Defects detection and recognition of lithium battery electrode plate coating based on WOA-BPNN

doi:10.19799/j.cnki.2095-4239.2022.0226

Abstract

Abstract:

The positive and negative electrodes of a lithium battery are crucial parts of the battery. The electrode coating quality is significantly related to the battery's performance and service life, and a defective electrode is often the cause of the battery's potential safety hazard. This study presents a set of algorithms based on a whale optimization algorithm-back propagation neural network (WOA-BPNN) to further improve the automation level of defect detection and recognition for lithium-battery electrode plate coating. First, image preprocessing is performed on the collected lithium-battery electrode plate coating image. Then, the shape, gray, and texture features of the defect target area are extracted after being segmented from the image. Next, the BPNN is built, and the fused feature vector after serial fusion is used as the network's input. Finally, the WOA is used to assist in parameter adjustment while training the neural network classification model to further improve the model's recognition accuracy. This algorithm can accurately detect and recognize eight types of common lithium-battery electrode plate coating defects, including scratch, metal exposure, hole, crack, abnormal pollution, and carbon spalling. The experimental results show that when the width of the lithium-battery electrode plate is 200 mm, the detection accuracy is 0.05 mm and the detection speed is 60 m/min, and the average missed detection rate of this algorithm is 1.68%, the average false detection rate is 0%, and the average classification and recognition accuracy is 97.08%. This algorithm can be used to effectively detect defects in lithium-battery electrode plate coating at high speeds and with high precision, and it has practical applications in the field of lithium battery intelligent manufacturing.

Key words: machine vision, defect detection, image classification, lithium battery electrode plate

CLC Number:

TP 391.41

Jianping ZHONG, Tao FEI. Defects detection and recognition of lithium battery electrode plate coating based on WOA-BPNN[J]. Energy Storage Science and Technology, 2022, 11(8): 2537-2545.

Figures/Tables 7

Fig. 1

Fig. 2

Fig. 3

Table 1

Table 2

Table 3

Table 4

References 16

1	张向倩. 锂电池检测的安全标准及安全防护研究[J]. 安全, 2020, 41(3): 49-53.
	ZHANG X Q. Research on the safety standards and safety protection of lithium battery testing[J]. Safety & Security, 2020, 41(3): 49-53.
2	孙正军. 基于图像边缘提取的电池极片瑕疵检测研究[D]. 长沙: 中南大学, 2009.
	SUN Z J. Research on defect detection of battery electrode based on image edge extraction[D]. Changsha: Central South University, 2009.
3	郑岩. 基于DSP的锂电池电极表面缺陷检测系统[D]. 秦皇岛: 燕山大学, 2014.
	ZHENG Y. The surface defects of lithium electrode detection system based on DSP[D]. Qinhuangdao: Yanshan University, 2014.
4	陈功, 朱锡芳, 许清泉, 等. 最大熵和高斯模型在锂电池缺陷识别中的应用[J]. 电源技术, 2014, 38(6): 1063-1065.
	CHEN G, ZHU X F, XU Q Q, et al. Application of maximum entropy threshold and Gaussian mixture model in defects recognition of lithium battery[J]. Chinese Journal of Power Sources, 2014, 38(6): 1063-1065.
5	胡玥红. 基于机器视觉的锂电池极片缺陷检测研究[D]. 哈尔滨:哈尔滨工业大学,2015.
	HU Y H. Research on defect detection of lithium battery electrode sheet based on machine vision[D]. Harbin:Harbin Institute of Technology,2015.
6	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.
	ZHANG Z G. Research on visual detection algorithm for surface defects of cell based on intelligent learning[D]. Guangzhou: South China University of Technology,2019.
7	黄梦涛, 连一鑫. 基于改进Canny算子的锂电池极片表面缺陷检测[J]. 仪器仪表学报, 2021, 42(10): 199-209.
	HUANG M T, LIAN Y X. Lithium battery electrode plate surface defect detection based on improved Canny operator[J]. Chinese Journal of Scientific Instrument, 2021, 42(10): 199-209.
8	唐凤雄. 我国锂电池产业发展需要新思路——访国务院发展研究中心资源与环境政策研究所吴平[J]. 中国高新技术企业, 2010(20): 17-19.
9	蓝兹炜, 张建茹, 李园园, 等. 基于锂离子电池正极材料的一元/二元复合正极材料研究进展[J]. 储能科学与技术, 2021, 10(1): 27-39.
	LAN Z W, ZHANG J R, LI Y Y, et al. Research progress of mono/binary composite cathode materials based on lithium-ion battery cathode materials[J]. Energy Storage Science and Technology, 2021, 10(1): 27-39.
10	刘洋洋, 王旭阳, 徐谢宇, 等. 锂金属负极用集流体改性研究及进展[J]. 储能科学与技术, 2021, 10(4): 1261-1272.
	LIU Y Y, WANG X Y, XU X Y, et al. Research progresses on modified current collector for lithium metal anode[J]. Energy Storage Science and Technology, 2021, 10(4): 1261-1272.
11	刘丽, 赵凌君, 郭承玉, 等. 图像纹理分类方法研究进展和展望[J]. 自动化学报, 2018, 44(4): 584-607.
	LIU L, ZHAO L J, GUO C Y, et al. Texture classification: State-of-the-art methods and prospects[J]. Acta Automatica Sinica, 2018, 44(4): 584-607.
12	HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610-621.
13	ULABY F T, KOUYATE F, BRISCO B, et al. Textural infornation in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 1986, GE-24(2): 235-245.
14	胡志新, 王涛. 改进遗传算法优化BP神经网络的双目相机标定[J]. 电光与控制, 2022, 29(1): 75-79.
	HU Z X, WANG T. Binocular camera calibration based on BP neural network optimized by improved genetic algorithm[J]. Electronics Optics & Control, 2022, 29(1): 75-79.
15	马创, 周代棋, 张业. 基于改进鲸鱼算法的BP神经网络水资源需求预测方法[J]. 计算机科学, 2020, 47(S2): 486-490.
	MA C, ZHOU D Q, ZHANG Y. BP neural network water resource demand prediction method based on improved whale algorithm[J]. Computer Science, 2020, 47(S2): 486-490.
16	MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67.

缺陷类型	图像幅数	缺陷个数	漏检数	检测时间/ms
总计	400	477	8	93005
正极划痕	50	56	0	11832
负极划痕	50	59	0	11453
正极漏铝	50	62	0	11911
负极漏铜	50	60	0	11357
孔洞	50	55	0	11651
裂纹	50	50	0	11256
异污	50	54	3	11557
脱碳	50	81	5	11988

分类方法	分类准确率
BPNN+形态特征	48.54%
BPNN+灰度特征	62.92%
BPNN+GLCM纹理特征	70.83%
BPNN+形态特征+灰度特征	84.38%
本工作特征算法	97.08%

缺陷类型	评价指标
缺陷类型	精确度	召回率	F₁值
正极划痕	96.77%	100.00%	98.36%
负极划痕	100.00%	96.67%	98.31%
正极漏铝	95.16%	98.33%	96.72%
负极漏铜	98.28%	95.00%	96.61%
孔洞	95.00%	95.00%	95.00%
裂纹	100.00%	100.00%	100.00%
异污	95.08%	96.67%	95.87%
脱碳	96.61%	95.00%	95.80%

参数选取方法	分类准确率
随机初始化	92.29%
遗传算法	93.96%
粒子群优化算法	94.79%
本工作优化算法	97.08%