STATE-OF-HEALTH ESTIMATION OF LITHIUM-ION BATTERIES BASED ON CEEMDAN-GRA-ANFIS

Zhang Youbing; Wu Yixuan; Gu Jipeng; Zhu Lidan; Zhang Zhiming; Dai Lingjun

doi:10.19912/j.0254-0096.tynxb.2025-1123

PDF(3134 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (12) : 30-43. DOI: 10.19912/j.0254-0096.tynxb.2025-1123

STATE-OF-HEALTH ESTIMATION OF LITHIUM-ION BATTERIES BASED ON CEEMDAN-GRA-ANFIS

Zhang Youbing¹, Wu Yixuan¹, Gu Jipeng², Zhu Lidan³, Zhang Zhiming⁴, Dai Lingjun⁴

Author information +

History +

Abstract

Accurate and reliable estimation of the state of health （SOH） of lithium-ion batteries （LIBs）can help improve the safety and stable operation of battery-powered equipment. A lithium-ion battery SOH estimation method based on complete ensemble empirical mode decomposition with adaptive noise-grey relational analysis-adaptive neural fuzzy inference system （CEEMDAN-GRA-ANFIS） is proposed to address the current issues of inability to directly measure SOH in lithium-ion batteries, difficulty in extracting health features, and insufficient estimation methods. The method is validated using publicly available lithium-ion battery degradation test data from NASA Ames Research Center and the Advanced Lifecycle Engineering Center at the University of Maryland. Firstly, the battery charge/discharge curves are processed and CEEMDAN is used to decompose the battery degradation data into signals to extract health-related features. Then use GRA to perform correlation analysis on the feature components to select input variables for the model. Finally, the selected input-output data with obvious relevant characteristics is put into ANFIS for battery SOH estimation. The experimental results show that this method can accurately estimate the SOH of lithium-ion batteries, including both single cell and multi cell cases. The R² of the estimation results is always greater than 99%, further proving that the proposed estimation model has good generalization and robustness.

Key words

lithium-ion batteries / state estimation / battery management systems / state of health / complete ensemble empirical mode decomposition with adaptive noise （CEEMDAN） / grey relation analysis（GRA） / adaptive neuro-fuzzy inference system（ANFIS）

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhang Youbing, Wu Yixuan, Gu Jipeng, Zhu Lidan, Zhang Zhiming, Dai Lingjun. STATE-OF-HEALTH ESTIMATION OF LITHIUM-ION BATTERIES BASED ON CEEMDAN-GRA-ANFIS[J]. Acta Energiae Solaris Sinica. 2026, 47(12): 30-43 https://doi.org/10.19912/j.0254-0096.tynxb.2025-1123

References

[1] 熊庆, 邸振国, 汲胜昌. 锂离子电池健康状态估计及寿命预测研究进展综述[J]. 高电压技术, 2024, 50(3): 1182-1195.
Xiong Q, Di Z G, Ji S C.Review on health state estimation and life prediction of lithium-ion batteries[J]. High Voltage Engineering, 2024, 50(3): 1182-1195.
[2] 朱丽群, 张建秋. 一种联合锂电池健康和荷电状态的新模型[J]. 中国电机工程学报, 2018, 38(12): 3613-3620, 21.
Zhu L Q, Zhang J Q.A new model of jointed states of charge and health for lithium batteries[J]. Proceedings of the CSEE, 2018, 38(12): 3613-3620, 21.
[3] Li C R, Xiao F, Fan Y X.An approach to state of charge estimation of lithium-ion batteries based on recurrent neural networks with gated recurrent unit[J]. Energies, 2019, 12(9): 1592.
[4] Dai H D, Zhao G C, Lin M Q, et al.A novel estimation method for the state of health of lithium-ion battery using prior knowledge-based neural network and Markov chain[J]. IEEE Transactions on Industrial Electronics, 2019, 66(10): 7706-7716.
[5] 刘芳, 马杰, 苏卫星, 等. 基于自适应回归扩展卡尔曼滤波的电动汽车动力电池全生命周期的荷电状态估算方法[J]. 电工技术学报, 2020, 35(4): 698-707.
Liu F, Ma J, Su W X, et al.State of charge estimation method of electric vehicle power battery life cycle based on auto regression extended Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(4): 698-707.
[6] Ramadan H S, Becherif M, Claude F.Extended Kalman filter for accurate state of charge estimation of lithium-based batteries: a comparative analysis[J]. International Journal of Hydrogen Energy, 2017, 42(48): 29033-29046.
[7] 郝文美, 张立伟, 彭博, 等. 动车组钛酸锂电池荷电状态估计[J]. 电工技术学报, 2021, 36(S1): 362-371.
Hao W M, Zhang L W, Peng B, et al.State of charge estimation of lithium titanate battery for electric multiple units[J]. Transactions of China Electrotechnical Society, 2021, 36(S1): 362-371.
[8] 宫明辉, 乌江, 焦朝勇. 基于模糊自适应扩展卡尔曼滤波器的锂电池SOC估算方法[J]. 电工技术学报, 2020, 35(18): 3972-3978.
Gong M H, Wu J, Jiao C Y.SOC estimation method of lithium battery based on fuzzy adaptive extended Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(18): 3972-3978.
[9] 李超然, 肖飞, 樊亚翔, 等. 基于门控循环单元神经网络和Huber-M估计鲁棒卡尔曼滤波融合方法的锂离子电池荷电状态估算方法[J]. 电工技术学报, 2020, 35(9): 2051-2062.
Li C R, Xiao F, Fan Y X, et al.A hybrid approach to lithium-ion battery SOC estimation based on recurrent neural network with gated recurrent unit and Huber-M robust Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(9): 2051-2062.
[10] 庞辉, 郭龙, 武龙星, 等. 考虑环境温度影响的锂离子电池改进双极化模型及其荷电状态估算[J]. 电工技术学报, 2021, 36(10): 2178-2189.
Pang H, Guo L, Wu L X, et al.An improved dual polarization model of Li-ion battery and its state of charge estimation considering ambient temperature[J]. Transactions of China Electrotechnical Society, 2021, 36(10): 2178-2189.
[11] 董磊, 赖纪东, 苏建徽, 等. 基于IMAFFRLS-EKF的锂电池在线参数辨识和SOC估计方法[J]. 太阳能学报, 2024, 45(6): 66-74.
Dong L, Lai J D, Su J H, et al.Online parameter identification and SOC estimation of lithium battery based on IMAFFRLS-EKF[J]. Acta Energiae Solaris Sinica, 2024, 45(6): 66-74.
[12] 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.
[13] Ding P, Xia M L, Wang X J, et al.Advanced lithium-ion battery health state estimation using a Bayesian optimization hybrid neural network model[J]. Journal of Energy Storage, 2025, 123: 116562.
[14] Zhang N, Li J, Ma Y F, et al.Lithium-ion batteries state of health estimation based on optimized TCN-GRU-WNN[J]. Energy Reports, 2025, 13: 2502-2515.
[15] 宋显华, 姚全正. 基于片段充电数据和DEKF-WNN-WLSTM的锂电池健康状态实时估计[J]. 电工技术学报, 2024, 39(5): 1565-1576.
Song X H, Yao Q Z.Real-time state of health estimation for lithium-ion batteries based on daily segment charging data and dual extended Kalman filters-wavelet neural network-wavelet long short-term memory neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(5): 1565-1576.
[16] 方斯顿, 刘龙真, 孔赖强, 等. 基于双向长短期记忆网络含间接健康指标的锂电池SOH估计[J]. 电力系统自动化, 2024, 48(4): 160-168.
Fang S D, Liu L Z, Kong L Q, et al.State-of-health estimation for lithium-ion batteries incorporating indirect health indicators based on bi-directional long short-term memory networks[J]. Automation of Electric Power Systems, 2024, 48(4): 160-168.
[17] 李鹏, 葛儒哲, 董存, 等. 基于转置Transformer模型的电化学储能自适应SOH估计方法[J]. 高电压技术, 2025, 51(6): 2945-2953.
Li P, Ge R Z, Dong C, et al.Adaptive SOH estimation method based on the transpose Transformer model for electrochemical energy storage[J]. High Voltage Engineering, 2025, 51(6): 2945-2953.
[18] 王萍, 彭香园, 程泽. 基于DTV-IGPR模型的锂离子电池SOH估计方法[J]. 汽车工程, 2021, 43(11): 1710-1719.
Wang P, Peng X Y, Cheng Z.SOH estimation method for lithium-ion batteries based on DTV-IGPR model[J]. Automotive Engineering, 2021, 43(11): 1710-1719.
[19] 钱玉村, 杨博, 郑如意, 等. 基于经验模态分解-灰色关联度分析-蒲公英优化器改进Elman网络的锂离子电池健康状态估计[J]. 电网技术, 2024, 48(9): 3695-3704.
Qian Y C, Yang B, Zheng R Y, et al.State-of-health estimation of lithium-ion batteries based on EMD-DO-Elman and GRA[J]. Power System Technology, 2024, 48(9): 3695-3704.
[20] 陈媛, 段文献, 何怡刚, 等. 带降噪自编码器和门控递归混合神经网络的电池健康状态估算[J]. 电工技术学报, 2024, 39(24): 7933-7949.
Chen Y, Duan W X, He Y G, et al.State of health estimation of lithium ion battery based on denoising autoencoder-gated recurrent unit[J]. Transactions of China Electrotechnical Society, 2024, 39(24): 7933-7949.
[21] 詹莹, 王潇添, 王旭, 等. 基于综合距离相似的CEEMDAN-Informer光伏功率组合预测模型研究[J]. 太阳能学报, 2025, 46(8): 315-326.
Zhan Y, Wang X T, Wang X, et al.Study on photovoltaic power combined prediction model employing CEEMDAN-Informer based on comprehensive distance similar[J]. Acta Energiae Solaris Sinica, 2025, 46(8): 315-326.
[22] 李练兵, 高国强, 陶鹏, 等. 基于SFLA和MSISSA-ANFIS的超短期光伏功率动态预测方法[J]. 太阳能学报, 2024, 45(10): 326-335.
Li L B, Gao G Q, Tao P, et al.Ultra-short-term PV power dynamic prediction method based on SFLA and MSISSA-ANFIS[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 326-335.