动态条件下基于深度学习的锂电池容量估计

doi:10.19562/j.chinasae.qcgc.2022.06.008

Abstract

Abstract:

In the aging course of lithium-ion battery， nonlinear complicated changes occur inside the battery， therefore directly using the operation data of lithium-ion battery such as current， voltage and temperature in certain time sections to conduct real-time estimation on the battery state of health under dynamic condition is a challenging issue. In this paper， the random charging and discharging data of lithium-ion battery are selected， the time and frequency features of some segments of dynamic data are extracted to compose time and frequency feature matrices as input， a cascaded convolutional neural network and a gated recurrent unit capacity estimation model are constructed to extract the intrinsic features of input data， and the related features of each time sequence are further explored to fulfill the estimation of battery capacity under dynamic condition. The results of experimental verification utilizing NASA's lithium-ion battery random use data set show that the method adopted can accurately estimate the capacity of lithium-ion battery under the condition of only the nominal capacity of battery is known. Finally， the effects of the setting of model’s hyper-parameters， the time-sequence length of raw data， network input and model structure on the accuracy of battery capacity estimation are analyzed.

Key words: lithium-ion battery, capacity estimation, CNN, GRU-RNN, deep learning

Guihong Bi,Xu Xie,Zilong Cai,Zhao Luo,Chenpeng Chen,Xin Zhao. Capacity Estimation of Lithium-ion Battery Based on Deep Learning Under Dynamic Conditions[J].Automotive Engineering, 2022, 44(6): 868-878.

Figures/Tables 17

References 25

1	REN Guizhou， MA Guoqing， CONG Ning. Review of electrical energy storage system for vehicular applications［J］. Renewable and Sustainable Energy Reviews， 2015， 41： 225-236.
2	殷豪，欧祖宏，陈德，等. 基于二次模式分解和级联式深度学习的超短期风电功率预测［J］. 电网技术， 2020， 44（2）： 445-453.
	YIN Hao， OU Zuhong， CHEN De， et al. Ultra-short-term wind power prediction based on two-layer mode decomposition and cascaded deep learning［J］. Power System Technology， 2020， 44（2）： 445-453.
3	胡天中，余建波. 基于多尺度分解和深度学习的锂电池寿命预测［J］. 浙江大学学报（工学版）， 2019， 53（10）： 1852-1864.
	HU Tianzhong， YU Jianbo. Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning［J］. Journal of Zhejiang University （Engineering Science）， 2019， 53（10）： 1852-1864.
4	CHOI Yoh Wan， et al. Machine learning-based lithium-ion battery capacity estimation exploiting multi-channel charging profiles［J］. IEEE Access，2019， 7 ： 75143-75152.
5	李超然，肖飞，樊亚翔，等.基于卷积神经网络的锂离子电池SOH估算［J］. 电工技术学报， 2020， 35（19）：4106-4119.
	LI Chaoran， XIAO Fei， FAN Yaxiang， et al. An approach to lithium-ion battery SOH estimation based onconvolutional neural network［J］. Transaction of China Electrotechnical Society， 2020， 35（19）： 4106-4119.
6	FAN Y， XIAO F， LI C， et al. A novel deep learning framework for state of health estimation of lithium-ion battery［J］. Journal of Energy Storage， 2020， 32 ： 101741.
7	SHEN S， SADOUGHI M， LI M， et al. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries［J］. Applied Energy， 2020， 260（C）： 114296-114296.
8	EL-DALAHMEH Ma’d， AL-GREER Maher，EL-DALAHMEH Mo’ath，et al. Time-frequency image analysis and transfer learning for capacity prediction of lithium-ion batteries［J］. Energies， 2020， 13（20）： 5447-5447.
9	VENUGOPAL P，VIGNESWARAN T. State-of-health estimation of Li-ion batteries in electric vehicle using IndRNN under variable load condition［J］. Energies， 2019， 12（22）.
10	SALUCCI C B， BAKDI A， GLAD I K， et al. Multivariable fractional polynomials for lithium-ion batteries degradation models under dynamic conditions［J］. arXiv， 2021 ： 2102.08111. Available from： https：//arxiv.org/abs/2102.08111
11	DAI Houde， ZHAO Guangcai， LIN Mingqiang， 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.
12	WANG Zengkai，ZENG Shengkui GUO Jianbin，et al. State of health estimation of lithium-ion batteries based on the constant voltage charging curve［J］. Energy， 2019， 167 ： 661-669.
13	BOLE B， KULKARNI C S， DAIGLE M. Adaptation of an electrochemistry-based Li-Ion battery model to account for deterioration observed under randomized use［C］. Conference of the Prognostics & Health Management Society， 2014.
14	MA Shuai， JIANG Modi， TAO Peng， et al. Temperature effect and thermal impact in lithium-ion batteries： a review［J］. Progress in Natural Science： Materials International， 2018， 28（6）： 653-666.
15	CHEN Kebin，et al. Evaluation of the low temperature performance of lithium manganese oxide/lithium titanate lithium-ion batteries for start/stop applications［J］. Journal of Power Sources， 2015， 278 ： 411-419.
16	SNYDER Chelsea. The effects of charge/discharge rate on capacity fade of lithium ion batteries［M］. Rensselaer Polytechnic Institute， 2016.
17	MADANI S S， SCHALTZ E， KR S K，et al. Effect of current rate and prior cycling on the coulombic efficiency of a lithium-ion battery［J］. Batteries， 2019， 5（3）： 57-57.
18	ARMENTA-DEU C， CARRIQUIRY J P，et al. Capacity correction factor for Li-ion batteries： influence of the discharge rate［J］. Journal of Energy Storage， 2019， 25（C）： 100839-100839.
19	UNO M， TANAKA K. Influence of high-frequency charge-discharge cycling induced by cell voltage equalizers on the life performance of lithium-ion cells［J］. IEEE Transactions on Vehicular Technology， 2011， 60 ： 1505-1515.
20	REICHERT M， ANDRE D， ROESMANN A， et al. Influence of relaxation time on the lifetime of commercial lithium-ion cells［J］. Journal of Power Sources， 2013， 239 ： 45-53.
21	JUAREZ-ROBLES D， VYAS A A， FEAR C， et al. Overcharge and aging analytics of Li-Ion cells［J］. Journal of The Electrochemical Society， 2020， 167（9）： 090547.
22	LECUN Y， BOTTOU L， BENGIO Y， et al. Gradient-based learning applied to document recognition［J］. Proceedings of the IEEE， 1998， 86（11）： 2278-2324.
23	梁海峰，袁芃，高亚静. 基于CNN-Bi-LSTM网络的锂离子电池剩余使用寿命预测［J］. 电力自动化设备， 2021， 41（10）： 213-219.
	LIANG Haifeng， YUAN Peng， GAO Yajing. Remaining useful life prediction of lithium-ion battery based on CNN-Bi-LSTM network［J］. Electric Power Automation Equipment， 2021， 41（10）： 213-219.
24	张少宇，伍春晖，熊文渊. 采用门控循环神经网络估计锂离子电池健康状态［J］. 红外与激光工程， 2021， 50（2）： 236-243.
	ZHANG Shaoyu， WU Chunhui， XIONG Wenyuan. State of health estimation for lithium-ion batteries using recurrentneural networks with gated recurrent unit［J］. Infrared and Laser Engineering， 2021， 50（2）： 236-243.
25	李超然，肖飞，樊亚翔，等. 基于深度学习的锂离子电池SOC和SOH联合估算［J］. 中国电机工程学报， 2021， 41（2）： 681-692.
	LI Chaoran， XIAO Fei， FAN Yaxiang， et al. Joint estimation of the state of charge and the state of health based on deep learning for lithium-ion batteries［J］. Proceedings of the CSEE， 2021， 41（2）： 681-692.

[1]	LI Huan, HUANG Ying, ZHANG Fu-Jun, ZHAO Yu, GE Yan-Wu. [J]. , 2016, 38(12): 1420 -1426 .
[2]	HAO Han, WANG Si-南, LI Xiao, LIU Zong-Wei, ZHAO Fu-Quan. [J]. , 2017, 39(1): 1 -8 .
[3]	XU Cheng-Shan, JIANG Fa-Chao, SONG Sen-Nan, TIAN Guang-Yu. [J]. , 2017, 39(1): 9 -14 .
[4]	JIANG Ting, DAI Bing. [J]. , 2016, 38(12): 1459 -1466 .
[5]	ZHANG Yi-Bing, 吕Jian-Jun , YUAN Guang-Hui. [J]. , 2016, 38(12): 1467 -1470 .
[6]	ZHANG Lei, ZHANG Jin-Qiu, LUO Tao, BI Zhan-Dong, YAO Jun. [J]. , 2016, 38(12): 1494 -1499 .
[7]	CUI An, LI Bin, WANG Xue-Liang, ZHANG Shi-Zhan. [J]. , 2016, 38(12): 1521 -1525 .
[8]	CHU Liang, ZHAO Di, LI Wen-Hui. [J]. , 2017, 39(1): 61 -65 .
[9]	FENG Chong, ZHANG Dong-Hao, LUO Yu-Gong, LI Ke-Qiang. [J]. , 2017, 39(1): 66 -72 .
[10]	HAN Xiao-Mei, LIN Xue-Dong, LI De-Gang. [J]. , 2017, 39(1): 23 -27 .

电池关键特性	规格
制造商	LG Chem
电池化学成分	18650 钴氧化物（正极）石墨（负极）
额定容量	2 100 mA·h
下限截止电压	3.2 V
上限阈值电压	4.2 V

网络层	输入尺寸	卷积核尺寸	卷积核个数	输出尺寸
输入层	40×9	N/A	N/A	40×9
卷积层1	40×9	3×3	32	38×7
卷积层2	38×7	3×3	64	36×5
池化层	36×5	2×2	N/A	18×2
扁平层	18×2	N/A	N/A	18×128
GRU1	18×128	N/A	64	18×64
GRU2	18×64	N/A	64	1×64
全连接层	1×64	N/A	64	1×64
回归层	1×64	N/A	N/A	1

实验组	网络层	网络层超参数（卷积核大小、个数）	NRMSE/%
1	卷积层1	2×2，32	12.13
1	卷积层2	2×2，64	12.13
2	卷积层1	3×3，32	7.53
2	卷积层2	3×3，64	7.53
3	卷积层1	4×4，32	8.48
3	卷积层2	4×4，64	8.48
4	卷积层1	3×3，32	9.62
4	卷积层2	3×3，32	9.62
5	卷积层1	3×3，64	9.25
5	卷积层2	3×3，64	9.25
6	卷积层1	3×3，8	21.20
6	卷积层2	3×3，16	21.20
7	卷积层1	3×3，16	11.43
7	卷积层2	3×3，32	11.43
8	卷积层1	3×3，64	10.56
8	卷积层2	3×3，128	10.56

实验组	原始数据收集时长/h	时域特征矩阵尺寸
20RW步	1.08	760×7
40RW步	2.43	1520×7
60RW步	3.69	2280×7
80RW步	4.84	3040×7
100RW步	6.13	3800×7

网络输入	RMSE/%	NRMSE/%	训练时间/s
20RW步时域特征量	19.35	15.99	10.15
40RW步时域特征量	12.85	10.70	18.88
60RW步时域特征量	19.91	16.63	27.36
80RW步时域特征量	17.86	11.51	36.94
100RW步时域特征量	22.65	18.59	47.16

Capacity Estimation of Lithium-ion Battery Based on Deep Learning Under Dynamic Conditions

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 25

Related Articles 15

Metrics

Comments

Recommended 10

网络输入	电池编号	RMSE/%	NRMSE/%
时域特征量	RW9	12.21	11.31
	RW10	13.43	10.03
	RW11	16.96	13.11
	RW12	12.85	10.70
时域特征量+小波能量	RW9	9.75	7.60
	RW10	10.17	7.52
	RW11	12.80	9.82
	RW12	11.44	7.53

结构变量	系数选择	平均RMSE/%	平均NRMSE/%	参数数量
卷积层数	1层	17.89	14.50	60 225
	2层	11.03	8.12	84 865
	3层	19.57	16.80	158 721
池化层	有	11.03	8.12	84 865
池化层	无	15.77	13.22	121 729
Dropout	有	17.69	14.37	84 865
Dropout	无	11.03	8.12	84 865

方法	电池编号	RMSE/%	NRMSE/%	训练时间/s
GRU	RW9	9.66	7.45	26.60
	RW10	10.91	8.62	26.16
	RW11	12.65	9.72	26.48
	RW12	10.34	8.45	21.26
CNN	RW9	11.29	8.71	5.37
	RW10	19.59	16.89	5.56
	RW11	19.37	14.87	5.63
	RW12	17.10	11.72	4.80
CNN-GRU	RW9	9.75	7.60	24.21
	RW10	10.17	7.52	25.19
	RW11	12.80	9.82	25.02
	RW12	11.44	7.53	20.22

[1]	Ze Gao, Zunkang Chu, Jiasheng Shi, Fu Lin, Weixiong Rao, Haiyan Yu. Research on Fast Prediction Method of Stress Field of Automotive Parts Based on Graph Network [J]. Automotive Engineering, 2024, 46(1): 170-178.
[2]	Fei Chen,Xiangdong Kong,Yuedong Sun,Xuebing Han,Languang Lu,Yuejiu Zheng,Minggao Ouyang. Progress in Simulation Technology of Lithium-ion Battery Manufacturing Process [J]. Automotive Engineering, 2023, 45(9): 1516-1529.
[3]	Wenchao Guo,Lin Yang,Zhongwei Deng,Jilin Li,Zhixian Fan. Research on Multi-level Fault Warning Method for Lithium-ion Batteries Driven by Cloud Data [J]. Automotive Engineering, 2023, 45(9): 1677-1687.
[4]	Weiguo Liu,Zhiyu Xiang,Rui Liu,Guodong Li,Zixu Wang. Research on End-to-End Vehicle Motion Planning Method Based on Deep Learning [J]. Automotive Engineering, 2023, 45(8): 1343-1352.
[5]	Jiahao Zhao,Zhiquan Qi,Zhifeng Qi,Hao Wang,Lei He. Calculation of Heading Angle of Parallel Large Vehicle Based on Tire Feature Points [J]. Automotive Engineering, 2023, 45(6): 1031-1039.
[6]	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.
[7]	Yanyan Chen,Hai Wang,Yingfeng Cai,Long Chen,Yicheng Li. Efficient Automatic Driving Instance Segmentation Method Based on Detection [J]. Automotive Engineering, 2023, 45(4): 541-550.
[8]	Yubo Lian,Heping Ling,Qingchan Ma,Qiang Ren,Bin He. Research Progress on Pulse Heating Technology of Lithium-ion Battery for Electric Vehicles [J]. Automotive Engineering, 2023, 45(2): 169-174.
[9]	Fengchong Lan,Jikai Chen,Jiqing Chen,Xinping Jiang,Zihan Li,Wei Pan. Research on Lithium Battery Remaining Useful Life Prediction Method Driven by Real Vehicle Data [J]. Automotive Engineering, 2023, 45(2): 175-182.
[10]	Jianhao Zhang,Xingqi Gao,Li Zhang. Micro Short Circuit Diagnosis Method of Battery Pack Based on Capacity Increment Curve and Charge Capacity Difference [J]. Automotive Engineering, 2023, 45(2): 191-198.
[11]	Linhui Li,Xinliang Zhang,Yifan Fu,Jing Lian,Jiaxu Ma. Research on Visible Light and Infrared Post-Fusion Detection Based on TC-YOLOv7 Algorithm [J]. Automotive Engineering, 2023, 45(12): 2280-2290.
[12]	Xiaojun Zhang,Jingzhe Xi,Yanlei Shi,Anlu Yuan. Lightweight YOLOv7-R Algorithm for Road-Side View Target Detection [J]. Automotive Engineering, 2023, 45(10): 1833-1844.
[13]	Jie Hu,Yuanjie Li,Hao Geng,Huangzheng Geng,Xiong Guo,Hongwei Yi. Construction of Vehicle Fault Knowledge Graph Based on Deep Learning [J]. Automotive Engineering, 2023, 45(1): 52-60.
[14]	Jie Hu,Boyuan Xu,Zongquan Xiong,Minjie Chang,Di Guo,Lihao Xie. Cross-Domain Object Detection Algorithm Based on Multi-scale Mask Classification Domain Adaptive Network [J]. Automotive Engineering, 2022, 44(9): 1327-1338.
[15]	Ping Wang,Qingrui Gong,Ze Cheng,Ji’ang Zhang. An AUKF-Based SOC Estimation Method for Lithium-ion Battery [J]. Automotive Engineering, 2022, 44(7): 1080-1088.