Article(id=1209871351867896824, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1209871350727046121, articleNumber=null, orderNo=null, doi=10.19620/j.cnki.1000-3703.20231093, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=null, receivedDateStr=null, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1766385408607, onlineDateStr=2025-12-22, pubDate=1724428800000, pubDateStr=2024-08-24, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766385408607, onlineIssueDateStr=2025-12-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766385408607, creator=13701087609, updateTime=1766385408607, updator=13701087609, issue=Issue{id=1209871350727046121, tenantId=1146029695717560320, journalId=1189621681917173762, year='2024', volume='', issue='8', pageStart='1', pageEnd='62', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1766385408335, creator=13701087609, updateTime=1766386486799, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1209875874179051590, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1209871350727046121, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1209875874179051591, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1209871350727046121, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=27, endPage=37, ext={EN=ArticleExt(id=1209871352048251899, articleId=1209871351867896824, tenantId=1146029695717560320, journalId=1189621681917173762, language=EN, title=DDPG Energy Management of Extended-Range Electric Vehicle Based on LSTM Speed Prediction, columnId=null, journalTitle=Automobile Technology, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In order to improve the energy management of Range Extended Electric Vehicle (REEV), firstly Long Short-Term Memory (LSTM) neural network was used to predicate vehicle speed, then calculates the demand power in the prediction time domain, and the demand power in the prediction time domain and the demand power at the current moment were jointly inputted to the Deep Deterministic Policy Gradient (DDPG) agent, which outputted the control quantity. Finally, the hardware-in-the-loop simulation was carried out to verify the real-time performance of the control strategy. The validation results show that using the proposed LSTM-DDPG energy management strategy reduces the equivalent fuel consumption by 0.613 kg, 0.350 kg, and 0.607 kg compared to the DDPG energy management strategy, the Deep Q-Network (DQN) energy management strategy, and the power-following control strategy, respectively, under the World Transient Vehicle Cycling (WTVC) conditions, which is only 0.128 kg different from that of the dynamic planning control strategy when the dynamic planning control strategy is used.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Laiwei Lu, Hong Zhao, Fuliang Xü, Yong Luo), CN=ArticleExt(id=1209871356150280333, articleId=1209871351867896824, tenantId=1146029695717560320, journalId=1189621681917173762, language=CN, title=基于LSTM车速预测和深度确定性策略梯度的增程式电动汽车能量管理*, columnId=0, journalTitle=汽车技术, columnName=, runingTitle=null, highlight=null, articleAbstract=为提高增程式电动汽车的能量管理性能,首先利用长短时记忆(LSTM)神经网络进行车速预测,然后计算出预测时域内的需求功率,并将其与当前时刻的需求功率共同输入深度确定性策略梯度(DDPG)智能体,由智能体输出控制量,最后通过硬件在环仿真验证了控制策略的实时性。结果表明,采用所提出的LSTM-DDPG能量管理策略相对于DDPG能量管理策略、深度Q网络(DQN)能量管理策略、功率跟随控制策略在世界重型商用车辆瞬态循环(WTVC)工况下的等效燃油消耗量分别减少0.613 kg、0.350 kg、0.607 kg,与采用动态规划控制策略时的等效燃油消耗量仅相差0.128 kg。, correspAuthors=null, authorNote=null, correspAuthorsNote=
赵红(1973—),女,河南南阳人,副教授,工学博士,研究方向为汽车节能减排与新能源技术,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=4guHGNoVhlpiU7Yc8xGSow==, magXml=euyKJyospzXauUuxjh/JgA==, pdfUrl=null, pdf=WiLqjbnIWFMPw0oDuINLnA==, pdfFileSize=6400011, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=NchB4nDzyxF6rR4qaMeHKw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PPhLiGIyszBP9MUt18aZOw==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=路来伟, 赵红, 徐福良, 罗勇)}, authors=[Author(id=1209908875944398907, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209908877190107200, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908875944398907, language=EN, stringName=Laiwei Lu, firstName=Laiwei, middleName=null, lastName=Lu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Qingdao University, Qingdao 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209908877286576193, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908875944398907, language=CN, stringName=路来伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=青岛大学,青岛 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209908875847929909, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, xref=null, ext=[AuthorCompanyExt(id=1209908875852124214, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Qingdao University, Qingdao 266071), AuthorCompanyExt(id=1209908875864707127, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=青岛大学,青岛 266071)])]), Author(id=1209908877395628103, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=qdlizh@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209908877513068621, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908877395628103, language=EN, stringName=Hong Zhao, firstName=Hong, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Qingdao University, Qingdao 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209908877605343315, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908877395628103, language=CN, stringName=赵红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=青岛大学,青岛 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209908875847929909, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, xref=null, ext=[AuthorCompanyExt(id=1209908875852124214, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Qingdao University, Qingdao 266071), AuthorCompanyExt(id=1209908875864707127, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=青岛大学,青岛 266071)])]), Author(id=1209908877693423704, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209908877768921182, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908877693423704, language=EN, stringName=Fuliang Xü, firstName=Fuliang, middleName=null, lastName=Xü, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Qingdao University, Qingdao 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209908877886361699, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908877693423704, language=CN, stringName=徐福良, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=青岛大学,青岛 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209908875847929909, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, xref=null, ext=[AuthorCompanyExt(id=1209908875852124214, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Qingdao University, Qingdao 266071), AuthorCompanyExt(id=1209908875864707127, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=青岛大学,青岛 266071)])]), Author(id=1209908877982830696, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209908878087688302, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908877982830696, language=EN, stringName=Yong Luo, firstName=Yong, middleName=null, lastName=Luo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Qingdao University, Qingdao 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209908878205128818, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, authorId=1209908877982830696, language=CN, stringName=罗勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=青岛大学,青岛 266071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209908875847929909, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, xref=null, ext=[AuthorCompanyExt(id=1209908875852124214, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Qingdao University, Qingdao 266071), AuthorCompanyExt(id=1209908875864707127, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=青岛大学,青岛 266071)])])], keywords=[Keyword(id=1209908878398066805, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, orderNo=1, keyword=Extended-range electric vehicle), Keyword(id=1209908878523895932, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, orderNo=2, keyword=Long Short-Term Memory (LSTM) neural network), Keyword(id=1209908878599393407, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, orderNo=3, keyword=Deep Reinforcement Learning (DRL)), Keyword(id=1209908878679085186, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, orderNo=4, keyword=Deep Deterministic Policy Gradient (DDPG)), Keyword(id=1209908878754582662, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, orderNo=1, keyword=增程式电动汽车), Keyword(id=1209908878825885832, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, orderNo=2, keyword=长短时记忆神经网络), Keyword(id=1209908878909771914, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, orderNo=3, keyword=深度强化学习), Keyword(id=1209908878993657998, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, orderNo=4, keyword=深度确定性策略梯度)], refs=[Reference(id=1209908883880022276, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=222, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=FAYYAZI M, ABDOOS M, PHAN D, journalName=Expert Systems with Applications, refType=null, unstructuredReference=FAYYAZI M, ABDOOS M, PHAN D, et al. Real-Time Self-Adaptive Q-Learning Controller for Energy Management of Conventional Autonomous Vehicles[J]. Expert Systems with Applications, 2023, 222., articleTitle=Real-Time Self-Adaptive Q-Learning Controller for Energy Management of Conventional Autonomous Vehicles, refAbstract=null), Reference(id=1209908884031017224, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=8, issue=S8, pageStart=1009, pageEnd=1019, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=ZHU W Q, journalName=Energy Reports, refType=null, unstructuredReference=ZHU W Q. Optimization Strategies for Real-Time Energy Management of Electric Vehicles Based on LSTM Network Learning[J]. Energy Reports, 2022, 8(S8): 1009-1019., articleTitle=Optimization Strategies for Real-Time Energy Management of Electric Vehicles Based on LSTM Network Learning, refAbstract=null), Reference(id=1209908884131680523, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=274, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=YANG D, WANG L, YU K J, journalName=Energy Conversion and Management, refType=null, unstructuredReference=YANG D, WANG L, YU K J, et al. A Reinforcement Learning-Based Energy Management Strategy for Fuel Cell Hybrid Vehicle Considering Real-Time Velocity Prediction[J]. Energy Conversion and Management, 2022, 274., articleTitle=A Reinforcement Learning-Based Energy Management Strategy for Fuel Cell Hybrid Vehicle Considering Real-Time Velocity Prediction, refAbstract=null), Reference(id=1209908884211372298, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2023, volume=12, issue=12, pageStart=2642, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=LU L W, ZHAO H, LIU X T, journalName=Electronics, refType=null, unstructuredReference=LU L W, ZHAO H, LIU X T, et al. MPC-ECMS Energy Management of Extended-Range Vehicles Based on LSTM Multi-Signal Speed Prediction[J]. Electronics, 2023, 12(12): 2642., articleTitle=MPC-ECMS Energy Management of Extended-Range Vehicles Based on LSTM Multi-Signal Speed Prediction, refAbstract=null), Reference(id=1209908884286869772, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2018, volume=155, issue=null, pageStart=838, pageEnd=852, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=SHEN P H, ZHAO Z G, ZHAN X W, journalName=Energy, refType=null, unstructuredReference=SHEN P H, ZHAO Z G, ZHAN X W, et al. Optimal Energy Management Strategy for a Plug-in Hybrid Electric Commercial Vehicle Based on Velocity Prediction[J]. Energy, 2018, 155: 838-852., articleTitle=Optimal Energy Management Strategy for a Plug-in Hybrid Electric Commercial Vehicle Based on Velocity Prediction, refAbstract=null), Reference(id=1209908884353978638, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=238, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=WANG W D, GUO X H, YANG C, journalName=Energy, refType=null, unstructuredReference=WANG W D, GUO X H, YANG C, et al. A Multi-Objective Optimization Energy Management Strategy for Power Split HEV Based on Velocity Prediction[J]. Energy, 2022, 238., articleTitle=A Multi-Objective Optimization Energy Management Strategy for Power Split HEV Based on Velocity Prediction, refAbstract=null), Reference(id=1209908884425281808, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=24, pageStart=8273, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=XING J M, CHU L, HOU Z R, journalName=Sensors, refType=null, unstructuredReference=XING J M, CHU L, HOU Z R, et al. Energy Management Strategy Based on a Novel Speed Prediction Method[J]. Sensors, 2021, 21(24): 8273., articleTitle=Energy Management Strategy Based on a Novel Speed Prediction Method, refAbstract=null), Reference(id=1209908884484002066, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=520, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=CHEN R H, YANG C, HAN L J, journalName=Journal of Power Sources, refType=null, unstructuredReference=CHEN R H, YANG C, HAN L J, et al. Power Reserve Predictive Control Strategy for Hybrid Electric Vehicle Using Recognition-Based Long Short-Term Memory Network[J]. Journal of Power Sources, 2022, 520., articleTitle=Power Reserve Predictive Control Strategy for Hybrid Electric Vehicle Using Recognition-Based Long Short-Term Memory Network, refAbstract=null), Reference(id=1209908884567888148, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=251, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=HAN J, SHU H, TANG X L, journalName=Energy Conversion and Management, refType=null, unstructuredReference=HAN J, SHU H, TANG X L, et al. Predictive Energy Management for Plug-in Hybrid Electric Vehicles Considering Electric Motor Thermal Dynamics[J]. Energy Conversion and Management, 2022, 251., articleTitle=Predictive Energy Management for Plug-in Hybrid Electric Vehicles Considering Electric Motor Thermal Dynamics, refAbstract=null), Reference(id=1209908884634997012, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=322, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=RITTER A, WIDMER F, DUHR P, journalName=Applied Energy, refType=null, unstructuredReference=RITTER A, WIDMER F, DUHR P, et al. Long-Term Stochastic Model Predictive Control for the Energy Management of Hybrid Electric Vehicles Using Pontryagin’s Minimum Principle and Scenario-Based Optimization[J]. Applied Energy, 2022, 322., articleTitle=Long-Term Stochastic Model Predictive Control for the Energy Management of Hybrid Electric Vehicles Using Pontryagin’s Minimum Principle and Scenario-Based Optimization, refAbstract=null), Reference(id=1209908884697911574, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=269, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=LI M L, HE H W, FENG L, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=LI M L, HE H W, FENG L, et al. Hierarchical Predictive Energy Management of Hybrid Electric Buses Based on Driver Information[J]. Journal of Cleaner Production, 2020, 269., articleTitle=Hierarchical Predictive Energy Management of Hybrid Electric Buses Based on Driver Information, refAbstract=null), Reference(id=1209908884760826136, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=272, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=YU X, LIN C, TIAN Y, journalName=Energy, refType=null, unstructuredReference=YU X, LIN C, TIAN Y, et al. Real-Time and Hierarchical Energy Management-Control Framework for Electric Vehicles with Dual-Motor Powertrain System[J]. Energy, 2023, 272., articleTitle=Real-Time and Hierarchical Energy Management-Control Framework for Electric Vehicles with Dual-Motor Powertrain System, refAbstract=null), Reference(id=1209908884815352090, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=243, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=CHEN Z H, LIU Y G, ZHANG Y J, journalName=Energy, refType=null, unstructuredReference=CHEN Z H, LIU Y G, ZHANG Y J, et al. A Neural Network-Based ECMS for Optimized Energy Management of Plug-in Hybrid Electric Vehicles[J]. Energy, 2022, 243., articleTitle=A Neural Network-Based ECMS for Optimized Energy Management of Plug-in Hybrid Electric Vehicles, refAbstract=null), Reference(id=1209908884882460956, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=247, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=WEI C Y, CHEN Y, LI X Y, journalName=Energy, refType=null, unstructuredReference=WEI C Y, CHEN Y, LI X Y, et al. Integrating Intelligent Driving Pattern Recognition with Adaptive Energy Management Strategy for Extender Range Electric Logistics Vehicle[J]. Energy, 2022, 247., articleTitle=Integrating Intelligent Driving Pattern Recognition with Adaptive Energy Management Strategy for Extender Range Electric Logistics Vehicle, refAbstract=null), Reference(id=1209908884970541342, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=10, pageStart=370, pageEnd=375, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=ZHAO Z C, XUN J, WAN X, journalName=IFAC-PapersOnLine, refType=null, unstructuredReference=ZHAO Z C, XUN J, WAN X, et al. MPC Based Hybrid Electric Vehicles Energy Management Strategy[J]. IFAC-PapersOnLine, 2021, 54(10): 370-375., articleTitle=MPC Based Hybrid Electric Vehicles Energy Management Strategy, refAbstract=null), Reference(id=1209908886144946464, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=270, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=YANG N K, RUAN S M, HAN L J, journalName=Energy, refType=null, unstructuredReference=YANG N K, RUAN S M, HAN L J, et al. Reinforcement Learning-Based Real-Time Intelligent Energy Management for Hybrid Electric Vehicles in a Model Predictive Control Framework[J]. Energy, 2023, 270., articleTitle=Reinforcement Learning-Based Real-Time Intelligent Energy Management for Hybrid Electric Vehicles in a Model Predictive Control Framework, refAbstract=null), Reference(id=1209908886224638242, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=5, pageStart=683, pageEnd=691, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=张昊, 范钦灏, 王巍, journalName=汽车工程, refType=null, unstructuredReference=张昊, 范钦灏, 王巍, 等. 基于强化学习的多燃烧模式混合动力能量管理策略[J]. 汽车工程, 2021, 43(5): 683-691., articleTitle=基于强化学习的多燃烧模式混合动力能量管理策略, refAbstract=null), Reference(id=1209908886279164195, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=5, pageStart=683, pageEnd=691, url=null, language=null, rfNumber=[17], rfOrder=17, authorNames=ZHANG H, FAN Q H, WANG W, journalName=Automotive Engineering, refType=null, unstructuredReference=ZHANG H, FAN Q H, WANG W, et al. Reinforcement Learning Based Energy Management Strategy for Hybrid Electric Vehicles Using Multi-Mode Combustion[J]. Automotive Engineering, 2021, 43(5): 683-691., articleTitle=Reinforcement Learning Based Energy Management Strategy for Hybrid Electric Vehicles Using Multi-Mode Combustion, refAbstract=null), Reference(id=1209908886342078757, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=57, issue=22, pageStart=237, pageEnd=246, url=null, language=null, rfNumber=[18], rfOrder=18, authorNames=唐小林, 陈佳信, 刘腾, journalName=机械工程学报, refType=null, unstructuredReference=唐小林, 陈佳信, 刘腾, 等. 基于深度强化学习的混合动力汽车智能跟车控制与能量管理策略研究[J]. 机械工程学报, 2022, 57(22): 237-246., articleTitle=基于深度强化学习的混合动力汽车智能跟车控制与能量管理策略研究, refAbstract=null), Reference(id=1209908886400799015, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=57, issue=22, pageStart=237, pageEnd=246, url=null, language=null, rfNumber=[18], rfOrder=19, authorNames=TANG X L, CHEN J X, LIU T, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=TANG X L, CHEN J X, LIU T, et al. Research on Deep Reinforcement Learning-Based Intelligent Car-Following Control and Energy Management Strategy for Hybrid Electric Vehicles[J]. Journal of Mechanical Engineering, 2022, 57(22): 237-246., articleTitle=Research on Deep Reinforcement Learning-Based Intelligent Car-Following Control and Energy Management Strategy for Hybrid Electric Vehicles, refAbstract=null), Reference(id=1209908886467907881, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=16, pageStart=2008, pageEnd=2015, url=null, language=null, rfNumber=[19], rfOrder=20, authorNames=唐香蕉, 高祖成, 曾令全, journalName=中国机械工程, refType=null, unstructuredReference=唐香蕉, 高祖成, 曾令全, 等. 城市道路下混合动力汽车双层能量管理策略[J]. 中国机械工程, 2022, 33(16): 2008-2015., articleTitle=城市道路下混合动力汽车双层能量管理策略, refAbstract=null), Reference(id=1209908886551793963, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=16, pageStart=2008, pageEnd=2015, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=TANG X J, GAO Z C, ZENG L Q, journalName=China Mechanical Engineering, refType=null, unstructuredReference=TANG X J, GAO Z C, ZENG L Q, et al. Double-Layer Energy Management Strategy for Hybrid Vehicles under Urban Roads[J]. China Mechanical Engineering, 2022, 33(16): 2008-2015., articleTitle=Double-Layer Energy Management Strategy for Hybrid Vehicles under Urban Roads, refAbstract=null), Reference(id=1209908886610514221, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=245, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=CHEN Z, GU H J, SHEN S Q, journalName=Energy, refType=null, unstructuredReference=CHEN Z, GU H J, SHEN S Q, et al. Energy Management Strategy for Power-Split Plug-in Hybrid Electric Vehicle Based on MPC and Double Q-Learning[J]. Energy, 2022, 245., articleTitle=Energy Management Strategy for Power-Split Plug-in Hybrid Electric Vehicle Based on MPC and Double Q-Learning, refAbstract=null), Reference(id=1209908886686011694, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2018, volume=18, issue=3, pageStart=148, pageEnd=156, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=席利贺, 张欣, 耿聪, journalName=交通运输工程学报, refType=null, unstructuredReference=席利贺, 张欣, 耿聪, 等. 基于动态规划算法的增程式电动汽车能量管理策略优化[J]. 交通运输工程学报, 2018, 18(3): 148-156., articleTitle=基于动态规划算法的增程式电动汽车能量管理策略优化, refAbstract=null), Reference(id=1209908886744731952, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2018, volume=18, issue=3, pageStart=148, pageEnd=156, url=null, language=null, rfNumber=[21], rfOrder=24, authorNames=XI L H, ZHANG X, GENG C, journalName=Journal of Transportation Engineering, refType=null, unstructuredReference=XI L H, ZHANG X, GENG C, et al. Optimization of Energy Management Strategy for Extended-Range Electric Vehicle Based on Dynamic Programming Algorithm[J]. Journal of Transportation Engineering, 2018, 18(3): 148-156., articleTitle=Optimization of Energy Management Strategy for Extended-Range Electric Vehicle Based on Dynamic Programming Algorithm, refAbstract=null), Reference(id=1209908886811840818, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=25, authorNames=丁帅, journalName=基于随机动态规划的纯电动汽车能量管理控制策略研究, refType=null, unstructuredReference=丁帅. 基于随机动态规划的纯电动汽车能量管理控制策略研究[D]. 长沙: 湖南大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1209908886878949684, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=26, authorNames=DING S, journalName=Study on the Control Strategy of Pure Electric Vehicle Energy Management Based on Stochastic Dynamic Planning, refType=null, unstructuredReference=DING S. Study on the Control Strategy of Pure Electric Vehicle Energy Management Based on Stochastic Dynamic Planning[D]. Changsha: Hunan University, 2020., articleTitle=null, refAbstract=null), Reference(id=1209908886946058550, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2019, volume=41, issue=10, pageStart=1332, pageEnd=1341, url=null, language=null, rfNumber=[23], rfOrder=27, authorNames=林歆悠, 夏玉田, 魏申申, journalName=工程科学学报, refType=null, unstructuredReference=林歆悠, 夏玉田, 魏申申. 基于增强学习算法的插电式燃料电池电动汽车能量管理控制策略[J]. 工程科学学报, 2019, 41(10): 1332-1341., articleTitle=基于增强学习算法的插电式燃料电池电动汽车能量管理控制策略, refAbstract=null), Reference(id=1209908887013167416, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, doi=null, pmid=null, pmcid=null, year=2019, volume=41, issue=10, pageStart=1332, pageEnd=1341, url=null, language=null, rfNumber=[23], rfOrder=28, authorNames=LIN X Y, XIA Y T, WEI S S, journalName=Journal of Engineering Science, refType=null, unstructuredReference=LIN X Y, XIA Y T, WEI S S. Plug-in Fuel Cell Electric Vehicle Energy Management Control Strategy Based on Augmented Learning Algorithm[J]. Journal of Engineering Science, 2019, 41(10): 1332-1341., articleTitle=Plug-in Fuel Cell Electric Vehicle Energy Management Control Strategy Based on Augmented Learning Algorithm, refAbstract=null)], funds=[Fund(id=1209908883674501373, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, awardId=52175236, language=CN, fundingSource=*国家自然科学基金项目(52175236), fundOrder=null, country=null), Fund(id=1209908883733221632, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, awardId=24-1-8-cspz-18-nsh, language=CN, fundingSource=青岛市科技惠民示范专项(24-1-8-cspz-18-nsh), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1209908875847929909, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, xref=null, ext=[AuthorCompanyExt(id=1209908875852124214, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Qingdao University, Qingdao 266071), AuthorCompanyExt(id=1209908875864707127, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, companyId=1209908875847929909, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=青岛大学,青岛 266071)])], figs=[ArticleFig(id=1209908879165624466, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=XvmWtGCUa9cp//rfm0Ee6Q==, figureFileBig=4/HUh465bBytb5Fv7mewRQ==, tableContent=null), ArticleFig(id=1209908879257899155, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图1, caption=增程式汽车结构, figureFileSmall=XvmWtGCUa9cp//rfm0Ee6Q==, figureFileBig=4/HUh465bBytb5Fv7mewRQ==, tableContent=null), ArticleFig(id=1209908879392116887, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=CyTVMEE7ziOZpetLDDRlcw==, figureFileBig=rDytLEteb8rp4fXvVLyU0g==, tableContent=null), ArticleFig(id=1209908879450837145, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图2, caption=发动机与发电机准静态模型, figureFileSmall=CyTVMEE7ziOZpetLDDRlcw==, figureFileBig=rDytLEteb8rp4fXvVLyU0g==, tableContent=null), ArticleFig(id=1209908879522140315, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=eX1AZaWIRb9c/mw4yEwjCA==, figureFileBig=IfmiX9qcH4/uOsSyOEMLUg==, tableContent=null), ArticleFig(id=1209908879601832094, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图3, caption=增程器最佳燃油消耗率曲线, figureFileSmall=eX1AZaWIRb9c/mw4yEwjCA==, figureFileBig=IfmiX9qcH4/uOsSyOEMLUg==, tableContent=null), ArticleFig(id=1209908879668940961, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=Az8nsXQxNkYoCeZilKqBcw==, figureFileBig=Xje/j1P4yPkJFcUHvYQ9iw==, tableContent=null), ArticleFig(id=1209908879740244132, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图4, caption=动力电池模型, figureFileSmall=Az8nsXQxNkYoCeZilKqBcw==, figureFileBig=Xje/j1P4yPkJFcUHvYQ9iw==, tableContent=null), ArticleFig(id=1209908879794770086, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=CAruSCCnD1wE25uTPX0Tsg==, figureFileBig=hWCdHNw4lIsUImQVKyDJuQ==, tableContent=null), ArticleFig(id=1209908879853490344, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图5, caption=单个驱动电机MAP图, figureFileSmall=CAruSCCnD1wE25uTPX0Tsg==, figureFileBig=hWCdHNw4lIsUImQVKyDJuQ==, tableContent=null), ArticleFig(id=1209908879937376426, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=aCBYgGS+b/pc0dkkjJhqUQ==, figureFileBig=McR6tIiUnxMR063wZEqtwA==, tableContent=null), ArticleFig(id=1209908880017068204, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图6, caption=车速预测训练集, figureFileSmall=aCBYgGS+b/pc0dkkjJhqUQ==, figureFileBig=McR6tIiUnxMR063wZEqtwA==, tableContent=null), ArticleFig(id=1209908880084177071, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=bv0Hz8EvOCtscDiYNh2Qeg==, figureFileBig=xq56XV6nZob3fm7Ep4gmDg==, tableContent=null), ArticleFig(id=1209908880163868850, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图7, caption=车速预测和DDPG能量管理流程, figureFileSmall=bv0Hz8EvOCtscDiYNh2Qeg==, figureFileBig=xq56XV6nZob3fm7Ep4gmDg==, tableContent=null), ArticleFig(id=1209908880251949236, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=ypYm4ER2ph5uXHXhlQaa5w==, figureFileBig=RpyRoDrcqou5zaGEApmJIQ==, tableContent=null), ArticleFig(id=1209908880319058103, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图8, caption=LSTM神经网络结构, figureFileSmall=ypYm4ER2ph5uXHXhlQaa5w==, figureFileBig=RpyRoDrcqou5zaGEApmJIQ==, tableContent=null), ArticleFig(id=1209908880394555578, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=uKxNAaxJVrpD/7LOZE8Cog==, figureFileBig=AQKyV9u1z/u7x0VLbkagjQ==, tableContent=null), ArticleFig(id=1209908880474247356, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图9, caption=LSTM车速预测过程示意, figureFileSmall=uKxNAaxJVrpD/7LOZE8Cog==, figureFileBig=AQKyV9u1z/u7x0VLbkagjQ==, tableContent=null), ArticleFig(id=1209908881678012607, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=hqeVmfLYhpABXGKU4KyF4Q==, figureFileBig=4d2qX54wHIoeg7C5DaKF2Q==, tableContent=null), ArticleFig(id=1209908881761898690, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图10, caption=适应度函数变化过程, figureFileSmall=hqeVmfLYhpABXGKU4KyF4Q==, figureFileBig=4d2qX54wHIoeg7C5DaKF2Q==, tableContent=null), ArticleFig(id=1209908881866756291, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=vd4jkX8Jx1u5Bc4SsF59MQ==, figureFileBig=xWqENmPI0P2T95rsuiUEvg==, tableContent=null), ArticleFig(id=1209908881938059462, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图11, caption=训练过程中的损失与均方根误差变化情况, figureFileSmall=vd4jkX8Jx1u5Bc4SsF59MQ==, figureFileBig=xWqENmPI0P2T95rsuiUEvg==, tableContent=null), ArticleFig(id=1209908882000974025, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=1VOlXAC6fvfxRnScNO7YyA==, figureFileBig=ve2cHvCjiUq6l3geHglYpw==, tableContent=null), ArticleFig(id=1209908882101637324, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图12, caption=不同预测方法车速预测热图, figureFileSmall=1VOlXAC6fvfxRnScNO7YyA==, figureFileBig=ve2cHvCjiUq6l3geHglYpw==, tableContent=null), ArticleFig(id=1209908882177134798, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=/Ehvc7fdqJ0Udtkg5xAMow==, figureFileBig=LrXvAiuNU6jlm/jvIkEyYg==, tableContent=null), ArticleFig(id=1209908882235855056, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图13, caption=DDPG原理, figureFileSmall=/Ehvc7fdqJ0Udtkg5xAMow==, figureFileBig=LrXvAiuNU6jlm/jvIkEyYg==, tableContent=null), ArticleFig(id=1209908882315546833, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=YeGZ6tm4ifUozGX/TetYWw==, figureFileBig=kWpWF9NNJukxOCjNmuzWaQ==, tableContent=null), ArticleFig(id=1209908882374267092, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图14, caption=不同强化学习能量管理策略迭代过程, figureFileSmall=YeGZ6tm4ifUozGX/TetYWw==, figureFileBig=kWpWF9NNJukxOCjNmuzWaQ==, tableContent=null), ArticleFig(id=1209908882458153174, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=5sN58iA373WLcYn48fByoQ==, figureFileBig=p6y9Jv1Hk/PHU+2wznicSg==, tableContent=null), ArticleFig(id=1209908882546233561, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图15, caption=不同控制策略下SOC与燃油消耗量的变化情况, figureFileSmall=5sN58iA373WLcYn48fByoQ==, figureFileBig=p6y9Jv1Hk/PHU+2wznicSg==, tableContent=null), ArticleFig(id=1209908882625925339, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=Tu6oLMLvEdIDrvkY7knL4g==, figureFileBig=IoctCUYqDJ8f97aQblMNPg==, tableContent=null), ArticleFig(id=1209908882714005725, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图16, caption=不同控制策略工作点分布, figureFileSmall=Tu6oLMLvEdIDrvkY7knL4g==, figureFileBig=IoctCUYqDJ8f97aQblMNPg==, tableContent=null), ArticleFig(id=1209908882793697503, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=c0RW98+JgiUfIJcq4eN2cg==, figureFileBig=7gFLjAlka0keUXY8iFJF/A==, tableContent=null), ArticleFig(id=1209908882869194976, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图17, caption=硬件在环仿真示意, figureFileSmall=c0RW98+JgiUfIJcq4eN2cg==, figureFileBig=7gFLjAlka0keUXY8iFJF/A==, tableContent=null), ArticleFig(id=1209908882927915234, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=LfsiLVXR42krUMBn05+abQ==, figureFileBig=CTTtBE6cLDjgT49pKtCvCg==, tableContent=null), ArticleFig(id=1209908882999218404, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图18, caption=硬件在环仿真与Simulink仿真结果对比, figureFileSmall=LfsiLVXR42krUMBn05+abQ==, figureFileBig=CTTtBE6cLDjgT49pKtCvCg==, tableContent=null), ArticleFig(id=1209908883066327270, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=vExA4dL/k0e4IkP4zBpLWQ==, figureFileBig=TGCxxEcDUXURG5fbvE2x4w==, tableContent=null), ArticleFig(id=1209908883129241833, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=图19, caption=不同控制策略HIL仿真实时功率输出结果对比, figureFileSmall=vExA4dL/k0e4IkP4zBpLWQ==, figureFileBig=TGCxxEcDUXURG5fbvE2x4w==, tableContent=null), ArticleFig(id=1209908883196350699, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
名称 参数 数值
整车 整车质量/kg 7 000
车轮半径/m 0.60
空气阻力系数 0.55
迎风面积/m2 9
发动机 类型 柴油发动机
最大扭矩/N·m 2 200
最大转速/r·min-1 2 000
驱动电机(单个) 最大转矩/N·m 1 050
最大转速/r·min-1 2 670
类型 永磁同步电动机
发电机 最大转矩/N·m 2 180
最大转速/r·min-1 2 000
电池组 电压/V 550
容量/A·h 200
), ArticleFig(id=1209908883250876654, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=表1, caption=

增程式汽车及其主要部件参数

, figureFileSmall=null, figureFileBig=null, tableContent=
名称 参数 数值
整车 整车质量/kg 7 000
车轮半径/m 0.60
空气阻力系数 0.55
迎风面积/m2 9
发动机 类型 柴油发动机
最大扭矩/N·m 2 200
最大转速/r·min-1 2 000
驱动电机(单个) 最大转矩/N·m 1 050
最大转速/r·min-1 2 670
类型 永磁同步电动机
发电机 最大转矩/N·m 2 180
最大转速/r·min-1 2 000
电池组 电压/V 550
容量/A·h 200
), ArticleFig(id=1209908883330568432, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
控制策略 SOC终值 燃油消耗量
/kg
等效燃油消耗量
/kg
DDPG 0.334 3 4.440 3.535
DP 0.290 2 2.536 2.794
DQN 0.332 5 4.129 3.272
LSTM-DDPG 0.284 7 2.518 2.922
功率跟随 0.336 8 4.499 3.529
), ArticleFig(id=1209908883406065907, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=表2, caption=

不同控制策略仿真结果

, figureFileSmall=null, figureFileBig=null, tableContent=
控制策略 SOC终值 燃油消耗量
/kg
等效燃油消耗量
/kg
DDPG 0.334 3 4.440 3.535
DP 0.290 2 2.536 2.794
DQN 0.332 5 4.129 3.272
LSTM-DDPG 0.284 7 2.518 2.922
功率跟随 0.336 8 4.499 3.529
), ArticleFig(id=1209908883468980470, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
控制策略 平均误差
LSTM-DDPG 0.394
功率跟随 0.432
DDPG 0.486
), ArticleFig(id=1209908883536089336, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1209871351867896824, language=CN, label=表3, caption=

不同控制策略HIL仿真与Simulink仿真结果误差 %

, figureFileSmall=null, figureFileBig=null, tableContent=
控制策略 平均误差
LSTM-DDPG 0.394
功率跟随 0.432
DDPG 0.486
)], attaches=null, journal=Journal(id=1149693407745847311, delFlag=0, nameCn=汽车技术, nameEn=Automobile Technology, nameHistory1=null, nameHistory2=null, issn=1000-3703, eissn=null, cn=22-1113/U, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=rYFtDx/CU9+iX8QTM0ckbw==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1752037868679, updatedTime=1761735668047, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=rYFtDx/CU9+iX8QTM0ckbw==, picEn=oFT2NmUwKPUjZ27C1+d9pw==, jcr=null, cjcr=null, exts=[JournalExt(id=1190368926564450443, language=CN, name=汽车技术, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735668078, updatedTime=1761735668078, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190368926618976396, language=EN, name=Automobile Technology, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735668091, updatedTime=1761735668091, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189621681917173762, websiteList=[Website(id=1189624193747526544, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189621681917173762, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/qcjs/CN, language=CN, createTime=1761558109939, createBy=18614031015, updateTime=1761558140534, updateBy=18614031015, name=汽车技术-中, tplId=1146099689490845704, title=汽车技术, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189625424704451180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=articleTextType, value=kx, createTime=1761558403421, updateTime=1761558403421, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424675091049, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=banner, value=null, createTime=1761558403414, updateTime=1761558403414, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424733811311, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=grayFlag, value=0, createTime=1761558403428, updateTime=1761558403428, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424658313832, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=logo, value=https://castjournals.cast.org.cn/joweb/qcjs/CN/file/pic?fileId=7En9rzX2QCa/1J8NnKt/Fg==, createTime=1761558403410, updateTime=1761558403410, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424746394225, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=minRunFlag, value=0, createTime=1761558403431, updateTime=1761558403431, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424691868267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcjs/CN/file/pic, createTime=1761558403418, updateTime=1761558403418, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424742199920, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=silenceFlag, value=0, createTime=1761558403430, updateTime=1761558403430, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424683479658, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761558403416, updateTime=1761558403416, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424712839789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=themeColor, value=null, createTime=1761558403423, updateTime=1761558403423, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424725422702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=themeStyle, value=null, createTime=1761558403426, updateTime=1761558403426, creator=18614031015, updator=18614031015)]), Website(id=1189624193869161363, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189621681917173762, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/qcjs/EN, language=EN, createTime=1761558109967, createBy=18614031015, updateTime=1761558340679, updateBy=18614031015, name=汽车技术-英文, tplId=1146101810881728533, title=Automobile Technology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189625550722311064, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=articleTextType, value=kx, createTime=1761558433466, updateTime=1761558433466, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550688756629, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=banner, value=null, createTime=1761558433458, updateTime=1761558433458, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550739088283, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=grayFlag, value=0, createTime=1761558433470, updateTime=1761558433470, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550676173716, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=logo, value=https://castjournals.cast.org.cn/joweb/qcjs/EN/file/pic?fileId=7En9rzX2QCa/1J8NnKt/Fg==, createTime=1761558433455, updateTime=1761558433455, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550751671197, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=minRunFlag, value=0, createTime=1761558433473, updateTime=1761558433473, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550713922455, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcjs/EN/file/pic, createTime=1761558433464, updateTime=1761558433464, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550743282588, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=silenceFlag, value=0, createTime=1761558433471, updateTime=1761558433471, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550705533846, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761558433462, updateTime=1761558433462, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550726505369, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=themeColor, value=null, createTime=1761558433467, updateTime=1761558433467, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550734893978, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=themeStyle, value=null, createTime=1761558433469, updateTime=1761558433469, creator=18614031015, updator=18614031015)])], journalTitle=汽车技术, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Automobile Technology, journalPhotoCn=rYFtDx/CU9+iX8QTM0ckbw==, journalPhotoEn=oFT2NmUwKPUjZ27C1+d9pw==, journalFirstLetter=A, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/qcjs/CN/10.19620/j.cnki.1000-3703.20231093, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcjs/EN/10.19620/j.cnki.1000-3703.20231093, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcjs/CN/PDF/10.19620/j.cnki.1000-3703.20231093, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcjs/EN/PDF/10.19620/j.cnki.1000-3703.20231093, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于LSTM车速预测和深度确定性策略梯度的增程式电动汽车能量管理*
收藏切换
PDF下载
路来伟 , 赵红 , 徐福良 , 罗勇
汽车技术 | 2024,(8): 27-37
收起
收藏切换
汽车技术 | 2024, (8): 27-37
基于LSTM车速预测和深度确定性策略梯度的增程式电动汽车能量管理*
全屏
路来伟, 赵红 , 徐福良, 罗勇
作者信息
  • 青岛大学,青岛 266071

通讯作者:

赵红(1973—),女,河南南阳人,副教授,工学博士,研究方向为汽车节能减排与新能源技术,
DDPG Energy Management of Extended-Range Electric Vehicle Based on LSTM Speed Prediction
Laiwei Lu, Hong Zhao , Fuliang Xü, Yong Luo
Affiliations
  • Qingdao University, Qingdao 266071
出版时间: 2024-08-24 doi: 10.19620/j.cnki.1000-3703.20231093
文章导航
收藏切换
为提高增程式电动汽车的能量管理性能,首先利用长短时记忆(LSTM)神经网络进行车速预测,然后计算出预测时域内的需求功率,并将其与当前时刻的需求功率共同输入深度确定性策略梯度(DDPG)智能体,由智能体输出控制量,最后通过硬件在环仿真验证了控制策略的实时性。结果表明,采用所提出的LSTM-DDPG能量管理策略相对于DDPG能量管理策略、深度Q网络(DQN)能量管理策略、功率跟随控制策略在世界重型商用车辆瞬态循环(WTVC)工况下的等效燃油消耗量分别减少0.613 kg、0.350 kg、0.607 kg,与采用动态规划控制策略时的等效燃油消耗量仅相差0.128 kg。
增程式电动汽车  /  长短时记忆神经网络  /  深度强化学习  /  深度确定性策略梯度

In order to improve the energy management of Range Extended Electric Vehicle (REEV), firstly Long Short-Term Memory (LSTM) neural network was used to predicate vehicle speed, then calculates the demand power in the prediction time domain, and the demand power in the prediction time domain and the demand power at the current moment were jointly inputted to the Deep Deterministic Policy Gradient (DDPG) agent, which outputted the control quantity. Finally, the hardware-in-the-loop simulation was carried out to verify the real-time performance of the control strategy. The validation results show that using the proposed LSTM-DDPG energy management strategy reduces the equivalent fuel consumption by 0.613 kg, 0.350 kg, and 0.607 kg compared to the DDPG energy management strategy, the Deep Q-Network (DQN) energy management strategy, and the power-following control strategy, respectively, under the World Transient Vehicle Cycling (WTVC) conditions, which is only 0.128 kg different from that of the dynamic planning control strategy when the dynamic planning control strategy is used.

Extended-range electric vehicle  /  Long Short-Term Memory (LSTM) neural network  /  Deep Reinforcement Learning (DRL)  /  Deep Deterministic Policy Gradient (DDPG)
路来伟, 赵红, 徐福良, 罗勇. 基于LSTM车速预测和深度确定性策略梯度的增程式电动汽车能量管理*. 汽车技术, 2024 , (8) : 27 -37 . DOI: 10.19620/j.cnki.1000-3703.20231093
Laiwei Lu, Hong Zhao, Fuliang Xü, Yong Luo. DDPG Energy Management of Extended-Range Electric Vehicle Based on LSTM Speed Prediction[J]. Automobile Technology, 2024 , (8) : 27 -37 . DOI: 10.19620/j.cnki.1000-3703.20231093
增程式电动汽车的增程器能够不断为动力电池供电,可缓解用户的里程焦虑问题。为兼顾汽车的燃油经济性和电池寿命,研究人员提出了多种控制策略,通过控制增程器和动力电池的功率分配优化能量管理。
将各种神经网络算法与模型预测控制-等效燃油消耗最小化策略(Model Predictive Control Equivalent Consumption Minimization Strategy,MPC-ECMS)相结合实现燃油经济性的提高是当前增程式电动汽车能量管理领域的研究热点[1-8]。Han等在研究车速预测与基于模型预测控制(Model Predictive Control,MPC)能量管理策略的基础上,设计了一种考虑电机温度的控制策略[9]。Ritter将长预测范围集成到混合动力电动汽车能量管理的随机MPC框架中[10]。Li等提出了一种基于驾驶员行为的分层预测能源管理策略[11]。Yu等[12]通过转矩预测的方式确定汽车工作模式优化控制策略。Chen等[13]结合贝叶斯正则化提出了基于双神经网络的智能等效燃油消耗最小化策略(Equivalent Consumption Minimization Strategy,ECMS)和新的等效因数校正方法来自适应地调节等效因数。Wei等[14]通过K-均值(K-Means)聚类算法针对不同驾驶模式进行分类能量管理。Zhao等[15]提出了一种基于两层MPC的能量管理方法降低油耗。随着强化学习的发展,众多研究人员利用强化学习的方法进行能量管理,整车燃油经济性得到明显提高[16-19],如Chen[20]结合MPC和双Q学习对混合动力汽车进行了能量分配。
现有研究虽然采用了多种深度学习算法,但未能充分发挥车速预测和强化学习两者的优势,本文结合车速预测和MPC强化学习进行能量管理,搭建增程式电动汽车动力系统模型及长短时记忆(Long Short-Term Memory,LSTM)车速预测模型,构建车速预测训练集,利用LSTM方法进行车速预测,同时与支持向量回归(Support Vector Regression,SVR)方法进行对比,控制策略根据车速预测结果计算预测时域内的需求功率,再将预测时域内的需求功率和当前时刻的需求功率作为智能体的状态输入对深度确定性策略梯度(Deep Deterministic Policy Gradient,DDPG)能量管理策略智能体进行训练,利用Simulink仿真对比本文提出的控制策略与其他控制策略的控制效果,并进行硬件在环(Hardware-In-the-Loop,HIL)仿真,验证控制策略的实时性。
本文的研究对象为某增程式客车,由增程器和动力电池提供能量,由驱动电机驱动,其中增程器主要由发动机和发电机组成,两者机械连接,电池通过DC/DC转换器与增程器和驱动电机相连接,如图1所示,整车及各主要部件参数如表1所示。
整车模型主要考虑汽车行驶阻力,根据整车动力学原理,汽车行驶时所受到的阻力之和为:

F=Gfcosα+CDAu2/21.15+Gsinα+δmdu/dt

式中:G为作用于汽车的重力,f为滚动阻力系数,α为道路坡度,CD为空气阻力系数,A为迎风面积,u为车速,d为旋转质量换算系数,m为整车质量,du/dt为行驶加速度。
本文中发动机、发电机都采用准静态模型,如图2所示。在每一时刻,发动机准静态模型均可根据发动机扭矩Teng与转速neng求解,获得发动机燃油消耗率mf

mf=Tengnengbe

式中:be为发动机等效燃油消耗率。
发动机与发电机通过机械方式连接,二者具有相同的转速和转矩,因此可以根据发动机万有特性和发电机效率MAP图计算增程器最佳工作曲线,增程器的最佳燃油消耗率曲线如图3所示。增程器的输出功率和燃油消耗率计算公式分别为[21]

Pgen=Pengη(Teng,neng)

feng=f(Teng,neng)

式中:Pgen为发电机输出功率;η(Teng,neng)为发电机的发电效率,可根据转矩、转速查表获得;Peng为发动机输出功率;feng为增程器燃油消耗率;f(Teng,neng)为燃油消耗率查表函数。
电池通过逆变器与驱动电机和发电机相连,本文电池模型采用等效电路模型[22],即将电池视为一个电压源与电阻串联,电池结构及动力电池开路电压UVOC与荷电状态(State of Charge,SOC)SSOC的关系如图4所示,其中,U为端电压,I为电池电流,R为电池内阻。
t时刻动力电池电流和SOC的计算公式分别为[23]
I ( t ) = U V O C ( t ) 2 R - U V O C ( t ) 2 2 R 2 - P b ( t ) R
S S O C ( t ) = S S O C i n i t + t 0 t U V O C ( t ) - U V O C ( t ) 2 - 4 R P b ( t ) 2 R Q d t
同时,SOC与电流应满足以下条件:

SSOC(t)∈[SSOCmin,SSOCmax]

I(t)∈[Imin,Imax]

式中:SSOCinit为初始SOC值,t0为初始时刻,UVOC(t)为t时刻电池开路电压,Pb(t)为t时刻电池功率,Q为电池容量,IminImax分别为动力电池允许的最大电流和最小电流,SSOCminSSOCmax分别为SOC的设定最大值和最小值。
驱动电机同样采用准静态模型,驱动电机与电机转速nm和转矩Tm有关,电机效率ηm的查表函数为:

ηm=f(Tm,nm)

本文车辆模型中4个电机采用同一模型,单个电机的MAP图如图5所示。
采用MPC对增程器输出功率进行控制,结合车速预测和DDPG算法进行能量管理,使用新欧洲驾驶循环(New European Driving Cycle,NEDC)、全球统一轻型车辆测试循环(Worldwide Lightduty Test Cycle,WLTC)、美国城市循环(Urban Dynamometer Driving Schedule,UDDS)、高速公路燃油经济性试验(Highway Fuel Economy Test,HWFET)、美国联邦测试程序-75(Federal Test Procedure-75,FTP-75)、市郊循环(Extra Urban Driving Cycle,EUDC)6种工况组成训练集,如图6所示。
使用LSTM神经网络对未来时域内的车速进行预测。首先,确定神经网络超参数和车速预测的预测时域,并使用训练集训练神经网络。然后,利用神经网络对训练集预测时域内每一时刻的车速进行预测,预测效果满足精度要求后,保存车速预测模型,将车速预测部分与能量管理部分结合。控制策略根据预测时域内的车速计算出预测时域内的需求功率,并与当前时刻的需求功率共同作为状态训练DDPG智能体。车速预测和DDPG能量管理流程如图7所示。
LSTM的短期记忆比普通的循环神经网络(Recurrent Neural Network,RNN)更长。图8所示为LSTM网络的结构,t时刻LSTM的输入包括当前时刻输入xt、上一时刻LSTM输出ht-1,以及上一时刻单元状态Ct-1,经计算得到当前时刻输出ht和当前时刻单元状态Ct。其中,ft为遗忘门输出值,it为输入门输出值,ot为输出门输出值,σiσfσo分别为输入门、遗忘门、输出门,WfWiWc*分别为遗忘门、输入门、输出门对应的参数,CtCt+1经过激活函数双曲正切函数tanh变为 C t * C t + 1 *
LSTM预测车速的过程如图9所示,以历史时域内的车速作为输入,采用循环预测获得预测时域内的车速作为输出,其中Nh为历史时域步长。模型在训练过程中不仅学习到了不同的特征,也学到了训练集中的噪声,从而可能造成网络在训练集上的性能很好,但在测试集上的测试效果不理想,出现过拟合的情况。因此,本文加入随机失活(Dropout)层,使神经网络以概率p随机丢弃隐藏层中的节点连接,从而构建一个新的网络结构,确保泛化能力,防止过拟合。为确保神经网络具有合适的概率p,通过遗传算法对不同的概率进行尝试,最终取p=0.4。在遗传算法求解过程中,如图10所示,适应度函数变化过程为:

P(t,erms)=αt+(1-α)erms

式中:tα分别为当前丢弃概率下车速预测用时及其加权系数,erms为预测车速的均方根误差,P ( )为适应度函数。
使用MATLAB/Simulink搭建整车模型,车速预测仿真在MATLAB 2022b上进行,计算机中央处理器型号为Intel i7-12700H,频率为2.3 GHz,配置16 GB内存。超参数确定后,训练LSTM车速预测网络,迭代次数为1 000次。仿真工况采用世界重型商用车辆瞬态循环(World Transient Vehicle Cycle,WTVC)工况,同时将LSTM与SVR车速预测结果进行对比,两种车速预测方法的历史时域为30 s,即选择过去30 s内的车速作为速度预测模型的输入数据。当两种车速预测模型的预测时域均为5 s时,LSTM车速预测的均方根误差(Root Mean Square Error,RMSE)为3.154 3 km/h,SVR车速预测(惩罚系数c=0.76,核函数宽度g=0.6)的均方根误差为4.248 2 km/h,训练过程中的均方根误差和损失如图11所示,在前50次迭代中损失和均方根误差下降明显,之后趋于稳定,训练结束后,均方根误差为0.286 88 km/h,损失为0.041 1,满足精度要求。
图12所示为两种车速预测方法预测车速分布情况,可以看出同一种预测算法预测时间越短,精度越高,相较于SVR方法,LSTM方法预测结果更接近真实值,预测效果更好。虽然较小的预测时域具有较高的预测精度,但过小的预测时域不利于控制策略给出更好的规划结果,车速预测将失去意义,因此本文车速预测部分的预测时域选定为5 s。
控制策略完成车速预测后,根据预测时域内的车速计算出预测时域内的需求功率输入给智能体,智能体根据需求功率和当前时刻SOC作出决策。
强化学习通过不断地与环境进行交互训练智能体。本文深度强化学习部分采用DDPG算法,环境为整车动力系统,车速预测时域为5 s,既有利于规划,又能保证准确性。
深度强化学习任务是一个马尔可夫决策过程(Markov Decision Process,MDP),MDP中状态集S、动作集A、状态转移概率矩阵P、奖励函数R、折扣因子γ∈[0,1]构成五元组<S,A,P,R,γ>。在强化学习中,动作和状态转移都具有随机性,给定状态s时,策略π(a|s)将输出动作a,状态转移的概率分布为P(s′|s),其中s′为转移后的状态。每一时刻环境会根据状态变化产生奖励R,为了评价当前步的动作,引入折扣回报GtRGt均为随机变量,需以Gt的期望来评价当前动作at和状态st的优劣。对Gt求期望得到价值函数Qπ,对Qπ求期望得到状态价值函数Vπ(st)[18]
DDPG是一种演员-评论家(Actor-Critic)算法,它使用2个神经网络:演员(Actor)网络用于学习策略,生成在当前状态下的动作;评论家(Critic)网络用于评估Actor网络生成的动作的优劣,以指导策略的更新。不同于传统的Actor-Critic算法,DDPG算法的Actor网络并非根据动作的概率分布随机产生动作,而是直接输出估计Q值最大的动作。
图13所示为DDPG能量管理算法的原理,每次迭代智能体从经验池中抽取经验训练,本文经验池大小为1 000 000。DDPG使用价值网络估计当前动作Q值,使用策略网络输出动作。与深度Q网络(Deep Q Network,DQN)算法类似,为了避免高估或者低估,DDPG算法同样具有目标网络。在t时刻,策略网络根据状态输出动作at,环境得到动作at后状态由st转移到状态st+1,价值网络根据状态st和动作at计算价值Q(st,at,w),其中w为当前网络的权重,目标策略网络根据状态st+1预测下一时刻的动作 a t + 1 ',动作 a t + 1 '只作为目标价值网络的输入,并不执行,目标价值网络根据st+1 a t + 1 '计算 a t + 1 '的价值Q′(st+1,at+1,w-)和时序差分目标(Temporal-Difference target,TD target),公式为:

Q′(st,at)=rt+γQ′(st+1,at+1,w-)

式中:rtt时刻的回报,w-为目标网络的权重。
时序差分误差(Temporal-Difference target,TD error)的计算公式为:

δt=Q(st,at,w)-[rt+γQ′(st+1,at+1,w-)]

通过梯度下降更新价值网络,通过梯度上升更新策略网络。每隔一段时间,网络参数由当前网络复制给目标网络。
根据LSTM预测的车速计算出预测时域的需求功率,智能体根据状态量训练出下一时刻增程器的输出功率,范围为0~285 kW。DDPG可以输出连续动作控制,相比于DQN算法,DDPG无需离散化动作,而且连续的动作能够实现更好的控制效果。
在控制过程中主要考虑SOC变化和等效燃油消耗,奖励函数为:
r t = β ( S S O C ( t ) - S S O C 0 ) 2 + μ ( α e q u a l ( S S O C ( t ) - S S O C 0 ) + f e i n s )
式中:βμ为系数,SSOC0为SOC初始值,αequal为等效油电转换因子,feins为瞬时燃油消耗量。
本文车速预测的历史时域为30 s,预测时域为5 s,根据预测时域的车速变化计算未来5 s的需求功率,对比WTVC工况下不同控制策略的控制效果。
深度强化学习的目标是使奖励不断增大,评价DDPG训练优劣的标准是能否使Q值不断增大且最终稳定收敛于某一最大值附近。本文提出的LSTM-DDPG能量管理策略中,LSTM车速预测神经网络为5层回归预测网络,DDPG中的价值网络由6层状态路径和2层动作路径以及5层共同路径组成,动作网络由10层反向传播(Back Propagation,BP)神经网络组成,主要用于产生动作,两个网络的优化算法均采用均方根传播(Root Mean Square Propagation,RMSProp)算法。
图14所示为DDPG能量管理和LSTM-DDPG能量管理训练过程。经过训练,DDPG最后一次迭代的奖励值为-10 847,LSTM-DDPG最后一次迭代奖励值为-6 109.1。LSTM-DDPG将预测时域需求功率也输送给智能体,智能体在训练过程中能够更好地作出规划,最终训练过程逐渐趋向稳定。DDPG只考虑当前时刻需求功率,无法在时域上作出规划,因此最终奖励值较小。
图15所示为不同控制策略在WTVC工况下的SOC变化情况和燃油消耗情况,各控制策略初始SOC均设置为0.3,如图15a所示,相较于DDPG和DQN,本文提出的LSTM-DDPG控制策略SOC变化与指定值0.3很接近,整体在0.3附近变化,DDPG与DQN算法则更加偏离指定值。这表明增程器做了更多的功,这两种算法更趋向于发电机发电,功率匹配还略有不足。虽然功率跟随控制策略SOC变化也比较稳定,但是如表2所示,功率跟随控制策略的等效燃油消耗量较高。
图15表2中可以看出,动态规划(Dynamic Programming,DP)控制策略的SOC变化很稳定,等效燃油消耗量也最小。这是因为动态规划是一种全局算法,是理论最优解,通常作为其他控制策略的参考标准。而相比于其他控制策略,本文提出的LSTM-DDPG控制策略等效燃油消耗量最接近于动态规划算法等效燃油消耗量,SOC变化也比较稳定。
图16所示为不同控制策略下发动机与发电机工况点的分布情况。从图16中可以看出:动态规划算法的工作点大多接近增程器的最优工作曲线,因为动态规划算法获得的结果是理论上的最佳值;本文提出的LSTM-DDPG控制策略大多数工作点也分布在最佳工作曲线附近,不在最优曲线附近的工作点则是增程器工作状态的迁移点。其他控制策略只是根据当前工作状态确定增程器的输出功率,而LSTM-DDPG算法则可以根据预测车速进行规划,从时间域上选择最优控制量,尽量减少增程器在低效区工作的时间,从而减少整车燃油消耗量。相较于传统的功率跟随控制策略,基于车速预测的强化学习控制策略通过大量的训练使智能体对各种不同工况有更强的适应能力。
为了验证控制策略的准确性与实时性,搭建了HIL仿真平台对多信号LSTM-MPC-DDQN控制策略进行仿真。图17所示为HIL仿真方案,HIL平台主要由上位机、MicroAutoBox控制器和SCALEXIO实时仿真硬件系统组成。
为LSTM-DDPG控制策略硬件在环仿真与Simulink仿真的对比结果。硬件在环仿真采样步长设置为0.01 s,从图18中可以看出,硬件在环仿真的结果与Simulink仿真结果基本吻合,SOC变化情况与Simulink仿真结果相差0.2%,燃油消耗量与Simulink仿真结果相差0.31%。
为验证控制策略的实时性,将LSTM-DDPG能量管理策略与功率跟随能量管理策略、DDPG能量管理策略的实时功率输出HIL仿真结果进行对比,如图19所示。
表3所示为3种控制策略控制过程中HIL仿真和Simulink仿真结果误差对比,从计算结果中可以看出,3种控制策略的误差均不超过1%,本文提出的LSTM-DDPG能量管理策略具有较好的实时性,能够满足驾驶过程中的动力需求。
本文以增程式客车为研究对象,提出了一种LSTM-DDPG能量管理策略,将车速预测与强化学习能量管理策略相结合,利用LSTM神经网络进行车速预测,控制策略根据预测的车速计算出预测时域内的需求功率,DDPG智能体根据当前时刻需求功率和SOC以及预测时域内的需求功率作出决策,控制增程器输出功率。仿真结果表明,相对于普通的强化学习能量管理策略以及功率跟随控制策略,LSTM-DDPG控制策略的等效燃油消耗量明显下降,非常接近动态规划算法。同时,电池SOC也比较稳定,避免了SOC变化过大对电池寿命的损害。硬件在环仿真结果验证了提出的控制策略具有很好的实时性。
本文提出的基于车速预测的强化学习能量管理方法同样适用于其他混合动力车型的能量管理。此外,后续研究中也可以尝试将更多状态作为强化学习智能体的输入,如发动机工作状态、路况等,同时改进强化学习智能体价值网络和策略网络结构,引入注意力机制,提高智能体对多状态输入的适应能力。
  • *国家自然科学基金项目(52175236)
  • 青岛市科技惠民示范专项(24-1-8-cspz-18-nsh)
参考文献 引证文献
排序方式:
[1]
FAYYAZI M, ABDOOS M, PHAN D, et al. Real-Time Self-Adaptive Q-Learning Controller for Energy Management of Conventional Autonomous Vehicles[J]. Expert Systems with Applications, 2023, 222.
[2]
ZHU W Q. Optimization Strategies for Real-Time Energy Management of Electric Vehicles Based on LSTM Network Learning[J]. Energy Reports, 2022, 8(S8): 1009-1019.
[3]
YANG D, WANG L, YU K J, et al. A Reinforcement Learning-Based Energy Management Strategy for Fuel Cell Hybrid Vehicle Considering Real-Time Velocity Prediction[J]. Energy Conversion and Management, 2022, 274.
[4]
LU L W, ZHAO H, LIU X T, et al. MPC-ECMS Energy Management of Extended-Range Vehicles Based on LSTM Multi-Signal Speed Prediction[J]. Electronics, 2023, 12(12): 2642.
[5]
SHEN P H, ZHAO Z G, ZHAN X W, et al. Optimal Energy Management Strategy for a Plug-in Hybrid Electric Commercial Vehicle Based on Velocity Prediction[J]. Energy, 2018, 155: 838-852.
[6]
WANG W D, GUO X H, YANG C, et al. A Multi-Objective Optimization Energy Management Strategy for Power Split HEV Based on Velocity Prediction[J]. Energy, 2022, 238.
[7]
XING J M, CHU L, HOU Z R, et al. Energy Management Strategy Based on a Novel Speed Prediction Method[J]. Sensors, 2021, 21(24): 8273.
[8]
CHEN R H, YANG C, HAN L J, et al. Power Reserve Predictive Control Strategy for Hybrid Electric Vehicle Using Recognition-Based Long Short-Term Memory Network[J]. Journal of Power Sources, 2022, 520.
[9]
HAN J, SHU H, TANG X L, et al. Predictive Energy Management for Plug-in Hybrid Electric Vehicles Considering Electric Motor Thermal Dynamics[J]. Energy Conversion and Management, 2022, 251.
[10]
RITTER A, WIDMER F, DUHR P, et al. Long-Term Stochastic Model Predictive Control for the Energy Management of Hybrid Electric Vehicles Using Pontryagin’s Minimum Principle and Scenario-Based Optimization[J]. Applied Energy, 2022, 322.
[11]
LI M L, HE H W, FENG L, et al. Hierarchical Predictive Energy Management of Hybrid Electric Buses Based on Driver Information[J]. Journal of Cleaner Production, 2020, 269.
[12]
YU X, LIN C, TIAN Y, et al. Real-Time and Hierarchical Energy Management-Control Framework for Electric Vehicles with Dual-Motor Powertrain System[J]. Energy, 2023, 272.
[13]
CHEN Z H, LIU Y G, ZHANG Y J, et al. A Neural Network-Based ECMS for Optimized Energy Management of Plug-in Hybrid Electric Vehicles[J]. Energy, 2022, 243.
[14]
WEI C Y, CHEN Y, LI X Y, et al. Integrating Intelligent Driving Pattern Recognition with Adaptive Energy Management Strategy for Extender Range Electric Logistics Vehicle[J]. Energy, 2022, 247.
[15]
ZHAO Z C, XUN J, WAN X, et al. MPC Based Hybrid Electric Vehicles Energy Management Strategy[J]. IFAC-PapersOnLine, 2021, 54(10): 370-375.
[16]
YANG N K, RUAN S M, HAN L J, et al. Reinforcement Learning-Based Real-Time Intelligent Energy Management for Hybrid Electric Vehicles in a Model Predictive Control Framework[J]. Energy, 2023, 270.
[17]
张昊, 范钦灏, 王巍, 等. 基于强化学习的多燃烧模式混合动力能量管理策略[J]. 汽车工程, 2021, 43(5): 683-691.
ZHANG H, FAN Q H, WANG W, et al. Reinforcement Learning Based Energy Management Strategy for Hybrid Electric Vehicles Using Multi-Mode Combustion[J]. Automotive Engineering, 2021, 43(5): 683-691.
[18]
唐小林, 陈佳信, 刘腾, 等. 基于深度强化学习的混合动力汽车智能跟车控制与能量管理策略研究[J]. 机械工程学报, 2022, 57(22): 237-246.
TANG X L, CHEN J X, LIU T, et al. Research on Deep Reinforcement Learning-Based Intelligent Car-Following Control and Energy Management Strategy for Hybrid Electric Vehicles[J]. Journal of Mechanical Engineering, 2022, 57(22): 237-246.
[19]
唐香蕉, 高祖成, 曾令全, 等. 城市道路下混合动力汽车双层能量管理策略[J]. 中国机械工程, 2022, 33(16): 2008-2015.
TANG X J, GAO Z C, ZENG L Q, et al. Double-Layer Energy Management Strategy for Hybrid Vehicles under Urban Roads[J]. China Mechanical Engineering, 2022, 33(16): 2008-2015.
[20]
CHEN Z, GU H J, SHEN S Q, et al. Energy Management Strategy for Power-Split Plug-in Hybrid Electric Vehicle Based on MPC and Double Q-Learning[J]. Energy, 2022, 245.
[21]
席利贺, 张欣, 耿聪, 等. 基于动态规划算法的增程式电动汽车能量管理策略优化[J]. 交通运输工程学报, 2018, 18(3): 148-156.
XI L H, ZHANG X, GENG C, et al. Optimization of Energy Management Strategy for Extended-Range Electric Vehicle Based on Dynamic Programming Algorithm[J]. Journal of Transportation Engineering, 2018, 18(3): 148-156.
[22]
丁帅. 基于随机动态规划的纯电动汽车能量管理控制策略研究[D]. 长沙: 湖南大学, 2020.
DING S. Study on the Control Strategy of Pure Electric Vehicle Energy Management Based on Stochastic Dynamic Planning[D]. Changsha: Hunan University, 2020.
[23]
林歆悠, 夏玉田, 魏申申. 基于增强学习算法的插电式燃料电池电动汽车能量管理控制策略[J]. 工程科学学报, 2019, 41(10): 1332-1341.
LIN X Y, XIA Y T, WEI S S. Plug-in Fuel Cell Electric Vehicle Energy Management Control Strategy Based on Augmented Learning Algorithm[J]. Journal of Engineering Science, 2019, 41(10): 1332-1341.
2024年第卷第8期
PDF下载
283
124
引用本文
BibTeX
文章信息
doi: 10.19620/j.cnki.1000-3703.20231093
  • 首发时间:2025-12-22
  • 出版时间:2024-08-24
补充材料
相关文章
文章信息
作者
出版历史
基金
*国家自然科学基金项目(52175236)
青岛市科技惠民示范专项(24-1-8-cspz-18-nsh)
作者信息
    青岛大学,青岛 266071

通讯作者:

赵红(1973—),女,河南南阳人,副教授,工学博士,研究方向为汽车节能减排与新能源技术,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcjs/CN/10.19620/j.cnki.1000-3703.20231093
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏