A Novel Method for the Application of the ECMS(Equivalent Consumption Minimization Strategy)to Reduce Hydrogen Consumption in Fuel Cell Hybrid Electric Vehicles

Fuel cell hybrid electric vehicles are currently being considered as ideal means to solve the energy crisis and global warming in today’s society.In this context,this paper proposes a method to solve the problem related to the dependence of the so-called optimal equivalent factor(determined in the framework of the equivalent consumption minimum strategy-ECMS)on the working conditions.The simulation results show that under typical conditions(some representative cities being considered),the proposed strategy can maintain the power balance;for different initial battery’s states of charge(SOC),after the SOC stabilizes,the fuel consumption is 5.25 L/100 km.

A review of hydrogen technologies and engineering solutions for railway vehicle design and operations

Interest in hydrogen-powered rail vehicles has gradually increased worldwide over recent decades due to the global pressure on reduction in greenhouse gas emissions,technology availability,and multiple options of power supply.In the past,research and development have been primarily focusing on light rail and regional trains,but the interest in hydrogen-powered freight and heavy haul trains is also growing.The review shows that some technical feasibility has been demonstrated from the research and experiments on proof-of-concept designs.Several rail vehicles powered by hydrogen either are currently operating or are the subject of experimental programmes.The paper identifies that fuel cell technology is well developed and has obvious application in providing electrical traction power,while hydrogen combustion in traditional IC engines and gas turbines is not yet well developed.The need for on-board energy storage is discussed along with the benefits of energy management and control systems.

Energy Security Planning for Hydrogen Fuel Cell Vehicles in Large-Scale Events:A Case Study of Beijing 2022 Winter Olympics

Energy security planning is fundamental to safeguarding the traffic operation in large-scale events.To guarantee the promo-tion of green,zero-carbon,and environmental-friendly hydrogen fuel cell vehicles(HFCVs)in large-scale events,a five-stage planning method is proposed considering the demand and supply potential of hydrogen energy.Specifically,to meet the requirements of the large-scale events’demand,a new calculation approach is proposed to calculate the hydrogen amount and the distribution of hydrogen stations.In addition,energy supply is guaranteed from four aspects,namely hydrogen produc-tion,hydrogen storage,hydrogen delivery,and hydrogen refueling.The emergency plan is established based on the overall support plan,which can realize multi-dimensional energy security.Furthermore,the planning method is demonstrative as it powers the Beijing 2022 Winter Olympics as the first“green”Olympic,providing both theoretical and practical evidence for the energy security planning of large-scale events.This study provides suggestions about ensuring the energy demand after the race,broadening the application scenarios,and accelerating the application of HFCVs.

Function approximation reinforcement learning of energy management with the fuzzy REINFORCE for fuel cell hybrid electric vehicles

In the paper,a novel self-learning energy management strategy(EMS)is proposed for fuel cell hybrid electric vehicles(FCHEV)to achieve the hydrogen saving and maintain the battery operation.In the EMS,it is proposed to approximate the EMS policy function with fuzzy inference system(FIS)and learn the policy parameters through policy gradient reinforcement learning(PGRL).Thus,a so-called Fuzzy REINFORCE algorithm is first proposed and studied for EMS problem in the paper.Fuzzy REINFORCE is a model-free method that the EMS agent can learn itself through interactions with environment,which makes it independent of model accuracy,prior knowledge,and expert experience.Meanwhile,to stabilize the training process,a fuzzy baseline function is adopted to approximate the value function based on FIS without affecting the policy gradient direction.More-over,the drawbacks of traditional reinforcement learning such as high computation burden,long convergence time,can also be overcome.The effectiveness of the proposed methods were verified by Hardware-in-Loop ex-periments.The adaptability of the proposed method to the changes of driving conditions and system states is also verified.

Analysis on carbon emission reduction intensity of fuel cell vehicles from a life-cycle perspective

The hydrogen fuel cell vehicle is rapidly developing in China for carbon reduction and neutrality.This paper evaluated the life-cycle cost and carbon emission of hydrogen energy via lots of field surveys,including hydrogen production and packing in chlor-alkali plants,transport by tube trailers,storage and refueling in hydrogen refueling stations(HRSs),and application for use in two different cities.It also conducted a comparative study for battery electric vehicles(BEVs)and internal combustion engine vehicles(ICEVs).The result indicates that hydrogen fuel cell vehicle(FCV)has the best environmental performance but the highest energy cost.However,a sufficient hydrogen supply can significantly reduce the carbon intensity and FCV energy cost of the current system.The carbon emission for FCV application has the potential to decrease by 73.1%in City A and 43.8%in City B.It only takes 11.0%–20.1%of the BEV emission and 8.2%–9.8%of the ICEV emission.The cost of FCV driving can be reduced by 39.1%in City A.Further improvement can be obtained with an economical and“greener”hydrogen production pathway.

Abating transport GHG emissions by hydrogen fuel cell vehicles： Chances for the developing world

Fuel cell vehicles, as the most promising clean vehicle technology for the future, represent the major chances for the developing world to avoid high-carbon lock-in in the transportation sector. In this paper, by taking China as an example, the unique advantages for China to deploy fuel cell vehicles are reviewed. Subsequently, this paper analyzes the greenhouse gas （GHG） emissions from 19 fuel cell vehicle utilization pathways by using the life cycle assessment approach. The results show that with the current grid mix in China, hydrogen from water electro- lysis has the highest GHG emissions, at 3.10 kgCO2/km, while by-product hydrogen from the chlor-alkali industry has the lowest level, at 0.08 kgCO2/krn. Regarding hydrogen storage and transportation, a combination of gas-hydrogen road transportation and single compression in the refueling station has the lowest GHG emissions. Regarding vehicle operation, GHG emissions from indirect methanol fuel cell are proved to be lower than those from direct hydrogen fuel cells. It is recommended that although fuel cell vehicles are promising for the developing world in reducing GHG emissions, the vehicle technology and hydrogen production issues should be well addressed to ensure the life-cycle low-carbon performance.

Advancing green energy solution with the impetus of COVID-19 pandemic

The global energy system needs a revolutionary transition from today’s fossil fuel to a low carbon energy system by having deep carbonization in all energy demand sectors.Especially in the transport sector,fossil fuel-based vehicles contribute to a more massive amount of greenhouse gas emissions(GHG),mainly carbon dioxide(CO_(2))and particulate matter(PM2.5),affecting human health,society,and the climate system.Hydrogen and fuel cell technology is a promising low carbon transition pathway that supports GHG mitigation and achieves sustainable development.Although hydrogen and fuel cells are assuring,fuel cell vehicle expensiveness and the high cost of hydrogen production with the low carbon footprint are significant hindrances for its widespread deployment.Besides the situation above,the present corona virus(COVID-19)has devastated our global economy and ramps down the future of fossil fuel.It provides opportunities to rethink and reshape our energy system to a low carbon footprint.By utilizing the situation,governments and policymakers need to eliminate fossil fuel and invest in the hydrogen and fuel cell technologies deployment as future energy systems.This review article provides a technical overview of a low carbon energy system,production,and end-use service in a hydrogen economy perspective for developing a sustainable energy future.The techno-economic analysis of the different hydrogen production routines and fuel cell vehicles and their infrastructures are primarily focused.Finally,a long-term policy alignment was outlined to advance the hydrogen energy system for post-COVID-19 in the United Nation’s(UN)sustainable development goals framework.

Deep reinforcement learning based energy management strategy for fuel cell/battery/supercapacitor powered electric vehicle

Vehicles using a single fuel cell as a power source often have problems such as slow response and inability to recover braking energy.Therefore,the current automobile market is mainly dominated by fuel cell hybrid vehicles.In this study,the fuel cell hybrid commercial vehicle is taken as the research object,and a fuel cell/battery/supercapacitor energy topology is proposed,and an energy management strategy based on a double-delay deep deterministic policy gradient is designed for this topological structure.This strategy takes fuel cell hydrogen consumption,fuel cell life loss,and battery life loss as the optimization goals,in which supercapacitors play the role of coordinating the power output of the fuel cell and the battery,providing more optimization ranges for the optimization of fuel cells and batteries.Compared with the deep deterministic policy gradient strategy(DDPG)and the nonlinear programming algorithm strategy,this strategy has reduced hydrogen consumption level,fuel cell loss level,and battery loss level,which greatly improves the economy and service life of the power system.The proposed EMS is based on the TD3 algorithm in deep reinforcement learning,and simultaneously optimizes a number of indicators,which is beneficial to prolong the service life of the power system.

基于TD3-PER的氢燃料电池混合动力汽车能量管理策略研究

为优化氢燃料电池混合动力汽车的燃料经济性及辅助动力电池性能,提出了一种基于优先经验采样的双延迟深度确定性策略梯度(TD3-PER)能量管理策略。采用双延迟深度确定性策略梯度(TD3)算法,在防止训练过优估计的同时实现了更精准的连续控制;同时结合优先经验采样(PER)算法,在获得更好优化性能的基础上加速了策略的训练。仿真结果表明:相较于深度确定性策略梯度(DDPG)算法,所提出的TD3-PER能量管理策略的百公里氢耗量降低了7.56%,平均功率波动降低了6.49%。

基于模型预测框架的燃料电池汽车混合动力系统能量管理

混合动力系统作为燃料电池汽车的关键组成部分,系统的能耗与寿命优化是推动其进一步商业化发展的关键,而能量管理策略(EMS)在提高燃料电池汽车混合动力系统的效率和燃料经济性方面发挥着重要作用。为有效降低混合动力系统的内部损耗,进一步提高系统经济性,提出了一种基于模型预测框架的混合动力系统能耗优化能量管理控制方法。首先构建包含动力系统内部损耗与氢气消耗的目标函数,然后利用模型预测架构求解目标函数来控制燃料电池的输出电流,以实现合理的能量分配,最后在Matlab中进行仿真,验证所制定方法的合理性和有效性。与应用较为广泛的等效氢耗最小策略(ECMS)相比,结果表明所提方法可以显著降低动力系统的内部损耗和氢气消耗。此外,该策略还可以有效保持蓄电池的荷电状态(SOC),延长动力系统的使用寿命。

基于深度强化学习的网联燃料电池混合动力汽车生态驾驶联合优化方法

随着物联网、无人驾驶等新技术的快速发展,基于网联交通驾驶环境为混合动力车辆节能驾驶与能量管理优化注入了新的研究思路。针对燃料电池混合动力汽车在多信号灯城市道路的驾驶场景,本文提出一种基于深度强化学习算法的车速与能量管理的多目标分层联合优化方法(DDPG-DP)。在上层节能速度规划方面采用DDPG算法,同时设计多目标奖励值函数和加入优先经验回放机制,在提高算法速度和稳定性的基础上,进行节能、驾驶舒适性以及通行效率的多目标速度规划。在下层能量管理方面采用动态规划算法(DP),以氢气消耗最小化为目标实现混合动力系统的最优节能控制。结果表明:在本文设定的2种场景中,DDPG-DP算法比IDM-DP算法在通行效率上分别提高15.25%、20.18%,氢气燃料消耗分别降低25.66%、17.86%;同时在本文设定的2种场景中DDPG-DP算法相比于全局最优算法(DP-DP)在通行时间上只存在5 s左右差距,氢气燃料消耗比最优算法仅相差2.84%、4.7%。在通行平稳性上DDPG-DP算法比另外2种算法(IDM-DP、DP-DP)速度波动更小且未出现急加减速情况,能够较好地保证乘坐的舒适性。本文通过速度规划和能量管理双层主动式架构,能够实现混合动力车辆主动式节能优化,将为混合动力汽车日常驾驶提供更大节能潜力,同时对于网联燃料电池混合动力汽车的多目标生态驾驶优化奠定了研究基础。

车用氢能储供阀门测试标准比较研究

氢能一直以来是全球能源界关注的重点,燃料电池汽车是氢能应用与发展的重要领域。氢气属于易燃易爆且小分子易泄漏气体,车用氢能储供阀门作为车载供氢系统的关键部件,产品的安全性能关系到整车的安全性和稳定性。本文通过对国内外车用氢能储供阀门常用的测试标准的比较研究,着重对GB/T 42536、EU406和GTR13三个标准的测试试验项目进行比较,对标准的试验要求进行了分析和总结,为更好地理解和应用标准提供了借鉴,对于车用氢能产业的发展具有重要的意义。

燃料电池汽车动力系统及能量管理策略研究进展

动力系统是燃料电池汽车(FCV)的核心,可分为单一式系统与混合动力系统两大类,其中,将燃料电池与辅助电源相结合组成“电-电”混合动力系统,已成为业界主流。本文根据辅助电源类型的不同,提出3类FCV混动系统的构建方案,分别为燃料电池+动力电池方案、燃料电池+超级电容方案、燃料电池+动力电池+超级电容方案,并对各方案的优势和劣势进行比较。同时,本文综述了近年来国内外学者提出的面向FCV的代表性能量管理策略,从理论基础与求解方法的差异出发,将现有燃料电池汽车的能量管理策略分为3类:基于规则定义的策略、基于最优化方法的策略以及基于机器学习的策略,并总结了各类策略在最优性与实时性等方面的优势和劣势。其中,基于规则定义的策略最易实现,在工程应用中最为普遍,但无法实现性能最优;基于最优化方法的策略能够接近甚至达到理论最优,但存在计算量过大、计算耗时过长、实时性差等问题;以强化学习为代表的基于机器学习的策略有望在最优性与实时性之间实现理想的平衡,但目前还存在模型训练耗时长、试错代价高等困难,在实车应用层面还存在一定挑战。基于文献研究与分析,本文提出以下观点:1)以大功率燃料电池为核心的功率混合型系统是FCV混动系统的未来发展方向;2)必须进一步提升智能化程度,根据实际使用场景开发具有个性化的能量管理策略;3)亟需建立关于燃料电池汽车能量管理策略的综合评价体系。

锂电池与燃料电池混合观光车动力系统的优化设计

为了解决传统电动车续航焦虑的问题,对燃料电池观光车进行了功率匹配设计与仿真验证,提出了一种功率跟随型能量管理策略。对比了纯锂电池观光车(LI)、纯燃料电池观光车(FC)、LI与FC的混合动力观光车(LI-FC)的输出特性,并仿真试验。结果表明:LI-FC的爬坡度与纯锂电池观光车不相上下,续航里程较纯锂电池观光车提升了15%,等效氢耗较纯锂电池观光车减少了53%,动力电池荷电状态(SOC)能保持在0.5~0.9之间稳定工作,燃料电池也会在额定工况与怠速工况下稳定切换。因此,燃料电池锂电池混合动力观光车具有这3种观光车中最优续航能力、较好的使用经济性、最好的使用稳定性,燃料电池与动力电池都能在期望工况下稳定工作,有较好的竞争力。

氢燃料电池混合动力汽车能量管理策略研究综述

氢燃料电池混合动力汽车的能量管理是整车控制的核心与关键,尤其是在提高燃料经济性和电池耐久性方面有重要作用。文中梳理了国内外基于规则、基于优化、基于学习和混合能量管理策略的研究进展,分析了各种策略的优势和局限。结果发现:规则型的策略易于实现,但适应性差;优化型的策略灵活性好,但计算复杂;学习型的策略自适应强,但需要大量数据支持;而国内外学者所提出的混合策略在氢燃料电池汽车氢耗量和电池寿命等方面更有优势。未来的研究会聚焦于结合不同策略的优势,将优化算法和机器算法引入基于规则和基于优化的策略,以及优化强化学习中的智能算法以提升整车性能。

基于Stackelberg博弈的燃料电池混合动力汽车跟车能量管理

跟车场景下燃料电池混合动力汽车(FCHEV)的速度与能量管理协同优化是实现车辆节能的重要有效手段,针对现有策略中双能量源退化与能耗耦合关系不明,且难以兼顾全局优化与实时性能的问题,提出一种基于Stackelberg博弈的FCHEV跟车能量管理策略。首先,建立了燃料电池/锂电池的能耗与性能退化模型,并纳入到统一量纲的整车综合使用成本函数中;其次,提出了基于分层解耦的跟车能量管理策略,实现跟车速度与功率分配的解耦控制;最后,综合考虑跟车安全性、舒适性、燃料经济性和能源耐久性,建立跟车控制层与能量管理层对应的双层规划模型,并基于Stackelberg博弈思想设计了双层差分遗传算法对策略核心参数进行离线优化。仿真和实验结果表明:相较于模型预测控制方法,该方法可降低平均车间距误差37.7%、平均冲击度2.4%、等效氢气消耗9.3%和能源退化成本13.9%,实现了优化性能与实时性的兼顾。

中国氢燃料电池汽车市场发展现状及展望

[目的]燃料电池汽车产业作为氢能发展的主要赛道之一,在交通领域脱碳转型过程中承担着关键角色。针对当前政策环境和产业基础,对中国燃料电池汽车市场发展趋势和挑战展开系统性分析具有必要性。[方法]文章聚焦市场规模、细分方向、装备及氢源价格等市场要素,对政策驱动下的燃料电池汽车市场发展情况进行介绍与分析。[结果]中国燃料电池汽车市场的推广应用效果与政策扶持力度、奖补细则明确程度和地方优势企业带动密切相关;市场已根据主机厂和燃料电池系统配套企业综合竞争力初显头部企业效应;整车和动力系统价格相较2021年下降5%~20%,但综合应用成本尚未达到市场化水平。[结论]尽管中国燃料电池汽车市场化进程仍掣肘于装备制造成本、氢源价格和基础设施配套等因素,但产业发展的决心坚定,将不断随着产品性能验证、基础设施建设、商业模式创新得以稳步发展,展现出更大活力。

国内外燃料电池汽车政策发展展望

分析了美国、日本、韩国、欧盟等国家和地区燃料电池汽车产业支持政策,总结了我国以燃料电池汽车示范政策为代表的支持政策。通过分析、借鉴全球燃料电池汽车政策,结合我国燃料电池汽车产业发展现状,为进一步优化顶层政策设计,高效支撑、引导未来燃料电池汽车相关产业发展提供参考。

双碳经济背景下重庆市氢燃料电池关键材料在新能源汽车产业中的发展现状及建议

氢能作为一种可再生的二次能源,来源丰富,质量能量密度高,使用过程环境友好,无碳排放,是21世纪“最具发展潜力”的能源之一,已经被多国提升到战略的高度。我国也将氢能作为战略新兴产业重点发展的方向,其成为我国能源体系的重要组成部分,并且获得众多研究者以及新能源产业领域方面专家的高度关注。重庆有着丰富的天然气、页岩气资源,为氢能源产业提供了资源基础,加之其汽车产业优势,重庆市也在积极打造具有全国影响力的氢燃料电池汽车产业基地。本文围绕氢燃料电池关键材料及核心组件体系,较全面地分析了质子交换膜、催化剂、气体扩散层、双极板等国内外企业的情况,梳理了重庆市氢燃料电池关键材料、核心组件以及检测机构企业的发展现状,分析了重庆市氢燃料电池在新能源汽车产业中的发展基础以及存在的问题,最后提出了重庆市氢燃料电池关键材料及核心组件在新能源汽车产业中的发展建议。

燃料电池混合动力汽车深度强化学习能量管理优化

针对配备有锂电池与超级电容的燃料电池混合动力汽车,为降低车辆总体运行成本,延长能量源寿命,本文提出一种基于深度强化学习的能量管理策略.首先,依据超级电容高功率密度特性,建立基于模糊自适应滤波的功率分层结构,并依据燃料电池与锂电池的经验退化模型,建立能量源退化的成本函数,采用等效消耗最小策略平衡氢耗成本与能量源退化成本,以最小化总体运行成本为目标来优化能量源功率分配;然后,引入优先经验回放与软更新以提高深度强化学习的离线训练效率;最后,在多种工况下进行仿真,结果表明,与未考虑退化的策略相比,本文所提出策略在全球统一轻型车辆测试循环下可使氢耗量降低11.8%,并可有效减缓燃料电池与锂电池的退化速率,降低燃料电池混合动力汽车的总体运行成本.