通过应用于光学显微镜图像的卷积神经网络对铸铁合金进行分类

IF 1.9 3区 材料科学 Q2 METALLURGY & METALLURGICAL ENGINEERING steel research international Pub Date : 2024-08-28 DOI:10.1002/srin.202400120
Marta Bárcena, Lara Lloret Iglesias, Diego Ferreño, Isidro Carrascal
{"title":"通过应用于光学显微镜图像的卷积神经网络对铸铁合金进行分类","authors":"Marta Bárcena,&nbsp;Lara Lloret Iglesias,&nbsp;Diego Ferreño,&nbsp;Isidro Carrascal","doi":"10.1002/srin.202400120","DOIUrl":null,"url":null,"abstract":"<p>Classification of cast iron alloys based on graphite morphology plays a crucial role in materials science and engineering. Traditionally, this classification has relied on visual analysis, a method that is not only time-consuming but also suffers from subjectivity, leading to inconsistencies. This study introduces a novel approach utilizing convolutional neural networks—MobileNet for image classification and U-Net for semantic segmentation—to automate the classification process of cast iron alloys. A significant challenge in this domain is the limited availability of diverse and comprehensive datasets necessary for training effective machine learning models. This is addressed by generating a synthetic dataset, creating a rich collection of 2400 pure and 1500 mixed images based on the ISO 945-1:2019 standard. This ensures a robust training process, enhancing the model's ability to generalize across various morphologies of graphite particles. The findings showcase a remarkable accuracy in classifying cast iron alloys (achieving an overall accuracy of 98.9 ± 0.4%—and exceeding 97% for all six classes—for classification of pure images and ranging between 84% and 93% for semantic segmentation of mixed images) and also demonstrate the model's ability to consistently identify and graphite morphology with a level of precision and speed unattainable through manual methods.</p>","PeriodicalId":21929,"journal":{"name":"steel research international","volume":"95 12","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/srin.202400120","citationCount":"0","resultStr":"{\"title\":\"Classification of Cast Iron Alloys through Convolutional Neural Networks Applied on Optical Microscopy Images\",\"authors\":\"Marta Bárcena,&nbsp;Lara Lloret Iglesias,&nbsp;Diego Ferreño,&nbsp;Isidro Carrascal\",\"doi\":\"10.1002/srin.202400120\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Classification of cast iron alloys based on graphite morphology plays a crucial role in materials science and engineering. Traditionally, this classification has relied on visual analysis, a method that is not only time-consuming but also suffers from subjectivity, leading to inconsistencies. This study introduces a novel approach utilizing convolutional neural networks—MobileNet for image classification and U-Net for semantic segmentation—to automate the classification process of cast iron alloys. A significant challenge in this domain is the limited availability of diverse and comprehensive datasets necessary for training effective machine learning models. This is addressed by generating a synthetic dataset, creating a rich collection of 2400 pure and 1500 mixed images based on the ISO 945-1:2019 standard. This ensures a robust training process, enhancing the model's ability to generalize across various morphologies of graphite particles. The findings showcase a remarkable accuracy in classifying cast iron alloys (achieving an overall accuracy of 98.9 ± 0.4%—and exceeding 97% for all six classes—for classification of pure images and ranging between 84% and 93% for semantic segmentation of mixed images) and also demonstrate the model's ability to consistently identify and graphite morphology with a level of precision and speed unattainable through manual methods.</p>\",\"PeriodicalId\":21929,\"journal\":{\"name\":\"steel research international\",\"volume\":\"95 12\",\"pages\":\"\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-08-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/srin.202400120\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"steel research international\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/srin.202400120\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"steel research international","FirstCategoryId":"88","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/srin.202400120","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

摘要

根据石墨形态对铸铁合金进行分类在材料科学和工程学中起着至关重要的作用。传统上,这种分类依赖于视觉分析,这种方法不仅耗时,而且存在主观性,会导致不一致。本研究介绍了一种利用卷积神经网络(用于图像分类的 MobileNet 和用于语义分割的 U-Net)的新方法,以实现铸铁合金分类过程的自动化。该领域的一个重大挑战是训练有效机器学习模型所需的多样化综合数据集的可用性有限。为了解决这个问题,我们根据 ISO 945-1:2019 标准生成了一个合成数据集,创建了一个包含 2400 张纯图像和 1500 张混合图像的丰富集合。这就确保了训练过程的稳健性,增强了模型对各种形态的石墨颗粒的泛化能力。研究结果表明,该模型在铸铁合金分类方面具有出色的准确性(纯图像分类的总体准确性达到 98.9 ± 0.4%,所有六个类别的准确性均超过 97%,混合图像的语义分割准确性介于 84% 和 93% 之间),同时还证明了该模型能够始终如一地识别石墨形态,其准确性和速度是人工方法无法达到的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

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
Classification of Cast Iron Alloys through Convolutional Neural Networks Applied on Optical Microscopy Images

Classification of cast iron alloys based on graphite morphology plays a crucial role in materials science and engineering. Traditionally, this classification has relied on visual analysis, a method that is not only time-consuming but also suffers from subjectivity, leading to inconsistencies. This study introduces a novel approach utilizing convolutional neural networks—MobileNet for image classification and U-Net for semantic segmentation—to automate the classification process of cast iron alloys. A significant challenge in this domain is the limited availability of diverse and comprehensive datasets necessary for training effective machine learning models. This is addressed by generating a synthetic dataset, creating a rich collection of 2400 pure and 1500 mixed images based on the ISO 945-1:2019 standard. This ensures a robust training process, enhancing the model's ability to generalize across various morphologies of graphite particles. The findings showcase a remarkable accuracy in classifying cast iron alloys (achieving an overall accuracy of 98.9 ± 0.4%—and exceeding 97% for all six classes—for classification of pure images and ranging between 84% and 93% for semantic segmentation of mixed images) and also demonstrate the model's ability to consistently identify and graphite morphology with a level of precision and speed unattainable through manual methods.

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
相关文献
二甲双胍通过HDAC6和FoxO3a转录调控肌肉生长抑制素诱导肌肉萎缩
IF 8.9 1区 医学Journal of Cachexia, Sarcopenia and MusclePub Date : 2021-11-02 DOI: 10.1002/jcsm.12833
Min Ju Kang, Ji Wook Moon, Jung Ok Lee, Ji Hae Kim, Eun Jeong Jung, Su Jin Kim, Joo Yeon Oh, Sang Woo Wu, Pu Reum Lee, Sun Hwa Park, Hyeon Soo Kim
具有疾病敏感单倍型的非亲属供体脐带血移植后的1型糖尿病
IF 3.2 3区 医学Journal of Diabetes InvestigationPub Date : 2022-11-02 DOI: 10.1111/jdi.13939
Kensuke Matsumoto, Taisuke Matsuyama, Ritsu Sumiyoshi, Matsuo Takuji, Tadashi Yamamoto, Ryosuke Shirasaki, Haruko Tashiro
封面:蛋白质组学分析确定IRSp53和fastin是PRV输出和直接细胞-细胞传播的关键
IF 3.4 4区 生物学ProteomicsPub Date : 2019-12-02 DOI: 10.1002/pmic.201970201
Fei-Long Yu, Huan Miao, Jinjin Xia, Fan Jia, Huadong Wang, Fuqiang Xu, Lin Guo
来源期刊
steel research international
steel research international 工程技术-冶金工程
CiteScore
3.30
自引率
18.20%
发文量
319
审稿时长
1.9 months
期刊介绍: steel research international is a journal providing a forum for the publication of high-quality manuscripts in areas ranging from process metallurgy and metal forming to materials engineering as well as process control and testing. The emphasis is on steel and on materials involved in steelmaking and the processing of steel, such as refractories and slags. steel research international welcomes manuscripts describing basic scientific research as well as industrial research. The journal received a further increased, record-high Impact Factor of 1.522 (2018 Journal Impact Factor, Journal Citation Reports (Clarivate Analytics, 2019)). The journal was formerly well known as "Archiv für das Eisenhüttenwesen" and "steel research"; with effect from January 1, 2006, the former "Scandinavian Journal of Metallurgy" merged with Steel Research International. Hot Topics: -Steels for Automotive Applications -High-strength Steels -Sustainable steelmaking -Interstitially Alloyed Steels -Electromagnetic Processing of Metals -High Speed Forming
期刊最新文献
Cover Picture Issue Information Contents: steel research int. 2/2025 Cover Picture Issue Information
×
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