CAPACITY PREDICTION METHOD OF LITHIUM-ION BATTERY BASED ON RECURRENCE PLOTS AND CONVOLUTIONAL NEURAL NETWORK

Li Zhiming; Xia Xiangyang; Luo Yichong; Bai Wenqi; Peng Cheng

doi:10.19912/j.0254-0096.tynxb.2025-1152

PDF(1667 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (12) : 56-65. DOI: 10.19912/j.0254-0096.tynxb.2025-1152

CAPACITY PREDICTION METHOD OF LITHIUM-ION BATTERY BASED ON RECURRENCE PLOTS AND CONVOLUTIONAL NEURAL NETWORK

Li Zhiming¹, Xia Xiangyang¹, Luo Yichong¹, Bai Wenqi², Peng Cheng³

Author information +

History +

Abstract

This paper proposes a capacity prediction method for lithium-ion batteries based on Recurrence Plot （RP） and Convolutional Neural Network （CNN）. Firstly, the differential voltage （dV/dQ） curves of the batteries are converted into recurrence plots, effectively capturing the complex dynamic characteristics of capacity degradation during practical operation. Subsequently, a CNN is employed to extract multi-level features, achieving efficient capacity regression prediction. Finally, comprehensive validation is conducted using the public lithium-ion battery aging dataset from Tongji University and a lithium-ion battery aging experimental platform. The results indicate that the error metrics （MAE, RMSE, and MAPE） of the proposed method are all maintained at low levels. This verifies the effectiveness and robustness of the proposed capacity prediction method.

Key words

lithium-ion batteries / convolutional neural networks / state estimation / recurrence plot / battery capacity prediction / differential voltage / feature image

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Li Zhiming, Xia Xiangyang, Luo Yichong, Bai Wenqi, Peng Cheng. CAPACITY PREDICTION METHOD OF LITHIUM-ION BATTERY BASED ON RECURRENCE PLOTS AND CONVOLUTIONAL NEURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2026, 47(12): 56-65 https://doi.org/10.19912/j.0254-0096.tynxb.2025-1152

References

[1] 李卓昊, 石琼林, 王康丽, 等. 锂离子电池健康状态估计方法研究现状与展望[J]. 电力系统自动化, 2024, 48(20): 109-129.
Li Z H, Shi Q L, Wang K L, et al.Research status and prospects of state of health estimation methods for lithium-ion batteries[J]. Automation of Electric Power Systems, 2024, 48(20): 109-129.
[2] 陈凌彬, 夏向阳, 廖一丁, 等. 考虑多变量协同保护的储能变流器故障穿越策略[J]. 太阳能学报, 2023, 44(1): 442-450.
Chen L B, Xia X Y, Liao Y D, et al.Fault ride through strategy of power conversion system considering multi-variable cooperative protection[J]. Acta Energiae Solaris Sinica, 2023, 44(1): 442-450.
[3] 夏向阳, 陈贵全, 夏天, 等. 二次谐波分量下锂离子电池安全运行区间研究[J]. 太阳能学报, 2023, 44(10): 496-503.
Xia X Y, Chen G Q, Xia T, et al.Study on safe operation range of lithium-ion battery under second harmonic component[J]. Acta Energiae Solaris Sinica, 2023, 44(10): 496-503.
[4] 徐俊, 郭喆晨, 谢延敏, 等. 储能锂电池系统综合管理研究进展[J]. 西安交通大学学报, 2024, 58(10): 1-23.
Xu J, Guo Z C, Xie Y M, et al.Review of research progress in integrated management for energy storage lithium battery systems[J]. Journal of Xi’an Jiaotong University, 2024, 58(10): 1-23.
[5] 金帅, 董静. 基于数据驱动的锂离子电池健康状态估计研究进展综述[J]. 仪器仪表学报, 2024, 45(3): 45-59.
Jin S, Dong J.Review on progress of data-driven based health state estimation for lithium-ion batteries[J]. Chinese Journal of Scientific Instrument, 2024, 45(3): 45-59.
[6] Liu Y S, Wang L C, Li D Z, et al.State-of-health estimation of lithium-ion batteries based on electrochemical impedance spectroscopy: a review[J]. Protection and Control of Modern Power Systems, 2023, 8(1): 41.
[7] 夏向阳, 岳家辉, 张媛, 等. 基于特征数据信息熵的锂离子储能电站电芯健康状态评估与预测方法研究[J]. 太阳能学报, 2025, 46(2): 78-89.
Xia X Y, Yue J H, Zhang Y, et al.SOH estimation and prediction method for cells of lithium-ion energy storage power station based on information entropy of characteristic data[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 78-89.
[8] Xia Z Y, Abu Qahouq J A. Lithium-ion battery ageing behavior pattern characterization and state-of-health estimation using data-driven method[J]. IEEE Access, 2021, 9: 98287-98304.
[9] Li D Z, Yang D F, Li L W, et al.Electrochemical impedance spectroscopy based on the state of health estimation for lithium-ion batteries[J]. Energies, 2022, 15(18): 1-26.
[10] 董明, 罗阳, 雷万钧, 等. 基于电化学阻抗谱的并联电池状态差异辨识方法[J]. 电工技术学报, 2025, 40(20): 6744-6756.
Dong M, Luo Y, Lei W J, et al.State difference identification method of parallel battery module based on electrochemical impedance spectroscopy[J]. Transactions of China Electrotechnical Society, 2025, 40(20): 6744-6756.
[11] Zhang M, Liu Y, Li D, et al.Electrochemical impedance spectroscopy: A new chapter in the fast and accurate estimation of the state of health for lithium-ion batteries[J]. Energies, 2023, 16(4): 1599.
[12] Lee J, Sun H L, Liu Y S, et al.A machine learning framework for remaining useful lifetime prediction of li-ion batteries using diverse neural networks[J]. Energy and AI, 2024, 15: 100319.
[13] Li Q, Li H S, Xia Q T, et al.Extra storage capacity in transition metal oxide lithium-ion batteries revealed by in situ magnetometry[J]. Nature Materials, 2021, 20(1): 76-83.
[14] Chen Y, Lin A J.Order pattern recurrence for the analysis of complex systems[J]. Physica A: Statistical Mechanics and its Applications, 2022, 607: 128204.
[15] 夏向阳, 岳家辉, 曾小勇, 等. 基于状态相依的RBF-ARX模型的锂离子电池剩余容量估计方法[J]. 中国电机工程学报, 2025, 45(2): 638-649.
Xia X Y, Yue J H, Zeng X Y, et al.The remaining capacity estimation of battery based on state-dependent RBF-ARX model[J]. Proceedings of the CSEE, 2025, 45(2): 638-650.
[16] 车云弘, 邓忠伟, 李佳承, 等. 基于数据驱动的电池系统泛化SOH估计方法[J]. 机械工程学报, 2022, 58(24): 253-263.
Che Y H, Deng Z W, Li J C, et al.Generalized data-driven SOH estimation method for battery systems[J]. Journal of Mechanical Engineering, 2022, 58(24): 253-263.
[17] 江银锋, 宋文祥, 施语. 基于随机充放电片段和稀疏高斯过程回归的电池健康状态估计[J]. 电工技术学报, 2025, 40(19): 6359-6377.
Jiang Y F, Song W X, Shi Y.Battery state of health estimation using sparse Gaussian process regression based on random partial charge and discharge data[J]. Transactions of China Electrotechnical Society, 2025, 40(19): 6359-6377.
[18] 夏向阳, 吕崇耿, 吴小忠, 等. 基于混合模型的储能用锂离子电池剩余寿命预测方法研究[J]. 太阳能学报, 2024, 45(10): 726-735.
Xia X Y, Lyu C G, Wu X Z, et al.Research on remaining life prediction method of lithium-ion battery for energy storage based on hybrid model[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 726-735.
[19] Zhang W C, He H C, Li T T, et al.Lithium-ion battery state of health prognostication employing multi-model fusion approach based on image coding of charging voltage and temperature data[J]. Energy, 2024, 296: 131095.
[20] Guo F, Huang G S, Zhang W C, et al.State of Health estimation method for lithium batteries based on electrochemical impedance spectroscopy and pseudo-image feature extraction[J]. Measurement, 2023, 220: 113412.
[21] Zou W H, Hu Z Y, Yu K, et al.State of health estimation for lithium-ion batteries based on recurrence plot analysis using charging voltage curves[J]. Journal of Energy Storage, 2025, 123: 116804.
[22] Bloom I, Jansen A N, Abraham D P, et al.Differential voltage analyses of high-power, lithium-ion cells: 1. Technique and application[J]. Journal of Power Sources, 2005, 139(1-2): 295-303.
[23] 王睿茜, 周星, 王羽, 等. 基于微分曲线的锂离子电池老化诊断研究综述[J]. 中国电机工程学报, 2024, 44(22): 8920-8936
Wang R X, Zhou X, Wang Y, et al.A review of degradation diagnosis of lithium-ion batteries based on differential curves[J]. Proceedings of the CSEE, 2024, 44(22): 8920-8936.
[24] 孙玉树, 安娟, 黄存强, 等. 基于时间卷积网络的电池寿命评估方法[J]. 工程科学与技术, 2025, 57(4): 259-268.
Sun Y S, An J, Huang C Q, et al.Battery life evaluation method based on temporal convolution network[J]. Advanced Engineering Sciences, 2025, 57(4): 259-268.