Remaining useful life prediction of lithium-ion batteries based on dropout Monte Carlo recurrent neural network

doi:10.3969/j.issn.1674-8484.2022.03.016

Abstract

Abstract:

A dropout Monte Carlo (dropout-MC) recurrent neural network method was proposed for remaining useful life (RUL) prediction for lithium-ion batteries to guarantee the safety and reliability of electric vehicles. An equal charging voltage time was introduced as an indirect health indicator, and the variational mode decomposition (VMD) was adopted to reduce the influence of external interference and capacity regeneration. The long and short time series (LSTM) as the improved recurrent neural network was established for accurate RUL prediction. The dropout-MC method was proposed to obtain the 95% confidence interval for quantifying the uncertainty of the RUL prediction. Compared with traditional extreme learning machine (ELM) and nonlinear autoregressive neural network (NARX) methods, the proposed method not only can achieve a higher accuracy in RUL prediction with prediction performance below 2.4%, but also obtain reliability of RUL prediction.

Key words: vehicle safety, lithium-ion batteries, remaining useful life (RUL), variational mode decomposition (VMD), dropout Monte Carlo (dropout-MC) method, recurrent neural network

CLC Number:

U469.7

WEI Meng, WANG Qiao, YE Min, LIAN Gaoqi, XU Xinxin. Remaining useful life prediction of lithium-ion batteries based on dropout Monte Carlo recurrent neural network[J]. Journal of Automotive Safety and Energy, 2022, 13(3): 541-549.

Figures/Tables 11

References 30

[1]	LI Yi, LIU Kailong, Foley A M, et al. Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review[J]. Renew Sustain Energy Reviews, 2019, 113: 1-18
[2]	YAO Fang, HE Wenxuan, WU Youxi, et al. Remaining useful life prediction of lithium-ion batteries using a hybrid model[J]. Energy, 2022, 248: 1-13.
[3]	来鑫, 孟正, 韩雪冰, 等. 基于特征电压模型的锂离子电池容量估计与RUL预测[J]. 汽车安全与节能学报, 2022, 13(1): 194-201.
	LAI Xin, MENG Zheng, HAN Xuebing, et al. State of health estimation and remaining useful life prediction of lithium-ion battery based on characteristic voltage model[J]. J Automotive Safe Energy, 2022, 13(1): 194-201. (in Chinese)
[4]	张宏. 基于数据挖掘的汽车运行数据采集设备故障诊断方法[J]. 汽车安全与节能学报, 2019, 10(1): 54-59.
	ZHANG Hong. Fault diagnosis method of vehicle driving data acquisition devices based on data mining[J]. J Automotive Safe Energy, 2019, 10(1): 54-59. (in Chinese)
[5]	LI Wenhua, JIAO Zhipeng, DU Le, et al. An indirect RUL prognosis for lithium-ion battery under vibration stress using Elman neural network[J]. Int’l J Hydrog Energy, 2019, 44(23): 12270-12276.
[6]	周頔, 宋显华, 卢文斌, 等. 基于日常片段充电数据的锂电池健康状态实时评估方法研究[J]. 中国电机工程学报, 2019, 39(1):105-111.
	ZHOU Di, SANG Xianhua, LU Wenbin, et al. Real-time SOH estimation algorithm for lithium-ion batteries based on daily segment charging data[J]. Proc CSEE, 2019, 39(1):105-111. (in Chinese)
[7]	ZHANG Chenbin, CHEN Zonghai, WU Ji. An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks[J]. Appl Energy, 2016; 173:134-40. doi: 10.1016/j.apenergy.2016.04.057 URL
[8]	XIONG Rui, ZHANG Yongzhi, WANG Ju, et al. Lithium-Ion battery health prognosis based on a real battery management system used in electric vehicles[J]. IEEE Trans Vehi Technol. 2019; 68:4110-21.
[9]	马彦, 陈阳, 张帆, 等. 基于扩展H_∞粒子滤波算法的动力电池寿命预测方法[J]. 机械工程报, 2019, 55(20): 36-43.
	MA Yan, CHEN Yang, ZHANG Fan, et al. Remaining useful life prediction of power battery based on extend H_∞ particle filter algorithm[J]. J Mech Engi, 2019, 55(20): 36-43. (in Chinese)
[10]	FENG Hailin, SANG Dandan. A health indicator extraction based on surface temperature for lithium-ion batteries remaining useful life prediction[J]. J Energy Storage, 2021, 34:1-13.
[11]	TIAN Jiaqiang, WANG Yujie, CHEN Zonghai. An improved single particle model for lithium-ion batteries based on main stress factor compensation[J]. J Clean Prod, 2021, 278: 1-12.
[12]	HAN Sangwo, TANG Yifan, Rahimian S K. A numerically efficient method of solving the full-order pseudo-2-dimensional (P2D) Li-ion cell model[J]. J Power Sources, 2021, 490: 1-13.
[13]	Hettiarachchi D, Rajakaruna S, Ghosh A. A new approach to identify the optimum frequency ranges of the constituent storage devices of a hybrid energy storage system using the empirical mode decomposition technique[J]. J Energy Storage, 2022, 51: 1-11.
[14]	SUN Xiaofei, ZHONG Kai, HAN Min. A hybrid prognostic strategy with unscented particle filter and optimized multiple kernel relevance vector machine for lithium-ion battery[J]. Measurement, 2021, 170: 1-14.
[15]	Jcoutoa L D, Schorscha J, Jobb N, et al. State of health estimation for lithium ion batteries based on an equivalent-hydraulic model: An iron phosphate application[J]. J Energy Storage, 2019, 21: 259-271. doi: 10.1016/j.est.2018.11.001 URL
[16]	舒星, 刘永刚, 申江卫, 等. 基于改进最小二乘支持向量机与Box-Cox变换的锂离子电池容量预测[J]. 机械工程学报, 2021, 57(14): 118-128. doi: 10.3901/JME.2021.14.118
	LIU Xing, LIU Yonggang, SHEN Jiangwei, et al. Capacity prediction for lithium-ion batteries based on improved least squares support vector machine and box-cox transformation[J]. J Mech Engi, 2021, 57(14): 118-128. (in Chinese)
[17]	CAI Lei, MENG Jinhao, Stroe D I, et al. Multi objective optimization of data-driven model for lithium-ion battery SOH estimation with short-term feature[J]. IEEE Trans Power Elect, 2020, 35(11): 11855 -11864. doi: 10.1109/TPEL.2020.2987383 URL
[18]	WANG Jinwei, DENG Zhongwei, YU Tao, et al. State of health estimation based on modified Gaussian process regression for lithium-ion batteries[J]. J Energy Storage, 2022, 51: 1-12.
[19]	GUO Pengyao, CHENG Ze, YANG Lei. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction[J]. J Power Sources, 2019, 412: 442-450. doi: 10.1016/j.jpowsour.2018.11.072 URL
[20]	REN Lei, CHENG Xuejun, WANG Xiaokang, et al. Multi-scale dense gate recurrent unit networks for bearing remaining useful life prediction[J]. Future Gener Comput Syst, 2019, 94:601-609 doi: 10.1016/j.future.2018.12.009 URL
[21]	LI Penghua, ZHANG Zijian, XIONG Qingyu, et al. State-of-health estimation and remaining useful life prediction for the lithium-ion battery based on a variant long short term memory neural network[J]. J Power Sources, 2020, 459:1-12.
[22]	Gal Y, Ghahramani Z. Dropout as a Bayesian approximation: representing model-uncertainty in deep learning[C]// The 33rd Int’l Conf Mach Learning, 2016: 1050-1059.
[23]	陈则王, 李福胜, 林娅. 基于GA-ELM的锂离子电池RUL间接预测方法[J]. 计量学报, 2020, 41(6): 735-742.
	CHEN Zewang, LI Fusheng, LIN Ya, et al. Indirect prediction method of RUL for lithium-ion battery based on GA-ELM[J]. Acta Metrologica Sinica, 2020, 41(6): 735-742. (in Chinese)
[24]	GOU Bin, XU Yan, FENG Xue, State-of-health estimation and remaining-useful-life prediction for lithium-ion battery using a hybrid data-driven method[J]. IEEE Trans Vehi Tech, 2020, 60(10) 10854-10867.
[25]	ZHANG Yongzhi, XIONG Rui, HE Hongwen, et al. Lithium-ion battery remaining useful life prediction with Box-Cox transformation and Monte Carlo simulation[J]. IEEE Trans Indu Electron. 2019, 66(2) 1585-1597.
[26]	庞晓琼, 王竹晴, 曾建潮, 等. 基于PCA-NARX的锂离子电池剩余使用寿命预测[J]. 北京理工大学学报, 2019, 39(4): 406-412.
	PANG Xiaoqiong, WANG Zhuqing, ZANG Jianchao, et al. Prediction for remaining useful life of lithium-ion battery based on PCA-NARX[J]. Transa Beijing Inst of Tech, 2019, 39(4): 406-412. (in Chinese)
[27]	Saha B, Goebel K. Battery data set[EB/OL]. (2019-05-10). https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository.
[28]	LI Xiaoyu, YUAN Changgui, LI Xiaohui, et al. State of health estimation for Li-ion battery using incremental capacity analysis and Gaussian process regression[J]. Energy, 2020, 190: 1-12.
[29]	王冉, 后麒麟, 石如玉, 等. 基于变分模态分解与集成深度模型的锂电池剩余寿命预测方法[J]. 仪器仪表学报, 2021, 42(4): 111-120.
	WANG Ran, HOU Qilin, SHI Ruyu, et al. Remaining useful life prediction method of lithium battery based on variational mode decomposition and integrated deep model[J]. Chin J Sci Instr, 2021, 42(4): 111-120. (in Chinese)
[30]	Pajovic M, Orlik P, Wada T. Remaining useful life estimation of batteries using dirichlet process with variational bayes inference[C]// 2018: 2729-2735.

	容量Cell#5	容量Cell#6	容量Cell#7
健康因子Cell#5	0.988	0.981	0.986
健康因子Cell#6	0.994	0.995	0.995
健康因子Cell#7	0.988	0.980	0.986

	容量Cell#5	容量Cell#6	容量Cell#7
健康因子Cell#5	0.988	0.981	0.986
健康因子Cell#6	0.994	0.995	0.995
健康因子Cell#7	0.988	0.980	0.986

方法	电池标号	误差 / %
方法	电池标号	RMSE	MAE	MAPE
ELM	#5	3.13	2.88	2.13
	#6	3.37	3.21	2.89
	#7	3.03	2.41	1.66
NARX	#5	2.96	2.02	1.51
	#6	2.97	2.03	1.60
	#7	1.65	1.63	1.26
dropout_MC LSTM	#5	1.69	1.33	0.98
	#6	2.40	1.93	1.57
	#7	1.53	1.49	1.23

方法	电池标号	误差 / %
方法	电池标号	RMSE	MAE	MAPE
ELM	#5	3.13	2.88	2.13
	#6	3.37	3.21	2.89
	#7	3.03	2.41	1.66
NARX	#5	2.96	2.02	1.51
	#6	2.97	2.03	1.60
	#7	1.65	1.63	1.26
dropout_MC LSTM	#5	1.69	1.33	0.98
	#6	2.40	1.93	1.57
	#7	1.53	1.49	1.23