基于DRL的无人船混合动力系统能量管理策略研究-豆柴文库

您所在位置：网站首页 / 基于DRL的无人船混合动力系统能量管理策略研究.docx / 文档详情

在线预览结束，喜欢就下载吧，查找使用更方便

5 金币

下载文档

/ 2

下载提示

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

文本预览

基于DRL的无人船混合动力系统能量管理策略研究
Abstract:
Withtherapiddevelopmentofmaritimetransportation,thedemandforunmannedshipshasgraduallyincreased.Duetothecharacteristicsofcomplexmarineenvironmentanddynamicchanges,itisdifficulttoensurethereliabilityandstabilityofthepowersystemofunmannedships.Therefore,thestudyofintelligentenergymanagementstrategiesforunmannedshipshasbecomeincreasinglyimportant.Thispaperproposesadeepreinforcementlearning(DRL)basedenergymanagementstrategyforamixedpowersystemofunmannedships.Theproposedstrategyhassignificantlyimprovedtheoverallperformanceoftheship'spowersystemwhilereducingfuelconsumption.
Introduction:
Thepowersystemofunmannedshipsisanimportantpartoftheiroperationasitdirectlyaffectstheirreliabilityandstability.Currently,themostwidelyusedpowersystemsinunmannedshipsarehybridpowersystems.However,thedynamicchangesinthemarineenvironmentmakeitdifficultfortraditionalenergymanagementstrategiestoaccuratelyandefficientlycontrolthepowersystem,leadingtoincreasedfuelconsumptionandoperatingcosts.
Inrecentyears,DRLhasbeenwidelyusedinenergymanagementofhybridpowersystemsforunmannedvehicles.Inthispaper,weproposeaDRLbasedenergymanagementstrategyforthepowersystemofunmannedships.TheproposedenergymanagementstrategyinnovativelycombinestheadvantagesoftraditionalenergymanagementstrategiesandDRL.Theproposedstrategynotonlyimprovesthereliabilityandstabilityofthepowersystemofunmannedshipsbutalsosignificantlyreducesfuelconsumptionandoperatingcosts.
Methodology:
TheproposedDRL-basedenergymanagementstrategyiscomposedofathree-layerdeepneuralnetwork,includingtheinputlayer,hiddenlayer,andoutputlayer.Theinputlayermainlyincludesthereal-timedataoftheship'spowersystemandthemarineenvironment,includingthebatterystateofcharge,hybridsystempower,speed,current,andotheressentialoperationalparameters.Thehiddenlayerandoutputlayerareresponsibleforcalculatingtheoptimalenergymanagementstrategyinreal-time.
Theenergymanagementstrategyproposedinthispaperisbasedonthetraditionalpowermanagementstrategy,whichma