No Cover Image

E-Thesis 281 views 291 downloads

Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill / SAMUEL LATHAM

Swansea University Author: SAMUEL LATHAM

DOI (Published version): 10.23889/SUThesis.69634

Abstract

Thousands of steel strips are processed through the Port Talbot Steelworks’ Hot Strip Mill every year. Hundreds of these, however, are either scrapped, sold at a concession, or require further processing due to a variety of defects, a significant percentage of which are width-related. Tata Steel has...

Full description

Published: Swansea University, Wales, UK 2023
Institution: Swansea University
Degree level: Doctoral
Degree name: EngD
Supervisor: Giannetti, C., and Hart, R.
URI: https://cronfa.swan.ac.uk/Record/cronfa69634
first_indexed 2025-06-05T13:52:06Z
last_indexed 2025-06-06T07:03:44Z
id cronfa69634
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-06-05T14:56:30.4639061</datestamp><bib-version>v2</bib-version><id>69634</id><entry>2025-06-05</entry><title>Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill</title><swanseaauthors><author><sid>3cc22951cb38b52c4fb8ae7096adead5</sid><firstname>SAMUEL</firstname><surname>LATHAM</surname><name>SAMUEL LATHAM</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-06-05</date><abstract>Thousands of steel strips are processed through the Port Talbot Steelworks&#x2019; Hot Strip Mill every year. Hundreds of these, however, are either scrapped, sold at a concession, or require further processing due to a variety of defects, a signi&#xFB01;cant percentage of which are width-related. Tata Steel has identi&#xFB01;ed this process as being abundant with underutilised data and is currently investing in innovative research and development which aims to address this issue as well as other industry-wide challenges including decarbonisation and digitisation of legacy processes. Currently, Arti&#xFB01;cial Intelligence and Machine Learning has become a popular technology for identifying and analysing defects in manufacturing processes. However, the scope of applications which utilise these technologies within the steel industry are currently limited and are often contained to speci&#xFB01;c subprocesses. Simultaneously, gathering expert knowledge from employees with &#xFB01;rst-hand experience is crucial to understanding defects and how they can be analysed. This thesis aims to expand the scope of Machine Learning tools for defect analysis in steel-making processes and showcase their potential when combined with expert knowledge on a process-wide scale. This is achieved by understanding the challenges of collecting and utilising industrial data, exploring the technologies available for various types of analyses, and reviewing the history and development of these technologies in manufacturing and in the steel industry. From this, technologies and analyses speci&#xFB01;c to the Port Talbot Hot Strip Mill process are selected, providing a platform on which tools for the analysis of width-related defects are developed. An in-depth understanding of these defects and their root causes is gained through continual communication with employees at the Port Talbot Steelworks and, using this, several Machine Learning models are created for the purpose of identifying them in several Hot Strip Mill subprocesses. Further to this, a new, data-driven decision-making process is developed for the purpose of identifying width-related defects and determining their root causes across the entire Hot Strip Mill process as they occur.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Steel Industry, Hot Strip Mill, Automation, Data Analytics, Machine Learning, Classification, Defect Detection, Root Cause Analysis, Knowledge Integration, Legacy Data</keywords><publishedDay>21</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-03-21</publishedDate><doi>10.23889/SUThesis.69634</doi><url/><notes>A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Giannetti, C., and Hart, R.</supervisor><degreelevel>Doctoral</degreelevel><degreename>EngD</degreename><degreesponsorsfunders>EPSRC, European Social Fund, Tata Steel</degreesponsorsfunders><apcterm/><funders>EPSRC, European Social Fund, Tata Steel</funders><projectreference/><lastEdited>2025-06-05T14:56:30.4639061</lastEdited><Created>2025-06-05T14:37:16.2878011</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>SAMUEL</firstname><surname>LATHAM</surname><order>1</order></author></authors><documents><document><filename>69634__34400__921f4df29f3b4610a04d7fe207853923.pdf</filename><originalFilename>2025_Latham_S.final.69634.pdf</originalFilename><uploaded>2025-06-05T14:49:55.7565885</uploaded><type>Output</type><contentLength>19802297</contentLength><contentType>application/pdf</contentType><version>E-Thesis &#x2013; open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author, Samuel Latham, 2025</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2025-06-05T14:56:30.4639061 v2 69634 2025-06-05 Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill 3cc22951cb38b52c4fb8ae7096adead5 SAMUEL LATHAM SAMUEL LATHAM true false 2025-06-05 Thousands of steel strips are processed through the Port Talbot Steelworks’ Hot Strip Mill every year. Hundreds of these, however, are either scrapped, sold at a concession, or require further processing due to a variety of defects, a significant percentage of which are width-related. Tata Steel has identified this process as being abundant with underutilised data and is currently investing in innovative research and development which aims to address this issue as well as other industry-wide challenges including decarbonisation and digitisation of legacy processes. Currently, Artificial Intelligence and Machine Learning has become a popular technology for identifying and analysing defects in manufacturing processes. However, the scope of applications which utilise these technologies within the steel industry are currently limited and are often contained to specific subprocesses. Simultaneously, gathering expert knowledge from employees with first-hand experience is crucial to understanding defects and how they can be analysed. This thesis aims to expand the scope of Machine Learning tools for defect analysis in steel-making processes and showcase their potential when combined with expert knowledge on a process-wide scale. This is achieved by understanding the challenges of collecting and utilising industrial data, exploring the technologies available for various types of analyses, and reviewing the history and development of these technologies in manufacturing and in the steel industry. From this, technologies and analyses specific to the Port Talbot Hot Strip Mill process are selected, providing a platform on which tools for the analysis of width-related defects are developed. An in-depth understanding of these defects and their root causes is gained through continual communication with employees at the Port Talbot Steelworks and, using this, several Machine Learning models are created for the purpose of identifying them in several Hot Strip Mill subprocesses. Further to this, a new, data-driven decision-making process is developed for the purpose of identifying width-related defects and determining their root causes across the entire Hot Strip Mill process as they occur. E-Thesis Swansea University, Wales, UK Steel Industry, Hot Strip Mill, Automation, Data Analytics, Machine Learning, Classification, Defect Detection, Root Cause Analysis, Knowledge Integration, Legacy Data 21 3 2023 2023-03-21 10.23889/SUThesis.69634 A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information. COLLEGE NANME COLLEGE CODE Swansea University Giannetti, C., and Hart, R. Doctoral EngD EPSRC, European Social Fund, Tata Steel EPSRC, European Social Fund, Tata Steel 2025-06-05T14:56:30.4639061 2025-06-05T14:37:16.2878011 Faculty of Science and Engineering School of Engineering and Applied Sciences - Materials Science and Engineering SAMUEL LATHAM 1 69634__34400__921f4df29f3b4610a04d7fe207853923.pdf 2025_Latham_S.final.69634.pdf 2025-06-05T14:49:55.7565885 Output 19802297 application/pdf E-Thesis – open access true Copyright: The Author, Samuel Latham, 2025 true eng
title Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
spellingShingle Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
SAMUEL LATHAM
title_short Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
title_full Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
title_fullStr Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
title_full_unstemmed Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
title_sort Combining Expert Knowledge and Machine Learning for Analysing Width Defects in a Hot Strip Mill
author_id_str_mv 3cc22951cb38b52c4fb8ae7096adead5
author_id_fullname_str_mv 3cc22951cb38b52c4fb8ae7096adead5_***_SAMUEL LATHAM
author SAMUEL LATHAM
author2 SAMUEL LATHAM
format E-Thesis
publishDate 2023
institution Swansea University
doi_str_mv 10.23889/SUThesis.69634
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 Thousands of steel strips are processed through the Port Talbot Steelworks’ Hot Strip Mill every year. Hundreds of these, however, are either scrapped, sold at a concession, or require further processing due to a variety of defects, a significant percentage of which are width-related. Tata Steel has identified this process as being abundant with underutilised data and is currently investing in innovative research and development which aims to address this issue as well as other industry-wide challenges including decarbonisation and digitisation of legacy processes. Currently, Artificial Intelligence and Machine Learning has become a popular technology for identifying and analysing defects in manufacturing processes. However, the scope of applications which utilise these technologies within the steel industry are currently limited and are often contained to specific subprocesses. Simultaneously, gathering expert knowledge from employees with first-hand experience is crucial to understanding defects and how they can be analysed. This thesis aims to expand the scope of Machine Learning tools for defect analysis in steel-making processes and showcase their potential when combined with expert knowledge on a process-wide scale. This is achieved by understanding the challenges of collecting and utilising industrial data, exploring the technologies available for various types of analyses, and reviewing the history and development of these technologies in manufacturing and in the steel industry. From this, technologies and analyses specific to the Port Talbot Hot Strip Mill process are selected, providing a platform on which tools for the analysis of width-related defects are developed. An in-depth understanding of these defects and their root causes is gained through continual communication with employees at the Port Talbot Steelworks and, using this, several Machine Learning models are created for the purpose of identifying them in several Hot Strip Mill subprocesses. Further to this, a new, data-driven decision-making process is developed for the purpose of identifying width-related defects and determining their root causes across the entire Hot Strip Mill process as they occur.
published_date 2023-03-21T05:27:29Z
_version_ 1851369612287934464
score 11.089572

Similar Items