Cross-Domain Feature-Based Battery State-of-Health Estimation from Rest Period for Real-World Electric Vehicles

IF 17 1区工程技术 Q1 ENERGY & FUELS

Etransportation Pub Date : 2025-09-02 DOI: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":null,"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":17.0000,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Etransportation","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590116825000785","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENERGY & FUELS","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

基于跨域特征的电动汽车静息期电池健康状态估计

准确的动力电池健康状态（SOH）估计是保证电动汽车稳定可靠运行的关键。然而，充电方法和电池材料（镍钴锰（NCM）和磷酸铁锂（LFP））的多样性给现场数据的SOH估计带来了挑战。在这项研究中，我们提出了一种通用的跨域特征提取方法，该方法结合了充电后两分钟休息时间的时域（TD）和频域（FD）特征以及细胞间不一致特征。利用106辆真实电动汽车的17,729个充电周期和28个实验室电池的10,912个充电周期的数据集，我们采用轻量级的基于树的模型进行可靠和快速的SOH估计。对于搭载5种不同容量NCM和LFP电池的电动汽车，在不同充电条件下均采用统一模型，平均绝对百分比误差（MAPE）小于1.94%，最大误差（MAXE）小于6.28%。这项研究强调了充电后休息期的特征在现实条件下实现高精度SOH估计的潜力，有助于降低成本，提高未来太瓦时规模的动力电池市场的效率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Etransportation Engineering-Automotive Engineering

CiteScore

19.80

自引率

12.60%

发文量

审稿时长

39 days

期刊介绍： eTransportation is a scholarly journal that aims to advance knowledge in the field of electric transportation. It focuses on all modes of transportation that utilize electricity as their primary source of energy, including electric vehicles, trains, ships, and aircraft. The journal covers all stages of research, development, and testing of new technologies, systems, and devices related to electrical transportation. The journal welcomes the use of simulation and analysis tools at the system, transport, or device level. Its primary emphasis is on the study of the electrical and electronic aspects of transportation systems. However, it also considers research on mechanical parts or subsystems of vehicles if there is a clear interaction with electrical or electronic equipment. Please note that this journal excludes other aspects such as sociological, political, regulatory, or environmental factors from its scope.