BATTERY STATE OF HEALTH ESTIMATION METHOD BASED ON MULTI-MODEL FUSION

Gao Bingmei; Bao Caijilahu; Wang Xin; Ma Zhiqiang; Wang Hongbin; Zhang Jiaqi

doi:10.19912/j.0254-0096.tynxb.2025-1128

PDF(1609 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (12) : 44-55. DOI: 10.19912/j.0254-0096.tynxb.2025-1128

BATTERY STATE OF HEALTH ESTIMATION METHOD BASED ON MULTI-MODEL FUSION

Gao Bingmei¹, Bao Caijilahu^1,2, Wang Xin¹, Ma Zhiqiang^1,2, Wang Hongbin^1,2, Zhang Jiaqi¹

Author information +

History +

Abstract

The capacity of batteries gradually decreases during long-term operation, and an accurate estimation of battery state of health is crucial to ensuring the safe operation of new energy storage power stations. Aiming at the problems of model uncertainty due to the difficulty of health feature selection and the loss of key information during feature extraction due to data noise, a battery state of health estimation method based on multi-model fusion is proposed. Firstly, the uncertainty of feature selection is reduced by analyzing the battery charging and discharging data and extracting key health features; Secondly, the features are extracted in depth using a noise-reducing autoencoder and an attention mechanism to convert the low-level features into key features and reduce the interference of noise; Finally, extreme gradient boosting modeling is used to capture the complex patterns and nonlinear dependencies in the data. Comparison, ablation, and generalization experiments are conducted based on publicly available datasets. The experimental results demonstrate that the proposed model reduces the average MAE by 38% and RMSE by 42% compared with the suboptimal model, indicating high accuracy and good generalization performance in battery SOH estimation tasks.

Key words

lithium-ion batteries / deep learning / machine learning / attention mechanism / state of health estimation

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Gao Bingmei, Bao Caijilahu, Wang Xin, Ma Zhiqiang, Wang Hongbin, Zhang Jiaqi. BATTERY STATE OF HEALTH ESTIMATION METHOD BASED ON MULTI-MODEL FUSION[J]. Acta Energiae Solaris Sinica. 2026, 47(12): 44-55 https://doi.org/10.19912/j.0254-0096.tynxb.2025-1128

References

[1] Sankar T K, Abhilash, Meshram P.Environmental impact assessment in the entire life cycle of lithium-ion batteries[J]. Reviews of Environmental Contamination and Toxicology, 2023, 262(1): 5.
[2] Mu J B, Liao S M, Shi L L, et al.Solid-state polymer electrolytes in lithium batteries: latest progress and perspective[J]. Polymer Chemistry, 2024, 15(6): 473-499
[3] Stokes R.Overview of Li-ion battery energy storage system failures and risk management considerations[J]. Process Safety Progress, 2022, 41(3): 437-439.
[4] 耿萌萌, 范茂松, 魏斌, 等. 基于片段数据的储能电池SOH估计[J]. 全球能源互联网, 2025, 8(1): 57-66.
Geng M M, Fan M S, Wei B, et al.SOH estimation of energy storage batteries based on fragmented data[J]. Journal of Global Energy Interconnection, 2025, 8(1): 57-66.
[5] 李青春, 徐君威, 张绍强, 等. 计及新能源波动平抑的储能电站日前-实时运行决策[J]. 太阳能学报, 2025, 46(3): 43-53.
Li Q C, Xu J W, Zhang S Q, et al.Decision for day-ahead and real-time operation of energy storage plants considering smoothing of new energy fluctuations[J]. Acta Energiae Solaris Sinica, 2025, 46(3): 43-53.
[6] 何冰琛, 杨薛明, 王劲松, 等. 基于PCA-GPR的锂离子电池剩余使用寿命预测[J]. 太阳能学报, 2022, 43(5): 484-491.
He B C, Yang X M, Wang J S, et al.Prediction of remaining useful life of lithium-ion batteries based on PCA-GPR[J]. Acta Energiae Solaris Sinica, 2022, 43(5): 484-491.
[7] Goodenough J B, Park K S.The Li-ion rechargeable battery: a perspective[J]. Journal of the American Chemical Society, 2013, 135(4): 1167-1176.
[8] 黄佳茵, 白俊琦, 贤燕华. 基于DOD-LN-GPR模型的锂离子电池SOH估计方法[J]. 太阳能学报, 2025, 46(2): 60-69.
Huang J Y, Bai J Q, Xian Y H.SOH estimation method of lithium-ion batteries based on DOD-LN-GPR model[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 60-69.
[9] Li J, Adewuyi K, Lotfi N, et al.A single particle model with chemical/mechanical degradation physics for lithium ion battery state of health (SOH) estimation[J]. Applied Energy, 2018, 212: 1178-1190.
[10] Hosseininasab S, Lin C W, Pischinger S, et al.State-of-health estimation of lithium-ion batteries for electrified vehicles using a reduced-order electrochemical model[J]. Journal of Energy Storage, 2022, 52: 104684.
[11] Gao Y Z, Liu K L, Zhu C, et al.Co-estimation of state-of-charge and state-of-health for lithium-ion batteries using an enhanced electrochemical model[J]. IEEE Transactions on Industrial Electronics, 2022, 69(3): 2684-2696.
[12] 陈猛, 乌江, 焦朝勇, 等. 锂离子电池健康状态多因子在线估计方法[J]. 西安交通大学学报, 2020, 54(1): 169-175.
Chen M, Wu J, Jiao C Y, et al.Multi-factor online estimation method for health status of lithium-ion battery[J]. Journal of Xi’an Jiaotong University, 2020, 54(1): 169-175.
[13] Yang J F, Cai Y F, Mi C C.State-of-health estimation for lithium-ion batteries based on decoupled dynamic characteristic of constant-voltage charging current[J]. IEEE Transactions on Transportation Electrification, 2022, 8(2): 2070-2079.
[14] 魏梓轩, 韩晓娟, 李炫. 基于深度神经网络的梯次利用电池健康状态评估[J]. 太阳能学报, 2022, 43(5): 518-524.
Wei Z X, Han X J, Li X.State of health assessment for echelon utilization batteries based on deep neural network[J]. Acta Energiae Solaris Sinica, 2022, 43(5): 518-524.
[15] Deng Z W, Hu X S, Li P H, et al.Data-driven battery state of health estimation based on random partial charging data[J]. IEEE Transactions on Power Electronics, 2022, 37(5): 5021-5031.
[16] Tian J P, Xiong R, Shen W X.State-of-health estimation based on differential temperature for lithium ion batteries[J]. IEEE Transactions on Power Electronics, 2020, 35(10): 10363-10373.
[17] Li P H, Zhang Z J, Xiong Q Y, et al.State-of-health estimation and remaining useful life prediction for the lithium-ion battery based on a variant long short term memory neural network[J]. Journal of Power Sources, 2020, 459: 228069.
[18] Bian X L, Wei Z B, He J T, et al.A novel model-based voltage construction method for robust state-of-health estimation of lithium-ion batteries[J]. IEEE Transactions on Industrial Electronics, 2021, 68(12): 12173-12184.
[19] 王凡, 史永胜, 刘博亲, 等. 基于注意力改进BiGRU的锂离子电池健康状态估计[J]. 储能科学与技术, 2021, 10(6): 2326-2333.
Wang F, Shi Y S, Liu B Q, et al.Health state estimation of lithium-ion batteries based on attention augmented BiGRU[J]. Energy Storage Science and Technology, 2021, 10(6): 2326-2333.
[20] 李凯, 胡丽, 宋婷婷. 基于CNN-Bi-LSTM的锂离子电池健康状态估算[J]. 山东电力技术, 2023, 50(10): 66-72.
Li K, Hu L, Song T T.Health state estimation of lithium-ion batteries based on CNN-Bi-LSTM[J]. Shandong Electric Power, 2023, 50(10): 66-72.
[21] Shu X, Shen J W, Li G, et al.A flexible state-of-health prediction scheme for lithium-ion battery packs with long short-term memory network and transfer learning[J]. IEEE Transactions on Transportation Electrification, 2021, 7(4): 2238-2248.
[22] Fan Y X, Xiao F, Li C R, et al.A novel deep learning framework for state of health estimation of lithium-ion battery[J]. Journal of Energy Storage, 2020, 32: 101741.
[23] Vincent P, Larochelle H, Lajoie I, et al.Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11: 3371-3408.
[24] Vaswani A, Shazeer N, Parmar N, et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, California, USA, 2017: 6000-6010.
[25] Chen T Q, Guestrin C.XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA, 2016: 785-794.