No Cover Image

Journal article 93 views 40 downloads

Deep learning for robust forecasting of hot metal silicon content in a blast furnace

Cinzia Giannetti Orcid Logo, Eugenio Borghini, Alex Carr, James Raleigh, Ben Rackham

The International Journal of Advanced Manufacturing Technology

Swansea University Authors: Cinzia Giannetti Orcid Logo, Eugenio Borghini

  • 65825.pdf

    PDF | Version of Record

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

    Download (643.7KB)

Check full text

DOI (Published version): 10.1007/s00170-024-13214-6

Abstract

The hot metal silicon content is a key indicator of the thermal state in the blast furnace and it needs to be kept within a pre-defined range in order to ensure efficient operations. Effective monitoring of silicon content is challenging due to the harsh environment in the furnace and irregularly sa...

Full description

Published in: The International Journal of Advanced Manufacturing Technology
ISSN: 0268-3768 1433-3015
Published: Springer Science and Business Media LLC 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65825
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-03-12T13:38:52Z
last_indexed 2024-03-12T13:38:52Z
id cronfa65825
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>65825</id><entry>2024-03-12</entry><title>Deep learning for robust forecasting of hot metal silicon content in a blast furnace</title><swanseaauthors><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>f4f3adbe64cb98a2d80004d570ad786c</sid><firstname>Eugenio</firstname><surname>Borghini</surname><name>Eugenio Borghini</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-03-12</date><deptcode>ACEM</deptcode><abstract>The hot metal silicon content is a key indicator of the thermal state in the blast furnace and it needs to be kept within a pre-defined range in order to ensure efficient operations. Effective monitoring of silicon content is challenging due to the harsh environment in the furnace and irregularly sampled measurements. Data-driven approaches have been proposed in the literature to predict silicon content using process data and overcome the sparsity of silicon content measurements. However, these approaches rely on the selection of hand-crafted features and ad hoc interpolation methods to deal with irregular sampling of the process variables, adding complexity to model training and optimisation, and requiring significant effort when tuning the model over time to keep it to the required level of accuracy. This paper proposes an improved framework for the prediction of silicon content using a novel deep learning approach based on Phased LSTM. The model has been trained using 3 years of data and validated over a 1-year period using a robust walk-forward validation method, therefore providing confidence in the model performance over time. The Phased LSTM model outperforms competing approaches due to its in-built ability to learn from event-based sequences and scalability for real-world deployments. This is the first time that Phased LSTM has been applied to real-world datasets and results suggest that the ability to learn from event-based data can be beneficial for the process industry where event-driven signals from multiple sensors are common.</abstract><type>Journal Article</type><journal>The International Journal of Advanced Manufacturing Technology</journal><volume>0</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0268-3768</issnPrint><issnElectronic>1433-3015</issnElectronic><keywords>Deep learning, Steel making, Blast furnace, Phased LSTM, Irregular sampling</keywords><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-03-01</publishedDate><doi>10.1007/s00170-024-13214-6</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>This work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) project EP/S001387/1 and EP/V061798/1. Cinzia Giannetti and Eugenio Borghini 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.</funders><projectreference/><lastEdited>2024-05-31T15:20:35.5762498</lastEdited><Created>2024-03-12T13:34:58.4324115</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>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>1</order></author><author><firstname>Eugenio</firstname><surname>Borghini</surname><order>2</order></author><author><firstname>Alex</firstname><surname>Carr</surname><order>3</order></author><author><firstname>James</firstname><surname>Raleigh</surname><order>4</order></author><author><firstname>Ben</firstname><surname>Rackham</surname><order>5</order></author></authors><documents><document><filename>65825__29693__63aad4f3602541a2ae87f49b1430cff5.pdf</filename><originalFilename>65825.pdf</originalFilename><uploaded>2024-03-12T13:38:51.0666565</uploaded><type>Output</type><contentLength>659146</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 65825 2024-03-12 Deep learning for robust forecasting of hot metal silicon content in a blast furnace a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false f4f3adbe64cb98a2d80004d570ad786c Eugenio Borghini Eugenio Borghini true false 2024-03-12 ACEM The hot metal silicon content is a key indicator of the thermal state in the blast furnace and it needs to be kept within a pre-defined range in order to ensure efficient operations. Effective monitoring of silicon content is challenging due to the harsh environment in the furnace and irregularly sampled measurements. Data-driven approaches have been proposed in the literature to predict silicon content using process data and overcome the sparsity of silicon content measurements. However, these approaches rely on the selection of hand-crafted features and ad hoc interpolation methods to deal with irregular sampling of the process variables, adding complexity to model training and optimisation, and requiring significant effort when tuning the model over time to keep it to the required level of accuracy. This paper proposes an improved framework for the prediction of silicon content using a novel deep learning approach based on Phased LSTM. The model has been trained using 3 years of data and validated over a 1-year period using a robust walk-forward validation method, therefore providing confidence in the model performance over time. The Phased LSTM model outperforms competing approaches due to its in-built ability to learn from event-based sequences and scalability for real-world deployments. This is the first time that Phased LSTM has been applied to real-world datasets and results suggest that the ability to learn from event-based data can be beneficial for the process industry where event-driven signals from multiple sensors are common. Journal Article The International Journal of Advanced Manufacturing Technology 0 Springer Science and Business Media LLC 0268-3768 1433-3015 Deep learning, Steel making, Blast furnace, Phased LSTM, Irregular sampling 1 3 2024 2024-03-01 10.1007/s00170-024-13214-6 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University SU Library paid the OA fee (TA Institutional Deal) This work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) project EP/S001387/1 and EP/V061798/1. Cinzia Giannetti and Eugenio Borghini 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. 2024-05-31T15:20:35.5762498 2024-03-12T13:34:58.4324115 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Cinzia Giannetti 0000-0003-0339-5872 1 Eugenio Borghini 2 Alex Carr 3 James Raleigh 4 Ben Rackham 5 65825__29693__63aad4f3602541a2ae87f49b1430cff5.pdf 65825.pdf 2024-03-12T13:38:51.0666565 Output 659146 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 Deep learning for robust forecasting of hot metal silicon content in a blast furnace
spellingShingle Deep learning for robust forecasting of hot metal silicon content in a blast furnace
Cinzia Giannetti
Eugenio Borghini
title_short Deep learning for robust forecasting of hot metal silicon content in a blast furnace
title_full Deep learning for robust forecasting of hot metal silicon content in a blast furnace
title_fullStr Deep learning for robust forecasting of hot metal silicon content in a blast furnace
title_full_unstemmed Deep learning for robust forecasting of hot metal silicon content in a blast furnace
title_sort Deep learning for robust forecasting of hot metal silicon content in a blast furnace
author_id_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6
f4f3adbe64cb98a2d80004d570ad786c
author_id_fullname_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
f4f3adbe64cb98a2d80004d570ad786c_***_Eugenio Borghini
author Cinzia Giannetti
Eugenio Borghini
author2 Cinzia Giannetti
Eugenio Borghini
Alex Carr
James Raleigh
Ben Rackham
format Journal article
container_title The International Journal of Advanced Manufacturing Technology
container_volume 0
publishDate 2024
institution Swansea University
issn 0268-3768
1433-3015
doi_str_mv 10.1007/s00170-024-13214-6
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
document_store_str 1
active_str 0
description The hot metal silicon content is a key indicator of the thermal state in the blast furnace and it needs to be kept within a pre-defined range in order to ensure efficient operations. Effective monitoring of silicon content is challenging due to the harsh environment in the furnace and irregularly sampled measurements. Data-driven approaches have been proposed in the literature to predict silicon content using process data and overcome the sparsity of silicon content measurements. However, these approaches rely on the selection of hand-crafted features and ad hoc interpolation methods to deal with irregular sampling of the process variables, adding complexity to model training and optimisation, and requiring significant effort when tuning the model over time to keep it to the required level of accuracy. This paper proposes an improved framework for the prediction of silicon content using a novel deep learning approach based on Phased LSTM. The model has been trained using 3 years of data and validated over a 1-year period using a robust walk-forward validation method, therefore providing confidence in the model performance over time. The Phased LSTM model outperforms competing approaches due to its in-built ability to learn from event-based sequences and scalability for real-world deployments. This is the first time that Phased LSTM has been applied to real-world datasets and results suggest that the ability to learn from event-based data can be beneficial for the process industry where event-driven signals from multiple sensors are common.
published_date 2024-03-01T15:20:34Z
_version_ 1800578252599721984
score 11.016258

Similar Items