true</active><ethesisStudent>false</ethesisStudent></author><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></swanseaauthors><date>2022-10-20</date><deptcode>MECH</deptcode><abstract>The economic cost of roll refurbishment in the steel-making industry is considerable. In a cold rolling mill, wear and damage of rolls disrupt the industrial environment, so it is critical to predict the remaining useful life early and change the roll without causing disruption to the manufacturing process. However, since cold rolling is a complex process affected by multiple variables which are operated in adverse conditions, it is very challenging to mathematically analyse the roll wear and failure. For this reason, in the present paper, a data-driven solution is proposed to predict the correct time for changing individual rolls. To develop an accurate predictive model, several datasets containing high-resolution production data and roll refurbishment data collected from a UK based steel plant have been acquired and processed in a way that the roll wear is modelled as a Remaining Useful Life (RUL) problem, where the number of coils that a roll is able to process is viewed as the remaining cycles. Then hybrid deep learning models are used to predict the Remaining Useful Life of rolls used in steel making. This novel data-driven approach achieves high prediction accuracy and has been validated on a real-world dataset. The proposed approach not only helps avoiding early failure but also can serve as a critical step towards the design of an optimal, automated maintenance schedule for the roll management.</abstract><type>Journal Article</type><journal>Procedia Computer Science</journal><volume>207</volume><journalNumber>C</journalNumber><paginationStart>1057</paginationStart><paginationEnd>1066</paginationEnd><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1877-0509</issnPrint><issnElectronic/><keywords>Cold mill rolls; Remaining useful life; Convolution Neural Network; LSTM; Bidirectional LSTM</keywords><publishedDay>19</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-10-19</publishedDate><doi>10.1016/j.procs.2022.09.161</doi><url/><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) projects EP/V061798/1 and EP/S018107/1. Cinzia Giannetti would like to acknowledge the support of the IMPACT, Supercomputing Wales and Accelerate AI projects, which are part-funded by the European Regional Development Fund (ERDF) via Welsh Government. The authors would like to thank Tata Steel UK for data access and Steve Thornton, Scientific Fellow at Tata Steel UK for discussion and feedback on the manuscript</funders><projectreference/><lastEdited>2023-09-21T13:20:46.9139455</lastEdited><Created>2022-10-20T08:29:37.6494399</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>Kayal</firstname><surname>Lakshmanan</surname><order>1</order></author><author><firstname>Eugenio</firstname><surname>Borghini</surname><order>2</order></author><author><firstname>Arnold</firstname><surname>Beckmann</surname><orcid>0000-0001-7958-5790</orcid><order>3</order></author><author><firstname>Cameron</firstname><surname>Pleydell-Pearce</surname><orcid/><order>4</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>5</order></author></authors><documents><document><filename>61602__25715__59403e08fdc741839c984519bdfe7d9a.pdf</filename><originalFilename>61602.pdf</originalFilename><uploaded>2022-11-09T14:05:08.6751705</uploaded><type>Output</type><contentLength>1187920</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2022 The Authors. This is an open access article under the CC BY-NC-ND license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 61602 2022-10-20 Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process 31fdeba4e76994bc72c5b8954389f8ab Kayal Lakshmanan Kayal Lakshmanan true false f4f3adbe64cb98a2d80004d570ad786c Eugenio Borghini Eugenio Borghini true false 1439ebd690110a50a797b7ec78cca600 0000-0001-7958-5790 Arnold Beckmann Arnold Beckmann true false 564c480cb2abe761533a139c7dbaaca1 Cameron Pleydell-Pearce Cameron Pleydell-Pearce true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2022-10-20 MECH The economic cost of roll refurbishment in the steel-making industry is considerable. In a cold rolling mill, wear and damage of rolls disrupt the industrial environment, so it is critical to predict the remaining useful life early and change the roll without causing disruption to the manufacturing process. However, since cold rolling is a complex process affected by multiple variables which are operated in adverse conditions, it is very challenging to mathematically analyse the roll wear and failure. For this reason, in the present paper, a data-driven solution is proposed to predict the correct time for changing individual rolls. To develop an accurate predictive model, several datasets containing high-resolution production data and roll refurbishment data collected from a UK based steel plant have been acquired and processed in a way that the roll wear is modelled as a Remaining Useful Life (RUL) problem, where the number of coils that a roll is able to process is viewed as the remaining cycles. Then hybrid deep learning models are used to predict the Remaining Useful Life of rolls used in steel making. This novel data-driven approach achieves high prediction accuracy and has been validated on a real-world dataset. The proposed approach not only helps avoiding early failure but also can serve as a critical step towards the design of an optimal, automated maintenance schedule for the roll management. Journal Article Procedia Computer Science 207 C 1057 1066 Elsevier BV 1877-0509 Cold mill rolls; Remaining useful life; Convolution Neural Network; LSTM; Bidirectional LSTM 19 10 2022 2022-10-19 10.1016/j.procs.2022.09.161 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University This work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) projects EP/V061798/1 and EP/S018107/1. Cinzia Giannetti would like to acknowledge the support of the IMPACT, Supercomputing Wales and Accelerate AI projects, which are part-funded by the European Regional Development Fund (ERDF) via Welsh Government. The authors would like to thank Tata Steel UK for data access and Steve Thornton, Scientific Fellow at Tata Steel UK for discussion and feedback on the manuscript 2023-09-21T13:20:46.9139455 2022-10-20T08:29:37.6494399 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised Kayal Lakshmanan 1 Eugenio Borghini 2 Arnold Beckmann 0000-0001-7958-5790 3 Cameron Pleydell-Pearce 4 Cinzia Giannetti 0000-0003-0339-5872 5 61602__25715__59403e08fdc741839c984519bdfe7d9a.pdf 61602.pdf 2022-11-09T14:05:08.6751705 Output 1187920 application/pdf Version of Record true © 2022 The Authors. This is an open access article under the CC BY-NC-ND license true eng https://creativecommons.org/licenses/by-nc-nd/4.0
title Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
spellingShingle Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
Kayal Lakshmanan
Eugenio Borghini
Arnold Beckmann
Cameron Pleydell-Pearce
Cinzia Giannetti
title_short Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
title_full Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
title_fullStr Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
title_full_unstemmed Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
title_sort Data modelling and Remaining Useful Life estimation of rolls in a steel making cold rolling process
author_id_str_mv 31fdeba4e76994bc72c5b8954389f8ab
f4f3adbe64cb98a2d80004d570ad786c
1439ebd690110a50a797b7ec78cca600
564c480cb2abe761533a139c7dbaaca1
a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv 31fdeba4e76994bc72c5b8954389f8ab_***_Kayal Lakshmanan
f4f3adbe64cb98a2d80004d570ad786c_***_Eugenio Borghini
1439ebd690110a50a797b7ec78cca600_***_Arnold Beckmann
564c480cb2abe761533a139c7dbaaca1_***_Cameron Pleydell-Pearce
a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
author Kayal Lakshmanan
Eugenio Borghini
Arnold Beckmann
Cameron Pleydell-Pearce
Cinzia Giannetti
author2 Kayal Lakshmanan
Eugenio Borghini
Arnold Beckmann
Cameron Pleydell-Pearce
Cinzia Giannetti
format Journal article
container_title Procedia Computer Science
container_volume 207
container_issue C
container_start_page 1057
publishDate 2022
institution Swansea University
issn 1877-0509
doi_str_mv 10.1016/j.procs.2022.09.161
publisher Elsevier BV
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 - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description The economic cost of roll refurbishment in the steel-making industry is considerable. In a cold rolling mill, wear and damage of rolls disrupt the industrial environment, so it is critical to predict the remaining useful life early and change the roll without causing disruption to the manufacturing process. However, since cold rolling is a complex process affected by multiple variables which are operated in adverse conditions, it is very challenging to mathematically analyse the roll wear and failure. For this reason, in the present paper, a data-driven solution is proposed to predict the correct time for changing individual rolls. To develop an accurate predictive model, several datasets containing high-resolution production data and roll refurbishment data collected from a UK based steel plant have been acquired and processed in a way that the roll wear is modelled as a Remaining Useful Life (RUL) problem, where the number of coils that a roll is able to process is viewed as the remaining cycles. Then hybrid deep learning models are used to predict the Remaining Useful Life of rolls used in steel making. This novel data-driven approach achieves high prediction accuracy and has been validated on a real-world dataset. The proposed approach not only helps avoiding early failure but also can serve as a critical step towards the design of an optimal, automated maintenance schedule for the roll management.
published_date 2022-10-19T13:20:45Z
_version_ 1777649681821597696
score 11.013686

Similar Items