Journal article 424 views 53 downloads
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill
SN Computer Science, Volume: 4, Issue: 5
Swansea University Authors: Sammy` Latham, Cinzia Giannetti
-
PDF | Version of Record
© The Author(s) 2023. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).
Download (2.59MB)
DOI (Published version): 10.1007/s42979-023-02104-5
Abstract
Width-related defects are a common occurrence in the Hot Strip Mill process which can lead to extra processing, concessions, or scrapping. The detection and Root Cause Analysis of these defects is a largely manual process and is vulnerable to several negative factors including human error, late feed...
Published in: | SN Computer Science |
---|---|
ISSN: | 2661-8907 |
Published: |
Springer Science and Business Media LLC
2023
|
Online Access: |
Check full text
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa64007 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
first_indexed |
2023-09-15T09:22:48Z |
---|---|
last_indexed |
2023-09-15T09:22:48Z |
id |
cronfa64007 |
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>64007</id><entry>2023-08-01</entry><title>A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill</title><swanseaauthors><author><sid>4b67f2411a98832eab6881a50263c4ab</sid><firstname>Sammy`</firstname><surname>Latham</surname><name>Sammy` Latham</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>2023-08-01</date><deptcode>FGSEN</deptcode><abstract>Width-related defects are a common occurrence in the Hot Strip Mill process which can lead to extra processing, concessions, or scrapping. The detection and Root Cause Analysis of these defects is a largely manual process and is vulnerable to several negative factors including human error, late feedback, and knock-on effects in successive steel strip products. Automated tools which utilize Artificial Intelligence and Machine Learning for defect detection and Root Cause Analysis in hot rolling have not yet been adopted outside of surface defect detection and roller force optimization. In this paper, we propose an automated tool for the detection and Root Cause Analysis of width-related defects in the hot rolling process which utilizes a combination of expert knowledge and several Machine Learning models. Through this, we aim to increase the scope, and encourage further development, of Machine Learning applications within the Hot Strip Mill process. Both classical algorithms and Computer Vision methods were used for the Machine Learning component of the tool, namely, classification trees and pre-trained convolutional neural networks. The tool is trained and validated using data from an existing hot rolling mill and thus the challenges of collecting and processing real-world legacy data are highlighted and discussed. The Machine Learning models used are shown to perform optimally by validation performance metrics. The tool is found to be suitable for the specified purpose and would be further improved with more training data.</abstract><type>Journal Article</type><journal>SN Computer Science</journal><volume>4</volume><journalNumber>5</journalNumber><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2661-8907</issnElectronic><keywords>Steel Industry, Hot Strip Mill, Automation, Data Analytics, Machine Learning, Classification, Defect Detection, Root Cause Analysis, Knowledge Integration, Legacy Data</keywords><publishedDay>22</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-08-22</publishedDate><doi>10.1007/s42979-023-02104-5</doi><url>http://dx.doi.org/10.1007/s42979-023-02104-5</url><notes/><college>COLLEGE NANME</college><department>Science and Engineering - Faculty</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>FGSEN</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>The authors would like to acknowledge the Materials and Manufacturing Academy (M2A) funding from the European Social Fund via the Welsh Government (c80816) and Tata Steel Europe that has made this research possible. Prof. Giannetti would like to acknowledge the support of the UK Engineering and Physical Sciences Research Council (EP/V061798/1). All authors would like to acknowledge the support of the IMPACT and AccelerateAI projects, part-funded by the European Regional Development Fund (ERDF) via the Welsh Government.</funders><projectreference/><lastEdited>2023-10-02T13:37:21.8233063</lastEdited><Created>2023-08-01T08:39:35.0757317</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>Sammy`</firstname><surname>Latham</surname><order>1</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>2</order></author></authors><documents><document><filename>64007__28543__a41f4997c8ca4bc09c6948cb9a3dc1c3.pdf</filename><originalFilename>64007.VOR.pdf</originalFilename><uploaded>2023-09-15T10:21:36.9091108</uploaded><type>Output</type><contentLength>2719336</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2023. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807> |
spelling |
v2 64007 2023-08-01 A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill 4b67f2411a98832eab6881a50263c4ab Sammy` Latham Sammy` Latham true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2023-08-01 FGSEN Width-related defects are a common occurrence in the Hot Strip Mill process which can lead to extra processing, concessions, or scrapping. The detection and Root Cause Analysis of these defects is a largely manual process and is vulnerable to several negative factors including human error, late feedback, and knock-on effects in successive steel strip products. Automated tools which utilize Artificial Intelligence and Machine Learning for defect detection and Root Cause Analysis in hot rolling have not yet been adopted outside of surface defect detection and roller force optimization. In this paper, we propose an automated tool for the detection and Root Cause Analysis of width-related defects in the hot rolling process which utilizes a combination of expert knowledge and several Machine Learning models. Through this, we aim to increase the scope, and encourage further development, of Machine Learning applications within the Hot Strip Mill process. Both classical algorithms and Computer Vision methods were used for the Machine Learning component of the tool, namely, classification trees and pre-trained convolutional neural networks. The tool is trained and validated using data from an existing hot rolling mill and thus the challenges of collecting and processing real-world legacy data are highlighted and discussed. The Machine Learning models used are shown to perform optimally by validation performance metrics. The tool is found to be suitable for the specified purpose and would be further improved with more training data. Journal Article SN Computer Science 4 5 Springer Science and Business Media LLC 2661-8907 Steel Industry, Hot Strip Mill, Automation, Data Analytics, Machine Learning, Classification, Defect Detection, Root Cause Analysis, Knowledge Integration, Legacy Data 22 8 2023 2023-08-22 10.1007/s42979-023-02104-5 http://dx.doi.org/10.1007/s42979-023-02104-5 COLLEGE NANME Science and Engineering - Faculty COLLEGE CODE FGSEN Swansea University SU Library paid the OA fee (TA Institutional Deal) The authors would like to acknowledge the Materials and Manufacturing Academy (M2A) funding from the European Social Fund via the Welsh Government (c80816) and Tata Steel Europe that has made this research possible. Prof. Giannetti would like to acknowledge the support of the UK Engineering and Physical Sciences Research Council (EP/V061798/1). All authors would like to acknowledge the support of the IMPACT and AccelerateAI projects, part-funded by the European Regional Development Fund (ERDF) via the Welsh Government. 2023-10-02T13:37:21.8233063 2023-08-01T08:39:35.0757317 Faculty of Science and Engineering School of Engineering and Applied Sciences - Materials Science and Engineering Sammy` Latham 1 Cinzia Giannetti 0000-0003-0339-5872 2 64007__28543__a41f4997c8ca4bc09c6948cb9a3dc1c3.pdf 64007.VOR.pdf 2023-09-15T10:21:36.9091108 Output 2719336 application/pdf Version of Record true © The Author(s) 2023. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/ |
title |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill |
spellingShingle |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill Sammy` Latham Cinzia Giannetti |
title_short |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill |
title_full |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill |
title_fullStr |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill |
title_full_unstemmed |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill |
title_sort |
A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill |
author_id_str_mv |
4b67f2411a98832eab6881a50263c4ab a8d947a38cb58a8d2dfe6f50cb7eb1c6 |
author_id_fullname_str_mv |
4b67f2411a98832eab6881a50263c4ab_***_Sammy` Latham a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti |
author |
Sammy` Latham Cinzia Giannetti |
author2 |
Sammy` Latham Cinzia Giannetti |
format |
Journal article |
container_title |
SN Computer Science |
container_volume |
4 |
container_issue |
5 |
publishDate |
2023 |
institution |
Swansea University |
issn |
2661-8907 |
doi_str_mv |
10.1007/s42979-023-02104-5 |
publisher |
Springer Science and Business Media LLC |
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 |
url |
http://dx.doi.org/10.1007/s42979-023-02104-5 |
document_store_str |
1 |
active_str |
0 |
description |
Width-related defects are a common occurrence in the Hot Strip Mill process which can lead to extra processing, concessions, or scrapping. The detection and Root Cause Analysis of these defects is a largely manual process and is vulnerable to several negative factors including human error, late feedback, and knock-on effects in successive steel strip products. Automated tools which utilize Artificial Intelligence and Machine Learning for defect detection and Root Cause Analysis in hot rolling have not yet been adopted outside of surface defect detection and roller force optimization. In this paper, we propose an automated tool for the detection and Root Cause Analysis of width-related defects in the hot rolling process which utilizes a combination of expert knowledge and several Machine Learning models. Through this, we aim to increase the scope, and encourage further development, of Machine Learning applications within the Hot Strip Mill process. Both classical algorithms and Computer Vision methods were used for the Machine Learning component of the tool, namely, classification trees and pre-trained convolutional neural networks. The tool is trained and validated using data from an existing hot rolling mill and thus the challenges of collecting and processing real-world legacy data are highlighted and discussed. The Machine Learning models used are shown to perform optimally by validation performance metrics. The tool is found to be suitable for the specified purpose and would be further improved with more training data. |
published_date |
2023-08-22T13:37:25Z |
_version_ |
1778647296960888832 |
score |
11.029921 |