No Cover Image

Journal article 454 views 48 downloads

Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation

CALLUM O'DONOVAN, IVAN POPOV, Grazia Todeschini, Cinzia Giannetti Orcid Logo

The International Journal of Advanced Manufacturing Technology, Volume: 126, Issue: 3-4, Pages: 1397 - 1416

Swansea University Authors: CALLUM O'DONOVAN, IVAN POPOV, Grazia Todeschini, Cinzia Giannetti Orcid Logo

  • 62838.VOR.pdf

    PDF | Version of Record

    This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

    Download (2.02MB)

Check full text

DOI (Published version): 10.1007/s00170-023-11151-4

Abstract

Deep learning in computer vision is becoming increasingly popular and useful for tracking object movement in many application areas, due to data collection burgeoning from the rise of the Internet of Things (IoT) and Big Data. So far, computer vision has been used in industry predominantly for quali...

Full description

Published in: The International Journal of Advanced Manufacturing Technology
ISSN: 0268-3768 1433-3015
Published: Springer Science and Business Media LLC 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62838
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-03-07T17:23:51Z
last_indexed 2023-03-21T04:23:25Z
id cronfa62838
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>62838</id><entry>2023-03-07</entry><title>Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation</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>2d8cadf14779ac092cf553be0690f967</sid><firstname>IVAN</firstname><surname>POPOV</surname><name>IVAN POPOV</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>c4ff9050b31bdec0e560b19bfb3b56d3</sid><firstname>Grazia</firstname><surname>Todeschini</surname><name>Grazia Todeschini</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>2023-03-07</date><abstract>Deep learning in computer vision is becoming increasingly popular and useful for tracking object movement in many application areas, due to data collection burgeoning from the rise of the Internet of Things (IoT) and Big Data. So far, computer vision has been used in industry predominantly for quality inspection purposes such as surface defect detection; however, an emergent research area is the application for process monitoring involving tracking moving machinery in real time. In steelmaking, the deployment of computer vision for process monitoring is hindered by harsh environments, poor lighting conditions and fume presence. Therefore, application of computer vision remains unplumbed. This paper proposes a novel method for tracking hot metal ladles during pouring in poor lighting. The proposed method uses contrast-limited adaptive histogram equalisation (CLAHE) for contrast enhancement, Mask R-CNN for segmentation prediction and Kalman filters for improving predictions. Pixel-level tracking enables pouring height and rotation angle estimation which are controllable parameters. Flame severity is also estimated to indicate process quality. The method has been validated with real data collected from ladle pours. Currently, no publications presenting a method for tracking ladle pours exist. The model achieved a mean average precision (mAP) of 0.61 by the Microsoft Common Objects in Context (MSCOCO) standard. It measures key process parameters and process quality in processes with high variability, which significantly contributes to process enhancement through root-cause analysis, process optimisation and predictive maintenance. With real-time tracking, predictions could automate ladle controls for closed-loop control to minimise emissions and eliminate variability from human error.</abstract><type>Journal Article</type><journal>The International Journal of Advanced Manufacturing Technology</journal><volume>126</volume><journalNumber>3-4</journalNumber><paginationStart>1397</paginationStart><paginationEnd>1416</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0268-3768</issnPrint><issnElectronic>1433-3015</issnElectronic><keywords>Computer vision, Deep learning, Manufacturing, Remote condition monitoring, Segmentation</keywords><publishedDay>1</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-05-01</publishedDate><doi>10.1007/s00170-023-11151-4</doi><url>http://dx.doi.org/10.1007/s00170-023-11151-4</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>EPSRC; European Social Fund; European Regional Development Fund</funders><projectreference/><lastEdited>2023-05-12T16:18:59.8609761</lastEdited><Created>2023-03-07T17:20:53.8331265</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>CALLUM</firstname><surname>O'DONOVAN</surname><order>1</order></author><author><firstname>IVAN</firstname><surname>POPOV</surname><order>2</order></author><author><firstname>Grazia</firstname><surname>Todeschini</surname><order>3</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>4</order></author></authors><documents><document><filename>62838__27462__c773f218ad15451faf7ed1549528d211.pdf</filename><originalFilename>62838.VOR.pdf</originalFilename><uploaded>2023-05-12T16:16:53.5410556</uploaded><type>Output</type><contentLength>2122550</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 62838 2023-03-07 Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation 424be877f02ec76255f2917d6c54c665 CALLUM O'DONOVAN CALLUM O'DONOVAN true false 2d8cadf14779ac092cf553be0690f967 IVAN POPOV IVAN POPOV true false c4ff9050b31bdec0e560b19bfb3b56d3 Grazia Todeschini Grazia Todeschini true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2023-03-07 Deep learning in computer vision is becoming increasingly popular and useful for tracking object movement in many application areas, due to data collection burgeoning from the rise of the Internet of Things (IoT) and Big Data. So far, computer vision has been used in industry predominantly for quality inspection purposes such as surface defect detection; however, an emergent research area is the application for process monitoring involving tracking moving machinery in real time. In steelmaking, the deployment of computer vision for process monitoring is hindered by harsh environments, poor lighting conditions and fume presence. Therefore, application of computer vision remains unplumbed. This paper proposes a novel method for tracking hot metal ladles during pouring in poor lighting. The proposed method uses contrast-limited adaptive histogram equalisation (CLAHE) for contrast enhancement, Mask R-CNN for segmentation prediction and Kalman filters for improving predictions. Pixel-level tracking enables pouring height and rotation angle estimation which are controllable parameters. Flame severity is also estimated to indicate process quality. The method has been validated with real data collected from ladle pours. Currently, no publications presenting a method for tracking ladle pours exist. The model achieved a mean average precision (mAP) of 0.61 by the Microsoft Common Objects in Context (MSCOCO) standard. It measures key process parameters and process quality in processes with high variability, which significantly contributes to process enhancement through root-cause analysis, process optimisation and predictive maintenance. With real-time tracking, predictions could automate ladle controls for closed-loop control to minimise emissions and eliminate variability from human error. Journal Article The International Journal of Advanced Manufacturing Technology 126 3-4 1397 1416 Springer Science and Business Media LLC 0268-3768 1433-3015 Computer vision, Deep learning, Manufacturing, Remote condition monitoring, Segmentation 1 5 2023 2023-05-01 10.1007/s00170-023-11151-4 http://dx.doi.org/10.1007/s00170-023-11151-4 COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) EPSRC; European Social Fund; European Regional Development Fund 2023-05-12T16:18:59.8609761 2023-03-07T17:20:53.8331265 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering CALLUM O'DONOVAN 1 IVAN POPOV 2 Grazia Todeschini 3 Cinzia Giannetti 0000-0003-0339-5872 4 62838__27462__c773f218ad15451faf7ed1549528d211.pdf 62838.VOR.pdf 2023-05-12T16:16:53.5410556 Output 2122550 application/pdf Version of Record true This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. true eng https://creativecommons.org/licenses/by/4.0/
title Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
spellingShingle Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
CALLUM O'DONOVAN
IVAN POPOV
Grazia Todeschini
Cinzia Giannetti
title_short Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
title_full Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
title_fullStr Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
title_full_unstemmed Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
title_sort Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation
author_id_str_mv 424be877f02ec76255f2917d6c54c665
2d8cadf14779ac092cf553be0690f967
c4ff9050b31bdec0e560b19bfb3b56d3
a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv 424be877f02ec76255f2917d6c54c665_***_CALLUM O'DONOVAN
2d8cadf14779ac092cf553be0690f967_***_IVAN POPOV
c4ff9050b31bdec0e560b19bfb3b56d3_***_Grazia Todeschini
a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
author CALLUM O'DONOVAN
IVAN POPOV
Grazia Todeschini
Cinzia Giannetti
author2 CALLUM O'DONOVAN
IVAN POPOV
Grazia Todeschini
Cinzia Giannetti
format Journal article
container_title The International Journal of Advanced Manufacturing Technology
container_volume 126
container_issue 3-4
container_start_page 1397
publishDate 2023
institution Swansea University
issn 0268-3768
1433-3015
doi_str_mv 10.1007/s00170-023-11151-4
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 - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
url http://dx.doi.org/10.1007/s00170-023-11151-4
document_store_str 1
active_str 0
description Deep learning in computer vision is becoming increasingly popular and useful for tracking object movement in many application areas, due to data collection burgeoning from the rise of the Internet of Things (IoT) and Big Data. So far, computer vision has been used in industry predominantly for quality inspection purposes such as surface defect detection; however, an emergent research area is the application for process monitoring involving tracking moving machinery in real time. In steelmaking, the deployment of computer vision for process monitoring is hindered by harsh environments, poor lighting conditions and fume presence. Therefore, application of computer vision remains unplumbed. This paper proposes a novel method for tracking hot metal ladles during pouring in poor lighting. The proposed method uses contrast-limited adaptive histogram equalisation (CLAHE) for contrast enhancement, Mask R-CNN for segmentation prediction and Kalman filters for improving predictions. Pixel-level tracking enables pouring height and rotation angle estimation which are controllable parameters. Flame severity is also estimated to indicate process quality. The method has been validated with real data collected from ladle pours. Currently, no publications presenting a method for tracking ladle pours exist. The model achieved a mean average precision (mAP) of 0.61 by the Microsoft Common Objects in Context (MSCOCO) standard. It measures key process parameters and process quality in processes with high variability, which significantly contributes to process enhancement through root-cause analysis, process optimisation and predictive maintenance. With real-time tracking, predictions could automate ladle controls for closed-loop control to minimise emissions and eliminate variability from human error.
published_date 2023-05-01T16:18:58Z
_version_ 1765702095121416192
score 11.016258

Similar Items