An optimal coordinated proton exchange membrane fuel cell heat management method based on large-scale multi-agent deep reinforcement learning

To improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), an optimal coordinated control strategy for addressing the poor coordination problem between the water pump and radiator in a PEMFC stack heat management system is proposed in this paper. To this end, a cooperative...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy reports Jg. 7; S. 6054 - 6068
Hauptverfasser: Li, Jiawen, Li, Yaping, Yu, Tao
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.11.2021
Elsevier
Schlagworte:
Cooperative exploration strategy large-scale multi-agent twin-delay deep policy gradient (CESL-MATD3), proton exchange membrane fuel cell (PEMFC), coordinated control of stack temperature
Distributed deep reinforcement learning
Stack heat management system
Distributed deep reinforcement learning
Cooperative exploration strategy large-scale multi-agent twin-delay deep policy gradient (CESL-MATD3), proton exchange membrane fuel cell (PEMFC), coordinated control of stack temperature
Stack heat management system
ISSN:2352-4847, 2352-4847
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract To improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), an optimal coordinated control strategy for addressing the poor coordination problem between the water pump and radiator in a PEMFC stack heat management system is proposed in this paper. To this end, a cooperative exploration strategy large-scale multiagent twin-delay deep policy gradient (CESL-MATD3) algorithm has been developed for this control strategy. In this algorithm, both the water pump and radiator are treated as individual agents, and the strategies of centralized training and decentralized execution are applied; thus, coordinated control over the two agents is realized. Moreover, the concepts of curriculum learning, imitation learning, and various novel parallel computing techniques are incorporated into the design of this algorithm, resulting in enhanced training efficiency; thus, a coordinated control strategy with better robustness is obtained. According to the experimental results, compared with other advanced control algorithms, this coordinated control strategy-based algorithm achieves better performance and robustness for PEMFC stack temperature management. The proposed method can effectively improve the response speed of the controllers, reduce the fluctuation and oscillation of the stack temperature and the temperature difference between the stack outlet and inlet (stack temperature difference) during heat management, and reduce the maximum overshoot of the stack temperature by 99.12% and of the stack temperature difference by 97.97%. •A novel 9-order dynamic PEMFC stack heat management system model is proposed.•A novel PEMFC stack temperature coordinated control strategy is proposed.•A new large-scale deep reinforcement learning algorithm is proposed for the strategy.•The strategy coordinates of pump and radiator and improve the efficiency of PEMFC.•The proposed algorithm has better robustness compared with conventional algorithms.
AbstractList To improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), an optimal coordinated control strategy for addressing the poor coordination problem between the water pump and radiator in a PEMFC stack heat management system is proposed in this paper. To this end, a cooperative exploration strategy large-scale multiagent twin-delay deep policy gradient (CESL-MATD3) algorithm has been developed for this control strategy. In this algorithm, both the water pump and radiator are treated as individual agents, and the strategies of centralized training and decentralized execution are applied; thus, coordinated control over the two agents is realized. Moreover, the concepts of curriculum learning, imitation learning, and various novel parallel computing techniques are incorporated into the design of this algorithm, resulting in enhanced training efficiency; thus, a coordinated control strategy with better robustness is obtained. According to the experimental results, compared with other advanced control algorithms, this coordinated control strategy-based algorithm achieves better performance and robustness for PEMFC stack temperature management. The proposed method can effectively improve the response speed of the controllers, reduce the fluctuation and oscillation of the stack temperature and the temperature difference between the stack outlet and inlet (stack temperature difference) during heat management, and reduce the maximum overshoot of the stack temperature by 99.12% and of the stack temperature difference by 97.97%.
To improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), an optimal coordinated control strategy for addressing the poor coordination problem between the water pump and radiator in a PEMFC stack heat management system is proposed in this paper. To this end, a cooperative exploration strategy large-scale multiagent twin-delay deep policy gradient (CESL-MATD3) algorithm has been developed for this control strategy. In this algorithm, both the water pump and radiator are treated as individual agents, and the strategies of centralized training and decentralized execution are applied; thus, coordinated control over the two agents is realized. Moreover, the concepts of curriculum learning, imitation learning, and various novel parallel computing techniques are incorporated into the design of this algorithm, resulting in enhanced training efficiency; thus, a coordinated control strategy with better robustness is obtained. According to the experimental results, compared with other advanced control algorithms, this coordinated control strategy-based algorithm achieves better performance and robustness for PEMFC stack temperature management. The proposed method can effectively improve the response speed of the controllers, reduce the fluctuation and oscillation of the stack temperature and the temperature difference between the stack outlet and inlet (stack temperature difference) during heat management, and reduce the maximum overshoot of the stack temperature by 99.12% and of the stack temperature difference by 97.97%. •A novel 9-order dynamic PEMFC stack heat management system model is proposed.•A novel PEMFC stack temperature coordinated control strategy is proposed.•A new large-scale deep reinforcement learning algorithm is proposed for the strategy.•The strategy coordinates of pump and radiator and improve the efficiency of PEMFC.•The proposed algorithm has better robustness compared with conventional algorithms.
Author Li, Jiawen
Li, Yaping
Yu, Tao
Author_xml – sequence: 1
  givenname: Jiawen
  surname: Li
  fullname: Li, Jiawen
  organization: College of Electric Power, South China University of Technology, 510640 Guangzhou, China
– sequence: 2
  givenname: Yaping
  surname: Li
  fullname: Li, Yaping
  organization: China Electric Power Research Institute (Nanjing), 210003 Nanjing, China
– sequence: 3
  givenname: Tao
  orcidid: 0000-0002-0143-261X
  surname: Yu
  fullname: Yu, Tao
  email: taoyu1@scut.edu.cn
  organization: College of Electric Power, South China University of Technology, 510640 Guangzhou, China
BookMark eNp9kd1q3DAQhU1IoGmaF8iVXsCuJEu7NuQmhP4EArlJr8V4NPJqkaVFVkrzEH3narstlF4EBmYQ5zvM6LxvzmOK1DQ3gneCi83HfUfza-4kl6LjY8eFPmsuZa9lqwa1Pf9nftdcr-uecy5GydWmv2x-3kWWDsUvEBimlK2PUMiyQ04lRUY_cAdxJrbQMmWIxNwLVSWFwHYEhS0QYaaFYh2p7JJlE6yVr2yAPFO7IoSKv4Ti26qsOkt0YJl8dCnjCQ0EOfo4f2guHISVrv_0q-bb50_P91_bx6cvD_d3jy0qwUtrheyHXrpeT5orGJG01b0eldpOGzEJN03ktONcjpYrh5YUaVRuGiRabWV_1TycfG2CvTnken5-NQm8-f2Q8mwgF4-BjNpUUGja9grVlg-AFmUthFGOworqNZy8MKd1zeQM-gLFp1gy-GAEN8eUzN4cUzLHlAwfTU2povI_9O8qb0K3J4jqB333lM2KniKS9Zmw1Av8W_gvPiyxdw
CitedBy_id crossref_primary_10_1016_j_etran_2022_100165
crossref_primary_10_1016_j_ijheatmasstransfer_2022_123226
crossref_primary_10_1109_TIE_2024_3454468
crossref_primary_10_1016_j_engappai_2022_105551
crossref_primary_10_3390_machines13060480
crossref_primary_10_1016_j_egyr_2023_07_036
crossref_primary_10_3390_en18174597
crossref_primary_10_1016_j_apenergy_2025_126142
crossref_primary_10_1016_j_applthermaleng_2024_124806
crossref_primary_10_1016_j_egyr_2021_11_260
crossref_primary_10_1016_j_ijhydene_2023_12_179
crossref_primary_10_1016_j_jpowsour_2022_232617
Cites_doi 10.1016/j.apenergy.2020.116386
10.1016/j.ijhydene.2014.03.175
10.1016/j.ijhydene.2010.06.046
10.1016/j.energy.2021.120592
10.1016/j.ijepes.2015.07.036
10.1016/j.est.2020.101760
10.1109/TEC.2015.2511155
10.1016/j.trc.2018.10.024
10.1016/j.renene.2019.09.048
10.1016/j.ijhydene.2013.07.052
10.1016/j.ins.2019.08.005
10.1016/S0378-7753(96)02360-9
10.1016/j.simpat.2012.04.001
10.1002/fuce.201600181
10.1016/j.jpowsour.2007.12.066
10.1016/j.ijhydene.2016.10.134
10.1109/TPWRS.2020.2999890
10.1016/j.ijhydene.2017.06.208
10.1016/j.ces.2007.09.017
10.1109/TPWRS.2020.2990179
10.1016/j.jclepro.2020.121660
10.1115/1.2349528
10.1016/j.renene.2004.05.001
10.1016/j.electacta.2014.04.003
10.1109/TEC.2015.2510030
10.1115/1.4001763
10.1109/TVT.2020.3014788
10.1016/j.ijhydene.2015.12.120
10.1016/j.energy.2013.08.031
10.1016/j.ijhydene.2010.07.111
10.1016/j.jpowsour.2010.02.074
10.1016/j.egyr.2021.02.043
10.1016/j.jpowsour.2015.02.106
10.1149/1.1946408
10.1016/j.apenergy.2021.117541
10.1109/TEC.2016.2587162
10.1016/j.est.2018.03.020
ContentType Journal Article
Copyright 2021 The Authors
Copyright_xml – notice: 2021 The Authors
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.egyr.2021.09.015
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2352-4847
EndPage 6068
ExternalDocumentID oai_doaj_org_article_46c4f15e734c4708acdc2dc2ca9291d1
10_1016_j_egyr_2021_09_015
S2352484721008192
GroupedDBID 0R~
4.4
457
5VS
6I.
AAEDT
AAEDW
AAFTH
AAIKJ
AALRI
AAXUO
AAYWO
ABMAC
ACGFS
ACVFH
ADBBV
ADCNI
ADEZE
ADVLN
AEUPX
AEXQZ
AFJKZ
AFPUW
AFTJW
AGHFR
AIGII
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
APXCP
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
KQ8
M41
M~E
O9-
OK1
ROL
SSZ
AAYXX
CITATION
ID FETCH-LOGICAL-c410t-d123832f35b504a9ce5d5359447b61b1fbbef5f0029d04fcde4e5c4fb82cd5d23
IEDL.DBID DOA
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000706216300006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2352-4847
IngestDate Fri Oct 03 12:29:52 EDT 2025
Thu Oct 16 04:31:20 EDT 2025
Tue Nov 18 22:30:41 EST 2025
Sat Nov 08 17:17:37 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Distributed deep reinforcement learning
Cooperative exploration strategy large-scale multi-agent twin-delay deep policy gradient (CESL-MATD3), proton exchange membrane fuel cell (PEMFC), coordinated control of stack temperature
Stack heat management system
Language English
License This is an open access article under the CC BY license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c410t-d123832f35b504a9ce5d5359447b61b1fbbef5f0029d04fcde4e5c4fb82cd5d23
ORCID 0000-0002-0143-261X
OpenAccessLink https://doaj.org/article/46c4f15e734c4708acdc2dc2ca9291d1
PageCount 15
ParticipantIDs doaj_primary_oai_doaj_org_article_46c4f15e734c4708acdc2dc2ca9291d1
crossref_citationtrail_10_1016_j_egyr_2021_09_015
crossref_primary_10_1016_j_egyr_2021_09_015
elsevier_sciencedirect_doi_10_1016_j_egyr_2021_09_015
PublicationCentury 2000
PublicationDate November 2021
2021-11-00
2021-11-01
PublicationDateYYYYMMDD 2021-11-01
PublicationDate_xml – month: 11
  year: 2021
  text: November 2021
PublicationDecade 2020
PublicationTitle Energy reports
PublicationYear 2021
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Cheng, Fang, Xu, Li, Ouyang (b7) 2016; 41
Hu, Cao, Zhu, Hu (b15) 2010; 35
Li, Yu (b20) 2021; 7
Zhu, Wang, Wang (b47) 2018; 97
Sun, Li, Hua, Jin (b33) 2020; 147
Liso, Nielsen, Kæ r, Mortensen (b24) 2014; 39
Pathapati, Xue, Tang (b29) 2005; 30
Pukrushpan (b30) 2003
Laribi, Mammar, Sahli, Koussa (b16) 2018; 17
Yang, Wang, Yu, Shu, Yu, Zhang, Yao, Sun (b40) 2020; 265
Li, Yu, Zhang, Li, Zhu (b22) 2021; 285
Lillicrap, Hunt, Pritzel, Heess, Erez, Tassa, Silver, Wierstra (b23) 2015
Yu, Han, Lee, Lee, Ahn (b42) 2010; 7
Cao, Li, Deng, Li, Qin (b5) 2013; 38
Chen, He, Chen, Xu (b6) 2018; 11
Guo, Yang (b12) 2016
You, Xu, Liu, Peng, Cheng (b41) 2014; 132
Lowe, Wu, Tamar, Harb, Abbeel, Mordatch (b25) 2017
Zhang, Mou, Gao, Jiang, Ding, Han (b44) 2020; 69
Zhou, Gao, Breaz, Ravey, Miraoui, Zhang (b46) 2016; 31
Han, Yu, Yi (b14) 2017; 42
Marsala, Ragusa (b26) 2012
Yang, Li, Zeng, Chen, Guo, Wang, Shu, Yu, Zhu (b39) 2021; 228
Ou, Wang, Kim (b28) 2017; 17
Yan, Xu (b37) 2020; 35
Nolan, Kolodziej (b27) 2010; 195
Chiou, Tsai, Liu (b8) 2012; 26
Pukrushpan, Stefanopoulou, Peng (b31) 2002
Cao, Li (b4) 2016; 31
Li, Li, Gao, Jin (b17) 2015; 283
Radu, Taccani (b32) 2006; 3
Wang, Ko (b35) 2010; 35
Hajimolana, Tonekabonimoghadam, Hussain, Chakrabarti, Jayakumar, Hashim (b13) 2013; 62
Li, Wang, Dai (b18) 2006
Gharibeh, Yazdankhah, Azizian (b9) 2020; 31
Li, Yu, Yang (b21) 2021
Zhan, Zhu, Guo, Rodrigue (b43) 2005
Ahn, Choe (b2) 2008; 179
Wang, Qin, Ou, Kim (b36) 2016; 31
Zhang, Wang, Wang, Wang (b45) 2020; 511
Ziegler, Yu, Schumacher (b48) 2005; 152
Grötsch, Mangold (b10) 2008; 63
Li, Yu (b19) 2021
Ahmadi, Abdi, Kakavand (b1) 2017; 42
Amphlett, Mann, Peppley, Roberge, Rodrigues (b3) 1996; 61
Guo, Chen, Liu, Li, Zhang (b11) 2016
Wang, Duan, Shi, Xu, Li, Diao (b34) 2020; 35
Yang, Jiang, Wang, Yao, Wu (b38) 2016; 74
Zhang (10.1016/j.egyr.2021.09.015_b45) 2020; 511
Amphlett (10.1016/j.egyr.2021.09.015_b3) 1996; 61
Li (10.1016/j.egyr.2021.09.015_b22) 2021; 285
Li (10.1016/j.egyr.2021.09.015_b19) 2021
Lowe (10.1016/j.egyr.2021.09.015_b25) 2017
Marsala (10.1016/j.egyr.2021.09.015_b26) 2012
Yu (10.1016/j.egyr.2021.09.015_b42) 2010; 7
Lillicrap (10.1016/j.egyr.2021.09.015_b23) 2015
Yang (10.1016/j.egyr.2021.09.015_b39) 2021; 228
You (10.1016/j.egyr.2021.09.015_b41) 2014; 132
Li (10.1016/j.egyr.2021.09.015_b20) 2021; 7
Guo (10.1016/j.egyr.2021.09.015_b11) 2016
Ziegler (10.1016/j.egyr.2021.09.015_b48) 2005; 152
Han (10.1016/j.egyr.2021.09.015_b14) 2017; 42
Pukrushpan (10.1016/j.egyr.2021.09.015_b30) 2003
Wang (10.1016/j.egyr.2021.09.015_b35) 2010; 35
Yang (10.1016/j.egyr.2021.09.015_b40) 2020; 265
Laribi (10.1016/j.egyr.2021.09.015_b16) 2018; 17
Hajimolana (10.1016/j.egyr.2021.09.015_b13) 2013; 62
Wang (10.1016/j.egyr.2021.09.015_b34) 2020; 35
Ahn (10.1016/j.egyr.2021.09.015_b2) 2008; 179
Liso (10.1016/j.egyr.2021.09.015_b24) 2014; 39
Wang (10.1016/j.egyr.2021.09.015_b36) 2016; 31
Ou (10.1016/j.egyr.2021.09.015_b28) 2017; 17
Li (10.1016/j.egyr.2021.09.015_b18) 2006
Nolan (10.1016/j.egyr.2021.09.015_b27) 2010; 195
Ahmadi (10.1016/j.egyr.2021.09.015_b1) 2017; 42
Radu (10.1016/j.egyr.2021.09.015_b32) 2006; 3
Yang (10.1016/j.egyr.2021.09.015_b38) 2016; 74
Li (10.1016/j.egyr.2021.09.015_b21) 2021
Chiou (10.1016/j.egyr.2021.09.015_b8) 2012; 26
Gharibeh (10.1016/j.egyr.2021.09.015_b9) 2020; 31
Cheng (10.1016/j.egyr.2021.09.015_b7) 2016; 41
Chen (10.1016/j.egyr.2021.09.015_b6) 2018; 11
Zhu (10.1016/j.egyr.2021.09.015_b47) 2018; 97
Guo (10.1016/j.egyr.2021.09.015_b12) 2016
Cao (10.1016/j.egyr.2021.09.015_b4) 2016; 31
Hu (10.1016/j.egyr.2021.09.015_b15) 2010; 35
Zhang (10.1016/j.egyr.2021.09.015_b44) 2020; 69
Zhou (10.1016/j.egyr.2021.09.015_b46) 2016; 31
Yan (10.1016/j.egyr.2021.09.015_b37) 2020; 35
Zhan (10.1016/j.egyr.2021.09.015_b43) 2005
Pathapati (10.1016/j.egyr.2021.09.015_b29) 2005; 30
Pukrushpan (10.1016/j.egyr.2021.09.015_b31) 2002
Cao (10.1016/j.egyr.2021.09.015_b5) 2013; 38
Grötsch (10.1016/j.egyr.2021.09.015_b10) 2008; 63
Li (10.1016/j.egyr.2021.09.015_b17) 2015; 283
Sun (10.1016/j.egyr.2021.09.015_b33) 2020; 147
References_xml – volume: 35
  start-page: 10437
  year: 2010
  end-page: 10445
  ident: b35
  article-title: Multivariable robust PID control for a PEMFC system
  publication-title: Int. J. Hydrog. Energy
– start-page: 4235
  year: 2016
  end-page: 4240
  ident: b11
  article-title: Temperature model and predictive control for fuel cells in switcher locomotive
  publication-title: 2016 35th Chinese Control Conference (CCC)
– volume: 69
  start-page: 11599
  year: 2020
  end-page: 11611
  ident: b44
  article-title: Uav-enabled secure communications by multi-agent deep reinforcement learning
  publication-title: IEEE Trans. Veh. Technol.
– year: 2021
  ident: b21
  article-title: A data-driven output voltage control of solid oxide fuel cell using multi-agent deep reinforcement learning
  publication-title: Appl. Energy
– volume: 195
  start-page: 4743
  year: 2010
  end-page: 4752
  ident: b27
  article-title: Modeling of an automotive fuel cell thermal system
  publication-title: J. Power Sources
– volume: 147
  start-page: 1642
  year: 2020
  end-page: 1652
  ident: b33
  article-title: A hybrid paradigm combining model-based and data-driven methods for fuel cell stack cooling control
  publication-title: Renew. Energy
– volume: 38
  start-page: 12404
  year: 2013
  end-page: 12417
  ident: b5
  article-title: Thermal management oriented steady state analysis and optimization of a kW scale solid oxide fuel cell stand-alone system for maximum system efficiency
  publication-title: Int. J. Hydrog. Energy
– volume: 42
  start-page: 4328
  year: 2017
  end-page: 4341
  ident: b14
  article-title: Advanced thermal management of automotive fuel cells using a model reference adaptive control algorithm
  publication-title: Int. J. Hydrog. Energy
– volume: 35
  start-page: 9110
  year: 2010
  end-page: 9123
  ident: b15
  article-title: Coolant circuit modeling and temperature fuzzy control of proton exchange membrane fuel cells
  publication-title: Int. J. Hydrog. Energy
– year: 2005
  ident: b43
  article-title: An intelligent controller for PEM fuel cell power system based on double closed-loop control
  publication-title: Australasian Universities Power Engineering Conference
– start-page: 1372
  year: 2016
  end-page: 1376
  ident: b12
  article-title: Temperature control of PEMFC stack based on BP neural network
  publication-title: 2016 4th International Conference on Machinery
– volume: 17
  start-page: 299
  year: 2017
  end-page: 307
  ident: b28
  article-title: Performance optimization for open-cathode fuel cell systems with overheating protection and air starvation prevention
  publication-title: Fuel Cells
– volume: 31
  year: 2020
  ident: b9
  article-title: Energy management of fuel cell electric vehicles based on working condition identification of energy storage systems, vehicle driving performance, and dynamic power factor
  publication-title: J. Energy Storage
– year: 2015
  ident: b23
  article-title: Continuous control with deep reinforcement learning
– volume: 7
  start-page: 1267
  year: 2021
  end-page: 1279
  ident: b20
  article-title: A new adaptive controller based on distributed deep reinforcement learning for PEMFC air supply system
  publication-title: Energy Rep.
– volume: 61
  start-page: 183
  year: 1996
  end-page: 188
  ident: b3
  article-title: A model predicting transient responses of proton exchange membrane fuel cells
  publication-title: J. Power Sources
– volume: 152
  start-page: A1555
  year: 2005
  end-page: A1567
  ident: b48
  article-title: Two-phase dynamic modeling of PEMFCs and simulation of cyclo-voltammograms
  publication-title: J. Electrochem. Soc.
– volume: 42
  start-page: 20430
  year: 2017
  end-page: 20443
  ident: b1
  article-title: Maximum power point tracking of a proton exchange membrane fuel cell system using PSO-PID controller
  publication-title: Int. J. Hydrog. Energy
– volume: 31
  start-page: 596
  year: 2016
  end-page: 605
  ident: b4
  article-title: Thermal management-oriented multivariable robust control of a kW-scale solid oxide fuel cell stand-alone system
  publication-title: IEEE Trans. Energy Convers.
– volume: 31
  start-page: 1399
  year: 2016
  end-page: 1412
  ident: b46
  article-title: Dynamic phenomena coupling analysis and modeling of proton exchange membrane fuel cells
  publication-title: IEEE T. Energy Conver.
– volume: 31
  start-page: 667
  year: 2016
  end-page: 675
  ident: b36
  article-title: Temperature control for a polymer electrolyte membrane fuel cell by using fuzzy rule
  publication-title: IEEE Trans. Energy Convers.
– volume: 62
  start-page: 320
  year: 2013
  end-page: 329
  ident: b13
  article-title: Thermal stress management of a solid oxide fuel cell using neural network predictive control
  publication-title: Energy
– volume: 3
  start-page: 452
  year: 2006
  end-page: 458
  ident: b32
  article-title: Simulink-FEMLAB integrated dynamic simulation model for a PEM fuel cell system
  publication-title: J. Fuel Cell Sci. Technol.
– year: 2003
  ident: b30
  article-title: Modeling and control of fuel cell systems and fuel processors
– year: 2021
  ident: b19
  article-title: novel data-driven controller for solid oxide fuel cell via deep reinforcement learning
  publication-title: J. Cleaner Production
– start-page: 908
  year: 2012
  end-page: 913
  ident: b26
  article-title: Increase of the performance of a low ripple boost converter for PEM FC applications using GA and PSO algorithms
  publication-title: 2012 IEEE Vehicle Power and Propulsion Conference
– volume: 17
  start-page: 327
  year: 2018
  end-page: 335
  ident: b16
  article-title: Air supply temperature impact on the PEMFC impedance
  publication-title: J. Energy Storage
– volume: 41
  start-page: 3313
  year: 2016
  ident: b7
  article-title: Model-based temperature regulation of a PEM fuel cell system on a city bus (vol 40, pg 13566, 2015)
  publication-title: Int. J. Hydrog. Energy
– volume: 179
  start-page: 252
  year: 2008
  end-page: 264
  ident: b2
  article-title: Coolant controls of a PEM fuel cell system
  publication-title: J. Power Sources
– year: 2017
  ident: b25
  article-title: Multi-agent actor-critic for mixed cooperative-competitive environments
– volume: 97
  start-page: 348
  year: 2018
  end-page: 368
  ident: b47
  article-title: Human-like autonomous car-following model with deep reinforcement learning
  publication-title: Transp. Res. Part C Emerg.
– volume: 39
  start-page: 8410
  year: 2014
  end-page: 8420
  ident: b24
  article-title: Thermal modeling and temperature control of a PEM fuel cell system for forklift applications
  publication-title: Int. J. Hydrog. Energy
– start-page: 3117
  year: 2002
  end-page: 3122
  ident: b31
  article-title: Modeling and control for PEM fuel cell stack system
  publication-title: Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301)
– start-page: 2159
  year: 2006
  end-page: 2162
  ident: b18
  article-title: Using artificial neural network to control the temperature of fuel cell
  publication-title: 2006 International Conference on Communications, Circuits and Systems
– volume: 511
  start-page: 1
  year: 2020
  end-page: 17
  ident: b45
  article-title: Adaptive robust control of oxygen excess ratio for PEMFC system based on type-2 fuzzy logic system
  publication-title: Inform. Sci.
– volume: 7
  year: 2010
  ident: b42
  article-title: A dynamic model of PEMFC system for the simulation of residential power generation
  publication-title: J. Fuel Cell Sci. Tech.
– volume: 132
  start-page: 389
  year: 2014
  end-page: 396
  ident: b41
  article-title: Study on air-cooled self-humidifying PEMFC control method based on segmented predict negative feedback control
  publication-title: Electrochim. Acta
– volume: 35
  start-page: 4644
  year: 2020
  end-page: 4654
  ident: b34
  article-title: A data-driven multi-agent autonomous voltage control framework using deep reinforcement learning
  publication-title: IEEE Trans. Power Syst.
– volume: 265
  year: 2020
  ident: b40
  article-title: A critical survey on proton exchange membrane fuel cell parameter estimation using meta-heuristic algorithms
  publication-title: J. Clean. Prod.
– volume: 285
  year: 2021
  ident: b22
  article-title: Efficient experience replay based deep deterministic policy gradient for AGC dispatch in integrated energy system
  publication-title: Appl. Energy
– volume: 26
  start-page: 49
  year: 2012
  end-page: 59
  ident: b8
  article-title: A PSO-based adaptive fuzzy PID-controllers
  publication-title: Simul. Model. Pract. Theory
– volume: 35
  start-page: 4599
  year: 2020
  end-page: 4608
  ident: b37
  article-title: A multi-agent deep reinforcement learning method for cooperative load frequency control of a multi-area power system
  publication-title: IEEE Trans. Power Syst.
– volume: 74
  start-page: 429
  year: 2016
  end-page: 436
  ident: b38
  article-title: Nonlinear maximum power point tracking control and modal analysis of DFIG based wind turbine
  publication-title: Int. J. Elec. Power
– volume: 30
  start-page: 1
  year: 2005
  end-page: 22
  ident: b29
  article-title: A new dynamic model for predicting transient phenomena in a PEM fuel cell system
  publication-title: Renew. Energy
– volume: 283
  start-page: 452
  year: 2015
  end-page: 463
  ident: b17
  article-title: On active disturbance rejection in temperature regulation of the proton exchange membrane fuel cells
  publication-title: J. Power Sources
– volume: 228
  year: 2021
  ident: b39
  article-title: Parameter extraction of PEMFC via Bayesian regularization neural network based meta-heuristic algorithms
  publication-title: Energy
– volume: 11
  year: 2018
  ident: b6
  article-title: Control strategy of speed servo systems based on deep reinforcement learning
  publication-title: Algorithms
– volume: 63
  start-page: 434
  year: 2008
  end-page: 447
  ident: b10
  article-title: A two-phase PEMFC model for process control purposes
  publication-title: Chem. Eng. Sci.
– volume: 285
  year: 2021
  ident: 10.1016/j.egyr.2021.09.015_b22
  article-title: Efficient experience replay based deep deterministic policy gradient for AGC dispatch in integrated energy system
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2020.116386
– volume: 39
  start-page: 8410
  year: 2014
  ident: 10.1016/j.egyr.2021.09.015_b24
  article-title: Thermal modeling and temperature control of a PEM fuel cell system for forklift applications
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2014.03.175
– year: 2017
  ident: 10.1016/j.egyr.2021.09.015_b25
– volume: 35
  start-page: 9110
  year: 2010
  ident: 10.1016/j.egyr.2021.09.015_b15
  article-title: Coolant circuit modeling and temperature fuzzy control of proton exchange membrane fuel cells
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2010.06.046
– volume: 228
  year: 2021
  ident: 10.1016/j.egyr.2021.09.015_b39
  article-title: Parameter extraction of PEMFC via Bayesian regularization neural network based meta-heuristic algorithms
  publication-title: Energy
  doi: 10.1016/j.energy.2021.120592
– start-page: 1372
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b12
  article-title: Temperature control of PEMFC stack based on BP neural network
– volume: 74
  start-page: 429
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b38
  article-title: Nonlinear maximum power point tracking control and modal analysis of DFIG based wind turbine
  publication-title: Int. J. Elec. Power
  doi: 10.1016/j.ijepes.2015.07.036
– volume: 31
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b9
  article-title: Energy management of fuel cell electric vehicles based on working condition identification of energy storage systems, vehicle driving performance, and dynamic power factor
  publication-title: J. Energy Storage
  doi: 10.1016/j.est.2020.101760
– year: 2021
  ident: 10.1016/j.egyr.2021.09.015_b19
  article-title: novel data-driven controller for solid oxide fuel cell via deep reinforcement learning
  publication-title: J. Cleaner Production
– volume: 31
  start-page: 667
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b36
  article-title: Temperature control for a polymer electrolyte membrane fuel cell by using fuzzy rule
  publication-title: IEEE Trans. Energy Convers.
  doi: 10.1109/TEC.2015.2511155
– volume: 97
  start-page: 348
  year: 2018
  ident: 10.1016/j.egyr.2021.09.015_b47
  article-title: Human-like autonomous car-following model with deep reinforcement learning
  publication-title: Transp. Res. Part C Emerg.
  doi: 10.1016/j.trc.2018.10.024
– volume: 11
  issue: 65
  year: 2018
  ident: 10.1016/j.egyr.2021.09.015_b6
  article-title: Control strategy of speed servo systems based on deep reinforcement learning
  publication-title: Algorithms
– start-page: 2159
  year: 2006
  ident: 10.1016/j.egyr.2021.09.015_b18
  article-title: Using artificial neural network to control the temperature of fuel cell
– volume: 147
  start-page: 1642
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b33
  article-title: A hybrid paradigm combining model-based and data-driven methods for fuel cell stack cooling control
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2019.09.048
– volume: 38
  start-page: 12404
  year: 2013
  ident: 10.1016/j.egyr.2021.09.015_b5
  article-title: Thermal management oriented steady state analysis and optimization of a kW scale solid oxide fuel cell stand-alone system for maximum system efficiency
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2013.07.052
– volume: 511
  start-page: 1
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b45
  article-title: Adaptive robust control of oxygen excess ratio for PEMFC system based on type-2 fuzzy logic system
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2019.08.005
– volume: 61
  start-page: 183
  issue: 1
  year: 1996
  ident: 10.1016/j.egyr.2021.09.015_b3
  article-title: A model predicting transient responses of proton exchange membrane fuel cells
  publication-title: J. Power Sources
  doi: 10.1016/S0378-7753(96)02360-9
– volume: 26
  start-page: 49
  year: 2012
  ident: 10.1016/j.egyr.2021.09.015_b8
  article-title: A PSO-based adaptive fuzzy PID-controllers
  publication-title: Simul. Model. Pract. Theory
  doi: 10.1016/j.simpat.2012.04.001
– volume: 17
  start-page: 299
  year: 2017
  ident: 10.1016/j.egyr.2021.09.015_b28
  article-title: Performance optimization for open-cathode fuel cell systems with overheating protection and air starvation prevention
  publication-title: Fuel Cells
  doi: 10.1002/fuce.201600181
– volume: 179
  start-page: 252
  year: 2008
  ident: 10.1016/j.egyr.2021.09.015_b2
  article-title: Coolant controls of a PEM fuel cell system
  publication-title: J. Power Sources
  doi: 10.1016/j.jpowsour.2007.12.066
– volume: 42
  start-page: 4328
  year: 2017
  ident: 10.1016/j.egyr.2021.09.015_b14
  article-title: Advanced thermal management of automotive fuel cells using a model reference adaptive control algorithm
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2016.10.134
– volume: 35
  start-page: 4599
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b37
  article-title: A multi-agent deep reinforcement learning method for cooperative load frequency control of a multi-area power system
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/TPWRS.2020.2999890
– volume: 42
  start-page: 20430
  year: 2017
  ident: 10.1016/j.egyr.2021.09.015_b1
  article-title: Maximum power point tracking of a proton exchange membrane fuel cell system using PSO-PID controller
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2017.06.208
– volume: 63
  start-page: 434
  issue: 2
  year: 2008
  ident: 10.1016/j.egyr.2021.09.015_b10
  article-title: A two-phase PEMFC model for process control purposes
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2007.09.017
– year: 2015
  ident: 10.1016/j.egyr.2021.09.015_b23
– volume: 35
  start-page: 4644
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b34
  article-title: A data-driven multi-agent autonomous voltage control framework using deep reinforcement learning
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/TPWRS.2020.2990179
– volume: 265
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b40
  article-title: A critical survey on proton exchange membrane fuel cell parameter estimation using meta-heuristic algorithms
  publication-title: J. Clean. Prod.
  doi: 10.1016/j.jclepro.2020.121660
– volume: 3
  start-page: 452
  issue: 4
  year: 2006
  ident: 10.1016/j.egyr.2021.09.015_b32
  article-title: Simulink-FEMLAB integrated dynamic simulation model for a PEM fuel cell system
  publication-title: J. Fuel Cell Sci. Technol.
  doi: 10.1115/1.2349528
– volume: 30
  start-page: 1
  issue: 1
  year: 2005
  ident: 10.1016/j.egyr.2021.09.015_b29
  article-title: A new dynamic model for predicting transient phenomena in a PEM fuel cell system
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2004.05.001
– volume: 132
  start-page: 389
  year: 2014
  ident: 10.1016/j.egyr.2021.09.015_b41
  article-title: Study on air-cooled self-humidifying PEMFC control method based on segmented predict negative feedback control
  publication-title: Electrochim. Acta
  doi: 10.1016/j.electacta.2014.04.003
– volume: 31
  start-page: 596
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b4
  article-title: Thermal management-oriented multivariable robust control of a kW-scale solid oxide fuel cell stand-alone system
  publication-title: IEEE Trans. Energy Convers.
  doi: 10.1109/TEC.2015.2510030
– year: 2005
  ident: 10.1016/j.egyr.2021.09.015_b43
  article-title: An intelligent controller for PEM fuel cell power system based on double closed-loop control
– start-page: 908
  year: 2012
  ident: 10.1016/j.egyr.2021.09.015_b26
  article-title: Increase of the performance of a low ripple boost converter for PEM FC applications using GA and PSO algorithms
– volume: 7
  issue: 6
  year: 2010
  ident: 10.1016/j.egyr.2021.09.015_b42
  article-title: A dynamic model of PEMFC system for the simulation of residential power generation
  publication-title: J. Fuel Cell Sci. Tech.
  doi: 10.1115/1.4001763
– volume: 69
  start-page: 11599
  year: 2020
  ident: 10.1016/j.egyr.2021.09.015_b44
  article-title: Uav-enabled secure communications by multi-agent deep reinforcement learning
  publication-title: IEEE Trans. Veh. Technol.
  doi: 10.1109/TVT.2020.3014788
– year: 2003
  ident: 10.1016/j.egyr.2021.09.015_b30
– volume: 41
  start-page: 3313
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b7
  article-title: Model-based temperature regulation of a PEM fuel cell system on a city bus (vol 40, pg 13566, 2015)
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2015.12.120
– volume: 62
  start-page: 320
  year: 2013
  ident: 10.1016/j.egyr.2021.09.015_b13
  article-title: Thermal stress management of a solid oxide fuel cell using neural network predictive control
  publication-title: Energy
  doi: 10.1016/j.energy.2013.08.031
– start-page: 3117
  year: 2002
  ident: 10.1016/j.egyr.2021.09.015_b31
  article-title: Modeling and control for PEM fuel cell stack system
– volume: 35
  start-page: 10437
  year: 2010
  ident: 10.1016/j.egyr.2021.09.015_b35
  article-title: Multivariable robust PID control for a PEMFC system
  publication-title: Int. J. Hydrog. Energy
  doi: 10.1016/j.ijhydene.2010.07.111
– volume: 195
  start-page: 4743
  year: 2010
  ident: 10.1016/j.egyr.2021.09.015_b27
  article-title: Modeling of an automotive fuel cell thermal system
  publication-title: J. Power Sources
  doi: 10.1016/j.jpowsour.2010.02.074
– volume: 7
  start-page: 1267
  year: 2021
  ident: 10.1016/j.egyr.2021.09.015_b20
  article-title: A new adaptive controller based on distributed deep reinforcement learning for PEMFC air supply system
  publication-title: Energy Rep.
  doi: 10.1016/j.egyr.2021.02.043
– volume: 283
  start-page: 452
  year: 2015
  ident: 10.1016/j.egyr.2021.09.015_b17
  article-title: On active disturbance rejection in temperature regulation of the proton exchange membrane fuel cells
  publication-title: J. Power Sources
  doi: 10.1016/j.jpowsour.2015.02.106
– volume: 152
  start-page: A1555
  issue: 8
  year: 2005
  ident: 10.1016/j.egyr.2021.09.015_b48
  article-title: Two-phase dynamic modeling of PEMFCs and simulation of cyclo-voltammograms
  publication-title: J. Electrochem. Soc.
  doi: 10.1149/1.1946408
– year: 2021
  ident: 10.1016/j.egyr.2021.09.015_b21
  article-title: A data-driven output voltage control of solid oxide fuel cell using multi-agent deep reinforcement learning
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2021.117541
– volume: 31
  start-page: 1399
  issue: 4
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b46
  article-title: Dynamic phenomena coupling analysis and modeling of proton exchange membrane fuel cells
  publication-title: IEEE T. Energy Conver.
  doi: 10.1109/TEC.2016.2587162
– start-page: 4235
  year: 2016
  ident: 10.1016/j.egyr.2021.09.015_b11
  article-title: Temperature model and predictive control for fuel cells in switcher locomotive
– volume: 17
  start-page: 327
  year: 2018
  ident: 10.1016/j.egyr.2021.09.015_b16
  article-title: Air supply temperature impact on the PEMFC impedance
  publication-title: J. Energy Storage
  doi: 10.1016/j.est.2018.03.020
SSID ssj0001920463
Score 2.27424
Snippet To improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), an optimal coordinated control strategy for addressing the poor...
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 6054
SubjectTerms Cooperative exploration strategy large-scale multi-agent twin-delay deep policy gradient (CESL-MATD3), proton exchange membrane fuel cell (PEMFC), coordinated control of stack temperature
Distributed deep reinforcement learning
Stack heat management system
Title An optimal coordinated proton exchange membrane fuel cell heat management method based on large-scale multi-agent deep reinforcement learning
URI https://dx.doi.org/10.1016/j.egyr.2021.09.015
https://doaj.org/article/46c4f15e734c4708acdc2dc2ca9291d1
Volume 7
WOSCitedRecordID wos000706216300006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2352-4847
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001920463
  issn: 2352-4847
  databaseCode: DOA
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2352-4847
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001920463
  issn: 2352-4847
  databaseCode: M~E
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV29btwwDBaCoEOWoEUb5JK20NCtEGrZ1Ok8pkWCDm3QoQWyCfqhggvufMHlUrRL3iDvXNLyHTwlSwHDgy1KBkmJJEx-FOKD8d7Y0EZlrPYKvKctFZugtGXzguTx5h5n9pu9vJxdXbU_Rq2-OCeswAMXxn2CaYSsDdoGIthq5mOKNV3Rk2HXqQ98KtuOgqmb4rcwFFbfWc7UCugMHipmSnIXXv9lMNBa9yCn3BN3ZJV68P6RcRoZnIuX4nDwFOVZ-cJXYg-71-LxrJMr2uVLehNXFDjOO3IWk2S4hVUn8U8p5JVLXFIY3KHM90gjcbGQfOrK5S7bRZbe0ZLNWJJEu-CccHVHMiNyTjNUnsuuZEK8lWvsEVZjIR1aTVy_Eb8uzn9--aqGjgoqgq42KpGdoi2cGxNMBb6NaJJpTAtgw1QHnUPAbDL_qksV5JgQ0BD_w6yOyaS6ORL73arDYyGtJ_brae0jIGQPbQO-CqEJrW3QB5gIveWoiwPcOHe9WLhtXtmNYyk4loKrWkdSmIiPO5rbArbx5OjPLKjdSAbK7h-Q-rhBfdxz6jMRZitmN_gcxZegqeZPLH7yPxY_FQc8ZSltfCv2N-t7fCdexN-b-d36fa_RdP_-cP4PoOH-Cw
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=An+optimal+coordinated+proton+exchange+membrane+fuel+cell+heat+management+method+based+on+large-scale+multi-agent+deep+reinforcement+learning&rft.jtitle=Energy+reports&rft.au=Jiawen+Li&rft.au=Yaping+Li&rft.au=Tao+Yu&rft.date=2021-11-01&rft.pub=Elsevier&rft.issn=2352-4847&rft.eissn=2352-4847&rft.volume=7&rft.spage=6054&rft.epage=6068&rft_id=info:doi/10.1016%2Fj.egyr.2021.09.015&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_46c4f15e734c4708acdc2dc2ca9291d1
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2352-4847&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2352-4847&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2352-4847&client=summon