18650 型锂电池安全性识别

taptap下载安装安卓学报 ›› 2023, taptap点点手机网页 ›› taptap点点手机网页版 : 24-30.

18650 型锂电池安全性识别

张威^1a，2，3，朱家慧^1b，王琼^1c，张博利^1d，2

（1. taptap下载安装安卓 a. 航空工程学院；b. 安全科学与工程学院；c. 理学院；d. 基础实验中心，天津 300300；2. 民航航空公司人工智能重点实验室，天津 300300；3. 中国民航航空地面特种设备研究基地，天津 300300）

收稿日期:2021-11-30 修回日期:2022-01-18 出版日期:2024-01-12 发布日期:2024-01-12
作者简介:男，湖南衡阳人，教授，博士，研究方向为临近航空器地面任务智能化、锂电池安全性
基金资助:
国家自然科学基金民航联合研究基金项目（U2033208）

Safety identification of 18650 lithium battery

ZHANG Wei ^{1a, 2, 3} , ZHU Jiahui ^1b , WANG Qiong^1c , ZHANG Boli ^{1d, 2}

(1a. College of Aeronautical Engineering; 1b. College of Safety Science and Engineering; 1c. College of Science; 1d. Basic Experiment
Center, CAUC, Tianjin 300300, China; 2. Civil Aviation Key Laboratory of Artificial Intelligence for Airlines, Tianjin 300300, China;
3. Aviation Special Ground Equipment Research Base, Tianjin 300300, China)

Received:2021-11-30 Revised:2022-01-18 Online:2024-01-12 Published:2024-01-12

摘要/Abstract

摘要： 目前航空货运和客运中锂电池爆炸起火的事故层出不穷，最主要原因在于锂电池内部结构状态发生变化，故锂电池内部结构状态的检测成为机场急需解决的重要问题。因此，本研究提出一种MLP（multi-layerperceptron）特征向量分类方法，该方法首先为锂电池内部结构的识别选择最佳的特征向量和分类器；然后对采集得到的锂电池图像样本进行感兴趣区域（ROI，regionofinterest）获取、图像裁剪与绘制、特征向量提取和分类器分类处理；最后，根据分类结果找到最佳的特征向量与分类器组合。实验表明：用该方法进行锂电池样本图像分类识别，其结果具有较高的准确率，可以有效降低锂电池在航空运输中的爆炸风险

Abstract:

At present, accidents of lithium battery explosions and fires in air cargo and passenger transportation are constantly occurring, mainly due to the changes of the internal structural state of lithium batteries. Therefore, the detection of internal structural state of lithium batteries has become a significant problem that airports need to solve urgently.

In this study, MLP (multi-layer perceptron) feature vector classification method is proposed. This method first selects the optimal feature vector and classifier for the recognition of the internal structure of lithium batteries and then performs ROI (region of interest) acquisition, image cropping and rendering, feature vector extraction and classifier classification processing on the collected lithium battery image samples. Finally, the optimal combina鄄 tion of feature vector and classifier are found according to the results of classification. The experiments show that the results of classification recognition of lithium battery sample image with this method have high accuracy, which can effectively reduce the explosion risk of lithium battery in air transport.

Key words: lithium battery, classification recognition, ROI acquisition, image cropping, feature extraction, classifier classification

中图分类号:

V353

张威, 朱家慧, 王琼, 张博利. 18650 型锂电池安全性识别[J]. taptap下载安装安卓学报, 2023, 41(6): 24-30.

ZHANG Wei , ZHU Jiahui , WANG Qiong, ZHANG Boli . Safety identification of 18650 lithium battery[J]. Journal of Civil Aviation University of China, 2023, 41(6): 24-30.

参考文献 19

[1]	FINEGAN D P, SCHEEL M, ROBINSON J B, et al． In-operando highspeed tomography of lithiumion batteries during thermal runaway [J]． Nature Communications, 2015, 6(1): 1-10．
[2]	FINEGAN D P, SCHEEL M, ROBINSON J B, et al． Investigating lithium-ion battery materials during overcharge-induced thermal runaway: an operando and multi-scale X-ray CT study[J]． Physical Chemistry Chemical Physics, 2016, 18(45): 30912-30919．
[3]	PFRANG A, KERSYS A, KRISTON A, et al． Long-term cycling induced jelly roll deformation in commercial 18650 cells[J]． Journal of Power Sources, 2018, 392: 168-175．
[4]	PARHIZI M, AHMED M B, JAIN A． Determination of the core tempera－ ture of a Li-ion cell during thermal runaway[J]． Journal of Power Sources, 2017, 370: 27-35．
[5]	FERNANDES Y, BRY A, DE PERSIS S． Identification and quantifica－ tion of gases emitted during abuse tests by overcharge of a commercial Li-ion battery[J]． Journal of Power Sources, 2018, 389: 106-119．
[6]	郑魁敬, 刘学超, 王萌萌．基于机器视觉的手机电池表面缺陷检测[J]．制造技术与机床, 2020(4): 105-112．
[7]	邓红红．锂电池表面缺陷检测研究[D]．哈尔滨: 哈尔滨工业大学, 2018．
[8]	李岩．圆柱形覆膜锂电池圆周面破膜检测方法研究[D]．沈阳: 沈阳工业大学, 2020．
[9]	苑玮琦, 李岩．圆柱形覆膜锂电池圆周面破膜检测方法研究[J]．信息与电脑(理论版), 2020, 32(2): 108-110．
[10]	张志国．基于智能学习的电池片表面缺陷视觉检测算法研究[D]．广州: 华南理工大学, 2019．
[11]	周佳禾, 宫临凡, 王盛瑶．方形卷绕式锂电池电极褶皱检测方法研究[J]．仪表技术与传感器, 2021(5): 107-111．
[12]	邬灏．基于 X 光图像分析的锂电池正负极片测量系统[D]．北京: 北京林业大学, 2018．
[13]	王东昆, 彭劼扬, 王家海, 等．基于图像识别的锂离子电池正负极距离检测[J]．制造业自动化, 2019, 41(10): 10-16.
[14]	动力电池技术.热失控原来是这样发生的[EB/OL]. (2017-11-12)[202111-30]. https: //baijiahao.baidu.com/s?id=1583865553119574850.
[15]	SZEGEDY C, IOFFE S, VANHOUCKE V, et al． Inception-v4, incep－ tion-ResNet and the impact of residual connections on learning[J]． Pro－ ceedings of the AAAI Conference on Artificial Intelligence, 2017, 31(1)： 4278-4284．
[16]	钜大 LARGE. 锂离子电池热失控的原因及解决办法[EB/OL].
	(2019-08-01)[2021-11-30]. http: //www.juda.cn/news/92843.html.
[17]	孙杰, 李吉刚, 党胜男, 等．锂离子电池及其材料热失控毒物研究[J]．储能科学与技术, 2015, 4(6): 609-615.
[18]	牛志远, 王怀铷, 金阳, 等．不同倍率下磷酸铁锂电池模组过充热失控特性研究[J]．电力工程技术, 2021, 40(4): 167-174．
[19]	YAO X Y, SAXENA S, SU L, et al． The explosive nature of tab burrs in Li-ion batteries[J]． IEEE Access, 2019, 7: 45978-45982.