EtransportationPub Date : 2025-09-11DOI: 10.1016/j.etran.2025.100466
Yizhao Gao, Simona Onori
{"title":"Advancing SOC estimation in LiFePO4 batteries: Enhanced dQ/dV curve and short-pulse methods","authors":"Yizhao Gao, Simona Onori","doi":"10.1016/j.etran.2025.100466","DOIUrl":"10.1016/j.etran.2025.100466","url":null,"abstract":"<div><div>Accurate state-of-charge (SOC) estimation for lithium iron phosphate (<span><math><msub><mrow><mi>LiFePO</mi></mrow><mrow><mn>4</mn></mrow></msub></math></span>) batteries remains challenging due to their inherently flat open-circuit voltage (OCV)–SOC characteristics, which impair observability for conventional voltage-based and equivalent circuit model (ECM) methods. To address this limitation, we propose a DQV-based SOC estimation framework that uses short-duration current pulses to extract informative voltage features. Complete DQV–SOC reference curves are constructed offline across multiple C-rates (<span><math><mo>±</mo></math></span> 1/30C, <span><math><mo>±</mo></math></span> 0.2C, <span><math><mo>±</mo></math></span> 0.5C, <span><math><mo>±</mo></math></span> 1C, and <span><math><mo>±</mo></math></span> 2C). During operation, voltage responses from brief current pulses are processed via exponential fitting to generate smooth, noise-resilient DQV segments. These segments are fused with the reference data within an Unscented Kalman Filter (UKF), enabling closed-loop SOC estimation with low computational overhead. Experimental results highlight the significant influence of C-rates on the DQV-based SOC estimator. We observe that pulse currents significantly enhance SOC estimation convergence across the full SOC range [0, 1]. However, employing a single C-rate pulse may not ensure robustness across diverse SOC ranges, emphasizing the importance of carefully selecting C-rates to achieve SOC estimation convergence throughout the entire SOC range of [0, 1]. This research contributes to advancing reliable management practices for <span><math><msub><mrow><mi>LiFePO</mi></mrow><mrow><mn>4</mn></mrow></msub></math></span> batteries in electric vehicles.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100466"},"PeriodicalIF":17.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096464","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}
EtransportationPub Date : 2025-09-08DOI: 10.1016/j.etran.2025.100464
Andreas Wiedenmann , Julian Estaller , Johannes Buberger , Wolfgang Grupp , Manuel Kuder , Antje Neve , Thomas Weyh
{"title":"A reconfigurable battery system for a Tesla Model Y: Package and efficiency analysis","authors":"Andreas Wiedenmann , Julian Estaller , Johannes Buberger , Wolfgang Grupp , Manuel Kuder , Antje Neve , Thomas Weyh","doi":"10.1016/j.etran.2025.100464","DOIUrl":"10.1016/j.etran.2025.100464","url":null,"abstract":"<div><div>This study investigates the integration of a modular multilevel inverter-based reconfigurable battery system into an existing electric vehicle. The aim is to evaluate how such systems can replace conventional traction inverters, battery management systems, and on-board chargers. To this end, a classification of the different topology levels and possible forms of integration of power electronics, control logic, and driver electronics is performed. A Tesla Model Y’s traction battery is redesigned, retaining its structural properties and the 4680 cell format. A package analysis shows that the multilevel system occupies a volume comparable to the conventional battery pack, while the volume previously reserved for dedicated power electronics becomes available. Efficiency simulations demonstrate that the multilevel inverter can increase the overall vehicle efficiency, especially in situations with low driving speeds and high torque requirements. As a result, WLTP energy consumption is reduced from 14.9 kWh/100km to 14.5 kWh/100km. However, the battery efficiency is reduced at higher speeds due to higher cell currents. In addition, the system enables bidirectional charging at full system power, including supply to external loads or the grid, and a more integrated vehicle architecture.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100464"},"PeriodicalIF":17.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096467","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}
EtransportationPub Date : 2025-09-08DOI: 10.1016/j.etran.2025.100469
Ibna Kawsar, Honggang Li, Binghe Liu, Yongzhi Zhang, Yongjun Pan
{"title":"Enhancing mechanical reliability and safety performance of a battery pack system for electric vehicles: A review","authors":"Ibna Kawsar, Honggang Li, Binghe Liu, Yongzhi Zhang, Yongjun Pan","doi":"10.1016/j.etran.2025.100469","DOIUrl":"10.1016/j.etran.2025.100469","url":null,"abstract":"<div><div>In electric vehicles (EVs), battery packs (BPs) are susceptible to mechanical and functional failures, where various environmental factors are influenced. Although standard testing procedures contribute to improved safety and overall performance, current research primarily examines individual factors, neglecting a comprehensive assessment of battery pack (BP) design solutions. This review comprehensively analyzes safety standards, empirical research, and advances in patent design to provide a broad perspective on the safety of battery pack systems (BPS). Specifically, it examines the responses of BPs to severe environmental conditions, including vibrations, mechanical shock, and collisions. The paper presents comprehensive design solutions, providing valuable knowledge on reducing the likelihood of failure and addressing safety concerns. The review emphasizes the importance of a complete optimization strategy for BPS, explicitly focusing on analyzing mechanical reactions, particularly concerning the reliability and efficacy of safety alerts. The conclusion highlights the imperative to meet operational requirements and safety standards in the design of BP, emphasizing the importance of adopting a robust structural design approach. The study suggested adopting harmonized standards for testing in realistic scenarios. Furthermore, this study makes an innovative contribution by exploring advanced technologies, such as FEA-DNN, reinforcement learning, and various intelligent optimization algorithms, to mitigate mechanical stresses, vibrations, shock impacts, and collision-induced damage in different work environments, providing engineering guidance to enhance the safety performance of BPS.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100469"},"PeriodicalIF":17.0,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060521","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":"Atmosphere-regulated thermal runaway characteristics and multidimensional safety assessment of sodium-ion and lithium-ion batteries","authors":"Zhixiang Cheng, Zhiyuan Li, Yuxuan Li, Yin Yu, Chaoshi Liu, Zhenwei Wu, Peiyu Duan, Huang Li, Wenxin Mei, Qingsong Wang","doi":"10.1016/j.etran.2025.100475","DOIUrl":"10.1016/j.etran.2025.100475","url":null,"abstract":"<div><div>Understanding and quantifying the thermal runaway behavior of emerging battery chemistries is essential for ensuring safety in real-world applications. This study systematically investigates the thermal runaway characteristics of sodium-ion (SIB) and lithium-ion (LIB) batteries of comparable volumes under both air and inert gas environments. Experimental results show that under low-oxygen conditions, SIB and nickel–cobalt–manganese (NCM) cells exhibit substantial mitigation of thermal runaway severity, including over 35 % decrease in gas generation metrics, while lithium iron phosphate (LFP) cells remain largely unaffected. In gas composition analysis, NCM cells show significant decreases in CO<sub>2</sub>/CO and O<sub>2</sub>/N<sub>2</sub> ratios, whereas SIB and LFP display no notable compositional changes. Based on experimental data and literature, a multidimensional database of thermal runaway parameters is developed, incorporating metrics such as gas explosiveness, toxicity, and heat of combustion. Three classical multi-criteria evaluation methods—Technique for Order Preference by Similarity to Ideal Solution, Principal Component Analysis, and a median-based approach—are applied and compared. To address limitations arising from dimensional and variance scale differences among parameters, an expected contribution method is proposed to enable balanced and consistent scoring. Results demonstrate that this method enhances fairness and interpretability, particularly in scenarios with substantial scale disparities among variables arising from cross-battery systems. This work establishes a quantitative safety assessment framework that enables cross-platform comparisons and provides guidance for battery system design, risk zoning, and thermal mitigation strategies. The framework is broadly applicable to emerging battery chemistries and advances battery safety evaluation across diverse application environments.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100475"},"PeriodicalIF":17.0,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145045875","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}
EtransportationPub Date : 2025-09-05DOI: 10.1016/j.etran.2025.100476
Lutong Wang , Ziqi Zhang , Fuqiang Xu , Jixian Luo , Chuang Yi , Hong Li , Liquan Chen , Fan Wu
{"title":"3D-printed honeycomb lithium-silicon alloy anodes for stabilized interface in sulfide all-solid-state batteries","authors":"Lutong Wang , Ziqi Zhang , Fuqiang Xu , Jixian Luo , Chuang Yi , Hong Li , Liquan Chen , Fan Wu","doi":"10.1016/j.etran.2025.100476","DOIUrl":"10.1016/j.etran.2025.100476","url":null,"abstract":"<div><div>Solid-state batteries have emerged as a crucial development direction for next-generation energy storage technologies, owing to their high energy density, long cycle life, and excellent safety. However, the most challenging issue of interfacial contact/degradation in solid-state batteries remains unsolved. Herein, a novel Si-C interlocking honeycomb electrode is designed/realized via 3D printing technology. Achieves 98.9 % capacity retention over 2100 cycles at 1C. The honeycomb pore walls form a mortise-tenon structure with the electrolyte to maintain good interfacial contact, while the hard carbon layer isolates the electrolyte from the lithium-silicon interface, thereby stabilizing the growth of the solid electrolyte interphase (SEI) and achieving stress-electrochemical coupling regulation. Moreover, as the honeycomb channels form an interpenetrating structure with the solid electrolyte, a three-dimensional ion transport network is established, shortening the lithium-ion diffusion path, enhancing the interfacial contact between the electrode and solid electrolyte, reducing the risk of lithium dendrite formation, and improving the rate performance of all-solid-state batteries. This approach leverages structural design to enhance material performance, for the first time enabling the compatibility of 3D-printed structured silicon-based anodes with sulfide-based all-solid-state systems, thus providing a scalable solution for next-generation high-energy-density batteries.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100476"},"PeriodicalIF":17.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004531","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}
EtransportationPub Date : 2025-09-05DOI: 10.1016/j.etran.2025.100474
Ganglin Cao , Shouxuan Chen , Yuanfei Geng , Shuzhi Zhang , Yao Jia , Rong Feng , Yongjun Liu
{"title":"State-of-charge estimation over full battery lifespan under diverse fast-charging protocols: A lightweight base-error joint modeling framework","authors":"Ganglin Cao , Shouxuan Chen , Yuanfei Geng , Shuzhi Zhang , Yao Jia , Rong Feng , Yongjun Liu","doi":"10.1016/j.etran.2025.100474","DOIUrl":"10.1016/j.etran.2025.100474","url":null,"abstract":"<div><div>Accurate state-of-charge (SOC) online estimation during various multi-stage constant current (MCC) fast-charging protocols over battery entire lifespan holds significant importance. In this work, we develop a lightweight-training oriented data-driven base-error joint modeling framework to fill this research gap. Through deep learning-based initial-cycle data training and lightweight machine learning-based typical-cycle data training, we only extract approximately 1 % of whole battery data for data-driven base-error joint modeling. With consideration of SOC time-dependency, short-term Ampere-hour is further combined via a simple filter structure to guarantee final SOC estimation accuracy. The validation, derived from a public battery degradation dataset comprising 8 different MCC fast-charging protocols from 46 cells, demonstrates that our framework allows rapid data-driven base-error joint modeling with training time only about l min, where both average mean absolute error and average root mean square error of SOC estimation during various MCC fast-charging protocols over battery entire lifespan are roughly below 0.3 %. Our work, for the first time, reveals the possibility of joint data-driven model trained via extremely few data on accurate SOC online estimation with consideration of various MCC fast-charging protocols and battery degradation status, and also offers a pretty concise but efficient solution for multi-scenario battery aging diagnosis and voltage dynamics forecast. The code accompanying this work is available at <span><span>https://github.com/szzhang96/A-light-weighted-training-oriented-data-driven-base-error-joint-modeling-method-for-SOC-estimation</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100474"},"PeriodicalIF":17.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010679","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}
EtransportationPub Date : 2025-09-04DOI: 10.1016/j.etran.2025.100467
Jiekai Xie , Junlin Li , Canbing Li , Xinyan Huang , Guoqing Zhang , Xiaoqing Yang
{"title":"Multi-level passive-active thermal control for battery thermal runaway prevention and suppression in electric vehicles","authors":"Jiekai Xie , Junlin Li , Canbing Li , Xinyan Huang , Guoqing Zhang , Xiaoqing Yang","doi":"10.1016/j.etran.2025.100467","DOIUrl":"10.1016/j.etran.2025.100467","url":null,"abstract":"<div><div>Resolving the contradiction between heat-dissipation during normal operation and thermal-insulation after thermal runaway (TR) is highly desirable for battery thermal safety system but remains challenges. Herein, a multi-leveled thermal control strategy, <em>i.e.</em>, passive cooling - active cooling - passive suppression - active suppression, has been proposed for TR prevention-suppression of the battery packs. The system is primarily designed by modular composite phase change material (CPCM), liquid cooling (LC) plates and aerogel plates (APs). Firstly, the passive cooling CPCM coordinated with active LC enables a suitable working temperature, low temperature gradient and low energy consumption of the battery pack under variable environments. Secondly, the modular design of the battery pack couples with the passive thermal-insulation effect of APs, successfully preventing TR from propagating to other modules. Thirdly, APs work synergistically with dynamic LC, greatly enhancing the directional heat-dissipation, and consequently, the TR propagation can be suppressed to the lowest level. By the flexible dynamic flow rate adjustment, the TR of large-scaled battery packs with different configurations of 4S12P, 6S8P, 8S6P and 12S4P can be successfully suppressed in the initially-triggered cell.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100467"},"PeriodicalIF":17.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019420","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":"Full-scene battery self-heating method based on powertrain system for electric vehicles at extremely low temperatures","authors":"Heping Ling, Lei Yan, Hua Pan, Siliang Chen, Fang Li, Shiyun Zhang","doi":"10.1016/j.etran.2025.100465","DOIUrl":"10.1016/j.etran.2025.100465","url":null,"abstract":"<div><div>The popularity of electric vehicles (EVs) in the cold regions is seriously hindered by the degradation of lithium-ion batteries (LIBs) at low temperatures. To settle such issue, it is necessary to preheat the LIBs to moderate temperature for normal operation. As one of attractive internal preheating methods, pulse self-heating possesses high heating rate and efficiency. However, the application of pulse self-heating still faces the challenges of the pulse current power source unavailable in EVs. Herein we proposed a novel battery self-heating method which reuses the powertrain system of EVs to generate pulse excitation onboard, eliminating additional hardware. Moreover, the decoupled control of battery self-heating and motor torque was further developed to achieve the full-scene application, including charging, parking and driving. When applied in EVs, the proposed self-heating method could realize fast temperature rising of battery pack, shortening 30.7 % charging time at −20 °C compared with the conventional heat pump method. It also achieves rapid startup of EVs even at low temperature of −38 °C with high heating rate (0.73 °C min<sup>−1</sup>) and low energy consumption (4.2 % SOC), as well as maintains the dynamic performance during driving at −30 °C. The proposed method provides a promising solution to preheat the battery pack for EVs application at extremely low temperatures.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100465"},"PeriodicalIF":17.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096466","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}
EtransportationPub Date : 2025-09-03DOI: 10.1016/j.etran.2025.100463
Yubo Lian, Heping Ling, Gan Song, Jiapei Yang, Hanzhi Wang, Zhe Zhang, Shaokuan Mao, Bin He
{"title":"Physics-enhanced U-net and deep reinforcement learning for automated optimization of pin-fin heat sinks in electric vehicle power modules","authors":"Yubo Lian, Heping Ling, Gan Song, Jiapei Yang, Hanzhi Wang, Zhe Zhang, Shaokuan Mao, Bin He","doi":"10.1016/j.etran.2025.100463","DOIUrl":"10.1016/j.etran.2025.100463","url":null,"abstract":"<div><div>The use of pin-fin structures in compact energy devices, such as electric vehicle power modules, is a widely adopted thermal management strategy to enhance heat transfer efficiency. In this study, we present an innovative deep learning framework that integrates a physics-enhanced U-net architecture with a deep reinforcement learning agent to achieve autonomous optimal design of pin-fin arrays. The physics-enhanced U-net is trained to predict thermal-flow fields, while the integrated deep reinforcement learning agent autonomously optimizes pin-fin configurations to minimize both pressure drop and junction temperature. First, we generate a high-fidelity training dataset through an automated computational pipeline that integrates COMSOL Multiphysics for thermal-flow field simulations with a custom Matlab script for parametric generation of 1080 training samples. Subsequently, we train our physics-enhanced U-net architecture to predict the velocity, pressure and temperature fields from various pin-fin structure inputs. The proposed model demonstrates both high prediction accuracy and robustness, achieving mean-squared-errors on the order of 10<sup>−4</sup> for all output fields. As a result, the trained U-net model achieves exceptional prediction accuracy, demonstrating 93.9 % precision for pressure drop and 99.5 % for junction temperature. Finally, we integrate the deep reinforcement learning agent with the trained U-net model to establish an automated optimization framework for pin-fin design, enabling intelligent exploration of design space. The proposed deep learning framework successfully automates the optimization of pin-fin heat sinks for a high power density module. The model demonstrates exceptional capability in generating optimal designs, with the optimized configuration achieving an 8.8 K reduction in junction temperature and 11.3 % decrease in pressure drop comparing to a baseline design. These improvements can be translated into approximately 10 % augmentation in power output, which validates both the effectiveness and robustness of our deep learning driven design approach.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100463"},"PeriodicalIF":17.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027081","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}
EtransportationPub Date : 2025-09-02DOI: 10.1016/j.etran.2025.100471
Siyi Tao , Jiangong Zhu , Yuan Li , Bo Jiang , Wei Chang , Haifeng Dai , Xuezhe Wei
{"title":"Cross-Domain Feature-Based Battery State-of-Health Estimation from Rest Period for Real-World Electric Vehicles","authors":"Siyi Tao , Jiangong Zhu , Yuan Li , Bo Jiang , Wei Chang , Haifeng Dai , Xuezhe Wei","doi":"10.1016/j.etran.2025.100471","DOIUrl":"10.1016/j.etran.2025.100471","url":null,"abstract":"<div><div>Accurate power battery state-of-health (SOH) estimation is essential for ensuring the stable and reliable operation of electric vehicles (EVs). However, the diversity of charging methods and battery materials (nickel-cobalt-manganese (NCM) and lithium iron phosphate (LFP)) poses challenges for generalizing SOH estimation on field data. In this study, we propose a general cross-domain feature extraction method that integrates time-domain (TD) and frequency-domain (FD) features, along with inter-cell inconsistency features, from a two-minute post-charging rest period. Leveraging datasets from 106 real EVs encompassing 17,729 charging cycles and 28 laboratory cells with 10,912 charging cycles, we employ lightweight tree-based models for reliable and rapid SOH estimation. For EVs equipped with five different capacities of NCM and LFP batteries under various charging conditions, a single unified model is employed across all cases, yielding a mean absolute percentage error (MAPE) of less than 1.94% and a maximum error (MAXE) below 6.28%. This study highlights the potential of features from post-charging rest period to enable high-accuracy SOH estimation in real-world conditions, contributing to reduced costs and improved efficiency for future TWh-scale power battery market.</div></div>","PeriodicalId":36355,"journal":{"name":"Etransportation","volume":"26 ","pages":"Article 100471"},"PeriodicalIF":17.0,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004530","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}