基于卷积神经网络的锂离子电池SOH估算

被引：168

作者：

李超然

肖飞

樊亚翔

杨国润

唐欣

机构：

[1] 舰船综合电力技术国防科技重点实验室(海军工程大学)

来源：

电工技术学报 | 2020年 / 35卷 / 19期

关键词：

锂离子电池; 健康状态; 卷积神经网络; 深度学习;

D O I：

暂无

中图分类号：

TM912 [蓄电池]; TP183 [人工神经网络与计算];

学科分类号：

080802 [电力系统及其自动化]; 140502 [人工智能];

摘要：

锂离子电池健康状态(SOH)描述了电池当前老化程度,其估算难点在于缺乏明确统一的定义、无法直接测量以及难以确定数量合适、相关性高的估算输入量。为了克服上述问题,该文从容量的角度定义SOH,并将锂离子电池恒流-恒压充电过程中的电压、电流、温度曲线作为输入,提出采用一维深度卷积神经网络(CNN)实现锂离子电池容量估算以获取SOH。在NASA锂离子电池随机使用数据集和牛津电池老化数据集上进行的实验结果表明,该方法能够实现准确的SOH估算,且具备网络参数少、占用内存小的优势。另外,通过实验讨论了网络输入、模型结构、数据增强对所提出的SOH估算方法的影响。

引用

页码：4106 / 4119

页数：14

共 25 条

[1]

State of health estimation of lithium-ion batteries based on the constant voltage charging curve.[J].Zengkai Wang;Shengkui Zeng;Jianbin Guo;Taichun Qin.Energy.2019,

[2]

A fast estimation algorithm for lithium-ion battery state of health.[J].Xiaopeng Tang;Changfu Zou;Ke Yao;Guohua Chen;Boyang Liu;Zhenwei He;Furong Gao.Journal of Power Sources.2018,

[3]

Novel battery state-of-health online estimation method using multiple health indicators and an extreme learning machine.[J].Haihong Pan;Zhiqiang Lü;Huimin Wang;Haiyan Wei;Lin Chen.Energy.2018,

[4]

A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve.[J].Duo Yang;Xu Zhang;Rui Pan;Yujie Wang;Zonghai Chen.Journal of Power Sources.2018,

[5]

A single particle model with chemical/mechanical degradation physics for lithium ion battery State of Health (SOH) estimation.[J].J. Li;K. Adewuyi;N. Lotfi;R.G. Landers;J. Park.Applied Energy.2018,

[6]

Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review [J].

Rawat, Waseem ;

Wang, Zenghui .

NEURAL COMPUTATION, 2017, 29 (09) :2352-2449

[7]

Gaussian process regression for forecasting battery state of health.[J].Robert R. Richardson;Michael A. Osborne;David A. Howey.Journal of Power Sources.2017,

[8]

A systematic model-based degradation behavior recognition and health monitoring method for lithium-ion batteries.[J].Rui Xiong;Jinpeng Tian;Hao Mu;Chun Wang.Applied Energy.2017,

[9]

Multi-time-scale observer design for state-of-charge and state-of-health of a lithium-ion battery.[J].Changfu Zou;Chris Manzie;Dragan Nešić;Abhijit G. Kallapur.Journal of Power Sources.2016,

[10]

Performance analysis and SOH (state of health) evaluation of lithium polymer batteries through electrochemical impedance spectroscopy.[J].Matteo Galeotti;Lucio Cinà;Corrado Giammanco;Stefano Cordiner;Aldo Di Carlo.Energy.2015,

← 1 2 3 →