Intelligent train control for cooperative train formation: A deep reinforcement learning approach
Considering the intelligent train control problem in long-term evolution for metro system, a new train-to-train communication-based train control system is proposed, where the cooperative train formation technology is introduced for realizing a more flexible train operation mode. To break the limita...
Gespeichert in:
| Veröffentlicht in: | Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering Journal of systems and control engineering, 2022-05, Vol.236 (5), p.975-988 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 988 |
|---|---|
| container_issue | 5 |
| container_start_page | 975 |
| container_title | Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering |
| container_volume | 236 |
| creator | Zhang, Danyang Zhao, Junhui Zhang, Yang Zhang, Qingmiao |
| description | Considering the intelligent train control problem in long-term evolution for metro system, a new train-to-train communication-based train control system is proposed, where the cooperative train formation technology is introduced for realizing a more flexible train operation mode. To break the limitation of centralized train control, a pre-exploration-based two-stage deep Q-learning algorithm is adopted in the cooperative train formation, which is one of the first intelligent approaches for urban railway formation control. In addition, a comfort-considered algorithm is given, where optimization measures are taken for providing superior passenger experience. The simulation results illustrate that the optimized algorithm has a smoother jerk curve during the train control process, and the passenger comfort can be improved. Furthermore, the proposed algorithm can effectively accomplish the train control task in the multi-train tracking scenarios, and meet the control requirements of the cooperative formation system. |
| doi_str_mv | 10.1177/09596518211064799 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2641365746</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sage_id>10.1177_09596518211064799</sage_id><sourcerecordid>2641365746</sourcerecordid><originalsourceid>FETCH-LOGICAL-c312t-f79524d22ad88e78d9a2a94407709dc763063220383f975b9391743a603a07563</originalsourceid><addsrcrecordid>eNp1UEtLAzEQDqJgrf4AbwHPq3ltsvFWio9CwYuel3F3tm7ZJmuSCv57s7TgQZzDPL8HDCHXnN1ybswds6XVJa8E50wrY-0JmQmmeCFzOiWz6V5MgHNyEeOW5aismRFYuYTD0G_QJZoC9I423qXgB9r5kHs_YoDUf-Hxmre7PHt3Txe0RRxpwN7lbYO7SWNACK53GwrjGDw0H5fkrIMh4tWxzsnb48Pr8rlYvzytlot10UguUtEZWwrVCgFtVaGpWgsCrFLMGGbbxmjJtBSCyUp21pTvVlpulATNJDBTajknNwfdbPu5x5jqrd8Hly1roRWXujRqQvEDqgk-xoBdPYZ-B-G75qyePln_-WTm3B44ETb4q_o_4QeHt3J4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2641365746</pqid></control><display><type>article</type><title>Intelligent train control for cooperative train formation: A deep reinforcement learning approach</title><source>SAGE Complete A-Z List</source><creator>Zhang, Danyang ; Zhao, Junhui ; Zhang, Yang ; Zhang, Qingmiao</creator><creatorcontrib>Zhang, Danyang ; Zhao, Junhui ; Zhang, Yang ; Zhang, Qingmiao</creatorcontrib><description>Considering the intelligent train control problem in long-term evolution for metro system, a new train-to-train communication-based train control system is proposed, where the cooperative train formation technology is introduced for realizing a more flexible train operation mode. To break the limitation of centralized train control, a pre-exploration-based two-stage deep Q-learning algorithm is adopted in the cooperative train formation, which is one of the first intelligent approaches for urban railway formation control. In addition, a comfort-considered algorithm is given, where optimization measures are taken for providing superior passenger experience. The simulation results illustrate that the optimized algorithm has a smoother jerk curve during the train control process, and the passenger comfort can be improved. Furthermore, the proposed algorithm can effectively accomplish the train control task in the multi-train tracking scenarios, and meet the control requirements of the cooperative formation system.</description><identifier>ISSN: 0959-6518</identifier><identifier>EISSN: 2041-3041</identifier><identifier>DOI: 10.1177/09596518211064799</identifier><language>eng</language><publisher>London, England: SAGE Publications</publisher><subject>Algorithms ; Communications systems ; Control systems ; Control tasks ; Cooperative control ; Deep learning ; Machine learning ; Mechanical engineering ; Monitoring systems ; Optimization ; Passenger comfort ; Subways</subject><ispartof>Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering, 2022-05, Vol.236 (5), p.975-988</ispartof><rights>IMechE 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c312t-f79524d22ad88e78d9a2a94407709dc763063220383f975b9391743a603a07563</citedby><cites>FETCH-LOGICAL-c312t-f79524d22ad88e78d9a2a94407709dc763063220383f975b9391743a603a07563</cites><orcidid>0000-0001-5958-6622</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://journals.sagepub.com/doi/pdf/10.1177/09596518211064799$$EPDF$$P50$$Gsage$$H</linktopdf><linktohtml>$$Uhttps://journals.sagepub.com/doi/10.1177/09596518211064799$$EHTML$$P50$$Gsage$$H</linktohtml><link.rule.ids>314,776,780,21798,27901,27902,43597,43598</link.rule.ids></links><search><creatorcontrib>Zhang, Danyang</creatorcontrib><creatorcontrib>Zhao, Junhui</creatorcontrib><creatorcontrib>Zhang, Yang</creatorcontrib><creatorcontrib>Zhang, Qingmiao</creatorcontrib><title>Intelligent train control for cooperative train formation: A deep reinforcement learning approach</title><title>Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering</title><description>Considering the intelligent train control problem in long-term evolution for metro system, a new train-to-train communication-based train control system is proposed, where the cooperative train formation technology is introduced for realizing a more flexible train operation mode. To break the limitation of centralized train control, a pre-exploration-based two-stage deep Q-learning algorithm is adopted in the cooperative train formation, which is one of the first intelligent approaches for urban railway formation control. In addition, a comfort-considered algorithm is given, where optimization measures are taken for providing superior passenger experience. The simulation results illustrate that the optimized algorithm has a smoother jerk curve during the train control process, and the passenger comfort can be improved. Furthermore, the proposed algorithm can effectively accomplish the train control task in the multi-train tracking scenarios, and meet the control requirements of the cooperative formation system.</description><subject>Algorithms</subject><subject>Communications systems</subject><subject>Control systems</subject><subject>Control tasks</subject><subject>Cooperative control</subject><subject>Deep learning</subject><subject>Machine learning</subject><subject>Mechanical engineering</subject><subject>Monitoring systems</subject><subject>Optimization</subject><subject>Passenger comfort</subject><subject>Subways</subject><issn>0959-6518</issn><issn>2041-3041</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp1UEtLAzEQDqJgrf4AbwHPq3ltsvFWio9CwYuel3F3tm7ZJmuSCv57s7TgQZzDPL8HDCHXnN1ybswds6XVJa8E50wrY-0JmQmmeCFzOiWz6V5MgHNyEeOW5aismRFYuYTD0G_QJZoC9I423qXgB9r5kHs_YoDUf-Hxmre7PHt3Txe0RRxpwN7lbYO7SWNACK53GwrjGDw0H5fkrIMh4tWxzsnb48Pr8rlYvzytlot10UguUtEZWwrVCgFtVaGpWgsCrFLMGGbbxmjJtBSCyUp21pTvVlpulATNJDBTajknNwfdbPu5x5jqrd8Hly1roRWXujRqQvEDqgk-xoBdPYZ-B-G75qyePln_-WTm3B44ETb4q_o_4QeHt3J4</recordid><startdate>202205</startdate><enddate>202205</enddate><creator>Zhang, Danyang</creator><creator>Zhao, Junhui</creator><creator>Zhang, Yang</creator><creator>Zhang, Qingmiao</creator><general>SAGE Publications</general><general>SAGE PUBLICATIONS, INC</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-5958-6622</orcidid></search><sort><creationdate>202205</creationdate><title>Intelligent train control for cooperative train formation: A deep reinforcement learning approach</title><author>Zhang, Danyang ; Zhao, Junhui ; Zhang, Yang ; Zhang, Qingmiao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c312t-f79524d22ad88e78d9a2a94407709dc763063220383f975b9391743a603a07563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Communications systems</topic><topic>Control systems</topic><topic>Control tasks</topic><topic>Cooperative control</topic><topic>Deep learning</topic><topic>Machine learning</topic><topic>Mechanical engineering</topic><topic>Monitoring systems</topic><topic>Optimization</topic><topic>Passenger comfort</topic><topic>Subways</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Danyang</creatorcontrib><creatorcontrib>Zhao, Junhui</creatorcontrib><creatorcontrib>Zhang, Yang</creatorcontrib><creatorcontrib>Zhang, Qingmiao</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Danyang</au><au>Zhao, Junhui</au><au>Zhang, Yang</au><au>Zhang, Qingmiao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Intelligent train control for cooperative train formation: A deep reinforcement learning approach</atitle><jtitle>Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering</jtitle><date>2022-05</date><risdate>2022</risdate><volume>236</volume><issue>5</issue><spage>975</spage><epage>988</epage><pages>975-988</pages><issn>0959-6518</issn><eissn>2041-3041</eissn><abstract>Considering the intelligent train control problem in long-term evolution for metro system, a new train-to-train communication-based train control system is proposed, where the cooperative train formation technology is introduced for realizing a more flexible train operation mode. To break the limitation of centralized train control, a pre-exploration-based two-stage deep Q-learning algorithm is adopted in the cooperative train formation, which is one of the first intelligent approaches for urban railway formation control. In addition, a comfort-considered algorithm is given, where optimization measures are taken for providing superior passenger experience. The simulation results illustrate that the optimized algorithm has a smoother jerk curve during the train control process, and the passenger comfort can be improved. Furthermore, the proposed algorithm can effectively accomplish the train control task in the multi-train tracking scenarios, and meet the control requirements of the cooperative formation system.</abstract><cop>London, England</cop><pub>SAGE Publications</pub><doi>10.1177/09596518211064799</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0001-5958-6622</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0959-6518 |
| ispartof | Proceedings of the Institution of Mechanical Engineers. Part I, Journal of systems and control engineering, 2022-05, Vol.236 (5), p.975-988 |
| issn | 0959-6518 2041-3041 |
| language | eng |
| recordid | cdi_proquest_journals_2641365746 |
| source | SAGE Complete A-Z List |
| subjects | Algorithms Communications systems Control systems Control tasks Cooperative control Deep learning Machine learning Mechanical engineering Monitoring systems Optimization Passenger comfort Subways |
| title | Intelligent train control for cooperative train formation: A deep reinforcement learning approach |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T22%3A43%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Intelligent%20train%20control%20for%20cooperative%20train%20formation:%20A%20deep%20reinforcement%20learning%20approach&rft.jtitle=Proceedings%20of%20the%20Institution%20of%20Mechanical%20Engineers.%20Part%20I,%20Journal%20of%20systems%20and%20control%20engineering&rft.au=Zhang,%20Danyang&rft.date=2022-05&rft.volume=236&rft.issue=5&rft.spage=975&rft.epage=988&rft.pages=975-988&rft.issn=0959-6518&rft.eissn=2041-3041&rft_id=info:doi/10.1177/09596518211064799&rft_dat=%3Cproquest_cross%3E2641365746%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2641365746&rft_id=info:pmid/&rft_sage_id=10.1177_09596518211064799&rfr_iscdi=true |