Real-time monitoring of molten zinc splatter using machine learning-based computer vision

O'DONOVAN, CALLUM; Giannetti, Cinzia; Pleydell-Pearce, Cameron

doi:10.1007/s10845-024-02418-y

Journal article 59 views 4 downloads

Real-time monitoring of molten zinc splatter using machine learning-based computer vision

CALLUM O'DONOVAN, Cinzia Giannetti

, Cameron Pleydell-Pearce

Journal of Intelligent Manufacturing

Swansea University Authors: CALLUM O'DONOVAN, Cinzia Giannetti , Cameron Pleydell-Pearce

PDF | Version of Record

© The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License.
Download (4.57MB)

Check full text

DOI (Published version): 10.1007/s10845-024-02418-y

Abstract

During steel galvanisation, immersing steel strip into molten zinc forms a protective coating. Uniform coating thickness is crucial for quality and is achieved using air knives which wipe off excess zinc. At high strip speeds, zinc splatters onto equipment, causing defects and downtime. Parameters s...

Full description

Published in:	Journal of Intelligent Manufacturing
ISSN:	0956-5515 1572-8145
Published:	Springer Science and Business Media LLC 2024
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa66472
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2024-05-20T09:10:39Z
last_indexed	2024-05-20T09:10:39Z
id	cronfa66472
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>66472</id><entry>2024-05-20</entry><title>Real-time monitoring of molten zinc splatter using machine learning-based computer vision</title><swanseaauthors><author><sid>424be877f02ec76255f2917d6c54c665</sid><firstname>CALLUM</firstname><surname>O'DONOVAN</surname><name>CALLUM O'DONOVAN</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><author><sid>564c480cb2abe761533a139c7dbaaca1</sid><ORCID/><firstname>Cameron</firstname><surname>Pleydell-Pearce</surname><name>Cameron Pleydell-Pearce</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-05-20</date><abstract>During steel galvanisation, immersing steel strip into molten zinc forms a protective coating. Uniform coating thickness is crucial for quality and is achieved using air knives which wipe off excess zinc. At high strip speeds, zinc splatters onto equipment, causing defects and downtime. Parameters such as knife positioning and air pressure influence splatter severity and can be optimised to reduce it. Therefore, this paper proposes a system that converges computer vision and manufacturing whilst addressing some challenges of real-time monitoring in harsh industrial environments, such as the extreme heat, metallic dust, dynamic machinery and high-speed processing at the galvanising site. The approach is primarily comprised of the Counting (CNT) background subtraction algorithm and YOLOv5, which together ensure robustness to noise produced by heat distortion and dust, as well as adaptability to the highly dynamic environment. The YOLOv5 element achieved precision, recall and mean average precision (mAP) values of 1. When validated against operator judgement using mean average error (MAE), interquartile range, median and scatter plot analysis, it was found that there was more discrepancy between the two operators than the operators and the model.This research also strategises the deployment process for integration into the galvanising line. The model proposed allows real-time monitoring and quantification of splatter severity which provides valuable insights into root-cause analysis, process optimisation and maintenance strategies. This research contributes to the digital transformation of manufacturing and whilst solving a current problem, also plants the seed for many other novel applications.</abstract><type>Journal Article</type><journal>Journal of Intelligent Manufacturing</journal><volume>0</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0956-5515</issnPrint><issnElectronic>1572-8145</issnElectronic><keywords>Galvanisation; Steel manufacturing; Computer vision; Deep learning</keywords><publishedDay>22</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-05-22</publishedDate><doi>10.1007/s10845-024-02418-y</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Cinzia Giannetti acknowledges the support of the UK Engineering and Physical Sciences Research Council (EPSRC) projects EP/S001387/1, EP/V061798/1. The authors would also like to acknowledge the M2A funding from the European Social Fund via the Welsh Government (c80816). We further acknowledge the support of the Supercomputing Wales (c80898 and c80900) and Ser Cymru AccelerateAI projects, which are partly funded by the European Regional Development Fund (ERDF) via the Welsh Government. This research would not have been possible without the air knife splatter video footage from the ZODIAC hot-dip galvanising process line at Llanwern Works, which is part of Tata Steel Europe Ltd. who are also acknowledged.</funders><projectreference/><lastEdited>2024-05-31T16:49:09.5291661</lastEdited><Created>2024-05-20T10:07:46.1913675</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering</level></path><authors><author><firstname>CALLUM</firstname><surname>O'DONOVAN</surname><order>1</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>2</order></author><author><firstname>Cameron</firstname><surname>Pleydell-Pearce</surname><orcid/><order>3</order></author></authors><documents><document><filename>66472__30506__7d06ab4bf98a4170987861a4bfb80433.pdf</filename><originalFilename>66472.VoR.pdf</originalFilename><uploaded>2024-05-31T16:45:56.4436226</uploaded><type>Output</type><contentLength>4795753</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	v2 66472 2024-05-20 Real-time monitoring of molten zinc splatter using machine learning-based computer vision 424be877f02ec76255f2917d6c54c665 CALLUM O'DONOVAN CALLUM O'DONOVAN true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 564c480cb2abe761533a139c7dbaaca1 Cameron Pleydell-Pearce Cameron Pleydell-Pearce true false 2024-05-20 During steel galvanisation, immersing steel strip into molten zinc forms a protective coating. Uniform coating thickness is crucial for quality and is achieved using air knives which wipe off excess zinc. At high strip speeds, zinc splatters onto equipment, causing defects and downtime. Parameters such as knife positioning and air pressure influence splatter severity and can be optimised to reduce it. Therefore, this paper proposes a system that converges computer vision and manufacturing whilst addressing some challenges of real-time monitoring in harsh industrial environments, such as the extreme heat, metallic dust, dynamic machinery and high-speed processing at the galvanising site. The approach is primarily comprised of the Counting (CNT) background subtraction algorithm and YOLOv5, which together ensure robustness to noise produced by heat distortion and dust, as well as adaptability to the highly dynamic environment. The YOLOv5 element achieved precision, recall and mean average precision (mAP) values of 1. When validated against operator judgement using mean average error (MAE), interquartile range, median and scatter plot analysis, it was found that there was more discrepancy between the two operators than the operators and the model.This research also strategises the deployment process for integration into the galvanising line. The model proposed allows real-time monitoring and quantification of splatter severity which provides valuable insights into root-cause analysis, process optimisation and maintenance strategies. This research contributes to the digital transformation of manufacturing and whilst solving a current problem, also plants the seed for many other novel applications. Journal Article Journal of Intelligent Manufacturing 0 Springer Science and Business Media LLC 0956-5515 1572-8145 Galvanisation; Steel manufacturing; Computer vision; Deep learning 22 5 2024 2024-05-22 10.1007/s10845-024-02418-y COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) Cinzia Giannetti acknowledges the support of the UK Engineering and Physical Sciences Research Council (EPSRC) projects EP/S001387/1, EP/V061798/1. The authors would also like to acknowledge the M2A funding from the European Social Fund via the Welsh Government (c80816). We further acknowledge the support of the Supercomputing Wales (c80898 and c80900) and Ser Cymru AccelerateAI projects, which are partly funded by the European Regional Development Fund (ERDF) via the Welsh Government. This research would not have been possible without the air knife splatter video footage from the ZODIAC hot-dip galvanising process line at Llanwern Works, which is part of Tata Steel Europe Ltd. who are also acknowledged. 2024-05-31T16:49:09.5291661 2024-05-20T10:07:46.1913675 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering CALLUM O'DONOVAN 1 Cinzia Giannetti 0000-0003-0339-5872 2 Cameron Pleydell-Pearce 3 66472__30506__7d06ab4bf98a4170987861a4bfb80433.pdf 66472.VoR.pdf 2024-05-31T16:45:56.4436226 Output 4795753 application/pdf Version of Record true © The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License. true eng http://creativecommons.org/licenses/by/4.0/
title	Real-time monitoring of molten zinc splatter using machine learning-based computer vision
spellingShingle	Real-time monitoring of molten zinc splatter using machine learning-based computer vision CALLUM O'DONOVAN Cinzia Giannetti Cameron Pleydell-Pearce
title_short	Real-time monitoring of molten zinc splatter using machine learning-based computer vision
title_full	Real-time monitoring of molten zinc splatter using machine learning-based computer vision
title_fullStr	Real-time monitoring of molten zinc splatter using machine learning-based computer vision
title_full_unstemmed	Real-time monitoring of molten zinc splatter using machine learning-based computer vision
title_sort	Real-time monitoring of molten zinc splatter using machine learning-based computer vision
author_id_str_mv	424be877f02ec76255f2917d6c54c665 a8d947a38cb58a8d2dfe6f50cb7eb1c6 564c480cb2abe761533a139c7dbaaca1
author_id_fullname_str_mv	424be877f02ec76255f2917d6c54c665_*_CALLUM O'DONOVAN a8d947a38cb58a8d2dfe6f50cb7eb1c6__Cinzia Giannetti 564c480cb2abe761533a139c7dbaaca1_**_Cameron Pleydell-Pearce
author	CALLUM O'DONOVAN Cinzia Giannetti Cameron Pleydell-Pearce
author2	CALLUM O'DONOVAN Cinzia Giannetti Cameron Pleydell-Pearce
format	Journal article
container_title	Journal of Intelligent Manufacturing
container_volume	0
publishDate	2024
institution	Swansea University
issn	0956-5515 1572-8145
doi_str_mv	10.1007/s10845-024-02418-y
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 Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering
document_store_str	1
active_str	0
description	During steel galvanisation, immersing steel strip into molten zinc forms a protective coating. Uniform coating thickness is crucial for quality and is achieved using air knives which wipe off excess zinc. At high strip speeds, zinc splatters onto equipment, causing defects and downtime. Parameters such as knife positioning and air pressure influence splatter severity and can be optimised to reduce it. Therefore, this paper proposes a system that converges computer vision and manufacturing whilst addressing some challenges of real-time monitoring in harsh industrial environments, such as the extreme heat, metallic dust, dynamic machinery and high-speed processing at the galvanising site. The approach is primarily comprised of the Counting (CNT) background subtraction algorithm and YOLOv5, which together ensure robustness to noise produced by heat distortion and dust, as well as adaptability to the highly dynamic environment. The YOLOv5 element achieved precision, recall and mean average precision (mAP) values of 1. When validated against operator judgement using mean average error (MAE), interquartile range, median and scatter plot analysis, it was found that there was more discrepancy between the two operators than the operators and the model.This research also strategises the deployment process for integration into the galvanising line. The model proposed allows real-time monitoring and quantification of splatter severity which provides valuable insights into root-cause analysis, process optimisation and maintenance strategies. This research contributes to the digital transformation of manufacturing and whilst solving a current problem, also plants the seed for many other novel applications.
published_date	2024-05-22T16:49:08Z
_version_	1800583824644505600
score	11.016704

Real-time monitoring of molten zinc splatter using machine learning-based computer vision

Similar Items