Data Analysis and Health Feature Construction for Lithium Battery Performance Testing
DOI:
https://doi.org/10.63313/AERpc.9082Keywords:
lithium battery, performance testing, data analysis, health characteristics, battery lifeAbstract
This study aims to conduct an in-depth analysis of lithium battery performance test data to reveal degradation patterns, enabling precise evaluation of battery health status and life prediction. In data collection, a multidimensional experimental framework was established based on NASA's standard battery aging dataset, systematically conducting feature mining and health factor extraction from charge-discharge data. By analyzing dynamic variations in parameters such as voltage, current, and temperature, combined with capacity increment analysis techniques, key features reflecting internal battery conditions were extracted. The research findings demonstrate that the constructed health features accurately reflect battery health status, which is crucial for ensuring performance, extending lifespan, and enhancing safety. These insights provide robust support for optimizing lithium battery applications across various scenarios.
References
[1] Ma J; Wan JJ. Prediction of lithium battery health status based on health feature screening and GWO-LSSVM [J]. Electrical Technology, 2024,25(2):37-44.
[2] Guo Xifeng; Huang Yuhai; Shan Dan; Yuan Baolong; Ning Yi. Improving global ZOA optimization for MVMD-SCN-based lithium battery SOH estimation [J]. Electronic Measurement Technology, 2024,47(5):22-30.
[3] Geng C; Meng JH; Peng Q; Liu TQ; Zeng SY; Chen G. Health state estimation of lithium-ion batteries based on relaxation process feature extraction[J]. Energy Storage Science and Technology, 2023,12(11):3479-3487.
[4] Shao Yibo; Lü Yuxiang; Sun Shengnan; Wang Shuai; Nan Yongbing. Detection of charge state performance and health status analysis of lithium-ion batteries [J]. Electrical Measurement and Instrumentation, 2019,56(13):113-116.
[5] Liu Dan; Wang Ruihu; Lü Wei; Qin Ling; Lin Shuichun. Health status monitoring of lithium batteries for new energy vehicles based on IPSO-LSTM [J]. China Journal of Safety Science, 2023,33(9):94-102.
[6] Chen W, Zhang M, Feng T. Extraction of lithium battery health factors and SOH prediction based on Douglas-Peucker fusion Min-style distance[J]. Energy Storage Science and Technology, 2022,11(10):3306-3315.
[7] Hu J, Lu Y, Lin B. RUL Prediction for Lithium-ion Batteries Using Combination Forecasting based on SVR and LSTM; proceedings of the 2021 China Automation Congress (CAC), F, 2021[C]. IEEE.
[8] Shi Y , Yang Y , Wen J ,et al. Remaining useful life Prediction for lithium-ion battery based on CEEMDAN and SVR[C]//2020 IEEE 18th International Conference on Industrial Informatics (INDIN).IEEE, 2020.
[9] Chen L , An J , Wang H ,[9] Chen L , An J , Wang H , et al. Remaining useful life prediction for lithium-ion battery by combining an improved particle filter with sliding-window gray model[J].Energy Reports, 2020, 6:2086-2093.
[10] Tang T , Yuan H .A hybrid approach based on decomposition algorithm and neural network for remaining useful life prediction of lithium-ion battery[J].Reliability Engineering & System Safety, 2022, 217:108082- 108093.
[11] Liwen H ,Wenbo W ,Guorong D .RUL prediction for lithium-ion batteries based on variational mode de- composition and hybrid network model[J].Signal, Image and Video Processing,2023,17(6):3109- 3117.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by author(s) and Erytis Publishing Limited.
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
