Etransportation最新文献

{"title":"Optimizing resilient parallel refueling operations: relaxed stochastic economic mobility scheduling for fuel cell vehicles with multiple hydrogen storage systems","authors":"Muhammad Bakr Abdelghany ,&nbsp;Ahmed Al-Durra ,&nbsp;Hatem Zeineldin ,&nbsp;Mohamed Shawky El Moursi ,&nbsp;Jiefeng Hu ,&nbsp;Fei Gao","doi":"10.1016/j.etran.2024.100393","DOIUrl":"10.1016/j.etran.2024.100393","url":null,"abstract":"<div><div>The growing demand for hydrogen-based mobility highlights the importance of management strategies for hydrogen refueling stations (HRSs), particularly in handling uncertainties related to hydrogen demand, energy forecasts, and market prices. This paper presents a sophisticated approach for managing an HRS powered by renewable energy sources (RESs) that addresses these uncertainties. The HRS is designed to support the simultaneous refueling of multiple hydrogen electric vehicles, including light vehicles and buses, and operates in both off-connected without access to the hydrogen market and on-connected with access to the hydrogen market. The connection to the hydrogen market allows for the purchase of hydrogen when RESs are insufficient and the sale of excess hydrogen. Additionally, a buffer-tank is integrated into the system to store surplus hydrogen, which can be converted to energy and sold to the electrical market when prices are favorable. The proposed strategy incorporates Boolean relaxations and a stochastic scenario-based approach within a model predictive control framework to enhance robustness against uncertainties and reduce computational complexity. Numerical simulations show that the strategy optimizes the use of multiple tanks for parallel refueling and ensures effective HRS operation by meeting hydrogen demands, satisfying operational constraints, minimizing costs, and maximizing profits. Furthermore, when compared to other strategies in the literature with a modeling and control perspective, incorporating degradation factors into control settings significantly reduces unnecessary electrolyzer switching, leading to a 30% decrease in operating expenses and over 2,000 fewer switching events annually, while the relaxed framework achieves nearly a 50% reduction in computation time with both open-source and commercial solvers (e.g., GUROBI).</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100393"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Business cases for degradation-aware bidirectional charging of residential users and heavy-duty vehicle fleets","authors":"David Menchaca Santos,&nbsp;Pauline Thüne,&nbsp;Jan Martin Zepter,&nbsp;Mattia Marinelli","doi":"10.1016/j.etran.2024.100389","DOIUrl":"10.1016/j.etran.2024.100389","url":null,"abstract":"<div><div>In the push towards decarbonizing the transport sector, integrating electric vehicles (EVs) is crucial. Vehicle-to-everything services can address concerns about EV acceptance and grid integration, but viable business models are necessary to incentivize user participation. This paper presents a techno-economic mixed integer linear programming optimization model to assess the feasibility of bidirectional charging for residential users (RUs) and heavy-duty fleet vehicles. The model ensures proper battery degradation management and integrates renewable energy sources at charging locations. Price arbitrage (PA), specifically vehicle-to-home (V2H) and residential vehicle-to-grid (V2G), is explored for RUs. For larger EV fleets, V2G PA and V2G combined with frequency containment reserve for disturbances (FCR-D) are investigated. Business cases guide the optimization, simulating a year of operation in Eastern Denmark. The results are compared to a baseline scenario with no bidirectional charging capability. RUs achieve average cost savings of 176<!--> <!-->€<!--> <!-->with a payback period of 5 to 23 years, depending on the charging equipment supplier. V2H proves most suitable for <em>remote</em> users with flexible charging patterns. While EV fleets do not see significant savings with V2G alone, V2G combined with FCR-D yields savings of 330<!--> <!--> <!-->thousand <!--> <!-->€<!--> <!-->with a payback period of 3 to 17 years. Challenges remain due to the rarity of commercially available bidirectional charging equipment and limited data on driving patterns. However, our analysis shows that bidirectional charging offers substantial financial incentives for both RUs and fleet managers, promoting EV adoption and advancing transport sector decarbonization.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100389"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electric vehicle charging flexibility assessment for load shifting based on real-world charging pattern identification","authors":"Xiaohui Li ,&nbsp;Zhenpo Wang ,&nbsp;Lei Zhang ,&nbsp;Zhijia Huang ,&nbsp;Fangce Guo ,&nbsp;Aruna Sivakumar ,&nbsp;Dirk Uwe Sauer","doi":"10.1016/j.etran.2024.100367","DOIUrl":"10.1016/j.etran.2024.100367","url":null,"abstract":"<div><div>Coordinated charging control for electric vehicles (EVs) can contribute to load balancing and renewable energy utilization. This paper proposes a novel framework for assessing the flexibility of EVs under different charging control strategies through a rule-based identification of charging patterns. First, key categories of EV charging activity chains, characterized by the sequence of parking and charging activities between adjacent trips, are extracted from real-world EV operation data. Simulations are then conducted by switching charging patterns to represent three coordinated charging control methods: delayed charging, reduced-power charging, and smart charging with Time-of-Use (ToU) tariffs. These strategies are applied by modifying the charging time or charging rate within the original charging sessions. Several evaluation metrics are introduced to quantify each strategy's impact on load profile reshaping, flexibility utilization efficiency, user involvement, and energy cost saving. Comparison results show that smart charging with ToU tariffs outperforms the other two strategies, though the effectiveness of each scheme varies with charging patterns. The findings highlight the idle parking time and its ratio to the required charging time as key indicators for identifying potential EV users for coordinated charging control. Additionally, it is shown that shifting 1 % of EV charging load out of peak periods requires at least 4 % of user participation, while at least 3 % is needed for shifting 1 % of EV charging load into valley periods. The proposed pattern-based charging model and evaluation framework offer valuable insights for designing more efficient, cost-effective, and user-friendly EV charging scheduling strategies.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100367"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"China's new energy vehicles and the new energy revolution: Innovation of energy storage batteries as foundation","authors":"Minggao Ouyang","doi":"10.1016/j.etran.2024.100385","DOIUrl":"10.1016/j.etran.2024.100385","url":null,"abstract":"","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100385"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143164510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Liquid hydrogen refueling stations as an alternative to gaseous hydrogen refueling stations: Process development and integrative analyses","authors":"Chaehee Gong ,&nbsp;Heeseung Na ,&nbsp;Sungil Yun ,&nbsp;Young-Ju Kim ,&nbsp;Wangyun Won","doi":"10.1016/j.etran.2024.100386","DOIUrl":"10.1016/j.etran.2024.100386","url":null,"abstract":"<div><div>The use of clean hydrogen is gaining attention as part of efforts to establish a sustainable energy value chain. However, current hydrogen refueling stations remain energy-intensive. To utilize hydrogen more cleanly, a thorough analysis of hydrogen refueling stations from an energy efficiency perspective is necessary. Liquid hydrogen refueling stations are emerging as an environmentally friendly alternative to current gaseous hydrogen refueling stations. For liquid hydrogen refueling stations to carve out a niche in a well-established market dominated by gaseous hydrogen refueling stations, the hydrogen selling price must be competitive. In this research, an energy-optimized design for liquid hydrogen refueling stations was proposed, focusing on reducing operating costs and mitigating potential environmental impacts. The developed design integrated three energy-saving systems into a basic liquid hydrogen refueling station: 1) a heat exchange system for hydrogen pre-cooling, 2) an organic Rankine cycle for waste heat recovery, and 3) a catalytic combustor for utilizing boil-off gas. To assess the viability of the integrated process, case studies were conducted focusing on economic, environmental, energy, and exergy performance. Consequently, the proposed design with integrated energy-saving systems demonstrated that while it increased the minimum hydrogen selling price by 5 % compared to the basic liquid hydrogen refueling station, it could reduce global warming potential by 41 %. We expect that our results will provide a better way to build the infrastructure of hydrogen refueling stations with the growth of the future hydrogen fuel cell electric vehicle market.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100386"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of high-energy-density lithium batteries: Liquid to all solid state","authors":"Haozhe Du ,&nbsp;Xu Zhang ,&nbsp;Haijun Yu","doi":"10.1016/j.etran.2024.100382","DOIUrl":"10.1016/j.etran.2024.100382","url":null,"abstract":"<div><div>With the rising demand of lithium batteries from application fields including electric vehicles (EVs) and various electric aircrafts, it is imperative to greatly enhance the energy density of lithium batteries by rational design. However, there is still a lack of design roadmap for high-energy-density lithium batteries, largely owing to the uncertain selections of electrochemically active materials and the complicated relationships of diverse factors. In this article, based on the discussion of effects of key components and prototype design of lithium batteries with different energy density classes, we aim to tentatively present an overall and systematic design principle and roadmap, covering the key factors and reflecting crucial relationships. This article starts from the fundamental principles of battery design, and the effects of cathode, anode, electrolyte, and other components to realize high-energy-density lithium batteries have been discussed. Based on the prototype design of high-energy-density lithium batteries, it is shown that energy densities of different classes up to 1000 Wh/kg can be realized, where lithium-rich layered oxides (LLOs) and solid-state electrolytes play central roles to gain high energy densities above 500 Wh/kg. Lithium batteries are thus categorized according to different energy density classes, with available component options, to meet their most suitable application scenes.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100382"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electric machine co-optimization for EV drive technology development: Integrating Bayesian optimization and nonlinear model predictive control","authors":"Christoph Wellmann ,&nbsp;Abdul Rahman Khaleel ,&nbsp;Tobias Brinkmann ,&nbsp;Alexander Wahl ,&nbsp;Christian Monissen ,&nbsp;Markus Eisenbarth ,&nbsp;Jakob Andert","doi":"10.1016/j.etran.2024.100392","DOIUrl":"10.1016/j.etran.2024.100392","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Electric powertrains are becoming increasingly prevalent in various mobile propulsion applications, not only due to legislations for lower CO&lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mrow&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt; emissions and local pollution, but also due to growing sustainable consciousness. However, conceptualizing those systems, consisting of component and controller design processes, is a complex task. The complexity itself arises from the amount of requirements for design objectives and use-cases, which can be met inside a multidimensional parameter space. Additionally, system design and evaluation are inherently tied to coupled component and system control strategy optimization. In this context, the paper presents a fully automated active machine learning methodology applied for a combined optimization of electric machine and system controller design, considering system performance, durability, and energy consumption. During this iterative approach a stochastic optimization of a permanent magnet synchronous machine (PMSM) takes place, constrained from a nonlinear model predictive control in a model-in-the-loop system environment. The active learning is covered by a Bayesian optimization algorithm with a Gaussian process regression to determine the most suitable parameter set in terms of exploration and exploitation. To demonstrate the feasibility of this novel methodology, a thermal subsystem from an electrified state-of-the-art powertrain has been used and further optimized regarding PMSM scaling and final gear ratio. Different real-world drive scenarios from highway to city were taken into account to cover typical sport utility vehicle use-cases. It could be shown that the electric machine losses of the optimized system are reduced by up to &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mn&gt;32&lt;/mn&gt;&lt;mo&gt;.&lt;/mo&gt;&lt;mn&gt;7&lt;/mn&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mstyle&gt;&lt;mtext&gt;%&lt;/mtext&gt;&lt;/mstyle&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt;, which equals a consumption of &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;mn&gt;0&lt;/mn&gt;&lt;mo&gt;.&lt;/mo&gt;&lt;mn&gt;43&lt;/mn&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mstyle&gt;&lt;mfrac&gt;&lt;mrow&gt;&lt;mi&gt;k&lt;/mi&gt;&lt;mi&gt;W&lt;/mi&gt;&lt;mi&gt;h&lt;/mi&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;mn&gt;100&lt;/mn&gt;&lt;mi&gt;k&lt;/mi&gt;&lt;mi&gt;m&lt;/mi&gt;&lt;/mrow&gt;&lt;/mfrac&gt;&lt;/mstyle&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; compared to the reference vehicle. Due to slightly worse operating conditions of the inverter the whole system consumption has been minimized by &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;mn&gt;0&lt;/mn&gt;&lt;mo&gt;.&lt;/mo&gt;&lt;mn&gt;35&lt;/mn&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mstyle&gt;&lt;mfrac&gt;&lt;mrow&gt;&lt;mi&gt;k&lt;/mi&gt;&lt;mi&gt;W&lt;/mi&gt;&lt;mi&gt;h&lt;/mi&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;mn&gt;100&lt;/mn&gt;&lt;mi&gt;k&lt;/mi&gt;&lt;mi&gt;m&lt;/mi&gt;&lt;/mrow&gt;&lt;/mfrac&gt;&lt;/mstyle&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt;. Three parameter studies with fixed iteration count have been executed to find the optimal machine diameter to be increased by &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mn&gt;25&lt;/mn&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mstyle&gt;&lt;mtext&gt;%&lt;/mtext&gt;&lt;/mstyle&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; and the length slightly reduced by &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mn&gt;16&lt;/mn&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;mstyle&gt;&lt;mtext&gt;%&lt;/mtext&gt;&lt;/mstyle&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt;. Moreover, the total gear ratio was adjusted by &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;mn&gt;31&lt;/mn&gt;&lt;mspace&gt;&lt;/mspace&gt;&lt;msty","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100392"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing lithium battery safety: Introducing a composite phase change material with anti-leakage and fire-resistant properties","authors":"Xinxi Li ,&nbsp;Wensheng Yang ,&nbsp;Likun Yin ,&nbsp;Shuangyi Zhang ,&nbsp;Yuhang Wu ,&nbsp;Ya Mao ,&nbsp;Wei Jia ,&nbsp;Di Wu ,&nbsp;Kai Chen ,&nbsp;Lifan Yuan ,&nbsp;Xiaoyu Zhou ,&nbsp;Canbing Li","doi":"10.1016/j.etran.2024.100387","DOIUrl":"10.1016/j.etran.2024.100387","url":null,"abstract":"<div><div>The thermal safety of batteries has still existed challenge in energy-storage power stations and electric vehicles. Composite phase change material (CPCM) as a passive cooling system has great potential in the application of controlling an uneven temperature distribution, but its high flammability and susceptibility to leakage severely restrict its widespread adoption, especially in battery packs for electric vehicles and energy storage. Herein, an innovative paraffin/expanded graphite/[Ca(polyethylene glycol)₂]Cl₂ coordination polymer/triphenyl phosphate (TPP)/hexaphenoxycyclotriphosphazene (HPCP) flame retardant multifunctional CPCM (PPCTH) has been introduced and utilized in battery module for thermal management and preventing thermal runaway. PPCTH2 has contained TPP/HPCP with the proportion of 1:1 which provides a multifunctional CPCM with excellent antileakage properties, high thermal conductivity, superior flame-retardant ability, the PPCTH2 exhibits excellent shape stability without collapsing at 200 °C. Moreover, the total heat release and smoke production of PPCTH2 are 108.8 MJ/m² and 8.4 m², respectively. Additionally, the prismatic battery module endowed with PPCTH2 can maintain the maximum temperature below 50 °C and balance the temperature difference within 4.2 °C at a 2 C discharge rate. Thus, the battery module with PPCTH2 can not only improve the temperature consistency even during long cycling processes but also lengthen the temperature rising time and decrease heat accumulation, further suppressing thermal runaway. Overall, this research presents a multifunctional CPCM with high fire resistance and shape stability, which may contribute to the research and design of improved thermal safety for battery packs and energy-storage units.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100387"},"PeriodicalIF":15.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143163251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving fuel cell vehicle efficiency: Exploring dynamic cooling strategies for stack radiators with intermittent spray cooling","authors":"Rajendran Prabakaran,&nbsp;M. Mohamed Souby,&nbsp;Jie Liu,&nbsp;Sung Chul Kim","doi":"10.1016/j.etran.2024.100384","DOIUrl":"10.1016/j.etran.2024.100384","url":null,"abstract":"<div><div>Advancements in stack cooling via air-cooled radiators for fuel cell (FC) electric vehicles have attracted significant attention. In this study, continuous spray cooling (CTSC) and intermittent spray cooling (IMSC) approaches for FC vehicles were developed at a lab-scale level. Additionally, the thermo-evaporation performance of various IMSC strategies, involving different spray intervals (0–120 s), continuous spray periods (10–60 s), and duty cycles (25–100 %), was investigated. Steady-state analysis revealed that, compared to conventional stack radiators, the CTSC approach using Nozzle#2 achieved superior thermal efficiency (η_th) with an improvement of 36.6–83.8 %, and enhanced spray evaporation efficiency (η_ev) by 18.2–23.9 %. In contrast, Nozzle#1 yielded only a 16.2–52.5 % increase in η_th and an 11.4–18.6 % improvement in η_ev. Compared to CTSC, IMSC extended the low-temperature operating range of the radiator even during the spray-off periods, leading to improved spray evaporation performance. However, excessive coolant exit temperature and heat rejection rate fluctuations were observed at higher spray periods with longer intervals (IMSC-60-60I and IMSC-40-40I) and lower duty cycles (&lt;50 %). On the other hand, the IMSC strategy with shorter intervals and spray periods, i.e., IMSC-30-20I, was identified as optimal, offering a 55.7 % improvement in η_ev compared to CTSC, despite a 2.8 % reduction in η_th. Overall, the optimal IMSC configuration exhibited a 69.4 % higher heat rejection capacity compared to conventional air-cooled stack radiators. Furthermore, variations in η_th were validated using existing correlations, and new empirical correlations for both η_th and air-side heat transfer coefficient were developed, with prediction accuracies of approximately 86 % and 85 %, respectively. Additionally, the radiator's heat transfer area could be reduced by up to 76.2 %, despite a 7.5 % increase in vehicle curb weight. In summary, this study highlights the potential of using IMSC strategies for stack radiators in FC vehicles. The findings provide valuable insights for designing and implementing IMSC-enhanced radiators in real-world applications.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100384"},"PeriodicalIF":15.0,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resource-efficient artificial intelligence for battery capacity estimation using convolutional FlashAttention fusion networks","authors":"Zhilong Lv ,&nbsp;Jingyuan Zhao","doi":"10.1016/j.etran.2024.100383","DOIUrl":"10.1016/j.etran.2024.100383","url":null,"abstract":"<div><div>Accurate battery capacity estimation is crucial for optimizing lifespan and monitoring health conditions. Deep learning has made notable strides in addressing long-standing issues in the artificial intelligence community. However, large AI models often face challenges such as high computational resource consumption, extended training times, and elevated deployment costs. To address these issues, we developed an efficient end-to-end hybrid fusion neural network model. This model combines FlashAttention-2 with local feature extraction through convolutional neural networks (CNNs), significantly reducing memory usage and computational demands while maintaining precise and efficient health estimation. For practical implementation, the model uses only basic parameters, such as voltage and charge, and employs partial charging data (from 80 % SOC to the upper limit voltage) as features, without requiring complex feature engineering. We evaluated the model using three datasets: 77 lithium iron phosphate (LFP) cells, 16 nickel cobalt aluminum (NCA) cells, and 50 nickel cobalt manganese (NCM) oxide cells. For LFP battery health estimation, the model achieved a root mean square error of 0.109 %, a coefficient of determination of 0.99, and a mean absolute percentage error of 0.096 %. Moreover, the proposed convolutional and flash-attention fusion networks deliver an average inference time of 57 milliseconds for health diagnosis across the full battery life cycle (approximately 1898 cycles per cell). The resource-efficient AI (REAI) model operates at an average of 1.36 billion floating point operations per second (FLOPs), with GPU power consumption of 17W and memory usage of 403 MB. This significantly outperforms the Transformer model with vanilla attention. Furthermore, the multi-fusion model proved to be a powerful tool for evaluating capacity in NCA and NCM cells using transfer learning. The results emphasize its ability to reduce computational complexity, energy consumption, and memory usage, while maintaining high accuracy and robust generalization capabilities.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"23 ","pages":"Article 100383"},"PeriodicalIF":15.0,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142699833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}