A Novel Dynamic Operation Optimization Method Based on Multiobjective Deep Reinforcement Learning for Steelmaking Process

This article studies a dynamic operation optimization problem for a steelmaking process. The problem is defined to determine optimal operation parameters that bring smelting process indices close to their desired values. The operation optimization technologies have been applied successfully for endp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transaction on neural networks and learning systems 2024-03, Vol.35 (3), p.1-15
Hauptverfasser: Liu, Chang, Tang, Lixin, Zhao, Chenche
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 15
container_issue 3
container_start_page 1
container_title IEEE transaction on neural networks and learning systems
container_volume 35
creator Liu, Chang
Tang, Lixin
Zhao, Chenche
description This article studies a dynamic operation optimization problem for a steelmaking process. The problem is defined to determine optimal operation parameters that bring smelting process indices close to their desired values. The operation optimization technologies have been applied successfully for endpoint steelmaking, but it is still challenging for the dynamic smelting process because of the high temperature and complex physical and chemical reactions. A framework of deep deterministic policy gradient is applied to solve the dynamic operation optimization problem in the steelmaking process. Then, an energy-informed restricted Boltzmann machine method with physical interpretability is developed to construct the actor and critic networks in reinforcement learning (RL) for dynamic decision-making operations. It can provide a posterior probability for each action to guide training in each state. Furthermore, in terms of the design of neural network (NN) architecture, a multiobjective evolutionary algorithm is used to optimize the model hyperparameters, and a knee solution strategy is designed to balance the model accuracy and complexity of neural networks. Experiments are conducted on real data from a steelmaking production process to verify the practicability of the developed model. The experimental results show the advantages and effectiveness of the proposed method compared with other methods. It can meet the requirements of the specified quality of molten steel.
doi_str_mv 10.1109/TNNLS.2023.3244945
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_2798711010</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10050437</ieee_id><sourcerecordid>2798711010</sourcerecordid><originalsourceid>FETCH-LOGICAL-c352t-6d19636e0898eb8646fb3cb69216acaf4fcd24899df9d68904c3543faefd9c1d3</originalsourceid><addsrcrecordid>eNpdkV1rFDEUhkOxtKX2D4hIwBtvds3XZCaXtR8qrFuxFbwLmeSkzTozWZOZwvbXm3XXIuYm5z085-UkL0KvKJlTStT7u-VycTtnhPE5Z0IoUR2gE0YlmzHeNC-e6_rHMTrLeUXKkaSSQh2hY14TVktWnaDNOV7GR-jw5WYwfbD4Zg3JjCEOpRpDH5524guMD9HhDyaDw1s9daXfrsCO4RHwJcAaf4Mw-Jgs9DCMeAEmDWG4x6WFb0eArjc_t_prihZyfokOvekynO3vU_T9-uru4tNscfPx88X5YmZ5xcaZdFRJLoE0qoG2kUL6lttWqvI-Y40X3jomGqWcV042iogyJ7g34J2y1PFT9G7nu07x1wR51H3IFrrODBCnrFmtmrp8KSUFffsfuopTGsp2minOZYFoXSi2o2yKOSfwep1Cb9JGU6K32eg_2ehtNnqfTRl6s7ee2h7c88jfJArwegcEAPjHkVRE8Jr_Bl2flAw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2933610117</pqid></control><display><type>article</type><title>A Novel Dynamic Operation Optimization Method Based on Multiobjective Deep Reinforcement Learning for Steelmaking Process</title><source>IEEE Electronic Library (IEL)</source><creator>Liu, Chang ; Tang, Lixin ; Zhao, Chenche</creator><creatorcontrib>Liu, Chang ; Tang, Lixin ; Zhao, Chenche</creatorcontrib><description>This article studies a dynamic operation optimization problem for a steelmaking process. The problem is defined to determine optimal operation parameters that bring smelting process indices close to their desired values. The operation optimization technologies have been applied successfully for endpoint steelmaking, but it is still challenging for the dynamic smelting process because of the high temperature and complex physical and chemical reactions. A framework of deep deterministic policy gradient is applied to solve the dynamic operation optimization problem in the steelmaking process. Then, an energy-informed restricted Boltzmann machine method with physical interpretability is developed to construct the actor and critic networks in reinforcement learning (RL) for dynamic decision-making operations. It can provide a posterior probability for each action to guide training in each state. Furthermore, in terms of the design of neural network (NN) architecture, a multiobjective evolutionary algorithm is used to optimize the model hyperparameters, and a knee solution strategy is designed to balance the model accuracy and complexity of neural networks. Experiments are conducted on real data from a steelmaking production process to verify the practicability of the developed model. The experimental results show the advantages and effectiveness of the proposed method compared with other methods. It can meet the requirements of the specified quality of molten steel.</description><identifier>ISSN: 2162-237X</identifier><identifier>EISSN: 2162-2388</identifier><identifier>DOI: 10.1109/TNNLS.2023.3244945</identifier><identifier>PMID: 37027625</identifier><identifier>CODEN: ITNNAL</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Chemical reactions ; Closed box ; Complexity ; Conditional probability ; Decision making ; Deep learning ; Deep reinforcement learning (DRL) ; dynamic operation optimization ; energy-informed restricted Boltzmann machine (EIRBM) ; Evolutionary algorithms ; Furnaces ; High temperature ; Liquid metals ; Machine learning ; Metallurgy ; Model accuracy ; multiobjective optimization ; Multiple objective analysis ; Neural networks ; Optimization ; Process control ; Production ; Smelting ; Steel ; Steel making ; steelmaking process</subject><ispartof>IEEE transaction on neural networks and learning systems, 2024-03, Vol.35 (3), p.1-15</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c352t-6d19636e0898eb8646fb3cb69216acaf4fcd24899df9d68904c3543faefd9c1d3</citedby><orcidid>0000-0002-9950-5169 ; 0000-0003-1004-590X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10050437$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10050437$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37027625$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Chang</creatorcontrib><creatorcontrib>Tang, Lixin</creatorcontrib><creatorcontrib>Zhao, Chenche</creatorcontrib><title>A Novel Dynamic Operation Optimization Method Based on Multiobjective Deep Reinforcement Learning for Steelmaking Process</title><title>IEEE transaction on neural networks and learning systems</title><addtitle>TNNLS</addtitle><addtitle>IEEE Trans Neural Netw Learn Syst</addtitle><description>This article studies a dynamic operation optimization problem for a steelmaking process. The problem is defined to determine optimal operation parameters that bring smelting process indices close to their desired values. The operation optimization technologies have been applied successfully for endpoint steelmaking, but it is still challenging for the dynamic smelting process because of the high temperature and complex physical and chemical reactions. A framework of deep deterministic policy gradient is applied to solve the dynamic operation optimization problem in the steelmaking process. Then, an energy-informed restricted Boltzmann machine method with physical interpretability is developed to construct the actor and critic networks in reinforcement learning (RL) for dynamic decision-making operations. It can provide a posterior probability for each action to guide training in each state. Furthermore, in terms of the design of neural network (NN) architecture, a multiobjective evolutionary algorithm is used to optimize the model hyperparameters, and a knee solution strategy is designed to balance the model accuracy and complexity of neural networks. Experiments are conducted on real data from a steelmaking production process to verify the practicability of the developed model. The experimental results show the advantages and effectiveness of the proposed method compared with other methods. It can meet the requirements of the specified quality of molten steel.</description><subject>Chemical reactions</subject><subject>Closed box</subject><subject>Complexity</subject><subject>Conditional probability</subject><subject>Decision making</subject><subject>Deep learning</subject><subject>Deep reinforcement learning (DRL)</subject><subject>dynamic operation optimization</subject><subject>energy-informed restricted Boltzmann machine (EIRBM)</subject><subject>Evolutionary algorithms</subject><subject>Furnaces</subject><subject>High temperature</subject><subject>Liquid metals</subject><subject>Machine learning</subject><subject>Metallurgy</subject><subject>Model accuracy</subject><subject>multiobjective optimization</subject><subject>Multiple objective analysis</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Process control</subject><subject>Production</subject><subject>Smelting</subject><subject>Steel</subject><subject>Steel making</subject><subject>steelmaking process</subject><issn>2162-237X</issn><issn>2162-2388</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkV1rFDEUhkOxtKX2D4hIwBtvds3XZCaXtR8qrFuxFbwLmeSkzTozWZOZwvbXm3XXIuYm5z085-UkL0KvKJlTStT7u-VycTtnhPE5Z0IoUR2gE0YlmzHeNC-e6_rHMTrLeUXKkaSSQh2hY14TVktWnaDNOV7GR-jw5WYwfbD4Zg3JjCEOpRpDH5524guMD9HhDyaDw1s9daXfrsCO4RHwJcAaf4Mw-Jgs9DCMeAEmDWG4x6WFb0eArjc_t_prihZyfokOvekynO3vU_T9-uru4tNscfPx88X5YmZ5xcaZdFRJLoE0qoG2kUL6lttWqvI-Y40X3jomGqWcV042iogyJ7g34J2y1PFT9G7nu07x1wR51H3IFrrODBCnrFmtmrp8KSUFffsfuopTGsp2minOZYFoXSi2o2yKOSfwep1Cb9JGU6K32eg_2ehtNnqfTRl6s7ee2h7c88jfJArwegcEAPjHkVRE8Jr_Bl2flAw</recordid><startdate>20240301</startdate><enddate>20240301</enddate><creator>Liu, Chang</creator><creator>Tang, Lixin</creator><creator>Zhao, Chenche</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QP</scope><scope>7QQ</scope><scope>7QR</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7TK</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-9950-5169</orcidid><orcidid>https://orcid.org/0000-0003-1004-590X</orcidid></search><sort><creationdate>20240301</creationdate><title>A Novel Dynamic Operation Optimization Method Based on Multiobjective Deep Reinforcement Learning for Steelmaking Process</title><author>Liu, Chang ; Tang, Lixin ; Zhao, Chenche</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c352t-6d19636e0898eb8646fb3cb69216acaf4fcd24899df9d68904c3543faefd9c1d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Chemical reactions</topic><topic>Closed box</topic><topic>Complexity</topic><topic>Conditional probability</topic><topic>Decision making</topic><topic>Deep learning</topic><topic>Deep reinforcement learning (DRL)</topic><topic>dynamic operation optimization</topic><topic>energy-informed restricted Boltzmann machine (EIRBM)</topic><topic>Evolutionary algorithms</topic><topic>Furnaces</topic><topic>High temperature</topic><topic>Liquid metals</topic><topic>Machine learning</topic><topic>Metallurgy</topic><topic>Model accuracy</topic><topic>multiobjective optimization</topic><topic>Multiple objective analysis</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Process control</topic><topic>Production</topic><topic>Smelting</topic><topic>Steel</topic><topic>Steel making</topic><topic>steelmaking process</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Chang</creatorcontrib><creatorcontrib>Tang, Lixin</creatorcontrib><creatorcontrib>Zhao, Chenche</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Calcium &amp; Calcified Tissue Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transaction on neural networks and learning systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liu, Chang</au><au>Tang, Lixin</au><au>Zhao, Chenche</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Novel Dynamic Operation Optimization Method Based on Multiobjective Deep Reinforcement Learning for Steelmaking Process</atitle><jtitle>IEEE transaction on neural networks and learning systems</jtitle><stitle>TNNLS</stitle><addtitle>IEEE Trans Neural Netw Learn Syst</addtitle><date>2024-03-01</date><risdate>2024</risdate><volume>35</volume><issue>3</issue><spage>1</spage><epage>15</epage><pages>1-15</pages><issn>2162-237X</issn><eissn>2162-2388</eissn><coden>ITNNAL</coden><abstract>This article studies a dynamic operation optimization problem for a steelmaking process. The problem is defined to determine optimal operation parameters that bring smelting process indices close to their desired values. The operation optimization technologies have been applied successfully for endpoint steelmaking, but it is still challenging for the dynamic smelting process because of the high temperature and complex physical and chemical reactions. A framework of deep deterministic policy gradient is applied to solve the dynamic operation optimization problem in the steelmaking process. Then, an energy-informed restricted Boltzmann machine method with physical interpretability is developed to construct the actor and critic networks in reinforcement learning (RL) for dynamic decision-making operations. It can provide a posterior probability for each action to guide training in each state. Furthermore, in terms of the design of neural network (NN) architecture, a multiobjective evolutionary algorithm is used to optimize the model hyperparameters, and a knee solution strategy is designed to balance the model accuracy and complexity of neural networks. Experiments are conducted on real data from a steelmaking production process to verify the practicability of the developed model. The experimental results show the advantages and effectiveness of the proposed method compared with other methods. It can meet the requirements of the specified quality of molten steel.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>37027625</pmid><doi>10.1109/TNNLS.2023.3244945</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-9950-5169</orcidid><orcidid>https://orcid.org/0000-0003-1004-590X</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2162-237X
ispartof IEEE transaction on neural networks and learning systems, 2024-03, Vol.35 (3), p.1-15
issn 2162-237X
2162-2388
language eng
recordid cdi_proquest_miscellaneous_2798711010
source IEEE Electronic Library (IEL)
subjects Chemical reactions
Closed box
Complexity
Conditional probability
Decision making
Deep learning
Deep reinforcement learning (DRL)
dynamic operation optimization
energy-informed restricted Boltzmann machine (EIRBM)
Evolutionary algorithms
Furnaces
High temperature
Liquid metals
Machine learning
Metallurgy
Model accuracy
multiobjective optimization
Multiple objective analysis
Neural networks
Optimization
Process control
Production
Smelting
Steel
Steel making
steelmaking process
title A Novel Dynamic Operation Optimization Method Based on Multiobjective Deep Reinforcement Learning for Steelmaking Process
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T03%3A31%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Novel%20Dynamic%20Operation%20Optimization%20Method%20Based%20on%20Multiobjective%20Deep%20Reinforcement%20Learning%20for%20Steelmaking%20Process&rft.jtitle=IEEE%20transaction%20on%20neural%20networks%20and%20learning%20systems&rft.au=Liu,%20Chang&rft.date=2024-03-01&rft.volume=35&rft.issue=3&rft.spage=1&rft.epage=15&rft.pages=1-15&rft.issn=2162-237X&rft.eissn=2162-2388&rft.coden=ITNNAL&rft_id=info:doi/10.1109/TNNLS.2023.3244945&rft_dat=%3Cproquest_RIE%3E2798711010%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2933610117&rft_id=info:pmid/37027625&rft_ieee_id=10050437&rfr_iscdi=true