Please wait a minute...
文章检索
复杂系统与复杂性科学  2024, Vol. 21 Issue (3): 154-159    DOI: 10.13306/j.1672-3813.2024.03.020
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于数据驱动的锂电池健康状态预测
崔孝凯, 王庆芝, 刘其朋
青岛大学自动化学院,山东 青岛 266071
A Data-driven Model for Prediction of Lithium Battery State of Health
CUI Xiaokai, WANG Qingzhi, LIU Qipeng
College of Automation, Qingdao University, Qingdao 266071, China
全文: PDF(3492 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 针对传统基于数据驱动锂电池健康状态预测模型所存在的精确度低、鲁棒性差等问题,构建了一个融合非线性与线性特征的时序预测模型,其中多尺度一维卷积神经网络串联双向门控循环神经网络形成非线性时序预测分支,自回归模型构成线性分支。两个分支并联,最终通过全连接层输出预测结果。模型具备非线性部分的泛化能力和线性部分的记忆能力,对输入的幅值变化更加灵敏,并采用鲸鱼优化算法寻找最优模型超参数。通过对比现有模型以及消融实验验证了所提模型的有效性。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
崔孝凯
王庆芝
刘其朋
关键词 电池健康状态双向门控循环神经网络自回归模型鲸鱼优化算法    
Abstract:To address the problems of low accuracy and poor robustness of traditional data-driven battery state of health prediction model, this paper develops a time series prediction model fusing both nonlinear and linear branches. The nonlinear time series prediction branch is formed by a one-dimensional convolutional neural network with a multi-size parallel structure in series with a bidirectional gated recurrent neural network, and the linear branch is constructed by an autoregressive model. Two branches in parallel output prediction results through a fully connected layer. The above prediction model has the generalization ability of the nonlinear part and the memory ability of the linear part, and is more sensitive to the change of input amplitude. The whale optimization algorithm is used to effectively search the optimal model hyper-parameters. The effectiveness and superiority of the linear nonlinear fusion prediction model proposed in this paper are verified by comparing existing models and ablation experiments.
Key wordsbattery state of health    bidirectional gated recurrent neural network    autoregressive model    whale optimization algorithm
收稿日期: 2022-11-25      出版日期: 2024-11-07
ZTFLH:  TM912  
  TP183  
基金资助:国家自然科学基金青年基金(61903212)
通讯作者: 王庆芝(1988-),女,山东济宁人,博士,讲师,主要研究方向为间歇控制、多智能体、切换系统、T-S模糊系统。   
作者简介: 崔孝凯(1997-),男,山东济南人,硕士,主要研究方向为人工智能。
引用本文:   
崔孝凯, 王庆芝, 刘其朋. 基于数据驱动的锂电池健康状态预测[J]. 复杂系统与复杂性科学, 2024, 21(3): 154-159.
CUI Xiaokai, WANG Qingzhi, LIU Qipeng. A Data-driven Model for Prediction of Lithium Battery State of Health[J]. Complex Systems and Complexity Science, 2024, 21(3): 154-159.
链接本文:  
https://fzkx.qdu.edu.cn/CN/10.13306/j.1672-3813.2024.03.020      或      https://fzkx.qdu.edu.cn/CN/Y2024/V21/I3/154
[1] 王其钰, 王朔, 周格, 等. 锂电池失效分析与研究进展[J]. 物理学报, 2018, 67(12): 279-290.
WANG Q Y, WANG S, ZHOU G, et al. Progress on the failure analysis of lithium battery[J]. Acta Physica Sinica, 2018, 67(12): 279-290.
[2] 罗伟林, 张立强, 吕超, 等. 锂离子电池寿命预测国外研究现状综述[J]. 电源学报, 2013 (1): 140-144.
LUO W L, ZHANG L Q, LV C, et al. Review on foreign status of life prediction of lithium-ion batteries[J]. Journal of Power Sources, 2013 (1): 140-144.
[3] ZHANG Q, WHITE R E. Capacity fade analysis of a lithium-ion cell[J]. Journal of Power Sources, 2008, 179(2): 793-798.
[4] 李超然,肖飞,樊亚翔,杨国润,唐欣.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 C R, XIAO F, FAN Y X, et al. An approach to lithium-ion battery SOH[J]. Transactions of China Electrotechnical Society,2020, 35(19): 4106-4119.
[5] 倪水平,李慧芳.基于一维卷积神经网络与长短期记忆网络结合的电池荷电状态预测方法[J].计算机应用,2021,41(5):1514-1521.
NI S P, LI H F. Battery state-of-charge prediction method based on one-dimensional convolutional neural network combined with long short-term memorynetwork[J]. Computer Applications, 2021, 41(5): 1514-1521.
[6] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2015: 1-9.
[7] LIU F, ZHENG J, ZHENG L, et al. Combining attention-based bidirectional gated recurrent neural network and two-dimensional convolutional neural network for document-level sentimentclassification[J]. Neurocomputing, 2020, 371: 39-50.
[8] PARK J, LEE M, KIM G, et al. Integrated approach based on dual extendedKalman filter and multivariate autoregressive model for predicting battery capacity using health indicator and SOC/SOH[J]. Energies, 2020, 13(9): 2138.
[9] MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67.
[10] 曹广华,赵中林,许昀昊.基于GRU的锂电池组健康状态预测研究[J].吉林大学学报(信息科学版),2022,40(2):181-187.
CAO G H, ZHAO L Z, XU Y H.Research on health state prediction of lithium battery pack based on GRU[J]. Journal of Jilin University (Information Science Edition), 2022, 40(2):181-187.
[11] 王鑫,吴际,刘超,杨海燕,杜艳丽,牛文生.基于LSTM循环神经网络的故障时间序列预测[J].北京航空航天大学学报,2018,44(4):772-784.
WANG X, WU J, LIU C, et al. Exploring LSTM based recurrent neural network for failure time series prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(4): 772-784.
[12] National Aeronautics and Space Administration Prognostics Center of Excellence.PCoE datasets[EB/OL].[2022-10-06].https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/#battery.
[13] 朱元富,贺文武,李建兴,等.基于Bi-LSTM/Bi-GRU循环神经网络的锂电池SOC估计[J].储能科学与技术,2021,10(3):1163-1176.
ZHU Y F, HE W W, LI J X, et al. Estimation of SOC of lithium battery based on Bi-LSTM/Bi-GRU recurrent neural network[J]. Energy Storage Science and Technology, 2021,10(3):1163-1176.
[14] 张国豪, 刘波. 采用 CNN 和 Bidirectional GRU 的时间序列分类研究[J]. 计算机科学与探索, 2019, 13(6): 916.
ZHANG G H, LIU B.Research on time series classification using CNN and Bidirectional GRU[J]. Journal of Frontiers of Computer Science and Techno, 2019, 13(6): 916.
[15] 周键. 测控专业综合实验教学改革和实践[J]. 智库时代,2021(42):104-106,145.
ZHOU J. Comprehensive experimental teaching reform and practice of measurement and control specialty[J] Think Tank Times, 2021 (42): 104-106,145.
[1] 田梦龙, 张纪会. 跨层四向穿梭车仓库复合作业路径优化[J]. 复杂系统与复杂性科学, 2024, 21(3): 100-107.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed