State of charge estimation of lithium iron phosphate batteries based on force-electric-temperature signals and a CNN-BiLSTM model

doi:10.19799/j.cnki.2095-4239.2025.0062

Abstract

Abstract:

The state of charge (SOC) of lithium batteries is a critical parameter for battery management systems. However, SOC cannot be measured directly because it is strongly coupled to the intricate electrochemical characteristics of the battery. Although data-driven methods recently demonstrated significant potential in SOC estimation, their accuracy depends greatly on the precision of input data. SOC estimation of lithium iron phosphate (LiFePO₄) batteries is challenging because the battery exhibits voltage plateau characteristics: voltage fluctuations and noise substantially degrade the estimation reliability. To overcome this challenge, this study proposes a hybrid experimental and data-driven approach that incorporates battery expansion force as a novel input dimension, thereby synergizing the electrochemical and mechanical properties of the battery to mitigate the impact of voltage plateau on SOC estimation. Experiments were conducted at four environmental temperatures and under two dynamic current test conditions. The acquired data were used to train and validate neural network models for evaluating the SOC estimation accuracy and to verify the feasibility and robustness of the proposed method. Furthermore, a hybrid model combining a convolutional neural network (CNN) and a bidirectional long short-term memory (Bi-LSTM) network was developed to simultaneously capture local temporal patterns and long-term dependencies in sequential data, further enhancing the SOC estimation reliability. The results indicated that the proposed method remarkably improved the SOC estimation accuracy for LiFePO₄ batteries, achieving an average reduction of 43.82% in the root-mean-square error (RMSE) compared to methods that did not incorporate expansion force signals. Moreover, the CNN-BiLSTM model outperformed conventional neural network models, achieving a maximum RMSE reduction of 53.88%. Thus, this study provides a novel perspective for high-precision SOC estimation and offers valuable knowledge for advancing the performance of battery management systems.

Key words: iron phosphate lithium battery, state of charge estimation, expansion force, data-driven, bi-directional long short-term memory model

CLC Number:

TM 912

Haoyuan MA, Yan WU, Tong WANG, Jinyang HU, Jia LI, Yuqi HUANG. State of charge estimation of lithium iron phosphate batteries based on force-electric-temperature signals and a CNN-BiLSTM model[J]. Energy Storage Science and Technology, 2025, 14(7): 2865-2874.

Figures/Tables 14

Table 1

Specifications of the test battery"

规格	参数
阴极材料	磷酸铁锂LFP
阳极材料	石墨
尺寸/mm×mm×mm	185×135×29.3
重量/g	1395±50
标称电压U/V	3.2
标称容量C/Ah	50
充电截止电压 $U'$ /V	3.65
放电截止电压 $U'$ /V	2.5
充电温度 $T 1$ /℃	0~55
放电温度 $T 2$ /℃	-20~55

Table 1

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Table 2

Fig. 9

Table 3

Fig. 10

Table 4

References 24

[1]	OMER A M. Energy, environment and sustainable development[J]. Renewable and Sustainable Energy Reviews, 2008, 12(9): 2265-2300. DOI: 10.1016/j.rser.2007.05.001.
[2]	XU J J, CAI X Y, CAI S M, et al. High-energy lithium-ion batteries: Recent progress and a promising future in applications[J]. Energy & Environmental Materials, 2023, 6(5): e12450. DOI: 10.1002/ee m2.12450.
[3]	RIVERA-BARRERA J P, MUÑOZ-GALEANO N, SARMIENTO-MALDONADO H O. SOC estimation for lithium-ion batteries: Review and future challenges[J]. Electronics, 2017, 6(4): 102. DOI: 10.3390/electronics6040102.
[4]	HOW D N T, HANNAN M A, HOSSAIN LIPU M S, et al. State of charge estimation for lithium-ion batteries using model-based and data-driven methods: A review[J]. IEEE Access, 2019, 7: 136116-136136.
[5]	ZHOU W L, ZHENG Y P, PAN Z J, et al. Review on the battery model and SOC estimation method[J]. Processes, 2021, 9(9): 1685. DOI: 10.3390/pr9091685.
[6]	DEMIRCI O, TASKIN S, SCHALTZ E, et al. Review of battery state estimation methods for electric vehicles - Part I: SOC estimation[J]. Journal of Energy Storage, 2024, 87: 111435. DOI: 10.1016/j.est.2024.111435.
[7]	SHEN Y Q. Adaptive online state-of-charge determination based on neuro-controller and neural network[J]. Energy Conversion and Management, 2010, 51(5): 1093-1098. DOI: 10.1016/j.enc onman.2009.12.015.
[8]	SHI Q S, ZHANG C H, CUI N X. Estimation of battery state-of-charge using ν-support vector regression algorithm[J]. International Journal of Automotive Technology, 2008, 9(6): 759-764. DOI: 10.1007/s12239-008-0090-x.
[9]	SESIDHAR D V S R, BADACHI C, GREEN R C Ⅱ. A review on data-driven SOC estimation with Li-Ion batteries: Implementation methods & future aspirations[J]. Journal of Energy Storage, 2023, 72: 108420. DOI: 10.1016/j.est.2023.108420.
[10]	SONG X B, YANG F F, WANG D, et al. Combined CNN-LSTM network for state-of-charge estimation of lithium-ion batteries[J]. IEEE Access, 2019, 7: 88894-88902.
[11]	JIAO M, WANG D Q, QIU J L. A GRU-RNN based momentum optimized algorithm for SOC estimation[J]. Journal of Power Sources, 2020, 459: 228051. DOI: 10.1016/j.jpowsou r.2020.228051.
[12]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.
[13]	CHEMALI E, KOLLMEYER P J, PREINDL M, et al. Long short-term memory networks for accurate state-of-charge estimation of Li-ion batteries[J]. IEEE Transactions on Industrial Electronics, 2018, 65(8): 6730-6739. DOI: 10.1109/TIE.2017.2787586.
[14]	张远进, 吴华伟, 叶从进. 基于AUKF-BP神经网络的锂电池SOC估算[J]. 储能科学与技术, 2021, 10(1): 237-241. DOI: 10.19799/j.cnki.2095-4239.2020.0285.
	ZHANG Y J, WU H W, YE C J. Estimation of the SOC of a battery based on the AUKF-BP algorithm[J]. Energy Storage Science and Technology, 2021, 10(1): 237-241. DOI: 10.19799/j.cnk i.20 95-4239.2020.0285.
[15]	FASAHAT M, MANTHOURI M. State of charge estimation of lithium-ion batteries using hybrid autoencoder and Long Short Term Memory neural networks[J]. Journal of Power Sources, 2020, 469: 228375. DOI: 10.1016/j.jpowsour.2020.228375.
[16]	时玮, 姜久春, 李索宇, 等. 磷酸铁锂电池SOC估算方法研究[J]. 电子测量与仪器学报, 2010, 24(8): 769-774. DOI: 10.3724/SP.J.11 87.2010.00769.
	SHI W, JIANG J C, LI S Y, et al. Research on SOC estimation for LiFePO₄ Li-ion batteries[J]. Journal of Electronic Measurement and Instrument, 2010, 24(8): 769-774. DOI: 10.3724/SP.J.1187. 2010.00769.
[17]	JIANG Y H, XU J, HOU W L, et al. A stack pressure based equivalent mechanical model of lithium-ion pouch batteries[J]. Energy, 2021, 221: 119804. DOI: 10.1016/j.energy.2021.119804.
[18]	FIGUEROA-SANTOS M A, SIEGEL J B, STEFANOPOULOU A G. Leveraging cell expansion sensing in state of charge estimation: Practical considerations[J]. Energies, 2020, 13(10): 2653. DOI: 10.3390/en13102653.
[19]	LIU M M, XU J, JIANG Y H, et al. Multi-dimensional features based data-driven state of charge estimation method for LiFePO₄ batteries[J]. Energy, 2023, 274: 127407. DOI: 10.1016/j.energy. 2023.127407.
[20]	CUI Z H, WANG L C, LI Q, et al. A comprehensive review on the state of charge estimation for lithium-ion battery based on neural network[J]. International Journal of Energy Research, 2022, 46(5): 5423-5440. DOI: 10.1002/er.7545.
[21]	XU P P, LI J Q, XUE Q, et al. A syncretic state-of-charge estimator for LiFePO₄ batteries leveraging expansion force[J]. Journal of Energy Storage, 2022, 50: 104559. DOI: 10.1016/j.est.2022.104559.
[22]	樊慧敏, 彭浩鸿, 孟辉, 等. 储能电池模组膨胀力特性研究及仿真分析[J/OL]. 储能科学与技术, 2025: 1-11. (2025-01-14). https://link.cnki.net/doi/10.19799/j.cnki.2095-4239.2024.1210.
	FAN H M, PENG H H, MENG H, et al. The research and simulation analysis of swelling force characteristics in energy storage battery modules[J/OL]. Energy Storage Science and Technology, 2025: 1-11. (2025-01-14). https://link.cnki.net/doi/10.19799/j.cnki.2095-4239.2024.1210.
[23]	LIU Y F, LI J Q, ZHANG G, et al. State of charge estimation of lithium-ion batteries based on temporal convolutional network and transfer learning[J]. IEEE Access, 2021, 9: 34177-34187.
[24]	朱大奇, 史慧. 人工神经网络原理及应用[M]. 北京: 科学出版社, 2006.
	ZHU D Q, SHI H. Principle and application of artificial neural network[M]. Beijing: Science Press, 2006.

温度	RMSE/%	MAE/%	ME/%
0 ℃(有力)	2.76	2.17	15.61
0 ℃ (无力)	4.78	3.88	16.38
10 ℃(有力)	1.19	0.73	7.80
10 ℃(无力)	4.41	3.28	14.12
25 ℃(有力)	2.07	1.48	10.81
25 ℃(无力)	4.05	2.60	26.45
40 ℃(有力)	2.18	2.26	8.14
40 ℃(无力)	4.90	3.65	23.64

工况	RMSE/%	MAE/%	ME/%
US06(有力)	1.77	1.37	5.10
US06(无力)	3.79	2.52	19.10
FUDS(有力)	2.07	1.48	10.81
FUDS(无力)	4.05	2.60	26.45

模型	RMSE/%	MAE/%	ME/%
CNN	2.58	1.99	12.11
LSTM	2.14	1.39	25.81
Transformer	1.68	1.21	9.04
CNN-BiLSTM	1.19	0.73	7.80