Remaining useful life prediction of lithium-ion battery based on CNN-Bi-LSTM network

被引：0
|
作者：
Liang H. [1 ]
Yuan P. [1 ]
Gao Y. [2 ]
机构：
[1] Department of Electrical Engineering, North China Electric Power University, Baoding
[2] Carbon Neutrality Research Institute of China Huaneng Group Co., Ltd., Beijing
来源：
Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2021年 / 41卷 / 10期
基金：
中国国家自然科学基金;
关键词：
Bi-directional long short-term memory network; Convolutional neural network; Lithium-ion battery; Remaining useful life prediction;
D O I：
10.16081/j.epae.202110030
中图分类号：
学科分类号：
摘要：
The RUL(Remaining Useful Life) prediction of the lithium-ion battery can evaluate the reliability of the battery, reduce the risk of battery use and provide a theoretical basis for battery maintenance. Combining the advantages of CNN(Convolutional Neural Network) and Bi-LSTM(Bi-directional Long Short-Term Memory) network, the CNN-Bi-LSTM network model for lithium-ion battery RUL prediction is proposed, which considers both multiple degradation characteristics and time sequence. The hyperparameters of CNN are obtained by simulation, the highly correlated feature parameters are selected as the prediction input, and the simulation experiment is carried out on the NASA lithium-ion battery aging data set. The experimental results show that the CNN-Bi-LSTM network model can accurately predict the RUL of lithium-ion batteries. Compared with other network models, it has the advantages of fewer network model parameters and smaller memory usage, and has good performance in accuracy and convergence. © 2021, Electric Power Automation Equipment Press. All right reserved.
引用
收藏
页码：213 / 219
页数：6
相关论文
共 20 条
  • [1] PENG Fei, LIU Zhixiang, REN Jingguo, Et al., PV/li-ion energy-storage power module based on non-balancing cell management and its MPPT control, Electric Power Automation Equipment, 37, 4, pp. 73-81, (2017)
  • [2] HAN Xuebing, OUYANG Minggao, LU Languang, Et al., A com-parative study of commercial lithium ion battery cycle life in electric vehicle: capacity loss estimation, Journal of Power Sources, 268, pp. 658-669, (2014)
  • [3] GOEBEL K, SAHA B, SAXENA A, Et al., Prognostics in bat-tery health management, IEEE Instrumentation & Measure-ment Magazine, 11, 4, pp. 33-40, (2008)
  • [4] SHI Yongsheng, SHI Mengzhuo, DING Ensong, Et al., Remai-ning useful life prediction of lithium ion battery based on multiple degradation characteristics, Chinese Journal of Po-wer Sources, 44, 6, pp. 836-840, (2020)
  • [5] LI Chaoran, XIAO Fei, FAN Yaxiang, Et al., An approach to lithium-ion battery SOH estimation based on convolutional neural network, Transactions of China Electrotechnical Society, 35, 19, pp. 4106-4119, (2020)
  • [6] BI Xiaojun, HU Songyi, Firefly algorithm with high precision mixed strategy optimized particle filter, Journal of Shanghai Jiao Tong University, 53, 2, pp. 232-238, (2019)
  • [7] YAN Gangui, CAI Changxing, DUAN Shuangming, Et al., Grou-ping mode optimization of lithium-ion energy storage battery, Electric Power Automation Equipment, 41, 4, pp. 148-153, (2021)
  • [8] WEI Zhinong, YUAN Kangkang, CHENG Lexiang, Et al., Para-meter identification of lithium-ion battery based on multi-innovation least squares algorithm, Automation of Electric Power Systems, 43, 15, pp. 139-145, (2019)
  • [9] LIU Yuefeng, ZHANG Gong, ZHANG Chenrong, Et al., Review of RUL prediction method for lithium-ion batteries, Computer Engineering, 46, 4, pp. 11-18, (2020)
  • [10] WU Ji, ZHANG Chenbin, CHEN Zhongcai, An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks, Applied Energy, 173, pp. 134-140, (2016)
12