基于TCN-LSTM模型的实车电池健康状态评估方法

doi:10.19562/j.chinasae.qcgc.2025.06.005

Abstract

Abstract:

For the problem of insufficient accuracy in battery state of health （SOH） evaluation caused by the poor quality of real-world vehicle data， in this study a battery health state evaluation method based on the TCN-LSTM model is proposed. Firstly， the random search algorithm is employed to extract constant-current charging voltage segments. Subsequently， a weighted fusion approach combining locally weighted regression and third-order polynomial regression is used to fit the global degradation trend and the local degradation trend of battery capacity. Then， features related to battery aging， including the capacity retention-corrected cumulative charge capacity， fully charged voltage， and battery consistency， are constructed and extracted. Finally， a TCN-LSTM-based evaluation model for battery health state is constructed to explore the relationship between extracted features and battery aging from multiple dimensions. The results show that the TCN-LSTM model effectively evaluates the complex capacity degradation relationship of power batteries under real-world vehicle data， achieving an RMSRE of only 0.002 1.

Key words: electric vehicles, SOH, TCN-LSTM, battery consistency

Jie Hu,Haojie Wang,Min Wei,Zhihong Wang,Lin Chen,Wentao Huang,Hanrui Kang. A TCN-LSTM Model-Based Approach for Real Vehicle Battery Health State Evaluation[J].Automotive Engineering, 2025, 47(6): 1060-1071.

Figures/Tables 23

References 19

1	TAO S， MA R， ZHAO Z， et al. Generative learning assisted state-of-health estimation for sustainable battery recycling with random retirement conditions［J］. Nature Communications， 2024， 15（1）： 10154.
2	JI G， WANG J， LIANG Z， et al. Direct regeneration of degraded lithium-ion battery cathodes with a multifunctional organic lithium salt［J］. Nature Communications， 2023， 14（1）： 584.
3	XIONG R， LI L， TIAN J. Towards a smarter battery management system： a critical review on battery state of health monitoring methods［J］. Journal of Power Sources， 2018， 405： 18-29.
4	HOSSEININASAB S， LIN C， 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.
5	WANG F， ZHAI Z， ZHAO Z， et al. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis［J］. Nature Communications， 2024， 15（1）： 4332.
6	NG M F， ZHAO J， YAN Q， et al. Predicting the state of charge and health of batteries using data-driven machine learning［J］. Nature Machine Intelligence， 2020， 2（3）： 161-170.
7	WANG Z， ZHAO X， FU L， et al. A review on rapid state of health estimation of lithium-ion batteries in electric vehicles［J］. Sustainable Energy Technologies and Assessments， 2023， 60： 103457.
8	LIU H， LI C， HU X， et al. Multi-modal framework for battery state of health evaluation using open-source electric vehicle data［J］. Nature Communications， 2025， 16（1）： 1137.
9	HONG J， LI K， LIANG F， et al. A novel state of health prediction method for battery system in real-world vehicles based on gated recurrent unit neural networks［J］. Energy， 2024， 289： 129918.
10	ZHAO X， HU J， HU G， et al. A state of health estimation framework based on real-world electric vehicles operating data［J］. Journal of Energy Storage， 2023， 63： 107031.
11	QI Q， LIU W， DENG Z， et al. Battery pack capacity estimation for electric vehicles based on enhanced machine learning and field data［J］. Journal of Energy Chemistry， 2024， 92： 605-618.
12	TANG W， CHEN J， CHEN D. Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer［J］. Scientific Reports， 2025， 15（1）： 2200.
13	TOUGHZAOUI Y， TOOSI S B， CHAOUI H， et al. State of health estimation and remaining useful life assessment of lithium-ion batteries： a comparative study［J］. Journal of Energy Storage， 2022， 51： 104520.
14	TU C， ZHOU F， PAN M. A model with high-precision on proton exchange membrane fuel cell performance degradation prediction based on temporal convolutional network-long short-term memory［J］. International Journal of Hydrogen Energy， 2024， 74： 414-422.
15	SHEN J， MA W， SHU X， et al. Accurate state of health estimation for lithium-ion batteries under random charging scenarios［J］. Energy， 2023， 279： 128092.
16	LI K， ZHOU P， LU Y， et al. Battery life estimation based on cloud data for electric vehicles［J］. Journal of Power Sources， 2020， 468： 228192.
17	MENG J， CAI L， STROE D I， et al. Lithium-ion battery state-of-health estimation in electric vehicle using optimized partial charging voltage profiles［J］. Energy， 2019， 185： 1054-1062.
18	LI Y， STROE D I， CHENG Y， et al. On the feature selection for battery state of health estimation based on charging–discharging profiles［J］. Journal of Energy Storage， 2021， 33： 102122.
19	LIU X， LI S， TIAN J， et al. Health estimation of lithium-ion batteries with voltage reconstruction and fusion model［J］. Energy， 2023， 282： 128216.

缩写	描述
BiGRU	双向门控循环单元
CEEMDAN	经验模态分解
CNN	卷积神经网联
EVs	纯电动汽车
GAM	广义加性模型
GRU	门控循环单元
GPR	高斯过程回归
ICA	容量增量分析
PR	多项式拟合
LOESS	局部加权回归
LSTM	长短时记忆模型
PEMFC	质子交换膜燃料电池
PINN	物理信息神经网络
PSO-ELM	粒子群优化-极限学习机
RNN	循环神经网络
RVM	相关向量机
SOH	电池健康状态
SVM	支持向量机
TCN	时间卷积网络
XGBoost	极限梯度提升

数据名称	数据格式
数据采集时间	yymmdd-hhmmss
车辆标签	XXX_xxx
车辆状态	01 启动，02 熄火，03 其他状态
充电状态	01 停车充电，02 行驶充电， 03 未充电，04 充电完成
车辆运行模式	01 纯电，02 混动，03 燃油
车速	0~220 km/h
累计里程	0~999 999.9 km
总电压	0~10 000 V
总电流	-1 000~1 000 A
SOC	0~100%
单体电压最高值范围	0~15 000，最小单位 0.001 V
单体电压最低值范围	0~15 000，最小单位 0.001 V
最高温度值范围	-40~210 ℃
最低温度值范围	-40~210 ℃

模型	MAE	R²	RMSRE
XGBoost	0.003 9	0.890 4	0.003 7
LSTM	0.002 7	0.933 2	0.002 8
GRU	0.003 0	0.911 8	0.003 1
Transformer	0.001 9	0.950 3	0.002 4
TCN-LSTM	0.001 6	0.962 6	0.002 1

车辆	MAE	R²	RMSRE
Car2	0.001 9	0.917 5	0.002 5
Car3	0.002 7	0.886 1	0.003 4
Car4	0.003 0	0.850 1	0.003 7

[1]	Yang Yang,Zhi Zhang,Bo Xu,Yang Dong. Research on the DDDQ Magnetic Coupled Structure of the Wireless Charging System for Electric Vehicles [J]. Automotive Engineering, 2025, 47(6): 1007-1021.
[2]	Qianwen Zhang,Lei Xu,Qingyang Wang,Shengjin Xu. Dynamic Effect of Underbody Flow Separation on Aerodynamic Drag in Electric Vehicles [J]. Automotive Engineering, 2025, 47(5): 910-919.
[3]	Yansong Lu,Chong Zhu,Xi Zhang. A Lumped Parameter Model of Circulating Cooling Oil Temperature for Automotive High-Speed Motor [J]. Automotive Engineering, 2025, 47(5): 920-930.
[4]	Yi Luo,Wenbin Ma,Ling Su,Yueqiao Liu,Bo Xiao. Research on the Performance of an Integrated Thermal Management System for Electric Vehicles Based on R290 Refrigerant [J]. Automotive Engineering, 2025, 47(5): 931-939.
[5]	Zichen Zheng,Shu Wang,Xuan Zhao,Zhaoke Li. Integrated Control of Distributed Drive Electric Vehicle AFS/DYC Based on Hybrid Model Predictive Control [J]. Automotive Engineering, 2025, 47(3): 470-480.
[6]	Qin Li,Zhuang Li,Jianming Tang,Yong Wang,Boyuan Zhang,Deqiang He. Multi-objective Torque Distribution Strategy for Distributed Drive Electric Vehicles [J]. Automotive Engineering, 2025, 47(3): 489-498.
[7]	Bolin He,Yong Chen,Qinglin Dai. Control Strategy for Dual-Clutch Transmission Gear Shifting Process in Pure Electric Vehicles Based on LADRC [J]. Automotive Engineering, 2024, 46(9): 1668-1677.
[8]	Changzhao Liu,Kun Wang,Jian Song,Shuoming Fan,Xianglong Chen. Electromechanical Control Collaborative Design of Switched Reluctance Electric Drive System [J]. Automotive Engineering, 2024, 46(8): 1457-1468.
[9]	Longfei Ma,Baoqun Zhang,Liyong Wang,Jiani Zeng,Ran Jiao,Cheng Gong. Research on Participation of Electric Vehicles in Microgrid Load Power Fluctuation Mitigation Based on Digital Twin Hybrid Energy Storage [J]. Automotive Engineering, 2024, 46(6): 1045-1053.
[10]	Tianyang Yang,Huiming Zou,Hui Zhou,Chunlei Wang,Changqing Tian. Research on the Adaptability of CO₂ Ejector Under Automotive Conditions Ranging from -30 to 50 ℃ [J]. Automotive Engineering, 2024, 46(4): 682-690.
[11]	Jie Hu,Lin Chen,Zhihong Wang,Haihua Qing,Haojie Wang. Transformer-Based Prediction of Charging Time for Pure Electric Vehicles [J]. Automotive Engineering, 2024, 46(11): 2059-2067.
[12]	Zhipeng Jiao, Jian Ma, Xuan Zhao, Kai Zhang, Dean Meng, Qi Han, Zhao Zhang. Research on Short-Time Test Cycle and Method Based on Electric Vehicle Braking Safety Detection [J]. Automotive Engineering, 2024, 46(1): 109-119.
[13]	Jiangxin Yuan, Liping He, Yaodong Li, Gang Li. Thermal Analysis and Optimization Design of a BMS Slave Unit for Electric Vehicles [J]. Automotive Engineering, 2024, 46(1): 128-138.
[14]	Haiqiang Liang,Hongwen He,Kangwei Dai,Bo Pang,Peng Wang. Research on Lithium Ion Battery Life Prediction Method Based on Empirical Aging Model and Mechanism Model for Electric Vehicles [J]. Automotive Engineering, 2023, 45(5): 825-835.
[15]	Yapeng Li,Xiaolin Tang,Xiaosong Hu. Study on Eco-driving of PHEVS Based on Hierarchical Control Strategy [J]. Automotive Engineering, 2023, 45(4): 551-560.

A TCN-LSTM Model-Based Approach for Real Vehicle Battery Health State Evaluation

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 23

References 19

Related Articles 15

Metrics

Comments

Recommended 0