Objective To improve the technical economy of battery system applications, a temporal convolutional network (TCN) is employed to evaluate battery life from two perspectives: State of health (SOH) and remaining useful life (RUL). SOH is typically quantified by capacity, while RUL is measured in terms of the remaining number of charge-discharge cycles. Methods First, the TCN-based approach to battery life assessment is introduced. Compared to classical recurrent neural networks, TCN has the advantages of improved gradient stability, faster data processing, and reduced memory consumption. Next, 14 indirect health-related features are extracted from readily available battery data including time, voltage, current, and temperature. The relevance of each feature to capacity is assessed using three correlation techniques: KL divergence, Pearson correlation coefficient, and gray relational analysis. Additionally, a polling strategy is employed using the TCN: each feature is used individually for capacity prediction, and the mean of six prediction outcomes per feature is taken as the final correlation score. Correlation results from all four methods are compared. Although Pearson correlation and TCN-based analysis yield similar rankings, both focus primarily on the top features. Due to the different principles of these methods, their outcomes often diverge significantly. Therefore, TCN-derived results are considered the most reliable for identifying factors influencing capacity prediction. For lithium-ion battery data from NASA, five features with the greatest impact on SOH are identified (in descending order of importance): cycle time, average voltage, voltage sample entropy, temperature sample entropy, and current. Results and Discussions To address redundancy caused by overlapping information among these features, Kernel principal component analysis (KPCA) is applied for dimensionality reduction. The contribution rates of principal components are calculated, and the top two principal components (PC1 and PC2) are selected as inputs for simulation to eliminate noise and improve computational efficiency. A comparative analysis of three prediction models including TCN, long short-term memory (LSTM) networks, and Backpropagation (BP) neural networks shows that the TCN achieves the lowest root mean square error (RMSE) of 0.019 3, indicating the highest predictive accuracy. Battery capacity regeneration can result in similar capacities at different numbers of cycles or times. When SOH is used to characterize battery life, significant errors will be introduced. In contrast, RUL will irreversibly decrease as the service time increases, which can provide a more reliable criterion for evaluation. To predict RUL, the same five key features (cycle time, average voltage, voltage sample entropy, temperature sample entropy, current) along with capacity are used. Six principal components are obtained through KPCA analysis, and PC1 and PC2 are also selected for prediction. Among the three models compared, the RMSE of TCN is lowest (0.019 3), which further proves its outstanding accuracy in RUL estimation. Conclusions This study validates the effectiveness of TCN for battery life prediction. By evaluating both SOH and RUL, the proposed TCN-based framework provides a more accurate and robust assessment of battery health.
LiuChun, LiPai, ZhangJinping,et al.Research of the role of energy storage system in power and energy balance of the new type power system[J/OL].Power System Technology(2025-03-12)[2025-06-15].
LiJianlin, XiaoHeng.Review on modeling of lithium-ion battery[J].Energy Storage Science and Technology,2022,11(2):697-703.
[4]
李建林,肖珩.锂离子电池建模现状综述[J].储能科学与技术,2022,11(2):697-703.
[5]
SuiXin, HeShan, VilsenS B,et al.A review of non-pro-babilistic machine learning-based state of health estimation techniques for Lithium-ion battery[J].Applied Energy,2021,300:117346. doi:10.1016/j.apenergy.2021.117346
[6]
ZhangCheng, LuWanlin, ZhangDongqing,et al.Joint estimation of lithium battery states based on improved fuzzy entropy fusion weighting method with regulation factors[J/OL].Transactions of China Electrotechnical Society(2025-04-15)[2025-06-15].
SunYushu, GongYichun, DongLiang,et al.Review of state estimation for battery energy storage systems[J].Journal of Central South University(Science and Technology),2024,55(6):2320-2333.
Khodadadi SadabadiK, JinXin, RizzoniG.Prediction of remaining useful life for a composite electrode lithium ion battery cell using an electrochemical model to estimate the state of health[J].Journal of Power Sources,2021,481:228861. doi:10.1016/j.jpowsour.2020.228861
[11]
GaoRenjing, ZhiqiangLü, ZhaoShuai,et al.Health state estimation of Li-ion batteries based on electrochemical mo-del[J].Transactions of Beijing Institute of Technology,2022,42(8):791-797.
BiYalan, YinYilin, ChoeS Y.Online state of health and aging parameter estimation using a physics-based life model with a particle filter[J].Journal of Power Sources,2020,476:228655. doi:10.1016/j.jpowsour.2020.228655
[14]
ZhangFengzhu, ZhangZhiyu, MaWentao.SREKF based state of health estimation for lithium battery[J].Chinese Journal of Power Sources,2020,44(5):740-743.
RenPu, WangShunli, HeMingfang,et al.State of health estimation of Li-ion battery based on dual calibration of internal resistance increasing and capacity fading[J].Energy Storage Science and Technology,2021,10(2):738-743. doi:10.1002/er.7230
ShiGaoya, ChenSiqi, YuanHao,et al.Determination of optimal indicators based on statistical analysis for the state of health estimation of a lithium-ion battery[J].Frontiers in Energy Research,2021,9:690266. doi:10.3389/fenrg.2021.690266
[19]
ChenYi, BaiYunfei, HeYing.Comparison of data-driven lithium battery state of health estimation methods[J].Energy Storage Science and Technology,2019,8(6):1204-1210.
LiuDatong, PangJingyue, ZhouJianbao,et al.Prognostics for state of health estimation of lithium-ion batteries based on combination Gaussian process functional regression[J].Microelectronics Reliability,2013,53(6):832-839. doi:10.1016/j.microrel.2013.03.010
[22]
ChenZewang, ZhangSongyuan, ShiNa,et al.Online state-of-health estimation of lithium-ion battery based on relevance vector machine with dynamic integration[J].App-lied Soft Computing,2022,129:109615. doi:10.1016/j.asoc.2022.109615
[23]
WangXue, YouGuodong, FangChengxin,et al.SOH estimation of lithium-ion battery based on IMOCS-BP neural network[J].Journal of Power Supply,2024,22(1):94-100.
VeeraraghavanA, AdithyaV, BhaveA,et al.Battery aging estimation with deep learning[C]//Proceedings of the 2017 IEEE Transportation Electrification Conference.Pune:IE-EE,2017:1-4. doi:10.1109/itec-india.2017.8333827
[26]
RenLei, ZhaoLi, HongSheng,et al.Remaining useful life prediction for lithium-ion battery:A deep learning approach[J].IEEE Access,2018,6:50587-50598. doi:10.1109/access.2018.2858856
[27]
HuTianzhong, YuJianbo.Life prediction of lithium-ion batteries based on multiscale decomposition and deep lear-ning[J].Journal of Zhejiang University(Engineering Science),2019,53(10):1852-1864.
WuPin, SunJunwu, ChangXuting,et al.Data-driven reduced order model with temporal convolutional neural network[J].Computer Methods in Applied Mechanics and Engineering,2020,360:112766. doi:10.1016/j.cma.2019.112766
[32]
LiZihao, WuWenchuan, ZhangBoming,et al.Kullback-Leibler divergence-based distributionally robust optimisation model for heat pump day-ahead operational schedule to improve PV integration[J].IET Generation,Transmission & Distribution,2018,12(13):3136-3144. doi:10.1049/iet-gtd.2017.2062
[33]
ChenZexi, SunYushu, ZhangYan,et al.Research on energy storage optimal allocation considering complementarity of wind power and PV[J].Transactions of China Electrotechnical Society,2021,36(Supp1):145-153.
ChenHaiyan, YangZhenpeng, LiXinjian,et al.Grey incidence analysis for factors influencing SOP of power battery[J].Chinese Journal of Power Sources,2019,43(6):1032-1033.
BoleB, KulkarniC S, DaigleM.Adaptation of an elec-trochemistry-based Li-ion battery model to account for deterioration observed under randomized use[C]//Proceedings of 2014 Annual Conference of the Prognostics and Health Management Society.Texas:PHM Society,2014:1-9. doi:10.36001/phmconf.2014.v6i1.2490
[38]
Souza FilhoJ B O, DinizP S R.Improving KPCA online extraction by orthonormalization in the feature space[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(4):1382-1387. doi:10.1109/tnnls.2017.2660441