Enhanced few-shot state-of-health estimation for lithium-ion batteries via Masked Autoencoder
Accurately estimating the state-of-health (SOH) of lithium-ion batteries (LIBs) is crucial for optimizing performance, ensuring operational safety, and enabling predictive maintenance in battery management systems. With the widespread adoption of LIBs, a large amount of field data has been generated...
Uložené v:
| Vydané v: | Energy (Oxford) Ročník 335; s. 138263 |
|---|---|
| Hlavní autori: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Ltd
30.10.2025
|
| Predmet: | |
| ISSN: | 0360-5442 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Accurately estimating the state-of-health (SOH) of lithium-ion batteries (LIBs) is crucial for optimizing performance, ensuring operational safety, and enabling predictive maintenance in battery management systems. With the widespread adoption of LIBs, a large amount of field data has been generated, yet current data-driven SOH estimation methods often fail to fully utilize it due to the lack of labeled data. To address this, we propose a method based on semi-supervised learning to exploit large-scale unlabeled data for accurate SOH estimation. A generative unsupervised model, the Masked Autoencoder (MAE), is pre-trained on unlabeled field charging data to automatically extract latent representations related to SOH. The model is then fine-tuned with a small amount of labeled data. Experimental results show that using only 20 % of the labeled data usually required for supervised learning, the method achieves an RMSE of 2.14 %. The latent representation extraction capability of the MAE is validated via incremental capacity (IC) analysis, which explains the 14 % improvement in estimation accuracy (RMSE of 1.84 %) when using data from a specific voltage range (3.8–3.9 V). Furthermore, experiments demonstrate that even with only 21.33 min of charging data—consisting of only charge quantity and voltage signals—the model can still achieve a competitive RMSE of 1.94 %. This work introduces a novel approach for SOH estimation using large-scale, unlabeled field data and provides valuable insights for battery management in the era of artificial intelligence.
•SOH labeling reduced by 80 % via MAE-based semi-supervised learning.•MAE-extracted SOH features match IC curves in mid-voltage zone.•1.94 % SOH error using charge quantity and voltage from a 21-min charge segment.•Semi-supervised MAE yields 1.7 % error on 2-year electric vehicle data. |
|---|---|
| AbstractList | Accurately estimating the state-of-health (SOH) of lithium-ion batteries (LIBs) is crucial for optimizing performance, ensuring operational safety, and enabling predictive maintenance in battery management systems. With the widespread adoption of LIBs, a large amount of field data has been generated, yet current data-driven SOH estimation methods often fail to fully utilize it due to the lack of labeled data. To address this, we propose a method based on semi-supervised learning to exploit large-scale unlabeled data for accurate SOH estimation. A generative unsupervised model, the Masked Autoencoder (MAE), is pre-trained on unlabeled field charging data to automatically extract latent representations related to SOH. The model is then fine-tuned with a small amount of labeled data. Experimental results show that using only 20 % of the labeled data usually required for supervised learning, the method achieves an RMSE of 2.14 %. The latent representation extraction capability of the MAE is validated via incremental capacity (IC) analysis, which explains the 14 % improvement in estimation accuracy (RMSE of 1.84 %) when using data from a specific voltage range (3.8–3.9 V). Furthermore, experiments demonstrate that even with only 21.33 min of charging data—consisting of only charge quantity and voltage signals—the model can still achieve a competitive RMSE of 1.94 %. This work introduces a novel approach for SOH estimation using large-scale, unlabeled field data and provides valuable insights for battery management in the era of artificial intelligence.
•SOH labeling reduced by 80 % via MAE-based semi-supervised learning.•MAE-extracted SOH features match IC curves in mid-voltage zone.•1.94 % SOH error using charge quantity and voltage from a 21-min charge segment.•Semi-supervised MAE yields 1.7 % error on 2-year electric vehicle data. |
| ArticleNumber | 138263 |
| Author | Shen, Yifan Liu, Xuyang Ouyang, Minggao Han, Xuebing Wang, Yu Zheng, Yuejiu Guo, Dongxu Chen, Jianguo |
| Author_xml | – sequence: 1 givenname: Yifan orcidid: 0009-0004-2676-7098 surname: Shen fullname: Shen, Yifan organization: School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China – sequence: 2 givenname: Dongxu orcidid: 0000-0003-3697-6913 surname: Guo fullname: Guo, Dongxu email: guodx12@gmail.com organization: School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China – sequence: 3 givenname: Yu surname: Wang fullname: Wang, Yu organization: State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, 100084, China – sequence: 4 givenname: Jianguo surname: Chen fullname: Chen, Jianguo organization: School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China – sequence: 5 givenname: Xuyang surname: Liu fullname: Liu, Xuyang organization: School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China – sequence: 6 givenname: Xuebing surname: Han fullname: Han, Xuebing email: hanxuebing@tsinghua.edu.cn organization: State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, 100084, China – sequence: 7 givenname: Yuejiu orcidid: 0000-0002-6359-8375 surname: Zheng fullname: Zheng, Yuejiu email: yuejiu_zheng@163.com organization: School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China – sequence: 8 givenname: Minggao surname: Ouyang fullname: Ouyang, Minggao organization: State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, 100084, China |
| BookMark | eNp9kL1OwzAYRT0UiRZ4Awa_gIMdx06yIFVV-ZGKWGBElmt_Ji5tjGy3qG9PojAzXd3hHl2dBZr1oQeEbhktGGXybldAD_HzXJS0FAXjTSn5DM0pl5SIqiov0SKlHaVUNG07Rx_rvtO9AYsd_JDUhYxT1hlIcKQDvc8dhpT9QWcfeuxCxHufO388kLFvdc4QPSR88hq_6PQ1gJbHHKA3wUK8RhdO7xPc_OUVen9Yv62eyOb18Xm13BBTijoTV_FKSKulBdo4IWpZO9ZIRmW7rbaussJIx4SxvOXcct1w0bLSQM04q8u64VeomrgmhpQiOPUdh8_xrBhVoxa1U5MWNWpRk5Zhdj_NYPh28hBVMh5GGz6CycoG_z_gFzmEce4 |
| Cites_doi | 10.1016/j.etran.2024.100338 10.1109/TIA.2019.2955396 10.1016/j.etran.2023.100226 10.1016/j.est.2022.105708 10.1016/j.ensm.2022.05.026 10.1016/j.apenergy.2023.121761 10.1016/j.ress.2023.109455 10.1109/TPEL.2011.2181868 10.1109/TTE.2020.3029295 10.1016/j.etran.2024.100361 10.1016/j.joule.2024.02.020 10.1002/er.5750 10.1016/j.rineng.2024.102770 10.1016/j.energy.2024.132213 10.1109/TII.2019.2951843 10.1016/j.jlp.2023.105156 10.1016/j.apenergy.2020.114817 10.1016/j.joule.2021.06.005 10.1016/j.est.2024.113502 10.1016/j.ensm.2021.07.016 10.1016/j.ymssp.2024.111585 10.1016/j.energy.2022.123973 10.1016/j.energy.2022.125234 10.1016/j.jclepro.2020.120813 10.3390/electronics12143049 10.1016/j.ensm.2022.10.030 10.1109/ACCESS.2018.2858856 10.1109/TTE.2022.3204843 10.1007/s00521-022-07291-5 10.1016/j.est.2020.101836 10.1016/j.neucom.2023.02.031 10.1016/j.joule.2024.07.002 10.1016/j.ress.2023.109790 10.1016/j.joule.2019.11.018 10.1016/j.energy.2022.125501 10.1016/j.joule.2023.07.018 10.1016/j.etran.2019.100034 10.1016/j.energy.2024.132993 10.3390/electronics11203378 10.1016/j.engfailanal.2024.108559 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.energy.2025.138263 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Environmental Sciences |
| ExternalDocumentID | 10_1016_j_energy_2025_138263 S0360544225039052 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAHBH AAHCO AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AARJD AATTM AAXKI AAXUO AAYWO ABJNI ABMAC ACDAQ ACGFS ACIWK ACLOT ACRLP ACVFH ADBBV ADCNI ADEZE AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFRAH AFTJW AGHFR AGUBO AGYEJ AHIDL AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP AXJTR BELTK BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W JARJE KOM LY6 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RNS ROL RPZ SDF SDG SES SEW SPC SPCBC SSR SSZ T5K TN5 XPP ZMT ~02 ~G- ~HD 29G 6TJ 9DU AAQXK AAYXX ABDPE ABFNM ABWVN ABXDB ACRPL ADMUD ADNMO ADXHL AGQPQ AHHHB ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 HVGLF HZ~ R2- SAC WUQ |
| ID | FETCH-LOGICAL-c257t-f43456da6de08f55767f1861069b4bf4d5c6f15cd3933d3a835912ce713172783 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001583733500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0360-5442 |
| IngestDate | Sat Nov 29 06:52:00 EST 2025 Wed Dec 10 14:24:00 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | SOH estimation Lithium-ion battery Electric vehicle data Semi-supervised learning Masked Autoencoder |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c257t-f43456da6de08f55767f1861069b4bf4d5c6f15cd3933d3a835912ce713172783 |
| ORCID | 0000-0003-3697-6913 0000-0002-6359-8375 0009-0004-2676-7098 |
| ParticipantIDs | crossref_primary_10_1016_j_energy_2025_138263 elsevier_sciencedirect_doi_10_1016_j_energy_2025_138263 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-10-30 |
| PublicationDateYYYYMMDD | 2025-10-30 |
| PublicationDate_xml | – month: 10 year: 2025 text: 2025-10-30 day: 30 |
| PublicationDecade | 2020 |
| PublicationTitle | Energy (Oxford) |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Ma, Shan, Gao, Chen (bib16) 2022; 251 Xiao, Singh, Mintun, Darrell, Dollar, Girshick (bib47) 2021; 34 Xiang, Fan, Zhu, Wei, Dai (bib22) 2024; 5 Pozzato, Allam, Pulvirenti, Negoita, Paxton, Onori (bib39) 2023; 7 Sulzer, Mohtat, Aitio, Lee, Yeh, Steinbacher, Khan, Lee, Siegel, Stefanopoulou, Howey (bib9) 2021; 5 Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner, Dehghani, Minderer, Heigold, Gelly, Uszkoreit, Houlsby (bib45) 2021 Zhang, Liu, Wang, Zhang (bib49) 2022; 239 Lin, Xu, Mei (bib13) 2023; 54 Wang, Shen, Zhang, Li, Zhang, Yang (bib26) 2023; 239 She, Wang, Sun, Liu, Zhang (bib51) 2020; 16 Peng, Zhu, Wu, Tang, Kan, Pecht (bib14) 2024; 308 Ren, Zhao, Hong, Zhao, Wang, Zhang (bib29) 2018; 6 Wu, Chen, Feng, Xiang, Zhu (bib31) 2022; 55 Ahfock, McLachlan (bib41) 2021 Chen, Koh, Halstead (bib42) 2022 Zhang, Ma, Zhou, Guan (bib55) 2024; 2846 Wen, Chen, Li, Li (bib53) 2022; 261 Xu, Guo, Saleh (bib32) 2022; 34 Zhou, Gao, Dong, Zhou, Zheng, Ma, Ming, Lian, Chen, Yang (bib11) 2024; 70 Kim, Yi, Chen, Tanim, Dufek (bib20) 2022; 45 Lucu, Azkue, Camblong, Martinez-Laserna (bib40) 2020 He, Sun, Wang, Lin, Zhang, Xiong, Deng, Zhu, Xie, Zhang, Wei, Cao, Zhai (bib1) 2022; 1 Zhao, Wang (bib15) 2024; 71 Pepe, Ciucci (bib17) 2023; 350 Wang, Wang, Liu, Zhang, Sauer, Li (bib34) 2023; 4 Zeng, Zhang, Xue, Li, Li, Zhang, Zheng (bib54) 2022; 11 Tian, Qin, Li, Zhao (bib21) 2020; 261 Cheng, Son, Wang, Lu, Zerhouni (bib18) 2020; 266 Jiang, Ren, Tang, Wu, Xia, Sun, Yang (bib25) 2024; 305 Ouyang, Weng, Chen, Wang, Wang (bib5) 2023; 85 Lu, Lin, Guo, Zhang, Wang, He, Ouyang (bib48) 2024; 21 Zhao, Yan, Chen, Mao, Wang, Gao (bib30) 2016 Feichtenhofer, Fan, Li, He (bib44) 2022 He, Chen, Xie, Li, Dollar, Girshick (bib46) 2022 Chen, Ma, Liu, Zeng, Luo (bib7) 2023; 532 Schimpe (bib43) 2023; 12 Li, Wei, Zhu, Du, Zhao, Ouyang (bib2) 2023; 16 Gu, See, Li, Shan, Wang, Zhao, Lim, Zhang (bib28) 2023; 262 Huang, Peng, Tang, Chen, Zio, Zheng (bib33) 2024; 242 Wang, Feng, Guo, Hsu, Hou, Zhang, Xu, Chen, Wang, Zhang, Ouyang (bib4) 2024; 8 Guo, Chen, Tao, Liu, Wan, Li (bib24) 2024; 8 Su, Li, Mou, Garg, Gao, Liu (bib27) 2023; 9 Hu, Xu, Lin, Pecht (bib10) 2020; 4 Liu, Zhang, Deng, Zhao, Zhang, Wang (bib56) 2024; 163 Lu, Guo, Xiong, Wei, Zhang, Wang, Ouyang (bib36) 2024; 22 Tong, Miao, Mao, Wang, Lu (bib50) 2022; 50 Hassini, Redondo-Iglesias, Venet (bib35) 2023; 9 Gou, Xu, Feng (bib19) 2021; 7 Ren, Hsu, Li, Feng, Guo, Han, Lu, He, Gao, Hou, Li, Wang, Ouyang (bib3) 2019; 2 Ye, Cheng, Yeung (bib8) 2012; 27 Liu, Deng, Che, Xu, Wang, Wang, Xie, Hu (bib37) 2024; 218 Krishna, Singh, Gehlot, Shaik, Twala, Priyadarshi (bib6) 2024; 23 Yu, Yang, Wu, Tang, Dai (bib23) 2020; 44 Song, Zhang, Liang, Han, Zhang (bib38) 2020; 32 Zhou, Qin, Yuen (bib12) 2024; 100 Stroe, Schaltz (bib52) 2020; 56 Cheng (10.1016/j.energy.2025.138263_bib18) 2020; 266 Xu (10.1016/j.energy.2025.138263_bib32) 2022; 34 Lucu (10.1016/j.energy.2025.138263_bib40) 2020 Yu (10.1016/j.energy.2025.138263_bib23) 2020; 44 Su (10.1016/j.energy.2025.138263_bib27) 2023; 9 Li (10.1016/j.energy.2025.138263_bib2) 2023; 16 Xiang (10.1016/j.energy.2025.138263_bib22) 2024; 5 Tong (10.1016/j.energy.2025.138263_bib50) 2022; 50 Guo (10.1016/j.energy.2025.138263_bib24) 2024; 8 Lin (10.1016/j.energy.2025.138263_bib13) 2023; 54 Gou (10.1016/j.energy.2025.138263_bib19) 2021; 7 Stroe (10.1016/j.energy.2025.138263_bib52) 2020; 56 Chen (10.1016/j.energy.2025.138263_bib7) 2023; 532 Ouyang (10.1016/j.energy.2025.138263_bib5) 2023; 85 Ren (10.1016/j.energy.2025.138263_bib29) 2018; 6 Xiao (10.1016/j.energy.2025.138263_bib47) 2021; 34 Sulzer (10.1016/j.energy.2025.138263_bib9) 2021; 5 Liu (10.1016/j.energy.2025.138263_bib37) 2024; 218 Ren (10.1016/j.energy.2025.138263_bib3) 2019; 2 Hu (10.1016/j.energy.2025.138263_bib10) 2020; 4 Pozzato (10.1016/j.energy.2025.138263_bib39) 2023; 7 Lu (10.1016/j.energy.2025.138263_bib48) 2024; 21 She (10.1016/j.energy.2025.138263_bib51) 2020; 16 He (10.1016/j.energy.2025.138263_bib46) 2022 Wang (10.1016/j.energy.2025.138263_bib34) 2023; 4 Feichtenhofer (10.1016/j.energy.2025.138263_bib44) 2022 Ahfock (10.1016/j.energy.2025.138263_bib41) 2021 Pepe (10.1016/j.energy.2025.138263_bib17) 2023; 350 Dosovitskiy (10.1016/j.energy.2025.138263_bib45) 2021 Krishna (10.1016/j.energy.2025.138263_bib6) 2024; 23 Huang (10.1016/j.energy.2025.138263_bib33) 2024; 242 Peng (10.1016/j.energy.2025.138263_bib14) 2024; 308 Zhou (10.1016/j.energy.2025.138263_bib11) 2024; 70 He (10.1016/j.energy.2025.138263_bib1) 2022; 1 Lu (10.1016/j.energy.2025.138263_bib36) 2024; 22 Liu (10.1016/j.energy.2025.138263_bib56) 2024; 163 Gu (10.1016/j.energy.2025.138263_bib28) 2023; 262 Zhang (10.1016/j.energy.2025.138263_bib55) 2024; 2846 Wu (10.1016/j.energy.2025.138263_bib31) 2022; 55 Zhao (10.1016/j.energy.2025.138263_bib30) 2016 Wen (10.1016/j.energy.2025.138263_bib53) 2022; 261 Hassini (10.1016/j.energy.2025.138263_bib35) 2023; 9 Ye (10.1016/j.energy.2025.138263_bib8) 2012; 27 Zhang (10.1016/j.energy.2025.138263_bib49) 2022; 239 Schimpe (10.1016/j.energy.2025.138263_bib43) 2023; 12 Wang (10.1016/j.energy.2025.138263_bib4) 2024; 8 Chen (10.1016/j.energy.2025.138263_bib42) 2022 Ma (10.1016/j.energy.2025.138263_bib16) 2022; 251 Zeng (10.1016/j.energy.2025.138263_bib54) 2022; 11 Zhou (10.1016/j.energy.2025.138263_bib12) 2024; 100 Tian (10.1016/j.energy.2025.138263_bib21) 2020; 261 Jiang (10.1016/j.energy.2025.138263_bib25) 2024; 305 Wang (10.1016/j.energy.2025.138263_bib26) 2023; 239 Song (10.1016/j.energy.2025.138263_bib38) 2020; 32 Zhao (10.1016/j.energy.2025.138263_bib15) 2024; 71 Kim (10.1016/j.energy.2025.138263_bib20) 2022; 45 |
| References_xml | – volume: 27 start-page: 3234 year: 2012 end-page: 3242 ident: bib8 article-title: Zero-current switching switched-capacitor zero-voltage-gap automatic equalization system for series battery string publication-title: IEEE Trans Power Electron – volume: 218 start-page: 17 year: 2024 ident: bib37 article-title: Big field data-driven battery pack health estimation for electric vehicles: a deep-fusion transfer learning approach publication-title: Mech Syst Signal Process – volume: 266 start-page: 15 year: 2020 ident: bib18 article-title: An ensemble prognostic method for lithium-ion battery capacity estimation based on time-varying weight allocation publication-title: Appl Energy – volume: 239 start-page: 12 year: 2023 ident: bib26 article-title: Self-supervised health representation decomposition based on contrast learning publication-title: Reliab Eng Syst Saf – volume: 32 start-page: 10 year: 2020 ident: bib38 article-title: Intelligent state of health estimation for lithium-ion battery pack based on big data analysis publication-title: J Energy Storage – year: 2021 ident: bib45 article-title: An image is worth 16x16 words: transformers for image recognition at scale publication-title: arXiv (USA) – volume: 44 start-page: 11345 year: 2020 end-page: 11353 ident: bib23 article-title: Online state-of-health prediction of lithium-ion batteries with limited labeled data publication-title: Int J Energy Res – volume: 16 start-page: 3345 year: 2020 end-page: 3354 ident: bib51 article-title: Battery aging assessment for real-world electric buses based on incremental capacity analysis and radial basis function neural network publication-title: IEEE Trans Ind Inf – volume: 56 start-page: 678 year: 2020 end-page: 685 ident: bib52 article-title: Lithium-ion battery state-of-health estimation using the incremental capacity analysis technique publication-title: IEEE Trans Ind Appl – volume: 163 start-page: 12 year: 2024 ident: bib56 article-title: A failure risk assessment method for lithium-ion batteries based on big data of after-sales vehicles publication-title: Eng Fail Anal – volume: 532 start-page: 152 year: 2023 end-page: 169 ident: bib7 article-title: An overview of data-driven battery health estimation technology for battery management system publication-title: Neurocomputing – volume: 12 start-page: 14 year: 2023 ident: bib43 article-title: Logging In-Operation battery data from android devices: a possible path to sourcing battery operation data publication-title: Electronics – start-page: 17 year: 2021 ident: bib41 article-title: Harmless label noise and informative soft-labels in supervised classification arXiv, arXiv (USA) – volume: 71 start-page: 17 year: 2024 ident: bib15 article-title: Specialized convolutional transformer networks for estimating battery health via transfer learning publication-title: Energy Storage Mater – volume: 261 start-page: 30 year: 2020 ident: bib21 article-title: A review of the state of health for lithium -ion batteries: research status and suggestions publication-title: J Clean Prod – volume: 2846 year: 2024 ident: bib55 article-title: Research on monitoring and energy management systems for energy storage stations on the power generation side publication-title: J Phys, Conf Ser (UK) – volume: 100 year: 2024 ident: bib12 article-title: Graph neural network-based lithium-ion battery state of health estimation using partial discharging curve publication-title: J Energy Storage – volume: 5 start-page: 1934 year: 2021 end-page: 1955 ident: bib9 article-title: The challenge and opportunity of battery lifetime prediction from field data publication-title: Joule – start-page: 15979 year: 2022 end-page: 15988 ident: bib46 article-title: Masked autoencoders are scalable vision learners publication-title: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR) – volume: 2 start-page: 13 year: 2019 ident: bib3 article-title: A comparative investigation of aging effects on thermal runaway behavior of lithium-ion batteries publication-title: eTransportation – volume: 239 start-page: 17 year: 2022 ident: bib49 article-title: State-of-health estimation for lithium-ion batteries by combining model-based incremental capacity analysis with support vector regression publication-title: Energy – volume: 350 start-page: 11 year: 2023 ident: bib17 article-title: Long-range battery state-of-health and end-of-life prediction with neural networks and feature engineering publication-title: Appl Energy – volume: 7 start-page: 2035 year: 2023 end-page: 2053 ident: bib39 article-title: Analysis and key findings from real-world electric vehicle field data publication-title: Joule – start-page: 28 year: 2022 end-page: 42 ident: bib42 article-title: Measuring difficulty of learning using ensemble methods publication-title: 20th australasian conference on data mining (AusDM) – volume: 85 start-page: 7 year: 2023 ident: bib5 article-title: Electrochemical and thermal features of aging lithium-ion batteries cycled at various current rates publication-title: J Loss Prev Process Ind – volume: 22 year: 2024 ident: bib36 article-title: Towards real-world state of health estimation: part 2, system level method using electric vehicle field data publication-title: eTransportation – volume: 251 start-page: 21 year: 2022 ident: bib16 article-title: A novel method for state of health estimation of lithium-ion batteries based on improved LSTM and health indicators extraction publication-title: Energy – volume: 5 start-page: 24 year: 2024 ident: bib22 article-title: Semi-supervised deep learning for lithium-ion battery state-of-health estimation using dynamic discharge profiles publication-title: Cell Rep Phys Sci – volume: 16 start-page: 11 year: 2023 ident: bib2 article-title: The path enabling storage of renewable energy toward carbon neutralization in China publication-title: eTransportation – volume: 242 start-page: 13 year: 2024 ident: bib33 article-title: A physics-informed autoencoder for system health state assessment based on energy-oriented system performance publication-title: Reliab Eng Syst Saf – volume: 54 start-page: 85 year: 2023 end-page: 97 ident: bib13 article-title: Improving state-of-health estimation for lithium-ion batteries via unlabeled charging data publication-title: Energy Storage Mater – start-page: 5600 year: 2020 end-page: 5607 ident: bib40 article-title: Ieee, data-driven nonparametric Li-Ion battery ageing model aiming at learning from real operation data: holistic validation with Ev driving profiles publication-title: 12th annual IEEE energy conversion congress and exposition (IEEE ECCE) – volume: 4 start-page: 21 year: 2023 ident: bib34 article-title: Large-scale field data-based battery aging prediction driven by statistical features and machine learning publication-title: Cell Rep Phys Sci – volume: 11 start-page: 31 year: 2022 ident: bib54 article-title: The design of a safe charging system based on PKS architecture publication-title: Electronics – volume: 8 start-page: 2639 year: 2024 end-page: 2651 ident: bib4 article-title: Temperature excavation to boost machine learning battery thermochemical predictions publication-title: Joule – volume: 45 start-page: 1002 year: 2022 end-page: 1011 ident: bib20 article-title: Rapid failure mode classification and quantification in batteries: a deep learning modeling framework publication-title: Energy Storage Mater – volume: 6 start-page: 50587 year: 2018 end-page: 50598 ident: bib29 article-title: Remaining useful life prediction for lithium-ion battery: a deep learning approach publication-title: IEEE Access – volume: 21 start-page: 11 year: 2024 ident: bib48 article-title: Towards real-world state of health estimation, part 1: cell-level method using lithium-ion battery laboratory data publication-title: eTransportation – volume: 50 start-page: 533 year: 2022 end-page: 542 ident: bib50 article-title: Prediction of Li-ion battery capacity degradation considering polarization recovery with a hybrid ensemble learning model publication-title: Energy Storage Mater – volume: 34 start-page: 15997 year: 2022 end-page: 16017 ident: bib32 article-title: A physics-informed dynamic deep autoencoder for accurate state-of-health prediction of lithium-ion battery publication-title: Neural Comput Appl – volume: 261 start-page: 8 year: 2022 ident: bib53 article-title: SOH prediction of lithium battery based on IC curve feature and BP neural network publication-title: Energy – volume: 4 start-page: 310 year: 2020 end-page: 346 ident: bib10 article-title: Battery lifetime prognostics publication-title: Joule – volume: 55 start-page: 11 year: 2022 ident: bib31 article-title: State of health estimation of lithium-ion batteries using autoencoders and ensemble learning publication-title: J Energy Storage – volume: 70 start-page: 28 year: 2024 ident: bib11 article-title: Vehicle-cloud-collaborated prognosis and health management for lithium-ion batteries: framework, technics and perspective publication-title: Energy Storage Mater – volume: 9 start-page: 1113 year: 2023 end-page: 1127 ident: bib27 article-title: A hybrid battery equivalent circuit model, deep learning, and transfer learning for battery state monitoring publication-title: IEEE Trans Transp Electrif – volume: 9 start-page: 37 year: 2023 ident: bib35 article-title: Lithium-ion battery data: from production to prediction publication-title: Batteries-Basel – volume: 34 year: 2021 ident: bib47 article-title: Early convolutions help transformers see better publication-title: Adv Neural Inf Process Syst – volume: 1 start-page: 24 year: 2022 ident: bib1 article-title: China's battery electric vehicles lead the world: achievements in technology system architecture and technological breakthroughs, green energy intell publication-title: Transp – volume: 262 start-page: 14 year: 2023 ident: bib28 article-title: A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer model publication-title: Energy – year: 2022 ident: bib44 article-title: Masked autoencoders as spatiotemporal learners publication-title: arXiv (USA) – volume: 308 start-page: 15 year: 2024 ident: bib14 article-title: SOH early prediction of lithium-ion batteries based on voltage interval selection and features fusion publication-title: Energy – year: 2016 ident: bib30 article-title: Deep learning and its applications to machine health monitoring: a survey publication-title: arXiv (USA) – volume: 8 start-page: 18 year: 2024 ident: bib24 article-title: Semi-supervised learning for explainable few-shot battery lifetime prediction publication-title: Joule – volume: 7 start-page: 422 year: 2021 end-page: 436 ident: bib19 article-title: An ensemble learning-based data-driven method for online state-of-health estimation of lithium-ion batteries publication-title: IEEE Trans Transp Electrif – volume: 305 start-page: 13 year: 2024 ident: bib25 article-title: An adaptive semi-supervised self-learning method for online state of health estimation of lithium-ion batteries publication-title: Energy – volume: 23 start-page: 19 year: 2024 ident: bib6 article-title: IoT-based real-time analysis of battery management system with long range communication and FLoRa publication-title: Results Eng – volume: 21 start-page: 11 year: 2024 ident: 10.1016/j.energy.2025.138263_bib48 article-title: Towards real-world state of health estimation, part 1: cell-level method using lithium-ion battery laboratory data publication-title: eTransportation doi: 10.1016/j.etran.2024.100338 – volume: 56 start-page: 678 year: 2020 ident: 10.1016/j.energy.2025.138263_bib52 article-title: Lithium-ion battery state-of-health estimation using the incremental capacity analysis technique publication-title: IEEE Trans Ind Appl doi: 10.1109/TIA.2019.2955396 – volume: 16 start-page: 11 year: 2023 ident: 10.1016/j.energy.2025.138263_bib2 article-title: The path enabling storage of renewable energy toward carbon neutralization in China publication-title: eTransportation doi: 10.1016/j.etran.2023.100226 – volume: 55 start-page: 11 year: 2022 ident: 10.1016/j.energy.2025.138263_bib31 article-title: State of health estimation of lithium-ion batteries using autoencoders and ensemble learning publication-title: J Energy Storage doi: 10.1016/j.est.2022.105708 – start-page: 28 year: 2022 ident: 10.1016/j.energy.2025.138263_bib42 article-title: Measuring difficulty of learning using ensemble methods – year: 2022 ident: 10.1016/j.energy.2025.138263_bib44 article-title: Masked autoencoders as spatiotemporal learners publication-title: arXiv (USA) – volume: 50 start-page: 533 year: 2022 ident: 10.1016/j.energy.2025.138263_bib50 article-title: Prediction of Li-ion battery capacity degradation considering polarization recovery with a hybrid ensemble learning model publication-title: Energy Storage Mater doi: 10.1016/j.ensm.2022.05.026 – volume: 350 start-page: 11 year: 2023 ident: 10.1016/j.energy.2025.138263_bib17 article-title: Long-range battery state-of-health and end-of-life prediction with neural networks and feature engineering publication-title: Appl Energy doi: 10.1016/j.apenergy.2023.121761 – volume: 239 start-page: 12 year: 2023 ident: 10.1016/j.energy.2025.138263_bib26 article-title: Self-supervised health representation decomposition based on contrast learning publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2023.109455 – volume: 2846 year: 2024 ident: 10.1016/j.energy.2025.138263_bib55 article-title: Research on monitoring and energy management systems for energy storage stations on the power generation side publication-title: J Phys, Conf Ser (UK) – volume: 27 start-page: 3234 year: 2012 ident: 10.1016/j.energy.2025.138263_bib8 article-title: Zero-current switching switched-capacitor zero-voltage-gap automatic equalization system for series battery string publication-title: IEEE Trans Power Electron doi: 10.1109/TPEL.2011.2181868 – volume: 7 start-page: 422 year: 2021 ident: 10.1016/j.energy.2025.138263_bib19 article-title: An ensemble learning-based data-driven method for online state-of-health estimation of lithium-ion batteries publication-title: IEEE Trans Transp Electrif doi: 10.1109/TTE.2020.3029295 – volume: 22 year: 2024 ident: 10.1016/j.energy.2025.138263_bib36 article-title: Towards real-world state of health estimation: part 2, system level method using electric vehicle field data publication-title: eTransportation doi: 10.1016/j.etran.2024.100361 – year: 2016 ident: 10.1016/j.energy.2025.138263_bib30 article-title: Deep learning and its applications to machine health monitoring: a survey publication-title: arXiv (USA) – volume: 34 year: 2021 ident: 10.1016/j.energy.2025.138263_bib47 article-title: Early convolutions help transformers see better publication-title: Adv Neural Inf Process Syst – volume: 8 start-page: 18 year: 2024 ident: 10.1016/j.energy.2025.138263_bib24 article-title: Semi-supervised learning for explainable few-shot battery lifetime prediction publication-title: Joule doi: 10.1016/j.joule.2024.02.020 – volume: 44 start-page: 11345 year: 2020 ident: 10.1016/j.energy.2025.138263_bib23 article-title: Online state-of-health prediction of lithium-ion batteries with limited labeled data publication-title: Int J Energy Res doi: 10.1002/er.5750 – start-page: 17 year: 2021 ident: 10.1016/j.energy.2025.138263_bib41 – start-page: 15979 year: 2022 ident: 10.1016/j.energy.2025.138263_bib46 article-title: Masked autoencoders are scalable vision learners – volume: 23 start-page: 19 year: 2024 ident: 10.1016/j.energy.2025.138263_bib6 article-title: IoT-based real-time analysis of battery management system with long range communication and FLoRa publication-title: Results Eng doi: 10.1016/j.rineng.2024.102770 – volume: 71 start-page: 17 year: 2024 ident: 10.1016/j.energy.2025.138263_bib15 article-title: Specialized convolutional transformer networks for estimating battery health via transfer learning publication-title: Energy Storage Mater – volume: 305 start-page: 13 year: 2024 ident: 10.1016/j.energy.2025.138263_bib25 article-title: An adaptive semi-supervised self-learning method for online state of health estimation of lithium-ion batteries publication-title: Energy doi: 10.1016/j.energy.2024.132213 – volume: 16 start-page: 3345 year: 2020 ident: 10.1016/j.energy.2025.138263_bib51 article-title: Battery aging assessment for real-world electric buses based on incremental capacity analysis and radial basis function neural network publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2019.2951843 – volume: 85 start-page: 7 year: 2023 ident: 10.1016/j.energy.2025.138263_bib5 article-title: Electrochemical and thermal features of aging lithium-ion batteries cycled at various current rates publication-title: J Loss Prev Process Ind doi: 10.1016/j.jlp.2023.105156 – volume: 70 start-page: 28 year: 2024 ident: 10.1016/j.energy.2025.138263_bib11 article-title: Vehicle-cloud-collaborated prognosis and health management for lithium-ion batteries: framework, technics and perspective publication-title: Energy Storage Mater – volume: 266 start-page: 15 year: 2020 ident: 10.1016/j.energy.2025.138263_bib18 article-title: An ensemble prognostic method for lithium-ion battery capacity estimation based on time-varying weight allocation publication-title: Appl Energy doi: 10.1016/j.apenergy.2020.114817 – volume: 5 start-page: 1934 year: 2021 ident: 10.1016/j.energy.2025.138263_bib9 article-title: The challenge and opportunity of battery lifetime prediction from field data publication-title: Joule doi: 10.1016/j.joule.2021.06.005 – volume: 100 year: 2024 ident: 10.1016/j.energy.2025.138263_bib12 article-title: Graph neural network-based lithium-ion battery state of health estimation using partial discharging curve publication-title: J Energy Storage doi: 10.1016/j.est.2024.113502 – volume: 45 start-page: 1002 year: 2022 ident: 10.1016/j.energy.2025.138263_bib20 article-title: Rapid failure mode classification and quantification in batteries: a deep learning modeling framework publication-title: Energy Storage Mater doi: 10.1016/j.ensm.2021.07.016 – volume: 218 start-page: 17 year: 2024 ident: 10.1016/j.energy.2025.138263_bib37 article-title: Big field data-driven battery pack health estimation for electric vehicles: a deep-fusion transfer learning approach publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2024.111585 – volume: 251 start-page: 21 year: 2022 ident: 10.1016/j.energy.2025.138263_bib16 article-title: A novel method for state of health estimation of lithium-ion batteries based on improved LSTM and health indicators extraction publication-title: Energy doi: 10.1016/j.energy.2022.123973 – volume: 261 start-page: 8 year: 2022 ident: 10.1016/j.energy.2025.138263_bib53 article-title: SOH prediction of lithium battery based on IC curve feature and BP neural network publication-title: Energy doi: 10.1016/j.energy.2022.125234 – volume: 261 start-page: 30 year: 2020 ident: 10.1016/j.energy.2025.138263_bib21 article-title: A review of the state of health for lithium -ion batteries: research status and suggestions publication-title: J Clean Prod doi: 10.1016/j.jclepro.2020.120813 – volume: 5 start-page: 24 year: 2024 ident: 10.1016/j.energy.2025.138263_bib22 article-title: Semi-supervised deep learning for lithium-ion battery state-of-health estimation using dynamic discharge profiles publication-title: Cell Rep Phys Sci – volume: 12 start-page: 14 year: 2023 ident: 10.1016/j.energy.2025.138263_bib43 article-title: Logging In-Operation battery data from android devices: a possible path to sourcing battery operation data publication-title: Electronics doi: 10.3390/electronics12143049 – volume: 54 start-page: 85 year: 2023 ident: 10.1016/j.energy.2025.138263_bib13 article-title: Improving state-of-health estimation for lithium-ion batteries via unlabeled charging data publication-title: Energy Storage Mater doi: 10.1016/j.ensm.2022.10.030 – start-page: 5600 year: 2020 ident: 10.1016/j.energy.2025.138263_bib40 article-title: Ieee, data-driven nonparametric Li-Ion battery ageing model aiming at learning from real operation data: holistic validation with Ev driving profiles – volume: 6 start-page: 50587 year: 2018 ident: 10.1016/j.energy.2025.138263_bib29 article-title: Remaining useful life prediction for lithium-ion battery: a deep learning approach publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2858856 – volume: 9 start-page: 1113 year: 2023 ident: 10.1016/j.energy.2025.138263_bib27 article-title: A hybrid battery equivalent circuit model, deep learning, and transfer learning for battery state monitoring publication-title: IEEE Trans Transp Electrif doi: 10.1109/TTE.2022.3204843 – volume: 34 start-page: 15997 year: 2022 ident: 10.1016/j.energy.2025.138263_bib32 article-title: A physics-informed dynamic deep autoencoder for accurate state-of-health prediction of lithium-ion battery publication-title: Neural Comput Appl doi: 10.1007/s00521-022-07291-5 – volume: 32 start-page: 10 year: 2020 ident: 10.1016/j.energy.2025.138263_bib38 article-title: Intelligent state of health estimation for lithium-ion battery pack based on big data analysis publication-title: J Energy Storage doi: 10.1016/j.est.2020.101836 – volume: 1 start-page: 24 year: 2022 ident: 10.1016/j.energy.2025.138263_bib1 article-title: China's battery electric vehicles lead the world: achievements in technology system architecture and technological breakthroughs, green energy intell publication-title: Transp – volume: 532 start-page: 152 year: 2023 ident: 10.1016/j.energy.2025.138263_bib7 article-title: An overview of data-driven battery health estimation technology for battery management system publication-title: Neurocomputing doi: 10.1016/j.neucom.2023.02.031 – volume: 8 start-page: 2639 year: 2024 ident: 10.1016/j.energy.2025.138263_bib4 article-title: Temperature excavation to boost machine learning battery thermochemical predictions publication-title: Joule doi: 10.1016/j.joule.2024.07.002 – volume: 9 start-page: 37 year: 2023 ident: 10.1016/j.energy.2025.138263_bib35 article-title: Lithium-ion battery data: from production to prediction publication-title: Batteries-Basel – volume: 239 start-page: 17 year: 2022 ident: 10.1016/j.energy.2025.138263_bib49 article-title: State-of-health estimation for lithium-ion batteries by combining model-based incremental capacity analysis with support vector regression publication-title: Energy – volume: 242 start-page: 13 year: 2024 ident: 10.1016/j.energy.2025.138263_bib33 article-title: A physics-informed autoencoder for system health state assessment based on energy-oriented system performance publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2023.109790 – volume: 4 start-page: 310 year: 2020 ident: 10.1016/j.energy.2025.138263_bib10 article-title: Battery lifetime prognostics publication-title: Joule doi: 10.1016/j.joule.2019.11.018 – volume: 262 start-page: 14 year: 2023 ident: 10.1016/j.energy.2025.138263_bib28 article-title: A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer model publication-title: Energy doi: 10.1016/j.energy.2022.125501 – volume: 7 start-page: 2035 year: 2023 ident: 10.1016/j.energy.2025.138263_bib39 article-title: Analysis and key findings from real-world electric vehicle field data publication-title: Joule doi: 10.1016/j.joule.2023.07.018 – volume: 2 start-page: 13 year: 2019 ident: 10.1016/j.energy.2025.138263_bib3 article-title: A comparative investigation of aging effects on thermal runaway behavior of lithium-ion batteries publication-title: eTransportation doi: 10.1016/j.etran.2019.100034 – volume: 308 start-page: 15 year: 2024 ident: 10.1016/j.energy.2025.138263_bib14 article-title: SOH early prediction of lithium-ion batteries based on voltage interval selection and features fusion publication-title: Energy doi: 10.1016/j.energy.2024.132993 – volume: 4 start-page: 21 year: 2023 ident: 10.1016/j.energy.2025.138263_bib34 article-title: Large-scale field data-based battery aging prediction driven by statistical features and machine learning publication-title: Cell Rep Phys Sci – year: 2021 ident: 10.1016/j.energy.2025.138263_bib45 article-title: An image is worth 16x16 words: transformers for image recognition at scale publication-title: arXiv (USA) – volume: 11 start-page: 31 year: 2022 ident: 10.1016/j.energy.2025.138263_bib54 article-title: The design of a safe charging system based on PKS architecture publication-title: Electronics doi: 10.3390/electronics11203378 – volume: 163 start-page: 12 year: 2024 ident: 10.1016/j.energy.2025.138263_bib56 article-title: A failure risk assessment method for lithium-ion batteries based on big data of after-sales vehicles publication-title: Eng Fail Anal doi: 10.1016/j.engfailanal.2024.108559 |
| SSID | ssj0005899 |
| Score | 2.4771852 |
| Snippet | Accurately estimating the state-of-health (SOH) of lithium-ion batteries (LIBs) is crucial for optimizing performance, ensuring operational safety, and... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 138263 |
| SubjectTerms | Electric vehicle data Lithium-ion battery Masked Autoencoder Semi-supervised learning SOH estimation |
| Title | Enhanced few-shot state-of-health estimation for lithium-ion batteries via Masked Autoencoder |
| URI | https://dx.doi.org/10.1016/j.energy.2025.138263 |
| Volume | 335 |
| WOSCitedRecordID | wos001583733500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0360-5442 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0005899 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbQhgQvCAYT4yY_8Fa5SuK4sR-rqdwEE9IG6h5QlDo2zdCSaUlGfz7Ht6RjCAESL1FqxU7r8_Xk88n5jhF6mURyVtJCEMESSVIVK1KUKSeFXGmVpIytbLb75_fZ0RFfLsVHX1ChtdsJZHXNNxtx8V9NDW1gbCOd_QtzD4NCA5yD0eEIZofjHxl-Ua_dW32tvpN23XQTKxoijSZO9DgxhTXOxyRDIOLrqj8n5vPKltuE1fPkqiomH4r2Gww077vG1LssfSZvCOQ72aCpV7pxKfJDUOHYaz5OKz2i73XfOMpef930YyDfOZvToeUw6EUqE0pttsMSiS1n6t-w2FhZ0MuMyUlOoxURlqbX_C919Upu-HIXVjibKvtrpuYmU1Mx0TvE61Wyj83QZmSgdFREDJ7Ku0nGBPjq3fnbxfLdmPfD7aaiw1cJekqb9HfzXr_mK1sc5OQ-uucXD3jujP4A3VL1HroTtOXtHtpfjLpFuNA77vYh-hJQgQMq8E-owCMqMFgTb6ECD6jAgArsUIG3UPEIfXq1ODl8Q_zOGkSCi-6ITikQ57KYlSrimsGaM9MxByY9E6vUpG4yOdMxkyUVlMJfGWi6iBOpspgawsvpPtqpm1o9RlinylSNBJbNge1JxrUxQUkjnZhO8gCRMH_5hSugkofMwrPczXdu5jt3832AsjDJuSeBjtzlgIvf9nzyzz2forsjhJ-hne6yV8_RbXnVVe3lCw-gH5cYgxw |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Enhanced+few-shot+state-of-health+estimation+for+lithium-ion+batteries+via+Masked+Autoencoder&rft.jtitle=Energy+%28Oxford%29&rft.au=Shen%2C+Yifan&rft.au=Guo%2C+Dongxu&rft.au=Wang%2C+Yu&rft.au=Chen%2C+Jianguo&rft.date=2025-10-30&rft.pub=Elsevier+Ltd&rft.issn=0360-5442&rft.volume=335&rft_id=info:doi/10.1016%2Fj.energy.2025.138263&rft.externalDocID=S0360544225039052 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-5442&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-5442&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-5442&client=summon |