Etransportation最新文献_第2页

Accurate electrolyte volume of lithium-ion battery via ultrasonic sensing and time-delay neural networks 基于超声传感和延时神经网络的锂离子电池电解液精确体积研究

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-05-01 Epub Date: 2026-01-31 DOI: 10.1016/j.etran.2026.100552

Fangze Zhao , Xuebing Han , Languang Lu , Xiangjun Li , Peng Guo , Lifang Liu , Jianfeng Hua , Yuejiu Zheng , Minggao Ouyang

Electrolyte content is a pivotal determinant of the electrochemical performance and thermal safety of lithium-ion batteries. Yet, current measurement approaches—ranging from destructive offline analyses to expensive nondestructive imaging—suffer from latency, complexity, or insufficient accuracy, limiting their suitability for real-time and high-precision monitoring. Here, we present a nondestructive strategy for electrolyte volume assessment that integrates ultrasonic sensing with deep learning. An acoustic simulation model was first developed to characterize wave propagation in wetted versus unwetted regions, revealing distinct transmission pathways and providing direct validation of the underlying physical mechanism. Ultrasonic measurements on cells with varying filling levels further demonstrated that conventional acoustic features, such as peak amplitude, time-of-flight, and energy, show weak correlations with electrolyte volume. By contrast, ultrasonic imaging clearly captured the progressive shrinkage of wetted regions as electrolyte decreased. Leveraging this insight, a time-delay neural network (TDNN) was employed to extract nonlinear temporal features directly from raw waveforms, while a physics-informed correction—incorporating the prior knowledge that electrolyte reduction leads to shrinkage of wetted regions—was introduced to refine predictions. Experimental validation confirmed that the method achieves a stable prediction error within ±2% and demonstrates strong generalizability across different battery chemistries. This work provides a practical and accurate nondestructive pathway for electrolyte volume determination, offering new opportunities for quality control and health monitoring in lithium-ion batteries.

电解质含量是决定锂离子电池电化学性能和热安全性的关键因素。然而，目前的测量方法——从破坏性的离线分析到昂贵的非破坏性成像——都存在延迟、复杂性或准确性不足的问题，限制了它们对实时和高精度监测的适用性。在这里，我们提出了一种无损的电解质体积评估策略，该策略将超声波传感与深度学习相结合。首先开发了一个声学模拟模型来表征波在湿润区域和非湿润区域的传播，揭示了不同的传播途径，并提供了潜在物理机制的直接验证。超声测量不同填充水平的电池进一步表明，传统的声学特征，如峰值振幅、飞行时间和能量，与电解质体积呈弱相关性。相比之下，超声成像清楚地捕捉到随着电解质的减少，湿区逐渐收缩。利用这一见解，采用延时神经网络（TDNN）直接从原始波形中提取非线性时间特征，同时引入物理校正（结合电解液还原导致湿区收缩的先验知识）来改进预测。实验验证表明，该方法的预测误差稳定在±2%以内，具有很强的通用性，适用于不同的电池化学成分。本研究为电解液体积测定提供了一种实用、准确的无损途径，为锂离子电池的质量控制和健康监测提供了新的机会。

{"title":"Accurate electrolyte volume of lithium-ion battery via ultrasonic sensing and time-delay neural networks","authors":"Fangze Zhao , Xuebing Han , Languang Lu , Xiangjun Li , Peng Guo , Lifang Liu , Jianfeng Hua , Yuejiu Zheng , Minggao Ouyang","doi":"10.1016/j.etran.2026.100552","DOIUrl":"10.1016/j.etran.2026.100552","url":null,"abstract":"<div><div>Electrolyte content is a pivotal determinant of the electrochemical performance and thermal safety of lithium-ion batteries. Yet, current measurement approaches—ranging from destructive offline analyses to expensive nondestructive imaging—suffer from latency, complexity, or insufficient accuracy, limiting their suitability for real-time and high-precision monitoring. Here, we present a nondestructive strategy for electrolyte volume assessment that integrates ultrasonic sensing with deep learning. An acoustic simulation model was first developed to characterize wave propagation in wetted versus unwetted regions, revealing distinct transmission pathways and providing direct validation of the underlying physical mechanism. Ultrasonic measurements on cells with varying filling levels further demonstrated that conventional acoustic features, such as peak amplitude, time-of-flight, and energy, show weak correlations with electrolyte volume. By contrast, ultrasonic imaging clearly captured the progressive shrinkage of wetted regions as electrolyte decreased. Leveraging this insight, a time-delay neural network (TDNN) was employed to extract nonlinear temporal features directly from raw waveforms, while a physics-informed correction—incorporating the prior knowledge that electrolyte reduction leads to shrinkage of wetted regions—was introduced to refine predictions. Experimental validation confirmed that the method achieves a stable prediction error within ±2% and demonstrates strong generalizability across different battery chemistries. This work provides a practical and accurate nondestructive pathway for electrolyte volume determination, offering new opportunities for quality control and health monitoring in lithium-ion batteries.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"28 ","pages":"Article 100552"},"PeriodicalIF":17.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173835","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}

引用次数: 0

Electrical load forecasting for V2G scheduling: A feature-driven multi-head attention-LSTM approach V2G调度的电力负荷预测：一种特征驱动的多头注意力- lstm方法

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-05-01 Epub Date: 2026-02-09 DOI: 10.1016/j.etran.2026.100556

Tianyu Yan , Jiahao Zhong , Ziyun Shao , C.C. Chan , Linni Jian

Electrical load forecasting (ELF) is a critical technology for vehicle-to-grid (V2G) scheduling, as it provides the necessary information to achieve the scheduling objective of minimizing load variance. Existing studies have demonstrated that the closer the relative magnitude relationships among forecasted loads at different time periods are to those of the actual loads, the more satisfactory V2G scheduling performance can be achieved. Inspired by the above conclusion, this paper proposes an ELF approach for V2G scheduling. By calculating the difference between load values at each time period and the daily average, a feature called load relative magnitude (LRM) is constructed to provide relative magnitude relationships between loads for the forecasting model, which is beneficial for enhancing V2G scheduling performance. Moreover, this approach builds a feature-driven multi-head attention-long short-term memory (FDMHA-LSTM) model and the constructed LRM feature is the driver. In particular, given that the multi-head attention (MHA) mechanism can be guided to focus on the key parts of the task, the LRM feature is employed to weight the Key matrix for enhancing prediction accuracy during peak and valley periods, and these periods are particularly important for V2G scheduling performance. Furthermore, extensive experiments on real-world load data demonstrate the effectiveness and superiority of the proposed model. Specifically, the proposed model can boost V2G scheduling performance by 15% to 22.3% under scenarios with varying numbers of EVs compared to LSTM model, and also demonstrates advantages over CNN and compact Transformer baselines.

电力负荷预测是车辆到电网调度的一项关键技术，它为实现负荷变化最小的调度目标提供了必要的信息。已有研究表明，不同时间段的预测负荷之间的相对量级关系与实际负荷之间的相对量级关系越接近，V2G调度性能越好。受上述结论的启发，本文提出了一种用于V2G调度的ELF方法。通过计算各时间段的负荷值与日平均值的差值，构建负荷相对量级（load relative magnitude， LRM）特征，为预测模型提供负荷之间的相对量级关系，有利于提高V2G调度性能。此外，该方法构建了一个特征驱动的多头注意-长短期记忆（FDMHA-LSTM）模型，并以构建的LRM特征为驱动因素。特别是，考虑到多头注意（MHA）机制可以引导人们关注任务的关键部分，我们利用LRM特征对关键矩阵进行加权，以提高峰谷期的预测精度，而峰谷期对V2G调度性能尤为重要。此外，在实际负荷数据上的大量实验证明了所提模型的有效性和优越性。具体来说，与LSTM模型相比，该模型在不同电动汽车数量的场景下可以将V2G调度性能提高15%至22.3%，并且也比CNN和紧凑型Transformer基线具有优势。

{"title":"Electrical load forecasting for V2G scheduling: A feature-driven multi-head attention-LSTM approach","authors":"Tianyu Yan , Jiahao Zhong , Ziyun Shao , C.C. Chan , Linni Jian","doi":"10.1016/j.etran.2026.100556","DOIUrl":"10.1016/j.etran.2026.100556","url":null,"abstract":"<div><div>Electrical load forecasting (ELF) is a critical technology for vehicle-to-grid (V2G) scheduling, as it provides the necessary information to achieve the scheduling objective of minimizing load variance. Existing studies have demonstrated that the closer the relative magnitude relationships among forecasted loads at different time periods are to those of the actual loads, the more satisfactory V2G scheduling performance can be achieved. Inspired by the above conclusion, this paper proposes an ELF approach for V2G scheduling. By calculating the difference between load values at each time period and the daily average, a feature called load relative magnitude (LRM) is constructed to provide relative magnitude relationships between loads for the forecasting model, which is beneficial for enhancing V2G scheduling performance. Moreover, this approach builds a feature-driven multi-head attention-long short-term memory (FDMHA-LSTM) model and the constructed LRM feature is the driver. In particular, given that the multi-head attention (MHA) mechanism can be guided to focus on the key parts of the task, the LRM feature is employed to weight the Key matrix for enhancing prediction accuracy during peak and valley periods, and these periods are particularly important for V2G scheduling performance. Furthermore, extensive experiments on real-world load data demonstrate the effectiveness and superiority of the proposed model. Specifically, the proposed model can boost V2G scheduling performance by 15% to 22.3% under scenarios with varying numbers of EVs compared to LSTM model, and also demonstrates advantages over CNN and compact Transformer baselines.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"28 ","pages":"Article 100556"},"PeriodicalIF":17.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173832","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}

引用次数: 0

Cooperative scheduling for multi-fleet battery swapping in electrified mines: A simulation-based optimization approach 电气化矿山多机队电池交换协同调度：一种基于仿真的优化方法

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-05-01 Epub Date: 2026-02-04 DOI: 10.1016/j.etran.2026.100562

Honghui Zou , Kaiqi Zhao , Yanli Liu , Ronghui Zhang , Xiaolei Ma

Global carbon reduction policies have accelerated the electrification transition in open-pit mine. To meet the continuous operational demands of mining truck fleets, the battery swapping (BS) mode has emerged as an efficient solution. This study investigates cooperative scheduling of multiple fleets in an open-pit mining system equipped with distributed BS stations and centralized charging facilities, including electric mining trucks and battery delivery vehicles. An innovative discrete event simulation (DES)-based optimization framework is proposed, which leverages the controllability of BS demand and battery supply to coordinate supply- and demand-side operations, thereby unlocking potential efficiencies and deriving an optimal scheduling scheme for mining truck operation, BS activities, and battery logistics. A DES model is developed to simulate the interactions among heterogeneous fleets, various resources and facilities, as well as cascading delays induced by queuing in the operational, BS, and battery pickup processes. Furthermore, the DES model is also employed as a repair tool to rapidly correct infeasible solutions. To address the curse of dimensionality inherent in simulation-based optimization, we propose the non-dominated sorting population-based large neighborhood search (NSPLNS) algorithm, which integrates the advantages of population-based multi-objective search and individual-directed enhancement. A series of customized operators tailored to improving the quality of solutions are designed, and parallel simulations to enhance algorithmic efficiency are explicitly incorporated into the algorithm. A real-world case study from Inner Mongolia, China, is used to evaluate the proposed framework and algorithm. Numerical experiments analyze algorithm performance, the impact of customized operators, and conduct sensitivity analyses. Numerical results demonstrate that the proposed model and algorithm enhance the operational economics by maximizing profit, and improve BS efficiency by minimizing queueing and BS time. The source code of this study is publicly available at: https://github.com/HonghuiZou/NSPLNS.

全球碳减排政策加速了露天矿的电气化转型。为了满足矿用卡车车队的持续运行需求，电池交换（BS）模式成为一种有效的解决方案。本文研究了露天采矿系统中多个车队的协同调度问题，该系统配备分布式BS站和集中式充电设施，包括电动矿用卡车和电池配送车。提出了一种创新的基于离散事件模拟（DES）的优化框架，利用BS需求和电池供应的可控性来协调供需侧操作，从而释放潜在的效率，并得出采矿卡车操作、BS活动和电池物流的最优调度方案。开发了一个DES模型来模拟异构车队、各种资源和设施之间的相互作用，以及在操作、BS和电池拾取过程中排队引起的级联延迟。此外，DES模型还可以作为一种修复工具来快速纠正不可行的解。为了解决基于仿真的优化中固有的维数问题，我们提出了基于非支配排序的基于种群的大邻域搜索（NSPLNS）算法，该算法融合了基于种群的多目标搜索和个体定向增强的优点。设计了一系列为提高求解质量而量身定制的算子，并在算法中明确加入了并行仿真以提高算法效率。最后，以中国内蒙古的一个实际案例对所提出的框架和算法进行了评估。数值实验分析算法性能、定制算子的影响，并进行敏感性分析。数值计算结果表明，该模型和算法以利润最大化来提高运营经济性，以最小化排队和最小化BS时间来提高BS效率。这项研究的源代码可以在https://github.com/HonghuiZou/NSPLNS上公开获得。

{"title":"Cooperative scheduling for multi-fleet battery swapping in electrified mines: A simulation-based optimization approach","authors":"Honghui Zou , Kaiqi Zhao , Yanli Liu , Ronghui Zhang , Xiaolei Ma","doi":"10.1016/j.etran.2026.100562","DOIUrl":"10.1016/j.etran.2026.100562","url":null,"abstract":"<div><div>Global carbon reduction policies have accelerated the electrification transition in open-pit mine. To meet the continuous operational demands of mining truck fleets, the battery swapping (BS) mode has emerged as an efficient solution. This study investigates cooperative scheduling of multiple fleets in an open-pit mining system equipped with distributed BS stations and centralized charging facilities, including electric mining trucks and battery delivery vehicles. An innovative discrete event simulation (DES)-based optimization framework is proposed, which leverages the controllability of BS demand and battery supply to coordinate supply- and demand-side operations, thereby unlocking potential efficiencies and deriving an optimal scheduling scheme for mining truck operation, BS activities, and battery logistics. A DES model is developed to simulate the interactions among heterogeneous fleets, various resources and facilities, as well as cascading delays induced by queuing in the operational, BS, and battery pickup processes. Furthermore, the DES model is also employed as a repair tool to rapidly correct infeasible solutions. To address the curse of dimensionality inherent in simulation-based optimization, we propose the non-dominated sorting population-based large neighborhood search (NSPLNS) algorithm, which integrates the advantages of population-based multi-objective search and individual-directed enhancement. A series of customized operators tailored to improving the quality of solutions are designed, and parallel simulations to enhance algorithmic efficiency are explicitly incorporated into the algorithm. A real-world case study from Inner Mongolia, China, is used to evaluate the proposed framework and algorithm. Numerical experiments analyze algorithm performance, the impact of customized operators, and conduct sensitivity analyses. Numerical results demonstrate that the proposed model and algorithm enhance the operational economics by maximizing profit, and improve BS efficiency by minimizing queueing and BS time. The source code of this study is publicly available at: <span><span>https://github.com/HonghuiZou/NSPLNS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"28 ","pages":"Article 100562"},"PeriodicalIF":17.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173834","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}

引用次数: 0

Visualizing electrolyte dynamics and monitoring salt concentration to improve commercial Si-based Li-ion batteries 可视化电解质动态和监测盐浓度，以改善商用硅基锂离子电池

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-05-01 Epub Date: 2026-01-28 DOI: 10.1016/j.etran.2026.100554

Nilanka M. Keppetipola , Clémence Alphen , Marina-Lamprini Vlara , Christoph Stangl , Christophe Caucheteur , Ozlem Sel , Jean-Marie Tarascon

The race for Li-ion batteries with higher energy density has led researchers toward Si-rich/Carbon composites, though their >200 % volume change induces strong electrolyte dynamics. The challenge is therefore to understand how this electrolyte dynamics contributes to cell formation and degradation under real operating conditions. Herein, we answer this question by combining optical calorimetry, and use of multiplexed tilted fiber Bragg grating sensors (TFBGs), to monitor electrolyte motion and Li-ion concentration gradient within a cell. For proof of concept, we used 21700 cylindrical prototype cells based on either graphite or SiC composite as negative electrode. We found a continuous and irreversible heat generation associated with the solid electrolyte interphase (SEI) formation throughout the entire charging process for SiC, unlike graphite-based cells. In addition, we provided evidence of reversible changes in hydrostatic pressure in SiC cells during cycling, related to the real-time movement of the electrolyte. Interestingly, the concomitant expansion-contraction and electrolyte movement caused depletion and inhomogeneous LiPF₆ concentration, with nearly 35 % in the bottom area and 10 % in the middle area of the cell mandrel after 100 cycles. These insights, obtained through operando optical detection of cylindrical cells, should be of great help to battery manufacturers in streamlining formation protocols and reducing manufacturing costs.

对具有更高能量密度的锂离子电池的竞争使研究人员转向了富硅/碳复合材料，尽管它们200%的体积变化会引起强烈的电解质动力学。因此，挑战在于了解这种电解质动力学如何在实际操作条件下促进电池的形成和降解。在这里，我们通过结合光学量热法和使用多路倾斜光纤布拉格光栅传感器（tfbg）来监测电池内的电解质运动和锂离子浓度梯度来回答这个问题。为了验证概念，我们使用了21700个基于石墨或SiC复合材料的圆柱形原型电池作为负极。我们发现，与石墨基电池不同，在整个充电过程中，与SiC固体电解质间相（SEI）形成相关的连续且不可逆的热量产生贯穿于整个充电过程。此外，我们提供的证据表明，在循环过程中，SiC电池中的静水压力发生了可逆的变化，这与电解质的实时运动有关。有趣的是，伴随的膨胀-收缩和电解质运动导致了LiPF6浓度的耗竭和不均匀，在100次循环后，电池芯轴底部区域的LiPF6浓度接近35%，中间区域的LiPF6浓度接近10%。通过对圆柱形电池的操作光学检测获得的这些见解，应该对电池制造商简化形成协议和降低制造成本有很大帮助。

{"title":"Visualizing electrolyte dynamics and monitoring salt concentration to improve commercial Si-based Li-ion batteries","authors":"Nilanka M. Keppetipola , Clémence Alphen , Marina-Lamprini Vlara , Christoph Stangl , Christophe Caucheteur , Ozlem Sel , Jean-Marie Tarascon","doi":"10.1016/j.etran.2026.100554","DOIUrl":"10.1016/j.etran.2026.100554","url":null,"abstract":"<div><div>The race for Li-ion batteries with higher energy density has led researchers toward Si-rich/Carbon composites, though their >200 % volume change induces strong electrolyte dynamics. The challenge is therefore to understand how this electrolyte dynamics contributes to cell formation and degradation under real operating conditions. Herein, we answer this question by combining optical calorimetry, and use of multiplexed tilted fiber Bragg grating sensors (TFBGs), to monitor electrolyte motion and Li-ion concentration gradient within a cell. For proof of concept, we used 21700 cylindrical prototype cells based on either graphite or SiC composite as negative electrode. We found a continuous and irreversible heat generation associated with the solid electrolyte interphase (SEI) formation throughout the entire charging process for SiC, unlike graphite-based cells. In addition, we provided evidence of reversible changes in hydrostatic pressure in SiC cells during cycling, related to the real-time movement of the electrolyte. Interestingly, the concomitant expansion-contraction and electrolyte movement caused depletion and inhomogeneous LiPF<sub>6</sub> concentration, with nearly 35 % in the bottom area and 10 % in the middle area of the cell mandrel after 100 cycles. These insights, obtained through <em>operando</em> optical detection of cylindrical cells, should be of great help to battery manufacturers in streamlining formation protocols and reducing manufacturing costs.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"28 ","pages":"Article 100554"},"PeriodicalIF":17.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173833","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}

引用次数: 0

The multifunctional organic phase change materials for battery thermal safety in electric transportation systems: A critical review 用于电力运输系统电池热安全的多功能有机相变材料：综述

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-05-01 Epub Date: 2026-02-03 DOI: 10.1016/j.etran.2026.100558

Xinxi Li , Beiwen Liang , Jian Deng , Wensheng Yang , Qiqiu Huang , Ziyu Huang , Gengfeng Zhao , Shuyao Li , Zikai Guo , Jianzhe Liu , Canbing Li

Electric transportation systems are great alternatives to conventional fossil-fuel-powered transportation systems. The thermal safety of high-energy-density lithium-ion batteries (LIBs), which are the main energy source in electric transportation systems, is one of the most major challenges facing the applications of these systems. Phase change material (PCM)-based battery thermal management systems are an effective solution for battery thermal safety, and they have a great application potential. However, the thermal safety of LIBs involves thermal management and thermal runaway protection, which require composite PCMs (CPCMs) with excellent thermal management cooling effect and stable thermal runaway protection capability. Thus, the optimizing strategies used for enhancing the structural stability, thermal conductivity, and flame retardancy of CPCMs were compared and analyzed. Moreover, the design of PCMs with thermal management and thermal-runaway-flame-retardant suppression capabilities was discussed. Finally, future research directions for using multifunctional PCMs in battery thermal safety systems were proposed based on critical thinking. This review will provide new insights and attract considerable attention to the reliability of thermal safety systems based on multifunctional PCMs in future designs, especially in the field of battery thermal safety.

电力运输系统是传统化石燃料动力运输系统的绝佳替代品。作为电动交通系统的主要能源，高能量密度锂离子电池（LIBs）的热安全性是其应用面临的最大挑战之一。基于相变材料（PCM）的电池热管理系统是解决电池热安全的有效方法，具有很大的应用潜力。然而，锂离子电池的热安全涉及热管理和热失控保护，这需要具有优异热管理冷却效果和稳定热失控保护能力的复合pccm （cpcm）。因此，比较和分析了用于提高cpcm结构稳定性、导热性和阻燃性的优化策略。此外，还讨论了具有热管理和热失控阻燃抑制能力的pcm的设计。最后，提出了基于批判性思维的多功能pcm在电池热安全系统中的未来研究方向。这一综述将为基于多功能pcm的热安全系统的可靠性提供新的见解，并在未来的设计中引起人们的重视，特别是在电池热安全领域。

{"title":"The multifunctional organic phase change materials for battery thermal safety in electric transportation systems: A critical review","authors":"Xinxi Li , Beiwen Liang , Jian Deng , Wensheng Yang , Qiqiu Huang , Ziyu Huang , Gengfeng Zhao , Shuyao Li , Zikai Guo , Jianzhe Liu , Canbing Li","doi":"10.1016/j.etran.2026.100558","DOIUrl":"10.1016/j.etran.2026.100558","url":null,"abstract":"<div><div>Electric transportation systems are great alternatives to conventional fossil-fuel-powered transportation systems. The thermal safety of high-energy-density lithium-ion batteries (LIBs), which are the main energy source in electric transportation systems, is one of the most major challenges facing the applications of these systems. Phase change material (PCM)-based battery thermal management systems are an effective solution for battery thermal safety, and they have a great application potential. However, the thermal safety of LIBs involves thermal management and thermal runaway protection, which require composite PCMs (CPCMs) with excellent thermal management cooling effect and stable thermal runaway protection capability. Thus, the optimizing strategies used for enhancing the structural stability, thermal conductivity, and flame retardancy of CPCMs were compared and analyzed. Moreover, the design of PCMs with thermal management and thermal-runaway-flame-retardant suppression capabilities was discussed. Finally, future research directions for using multifunctional PCMs in battery thermal safety systems were proposed based on critical thinking. This review will provide new insights and attract considerable attention to the reliability of thermal safety systems based on multifunctional PCMs in future designs, especially in the field of battery thermal safety.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"28 ","pages":"Article 100558"},"PeriodicalIF":17.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173841","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}

引用次数: 0

Exploiting physics-knowledge from unlabeled data to enhance battery lifetime prediction 利用未标记数据中的物理知识来增强电池寿命预测

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-05-01 Epub Date: 2026-01-29 DOI: 10.1016/j.etran.2026.100560

Aihua Tang , Yuehan Li , Jinpeng Tian , Quanqing Yu , Ning Yu , Yuchen Xu

Accurately predicting battery lifetime is essential for ensuring the long-term operation of electrochemical energy storage systems. While machine learning has provided promising solutions, its performance degrades significantly in the absence of sufficient full-life degradation data on which it heavily depends. In this study, although direct acquisition of remaining useful life and cycles to knee-point labels from battery degradation data without reaching end-of-life is infeasible, valuable physics-related degradation knowledge can still be extracted from such incomplete data to enhance lifetime prediction. Accordingly, a physics-knowledge guided lifetime prediction method is proposed to utilize one-cycle constant-current curve to jointly predict remaining useful life and cycles to knee-point. More critically, this method can implicitly guide convolutional neural network training with incremental capacity knowledge obtained from incomplete-lifespan degradation data. This yields a pre-trained model that can be rapidly adapted using only a few remaining useful life and cycles to knee-point labels. The validity of the proposed method has been extensively validated on three full-lifespan degradation datasets comprising over 40,000 samples. The validation results show that by using only 10 % of the lifetime labels from the samples, the proposed method can achieve prediction with an error of less than 21 cycles on cells with the end-of-life distribution of 100–500 cycles, which reduces the error by more than 50 % compared with the traditional method. In conclusion, this study emphasizes the prospect of enhancing battery lifetime prediction through physics-knowledge in rare-label cases.

准确预测电池寿命是保证电化学储能系统长期运行的关键。虽然机器学习提供了很有前途的解决方案，但在缺乏足够的全寿命退化数据的情况下，它的性能会显著下降，而这正是机器学习所依赖的。在本研究中，虽然在未达到寿命终止的情况下，从电池退化数据中直接获取剩余使用寿命和循环到膝点标签是不可行的，但仍然可以从这些不完整的数据中提取有价值的与物理相关的退化知识，以增强寿命预测。据此，提出了一种物理知识指导下的寿命预测方法，利用单周期恒流曲线联合预测剩余使用寿命和到膝点的周期。更关键的是，该方法可以隐式地指导卷积神经网络训练，使用从不完全寿命退化数据中获得的增量容量知识。这就产生了一个预训练的模型，该模型可以使用少量剩余的使用寿命和周期来快速适应膝点标签。所提出方法的有效性已在包含超过40,000个样本的三个全寿命退化数据集上得到广泛验证。验证结果表明，该方法仅使用样本中10%的寿命标签，就能对寿命终止分布在100-500个周期的细胞实现误差小于21个周期的预测，与传统方法相比，误差降低了50%以上。总之，这项研究强调了在罕见情况下通过物理知识增强电池寿命预测的前景。

{"title":"Exploiting physics-knowledge from unlabeled data to enhance battery lifetime prediction","authors":"Aihua Tang , Yuehan Li , Jinpeng Tian , Quanqing Yu , Ning Yu , Yuchen Xu","doi":"10.1016/j.etran.2026.100560","DOIUrl":"10.1016/j.etran.2026.100560","url":null,"abstract":"<div><div>Accurately predicting battery lifetime is essential for ensuring the long-term operation of electrochemical energy storage systems. While machine learning has provided promising solutions, its performance degrades significantly in the absence of sufficient full-life degradation data on which it heavily depends. In this study, although direct acquisition of remaining useful life and cycles to knee-point labels from battery degradation data without reaching end-of-life is infeasible, valuable physics-related degradation knowledge can still be extracted from such incomplete data to enhance lifetime prediction. Accordingly, a physics-knowledge guided lifetime prediction method is proposed to utilize one-cycle constant-current curve to jointly predict remaining useful life and cycles to knee-point. More critically, this method can implicitly guide convolutional neural network training with incremental capacity knowledge obtained from incomplete-lifespan degradation data. This yields a pre-trained model that can be rapidly adapted using only a few remaining useful life and cycles to knee-point labels. The validity of the proposed method has been extensively validated on three full-lifespan degradation datasets comprising over 40,000 samples. The validation results show that by using only 10 % of the lifetime labels from the samples, the proposed method can achieve prediction with an error of less than 21 cycles on cells with the end-of-life distribution of 100–500 cycles, which reduces the error by more than 50 % compared with the traditional method. In conclusion, this study emphasizes the prospect of enhancing battery lifetime prediction through physics-knowledge in rare-label cases.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"28 ","pages":"Article 100560"},"PeriodicalIF":17.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080680","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}

引用次数: 0

Quantification and forecasting of reserve capacity from electric trains 电力列车备用容量的量化与预测

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-01-01 Epub Date: 2025-12-08 DOI: 10.1016/j.etran.2025.100524

Agnes Nakiganda , Martin Lindahl , Callum Henderson , Agustí Egea-Àlvarez , Lars Herre

This paper explores the quantification and forecasting of reserve capacity from electric trains for participation in power system ancillary service markets. We first map train electricity consumption – traction and non-traction – to suitable reserve products, considering operational and regulatory constraints. Using historical data from the Danish railway operator DSB, we estimate the available flexibility for frequency containment reserves, focusing on controllable non-traction loads such as heating and air conditioning. To support market participation, we develop a low-resolution stochastic forecasting model based on conformal prediction, capable of estimating reserve availability for both day-ahead and hour-ahead horizons. Results show that a fleet of approximately 60 active trains can provide up to 10 MW of downward regulation and 1.5 MW of upward regulation from non-traction loads. Additionally, traction power from 25 trains can provide up to 5 MW of upward reserve in certain time periods. The findings demonstrate a viable pathway for integrating electric trains into flexibility markets, offering new revenue opportunities for operators and enhancing grid stability.

本文探讨了参与电力系统辅助服务市场的电力列车备用容量的量化与预测。我们首先将列车电力消耗（牵引和非牵引）映射到合适的储备产品，考虑运营和监管约束。利用丹麦铁路运营商DSB的历史数据，我们估计了频率控制储备的可用灵活性，重点关注供暖和空调等可控非牵引负荷。为了支持市场参与，我们开发了一个基于适形预测的低分辨率随机预测模型，能够估计前一天和一小时前的储备可用性。结果表明，一个由大约60列现役列车组成的车队可以提供高达10兆瓦的下行调节和1.5兆瓦的非牵引负载上行调节。此外，25列火车的牵引动力可以在特定时间段提供高达5兆瓦的上行储备。研究结果为将电动列车整合到灵活的市场提供了一条可行的途径，为运营商提供了新的收入机会，并提高了电网的稳定性。

{"title":"Quantification and forecasting of reserve capacity from electric trains","authors":"Agnes Nakiganda , Martin Lindahl , Callum Henderson , Agustí Egea-Àlvarez , Lars Herre","doi":"10.1016/j.etran.2025.100524","DOIUrl":"10.1016/j.etran.2025.100524","url":null,"abstract":"<div><div>This paper explores the quantification and forecasting of reserve capacity from electric trains for participation in power system ancillary service markets. We first map train electricity consumption – traction and non-traction – to suitable reserve products, considering operational and regulatory constraints. Using historical data from the Danish railway operator DSB, we estimate the available flexibility for frequency containment reserves, focusing on controllable non-traction loads such as heating and air conditioning. To support market participation, we develop a low-resolution stochastic forecasting model based on conformal prediction, capable of estimating reserve availability for both day-ahead and hour-ahead horizons. Results show that a fleet of approximately 60 active trains can provide up to 10MW of downward regulation and 1.5MW of upward regulation from non-traction loads. Additionally, traction power from 25 trains can provide up to 5MW of upward reserve in certain time periods. The findings demonstrate a viable pathway for integrating electric trains into flexibility markets, offering new revenue opportunities for operators and enhancing grid stability.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"27 ","pages":"Article 100524"},"PeriodicalIF":17.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839480","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}

引用次数: 0

Online energy management strategy for fuel cell hybrid powertrain based on multi-objective constraint rules embedded in soft actor-critic learning 基于软actor- critical学习的多目标约束规则的燃料电池混合动力在线能量管理策略

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-01-01 Epub Date: 2025-12-23 DOI: 10.1016/j.etran.2025.100532

Baobao Hu , Zhiguo Qu , Jianfei Zhang , Pingwen Ming

The fuel cell/battery hybrid powertrain offers a promising solution for fuel cell vehicles by integrating the high energy density of hydrogen fuel cells with the high-power density of batteries. However, real-time energy management of such a multi-source system faces challenges in simultaneously achieving economic efficiency, durability, and adaptability. To address this, this study proposes an online energy management strategy called MOCR-SAC. It incorporates multi-objective constraint rules (including hydrogen consumption, fuel cell degradation, battery degradation, fuel cell optimal efficiency deviation, and battery optimal state of charge deviation) within a Soft Actor-Critic reinforcement learning framework, enabling adaptive and intelligent power allocation. Evaluated on a 12-m fuel cell bus under standard Chinese driving cycles, MOCR-SAC reduces hydrogen consumption by at least 4.28 % and operating costs by 7.32 % compared to conventional SAC (without constraints or using single rules). It also outperforms other online reinforcement learning methods in component degradation, cost, battery SOC regulation, and hydrogen economy. Compared to the global optimum obtained by dynamic programming, its operating cost deviation remains within 4.50 %, while hydrogen consumption is 5.63 % lower. Under both deterministic and uncertain driving cycles, the total operating cost deviates by less than 10 %, demonstrating strong robustness and adaptability. The proposed strategy can be pre-trained offline and deployed online with minimal computational overhead, meeting the real-time requirements of vehicle energy management. In summary, MOCR-SAC significantly enhances the performance, efficiency, and durability of fuel cell hybrid powertrains, offering a practical and scalable solution for sustainable transportation.

燃料电池/电池混合动力系统通过将氢燃料电池的高能量密度与电池的高功率密度相结合，为燃料电池汽车提供了一个很有前途的解决方案。然而，这种多源系统的实时能源管理面临着同时实现经济效率、耐用性和适应性的挑战。为了解决这个问题，本研究提出了一种名为MOCR-SAC的在线能源管理策略。它将多目标约束规则（包括氢气消耗、燃料电池退化、电池退化、燃料电池最佳效率偏差和电池最佳充电状态偏差）纳入软行为者-评论家强化学习框架中，实现自适应和智能功率分配。在中国标准驾驶循环下对一辆12米燃料电池公交车进行的评估显示，与传统SAC（无约束或使用单一规则）相比，MOCR-SAC至少减少了4.28%的氢消耗和7.32%的运营成本。它在组件降解、成本、电池SOC调节和氢经济性方面也优于其他在线强化学习方法。与动态规划的全局最优方案相比，其运行成本偏差在4.50%以内，耗氢量降低5.63%。在确定性和不确定性工况下，总运行成本偏差均小于10%，具有较强的鲁棒性和适应性。该策略能够以最小的计算开销进行离线预训练和在线部署，满足车辆能量管理的实时性要求。总之，MOCR-SAC显著提高了燃料电池混合动力系统的性能、效率和耐用性，为可持续交通提供了实用且可扩展的解决方案。

{"title":"Online energy management strategy for fuel cell hybrid powertrain based on multi-objective constraint rules embedded in soft actor-critic learning","authors":"Baobao Hu , Zhiguo Qu , Jianfei Zhang , Pingwen Ming","doi":"10.1016/j.etran.2025.100532","DOIUrl":"10.1016/j.etran.2025.100532","url":null,"abstract":"<div><div>The fuel cell/battery hybrid powertrain offers a promising solution for fuel cell vehicles by integrating the high energy density of hydrogen fuel cells with the high-power density of batteries. However, real-time energy management of such a multi-source system faces challenges in simultaneously achieving economic efficiency, durability, and adaptability. To address this, this study proposes an online energy management strategy called MOCR-SAC. It incorporates multi-objective constraint rules (including hydrogen consumption, fuel cell degradation, battery degradation, fuel cell optimal efficiency deviation, and battery optimal state of charge deviation) within a Soft Actor-Critic reinforcement learning framework, enabling adaptive and intelligent power allocation. Evaluated on a 12-m fuel cell bus under standard Chinese driving cycles, MOCR-SAC reduces hydrogen consumption by at least 4.28 % and operating costs by 7.32 % compared to conventional SAC (without constraints or using single rules). It also outperforms other online reinforcement learning methods in component degradation, cost, battery <em>SOC</em> regulation, and hydrogen economy. Compared to the global optimum obtained by dynamic programming, its operating cost deviation remains within 4.50 %, while hydrogen consumption is 5.63 % lower. Under both deterministic and uncertain driving cycles, the total operating cost deviates by less than 10 %, demonstrating strong robustness and adaptability. The proposed strategy can be pre-trained offline and deployed online with minimal computational overhead, meeting the real-time requirements of vehicle energy management. In summary, MOCR-SAC significantly enhances the performance, efficiency, and durability of fuel cell hybrid powertrains, offering a practical and scalable solution for sustainable transportation.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"27 ","pages":"Article 100532"},"PeriodicalIF":17.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839478","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}

引用次数: 0

Lab-to-field gap in battery aging studies: Mismatch of operating conditions between laboratory environments and real-world automotive applications 电池老化研究中的实验室到现场差距：实验室环境和实际汽车应用之间的操作条件不匹配

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-01-01 Epub Date: 2025-11-29 DOI: 10.1016/j.etran.2025.100518

Markus Schreiber, Lukas Leonard Köning, Georg Balke, Kareem Abo Gamra, Jonas Kayl, Brian Dietermann, Raphael Urban, Cristina Grosu, Markus Lienkamp

In response to the growing demand for electric vehicles, ensuring the longevity of traction batteries has become a central focus of scientific research. While most aging studies rely on accelerated aging testing with tightened stress factors, real-world battery operation reveals fundamentally different load profiles and aging conditions. To disclose the gap between the laboratory and the real-world application, we collected and assessed almost 2600 stress factor combinations from 201 different calendar and cycle aging studies. Moreover, we gathered and analyzed vehicle data from over 72 000 km of everyday usage of seven vehicles in public road traffic in Germany and extracted the related battery-specific load spectra. The stress factor combinations chosen in the literature show a trend towards high temperatures and state of charges (SOCs) during storage in calendar aging studies. In contrast, cycle aging tests are predominantly performed at full depth of discharge (DOD) or elevated average SOC levels, with current rates of primarily

\pm 1 C

at 25 °C or slightly elevated temperatures. Contrary to this, the field data analysis reveals the following main findings: Driving events rarely exceed 30 km in distance or 40 min in duration, with an average driving speed of 61.1 km h

^{- 1}

. This leads to average current rates of

-

0.2 C in discharging and 0.1 C in charging direction and average cycle depths of less than 30%, while the average battery pack temperature ranges around 17 °C. Comparing laboratory test conditions with stress conditions in field applications reveals three major discrepancies: First, the stress levels applied are substantially higher than the stresses acting in real-world operation. Second, the dynamic load characteristic of real-world vehicle operation is rarely reflected; most studies work with synthetic constant current load cycles. Third, intermediate rest periods, which are predominant in real-world use, are omitted in most studies. This raises concerns about the transferability and applicability of findings from accelerated aging tests to automotive real-world applications.

为了应对日益增长的电动汽车需求，确保牵引电池的寿命已成为科学研究的中心焦点。虽然大多数老化研究依赖于收紧应力因素的加速老化测试，但实际电池运行显示出完全不同的负载分布和老化条件。为了揭示实验室与实际应用之间的差距，我们收集并评估了来自201个不同日历和周期衰老研究的近2600个压力因子组合。此外，我们收集并分析了7辆汽车在德国公共道路交通中超过72000公里的日常使用数据，并提取了相关的电池特定负载谱。在历法老化研究中，文献中选择的应力因子组合显示了在储存过程中高温和电荷状态（soc）的趋势。相比之下，循环老化测试主要在全放电深度（DOD）或平均SOC水平升高的情况下进行，在25°C或稍微升高的温度下，当前速率主要为±1C。与此相反，现场数据分析揭示了以下主要发现：驾驶事件的距离很少超过30公里或持续时间超过40分钟，平均驾驶速度为61.1 km h−1。这导致放电时的平均电流率为- 0.2 C，充电时的平均电流率为0.1 C，平均循环深度小于30%，而电池组的平均温度范围在17°C左右。将实验室测试条件与现场应用的应力条件进行比较，可以发现三个主要差异：首先，所施加的应力水平大大高于实际操作中的应力水平。二是实际车辆运行的动载荷特性很少得到体现；大多数研究都是在合成恒流负载循环下进行的。第三，大多数研究忽略了在实际应用中占主导地位的中间休息期。这引起了人们对加速老化试验结果在汽车实际应用中的可转移性和适用性的关注。

{"title":"Lab-to-field gap in battery aging studies: Mismatch of operating conditions between laboratory environments and real-world automotive applications","authors":"Markus Schreiber, Lukas Leonard Köning, Georg Balke, Kareem Abo Gamra, Jonas Kayl, Brian Dietermann, Raphael Urban, Cristina Grosu, Markus Lienkamp","doi":"10.1016/j.etran.2025.100518","DOIUrl":"10.1016/j.etran.2025.100518","url":null,"abstract":"<div><div>In response to the growing demand for electric vehicles, ensuring the longevity of traction batteries has become a central focus of scientific research. While most aging studies rely on accelerated aging testing with tightened stress factors, real-world battery operation reveals fundamentally different load profiles and aging conditions. To disclose the gap between the laboratory and the real-world application, we collected and assessed almost 2600 stress factor combinations from 201 different calendar and cycle aging studies. Moreover, we gathered and analyzed vehicle data from over 72000 km of everyday usage of seven vehicles in public road traffic in Germany and extracted the related battery-specific load spectra. The stress factor combinations chosen in the literature show a trend towards high temperatures and state of charges (SOCs) during storage in calendar aging studies. In contrast, cycle aging tests are predominantly performed at full depth of discharge (DOD) or elevated average SOC levels, with current rates of primarily <span><math><mrow><mo>±</mo><mn>1</mn><mspace></mspace><mtext>C</mtext></mrow></math></span> at 25°C or slightly elevated temperatures. Contrary to this, the field data analysis reveals the following main findings: Driving events rarely exceed 30km in distance or 40min in duration, with an average driving speed of 61.1 km h<span><math><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></math></span>. This leads to average current rates of <span><math><mo>−</mo></math></span>0.2 C in discharging and 0.1 C in charging direction and average cycle depths of less than 30%, while the average battery pack temperature ranges around 17°C. Comparing laboratory test conditions with stress conditions in field applications reveals three major discrepancies: First, the stress levels applied are substantially higher than the stresses acting in real-world operation. Second, the dynamic load characteristic of real-world vehicle operation is rarely reflected; most studies work with synthetic constant current load cycles. Third, intermediate rest periods, which are predominant in real-world use, are omitted in most studies. This raises concerns about the transferability and applicability of findings from accelerated aging tests to automotive real-world applications.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"27 ","pages":"Article 100518"},"PeriodicalIF":17.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839482","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}

引用次数: 0

Real-time AI-enabled digital twin for battery health estimation and fast charging using partial-discharge data 实时人工智能数字孪生，用于电池健康评估和使用部分放电数据的快速充电

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation

Pub Date : 2026-01-01 Epub Date: 2025-12-13 DOI: 10.1016/j.etran.2025.100528

Mohammad Qasem, Jeff Stubblefield, Moath Qandil, Yazan Yassin, Mariana Haddadin, Mahesh Krishnamurthy

Digital twin technology has emerged as a promising approach for integrating multi-physics models in real-time to optimize the operation of electric vehicles (EVs) and electric vertical take-off and landing (eVTOLs), particularly in terms of battery performance. However, the mitigation of dynamic lithium plating and solid electrolyte interphase (SEI) growth during fast charging remains unaddressed in current studies. This paper proposes an AI-enabled digital twin that uses partial-discharge data, data from incomplete discharge cycles, for real-time battery-health estimation and couples this insight with an age-aware fast-charging controller that adaptively controls the charging current to mitigate lithium plating and SEI growth. The experimental results demonstrated the framework’s robustness across varying ambient temperatures and initial state of charge (SoC) conditions. A novel real-time estimation model within the framework achieved a root mean square error (RMSE) of less than 0.5% and 0.4% for both battery capacity and internal resistance. Additionally, the proposed framework preserved battery capacity of 87.6% at 25 °

C

compared to 81.4% and 64.3% for MCC-CV and CC-CV, respectively, representing relative improvements of +7.6% and +36.2% over MCC-CV and CC-CV, respectively. This approach helped mitigate battery side reactions during fast charging, while it reduced the time required to reach 80% SoC to less than 25 min, which was 28.6% faster than MCC-CV (35 min) and 35.9% faster than CC-CV (39 min) after 200 cycles. These results support practical deployment in embedded BMS and EV/eVTOL charging to enhance safety, reduce plating risk, and extend service life.

数字孪生技术已经成为一种很有前途的方法，可以实时集成多物理场模型，以优化电动汽车（ev）和电动垂直起降（evtol）的运行，特别是在电池性能方面。然而，在目前的研究中，快速充电过程中动态镀锂和固体电解质间相（SEI）生长的减缓仍未得到解决。本文提出了一种支持人工智能的数字孪生，它使用部分放电数据（来自不完整放电周期的数据）进行实时电池健康估计，并将这种洞察力与年龄感知快速充电控制器相结合，该控制器可自适应控制充电电流，以减轻锂电镀和SEI增长。实验结果表明，该框架在不同的环境温度和初始充电状态（SoC）条件下具有鲁棒性。在该框架内，一种新的实时估计模型实现了电池容量和内阻的均方根误差（RMSE）分别小于0.5%和0.4%。此外，与MCC-CV和CC-CV分别为81.4%和64.3%相比，该框架在25°C下保留了87.6%的电池容量，比MCC-CV和CC-CV分别提高了+7.6%和+36.2%。这种方法有助于减轻电池在快速充电过程中的副反应，同时将达到80% SoC所需的时间缩短到25分钟以内，在200次循环后，比mc - cv（35分钟）快28.6%，比CC-CV（39分钟）快35.9%。这些结果支持嵌入式BMS和EV/eVTOL充电的实际部署，以提高安全性，降低电镀风险并延长使用寿命。

{"title":"Real-time AI-enabled digital twin for battery health estimation and fast charging using partial-discharge data","authors":"Mohammad Qasem, Jeff Stubblefield, Moath Qandil, Yazan Yassin, Mariana Haddadin, Mahesh Krishnamurthy","doi":"10.1016/j.etran.2025.100528","DOIUrl":"10.1016/j.etran.2025.100528","url":null,"abstract":"<div><div>Digital twin technology has emerged as a promising approach for integrating multi-physics models in real-time to optimize the operation of electric vehicles (EVs) and electric vertical take-off and landing (eVTOLs), particularly in terms of battery performance. However, the mitigation of dynamic lithium plating and solid electrolyte interphase (SEI) growth during fast charging remains unaddressed in current studies. This paper proposes an AI-enabled digital twin that uses partial-discharge data, data from incomplete discharge cycles, for real-time battery-health estimation and couples this insight with an age-aware fast-charging controller that adaptively controls the charging current to mitigate lithium plating and SEI growth. The experimental results demonstrated the framework’s robustness across varying ambient temperatures and initial state of charge (SoC) conditions. A novel real-time estimation model within the framework achieved a root mean square error (RMSE) of less than 0.5% and 0.4% for both battery capacity and internal resistance. Additionally, the proposed framework preserved battery capacity of 87.6% at 25 °<span><math><mi>C</mi></math></span> compared to 81.4% and 64.3% for MCC-CV and CC-CV, respectively, representing relative improvements of +7.6% and +36.2% over MCC-CV and CC-CV, respectively. This approach helped mitigate battery side reactions during fast charging, while it reduced the time required to reach 80% SoC to less than 25 min, which was 28.6% faster than MCC-CV (35 min) and 35.9% faster than CC-CV (39 min) after 200 cycles. These results support practical deployment in embedded BMS and EV/eVTOL charging to enhance safety, reduce plating risk, and extend service life.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"27 ","pages":"Article 100528"},"PeriodicalIF":17.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839484","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}

引用次数: 0