Segmentation and Metallographic Evaluation of Aluminium Slurry Coatings Using Machine Learning Techniques

IF 2.1 3区 材料科学 Q2 METALLURGY & METALLURGICAL ENGINEERING Oxidation of Metals Pub Date : 2024-10-26 DOI:10.1007/s11085-024-10321-3
Maria del Mar Juez Lorenzo, Vladislav Kolarik, Khyati Sethia, Petr Strakos
{"title":"Segmentation and Metallographic Evaluation of Aluminium Slurry Coatings Using Machine Learning Techniques","authors":"Maria del Mar Juez Lorenzo,&nbsp;Vladislav Kolarik,&nbsp;Khyati Sethia,&nbsp;Petr Strakos","doi":"10.1007/s11085-024-10321-3","DOIUrl":null,"url":null,"abstract":"<div><p>Analysis of scanning electron microscope (SEM) images is crucial for characterising aluminide diffusion coatings deposited via the slurry route on steels, yet challenging due to various factors like imaging artefacts, noise, and overlapping features such as resin, precipitates, cracks, and pores. This study focuses on determining the thicknesses of the coating layers Fe<sub>2</sub>Al<sub>5</sub> and, if present, FeAl, pore characteristics, and chromium precipitate fractions after the heat treatment that forms the diffusion coating. A deep learning SEM image segmentation model utilising U-Net architecture is proposed. Ground truth data were generated using the trainable Weka segmentation plugin in ImageJ, manually refined for accuracy, and supplemented with synthetic data from Blender 3D software for data augmentation of a limited number of SEM label images. The deep learning model trained on a combination of synthetic and real SEM data achieved mean dice scores of 98.7% ± 0.2 for the Fe<sub>2</sub>Al<sub>5</sub> layer, 82.6% ± 8.1 for pores, and 81.48% ± 3.6 for precipitates when evaluated on manually labelled SEM data. The deep learning procedure was applied to evaluate a series of SEM images of diffusion coatings obtained with three different slurry compositions. The evaluation revealed that using a slurry without a rheology modifier may lead to a thicker partial Fe<sub>2</sub>Al<sub>5</sub> layer that is formed by inward diffusion. The relation between the outward and inward diffusion Fe<sub>2</sub>Al<sub>5</sub> layers was not affected by the coating thickness. The thinner diffusion coating presents lower pores and chromium precipitate fractions independently of the slurry selected.</p></div>","PeriodicalId":724,"journal":{"name":"Oxidation of Metals","volume":"101 6","pages":"1497 - 1512"},"PeriodicalIF":2.1000,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11085-024-10321-3.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Oxidation of Metals","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s11085-024-10321-3","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

Analysis of scanning electron microscope (SEM) images is crucial for characterising aluminide diffusion coatings deposited via the slurry route on steels, yet challenging due to various factors like imaging artefacts, noise, and overlapping features such as resin, precipitates, cracks, and pores. This study focuses on determining the thicknesses of the coating layers Fe2Al5 and, if present, FeAl, pore characteristics, and chromium precipitate fractions after the heat treatment that forms the diffusion coating. A deep learning SEM image segmentation model utilising U-Net architecture is proposed. Ground truth data were generated using the trainable Weka segmentation plugin in ImageJ, manually refined for accuracy, and supplemented with synthetic data from Blender 3D software for data augmentation of a limited number of SEM label images. The deep learning model trained on a combination of synthetic and real SEM data achieved mean dice scores of 98.7% ± 0.2 for the Fe2Al5 layer, 82.6% ± 8.1 for pores, and 81.48% ± 3.6 for precipitates when evaluated on manually labelled SEM data. The deep learning procedure was applied to evaluate a series of SEM images of diffusion coatings obtained with three different slurry compositions. The evaluation revealed that using a slurry without a rheology modifier may lead to a thicker partial Fe2Al5 layer that is formed by inward diffusion. The relation between the outward and inward diffusion Fe2Al5 layers was not affected by the coating thickness. The thinner diffusion coating presents lower pores and chromium precipitate fractions independently of the slurry selected.

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
利用机器学习技术对铝浆涂层进行分段和金相评估
扫描电子显微镜 (SEM) 图像分析对于确定通过浆料路线沉积在钢材上的铝化物扩散涂层的特性至关重要,但由于成像伪影、噪声和重叠特征(如树脂、沉淀物、裂纹和孔隙)等各种因素的影响,这种分析具有挑战性。本研究的重点是确定形成扩散涂层的热处理后的涂层厚度 Fe2Al5 和 FeAl(如果存在)、孔隙特征和铬析出物分数。本文提出了一种利用 U-Net 架构的深度学习 SEM 图像分割模型。使用 ImageJ 中可训练的 Weka 分割插件生成地面实况数据,并进行人工改进以确保准确性,同时使用 Blender 3D 软件中的合成数据对数量有限的 SEM 标签图像进行数据增强。在人工标注的 SEM 数据上进行评估时,结合合成和真实 SEM 数据训练的深度学习模型对 Fe2Al5 层的平均骰子分数为 98.7% ± 0.2,对孔隙的平均骰子分数为 82.6% ± 8.1,对沉淀物的平均骰子分数为 81.48% ± 3.6。深度学习程序被用于评估使用三种不同浆料成分获得的一系列扩散涂层的 SEM 图像。评估结果表明,使用不含流变修饰剂的浆料可能会导致通过内向扩散形成较厚的部分 Fe2Al5 层。外向扩散和内向扩散 Fe2Al5 层之间的关系不受涂层厚度的影响。较薄的扩散涂层呈现较低的孔隙和铬沉淀分数,与所选浆料无关。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Oxidation of Metals
Oxidation of Metals 工程技术-冶金工程
CiteScore
5.10
自引率
9.10%
发文量
47
审稿时长
2.2 months
期刊介绍: Oxidation of Metals is the premier source for the rapid dissemination of current research on all aspects of the science of gas-solid reactions at temperatures greater than about 400˚C, with primary focus on the high-temperature corrosion of bulk and coated systems. This authoritative bi-monthly publishes original scientific papers on kinetics, mechanisms, studies of scales from structural and morphological viewpoints, transport properties in scales, phase-boundary reactions, and much more. Articles may discuss both theoretical and experimental work related to gas-solid reactions at the surface or near-surface of a material exposed to elevated temperatures, including reactions with oxygen, nitrogen, sulfur, carbon and halogens. In addition, Oxidation of Metals publishes the results of frontier research concerned with deposit-induced attack. Review papers and short technical notes are encouraged.
期刊最新文献
Segmentation and Metallographic Evaluation of Aluminium Slurry Coatings Using Machine Learning Techniques Editorial on Modeling, Prediction and Simulation Editorial on Oxidation in Complex Atmospheres Editorial on Oxidation of Novel Metallic Materials (Intermetallics, MMCs, HEAs…) Editorial on Coatings
×
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