基于深度学习图像分割的高容量镍基氧化物阴极二次粒子孔隙度可靠测量

IF 2.5 4区 化学 Q3 CHEMISTRY, ANALYTICAL Journal of Analytical Science and Technology Pub Date : 2023-11-21 DOI:10.1186/s40543-023-00407-z
Hee-Beom Lee, Min-Hyoung Jung, Young-Hoon Kim, Eun-Byeol Park, Woo-Sung Jang, Seon-Je Kim, Ki-ju Choi, Ji-young Park, Kee-bum Hwang, Jae-Hyun Shim, Songhun Yoon, Young-Min Kim
{"title":"基于深度学习图像分割的高容量镍基氧化物阴极二次粒子孔隙度可靠测量","authors":"Hee-Beom Lee, Min-Hyoung Jung, Young-Hoon Kim, Eun-Byeol Park, Woo-Sung Jang, Seon-Je Kim, Ki-ju Choi, Ji-young Park, Kee-bum Hwang, Jae-Hyun Shim, Songhun Yoon, Young-Min Kim","doi":"10.1186/s40543-023-00407-z","DOIUrl":null,"url":null,"abstract":"The optimization of geometrical pore control in high-capacity Ni-based cathode materials is required to enhance the cyclic performance of lithium-ion batteries. Enhanced porosity improves lithium-ion mobility by increasing the electrode–electrolyte contact area and reducing the number of ion diffusion pathways. However, excessive porosity can diminish capacity, thus necessitating optimizing pore distribution to compromise the trade-off relation. Accordingly, a statistically meaningful porosity estimation of electrode materials is required to engineer the local pore distribution inside the electrode particles. Conventional scanning electron microscopy (SEM) image-based porosity measurement can be used for this purpose. However, it is labor-intensive and subjected to human bias for low-contrast pore images, thereby potentially lowering measurement accuracy. To mitigate these difficulties, we propose an automated image segmentation method for the reliable porosity measurement of cathode materials using deep convolutional neural networks specifically trained for the analysis of porous cathode materials. Combined with the preprocessed SEM image datasets, the model trained for 100 epochs exhibits an accuracy of > 97% for feature segmentation with regard to pore detection on the input datasets. This automated method considerably reduces manual effort and human bias related to the digitization of pore features in serial section SEM image datasets used in 3D electron tomography. ","PeriodicalId":14967,"journal":{"name":"Journal of Analytical Science and Technology","volume":"56 5","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning image segmentation for the reliable porosity measurement of high-capacity Ni-based oxide cathode secondary particles\",\"authors\":\"Hee-Beom Lee, Min-Hyoung Jung, Young-Hoon Kim, Eun-Byeol Park, Woo-Sung Jang, Seon-Je Kim, Ki-ju Choi, Ji-young Park, Kee-bum Hwang, Jae-Hyun Shim, Songhun Yoon, Young-Min Kim\",\"doi\":\"10.1186/s40543-023-00407-z\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The optimization of geometrical pore control in high-capacity Ni-based cathode materials is required to enhance the cyclic performance of lithium-ion batteries. Enhanced porosity improves lithium-ion mobility by increasing the electrode–electrolyte contact area and reducing the number of ion diffusion pathways. However, excessive porosity can diminish capacity, thus necessitating optimizing pore distribution to compromise the trade-off relation. Accordingly, a statistically meaningful porosity estimation of electrode materials is required to engineer the local pore distribution inside the electrode particles. Conventional scanning electron microscopy (SEM) image-based porosity measurement can be used for this purpose. However, it is labor-intensive and subjected to human bias for low-contrast pore images, thereby potentially lowering measurement accuracy. To mitigate these difficulties, we propose an automated image segmentation method for the reliable porosity measurement of cathode materials using deep convolutional neural networks specifically trained for the analysis of porous cathode materials. Combined with the preprocessed SEM image datasets, the model trained for 100 epochs exhibits an accuracy of > 97% for feature segmentation with regard to pore detection on the input datasets. This automated method considerably reduces manual effort and human bias related to the digitization of pore features in serial section SEM image datasets used in 3D electron tomography. \",\"PeriodicalId\":14967,\"journal\":{\"name\":\"Journal of Analytical Science and Technology\",\"volume\":\"56 5\",\"pages\":\"\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2023-11-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Analytical Science and Technology\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://doi.org/10.1186/s40543-023-00407-z\",\"RegionNum\":4,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CHEMISTRY, ANALYTICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Analytical Science and Technology","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1186/s40543-023-00407-z","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, ANALYTICAL","Score":null,"Total":0}
引用次数: 0

摘要

为了提高锂离子电池的循环性能,需要优化高容量镍基正极材料的几何孔隙控制。孔隙率的提高通过增加电极-电解质接触面积和减少离子扩散途径的数量来提高锂离子的迁移率。然而,过高的孔隙度会降低产能,因此有必要优化孔隙分布以折衷关系。因此,需要对电极材料进行统计上有意义的孔隙率估计,以设计电极颗粒内部的局部孔隙分布。传统的基于扫描电子显微镜(SEM)图像的孔隙度测量可用于此目的。然而,对于低对比度的孔隙图像,它是劳动密集型的,并且容易受到人为偏见的影响,从而潜在地降低了测量精度。为了减轻这些困难,我们提出了一种自动图像分割方法,用于可靠的阴极材料孔隙度测量,该方法使用深度卷积神经网络,专门用于多孔阴极材料的分析。结合预处理后的SEM图像数据集,经过100次epoch训练的模型对输入数据集的孔隙检测进行特征分割的准确率达到了> 97%。这种自动化方法大大减少了与三维电子断层扫描中使用的连续切片SEM图像数据集的孔隙特征数字化相关的人工努力和人为偏差。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Deep learning image segmentation for the reliable porosity measurement of high-capacity Ni-based oxide cathode secondary particles
The optimization of geometrical pore control in high-capacity Ni-based cathode materials is required to enhance the cyclic performance of lithium-ion batteries. Enhanced porosity improves lithium-ion mobility by increasing the electrode–electrolyte contact area and reducing the number of ion diffusion pathways. However, excessive porosity can diminish capacity, thus necessitating optimizing pore distribution to compromise the trade-off relation. Accordingly, a statistically meaningful porosity estimation of electrode materials is required to engineer the local pore distribution inside the electrode particles. Conventional scanning electron microscopy (SEM) image-based porosity measurement can be used for this purpose. However, it is labor-intensive and subjected to human bias for low-contrast pore images, thereby potentially lowering measurement accuracy. To mitigate these difficulties, we propose an automated image segmentation method for the reliable porosity measurement of cathode materials using deep convolutional neural networks specifically trained for the analysis of porous cathode materials. Combined with the preprocessed SEM image datasets, the model trained for 100 epochs exhibits an accuracy of > 97% for feature segmentation with regard to pore detection on the input datasets. This automated method considerably reduces manual effort and human bias related to the digitization of pore features in serial section SEM image datasets used in 3D electron tomography.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Analytical Science and Technology
Journal of Analytical Science and Technology Environmental Science-General Environmental Science
CiteScore
4.00
自引率
4.20%
发文量
39
审稿时长
13 weeks
期刊介绍: The Journal of Analytical Science and Technology (JAST) is a fully open access peer-reviewed scientific journal published under the brand SpringerOpen. JAST was launched by Korea Basic Science Institute in 2010. JAST publishes original research and review articles on all aspects of analytical principles, techniques, methods, procedures, and equipment. JAST’s vision is to be an internationally influential and widely read analytical science journal. Our mission is to inform and stimulate researchers to make significant professional achievements in science. We aim to provide scientists, researchers, and students worldwide with unlimited access to the latest advances of the analytical sciences.
期刊最新文献
Inorganic iodine and bromine speciation in Arctic snow at picogram-per-grams levels by IC-ICP-MS Accurate determination of high sulfur content in sulfide samples: an optimized ICP-OES method Isotopic distribution of bioavailable Sr, Nd, and Pb in Chungcheongbuk-do Province, Korea Exploring the feasibility of a single-protoplast proteomic analysis Gaseous ozone inactivation of Bacillus atrophaeus spores on ceramic and porcelain tiles
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1