用于水泥浆和单体混合系统背散射电子图像相位分割的深度学习方法

IF 10.8 1区 工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY
Yan Yu, Guoqing Geng
{"title":"用于水泥浆和单体混合系统背散射电子图像相位分割的深度学习方法","authors":"Yan Yu,&nbsp;Guoqing Geng","doi":"10.1016/j.cemconcomp.2024.105810","DOIUrl":null,"url":null,"abstract":"<div><div>Quantitative microstructure analysis of supplementary cementitious material (SCM) - blended paste through backscattered electron (BSE) imaging has long been intractable owing to the sophisticated micro phase distribution and overlapped greyscale histogram. This study explores the use of Convolutional Neural Network (CNN) based supervised semantic segmentation methods for quantifying phase assemblage in BSE images of blank cement paste and SCM-blended cement pastes. Four types of SCMs, namely limestone, slag, quartz and metakaolin, were separately blended with WPC and OPC paste for analysis. U-Net architecture with and without ResNet backbones were trained to perform pixel-level image segmentation of anhydrous cement and SCM particles. The results indicate that deep learning models can robustly segment anhydrous cement particles from BSE images and achieve same level of precision as QXRD. For limestone, quartz and slag, deep learning models show strong potential for semi-quantitative segmentation. While metakaolin cannot be reliably segmented based solely on graphic information.</div></div>","PeriodicalId":9865,"journal":{"name":"Cement & concrete composites","volume":"155 ","pages":"Article 105810"},"PeriodicalIF":10.8000,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning methods for phase segmentation in backscattered electron images of cement paste and SCM-blended systems\",\"authors\":\"Yan Yu,&nbsp;Guoqing Geng\",\"doi\":\"10.1016/j.cemconcomp.2024.105810\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Quantitative microstructure analysis of supplementary cementitious material (SCM) - blended paste through backscattered electron (BSE) imaging has long been intractable owing to the sophisticated micro phase distribution and overlapped greyscale histogram. This study explores the use of Convolutional Neural Network (CNN) based supervised semantic segmentation methods for quantifying phase assemblage in BSE images of blank cement paste and SCM-blended cement pastes. Four types of SCMs, namely limestone, slag, quartz and metakaolin, were separately blended with WPC and OPC paste for analysis. U-Net architecture with and without ResNet backbones were trained to perform pixel-level image segmentation of anhydrous cement and SCM particles. The results indicate that deep learning models can robustly segment anhydrous cement particles from BSE images and achieve same level of precision as QXRD. For limestone, quartz and slag, deep learning models show strong potential for semi-quantitative segmentation. While metakaolin cannot be reliably segmented based solely on graphic information.</div></div>\",\"PeriodicalId\":9865,\"journal\":{\"name\":\"Cement & concrete composites\",\"volume\":\"155 \",\"pages\":\"Article 105810\"},\"PeriodicalIF\":10.8000,\"publicationDate\":\"2024-10-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cement & concrete composites\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0958946524003834\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CONSTRUCTION & BUILDING TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cement & concrete composites","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0958946524003834","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

由于微观相位分布复杂且灰度直方图重叠,通过背散射电子(BSE)成像对水泥基辅助材料(SCM)-混合浆料的微观结构进行定量分析一直是个难题。本研究探索了基于卷积神经网络(CNN)的监督语义分割方法,用于量化空白水泥浆和单片机混合水泥浆 BSE 图像中的相组合。将石灰石、矿渣、石英和偏高岭土四种 SCM 分别与 WPC 和 OPC 浆料混合进行分析。对带有和不带 ResNet 主干网的 U-Net 架构进行了训练,以对无水水泥和 SCM 颗粒进行像素级图像分割。结果表明,深度学习模型可以从 BSE 图像中稳健地分割无水水泥颗粒,并达到与 QXRD 相同的精度水平。对于石灰石、石英和矿渣,深度学习模型显示出半定量分割的强大潜力。而偏高岭土则无法仅根据图形信息进行可靠的分割。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep learning methods for phase segmentation in backscattered electron images of cement paste and SCM-blended systems
Quantitative microstructure analysis of supplementary cementitious material (SCM) - blended paste through backscattered electron (BSE) imaging has long been intractable owing to the sophisticated micro phase distribution and overlapped greyscale histogram. This study explores the use of Convolutional Neural Network (CNN) based supervised semantic segmentation methods for quantifying phase assemblage in BSE images of blank cement paste and SCM-blended cement pastes. Four types of SCMs, namely limestone, slag, quartz and metakaolin, were separately blended with WPC and OPC paste for analysis. U-Net architecture with and without ResNet backbones were trained to perform pixel-level image segmentation of anhydrous cement and SCM particles. The results indicate that deep learning models can robustly segment anhydrous cement particles from BSE images and achieve same level of precision as QXRD. For limestone, quartz and slag, deep learning models show strong potential for semi-quantitative segmentation. While metakaolin cannot be reliably segmented based solely on graphic information.
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
Cement & concrete composites
Cement & concrete composites 工程技术-材料科学:复合
CiteScore
18.70
自引率
11.40%
发文量
459
审稿时长
65 days
期刊介绍: Cement & concrete composites focuses on advancements in cement-concrete composite technology and the production, use, and performance of cement-based construction materials. It covers a wide range of materials, including fiber-reinforced composites, polymer composites, ferrocement, and those incorporating special aggregates or waste materials. Major themes include microstructure, material properties, testing, durability, mechanics, modeling, design, fabrication, and practical applications. The journal welcomes papers on structural behavior, field studies, repair and maintenance, serviceability, and sustainability. It aims to enhance understanding, provide a platform for unconventional materials, promote low-cost energy-saving materials, and bridge the gap between materials science, engineering, and construction. Special issues on emerging topics are also published to encourage collaboration between materials scientists, engineers, designers, and fabricators.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信