用于铝合金板材索状缺陷分析的深度学习方法:预测与分级

IF 4.2 2区 工程技术 Q2 ENGINEERING, MANUFACTURING
Yuan-Zhe Hu, Ru-Xue Liu, Jia-Peng He, Guo-Wei Zhou, Da-Yong Li
{"title":"用于铝合金板材索状缺陷分析的深度学习方法:预测与分级","authors":"Yuan-Zhe Hu,&nbsp;Ru-Xue Liu,&nbsp;Jia-Peng He,&nbsp;Guo-Wei Zhou,&nbsp;Da-Yong Li","doi":"10.1007/s40436-024-00499-9","DOIUrl":null,"url":null,"abstract":"<div><p>Roping is a severe band-like surface defect that occurs in deformed aluminum alloy sheets. Accurate roping prediction and rating are essential for industrial applications. Recently, the authors introduced an artificial neural network (ANN) model to efficiently forecast roping behavior across the thickness of large regions with texture gradients. In this study, the previously proposed ANN model for roping prediction is briefly reviewed, and a few-shot learning (FSL)-based method is developed for roping grading with limited samples. To consider the directionality of the roping patterns, the roping dataset constructed from experimental observations is transformed into the frequency domain for more compact characterization. A transfer-based FSL method is further presented for grade roping with manifold mixup regularization and the Sinkhorn mapping algorithm. A new component-focused representation is also implemented for data-processing, exploiting the close correlation between roping and power distribution in the frequency domain. The ultimate FSL method achieved an optimal accuracy of 95.65% in roping classification with only five training samples per class, outperforming four typical FSL methods. This FSL approach can be applied to grade the roping morphologies predicted by the ANN model. Consequently, the combination of prediction and grading using deep learning provides a new paradigm for roping analysis and control.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":null,"pages":null},"PeriodicalIF":4.2000,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning methods for roping defect analysis in aluminum alloy sheets: prediction and grading\",\"authors\":\"Yuan-Zhe Hu,&nbsp;Ru-Xue Liu,&nbsp;Jia-Peng He,&nbsp;Guo-Wei Zhou,&nbsp;Da-Yong Li\",\"doi\":\"10.1007/s40436-024-00499-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Roping is a severe band-like surface defect that occurs in deformed aluminum alloy sheets. Accurate roping prediction and rating are essential for industrial applications. Recently, the authors introduced an artificial neural network (ANN) model to efficiently forecast roping behavior across the thickness of large regions with texture gradients. In this study, the previously proposed ANN model for roping prediction is briefly reviewed, and a few-shot learning (FSL)-based method is developed for roping grading with limited samples. To consider the directionality of the roping patterns, the roping dataset constructed from experimental observations is transformed into the frequency domain for more compact characterization. A transfer-based FSL method is further presented for grade roping with manifold mixup regularization and the Sinkhorn mapping algorithm. A new component-focused representation is also implemented for data-processing, exploiting the close correlation between roping and power distribution in the frequency domain. The ultimate FSL method achieved an optimal accuracy of 95.65% in roping classification with only five training samples per class, outperforming four typical FSL methods. This FSL approach can be applied to grade the roping morphologies predicted by the ANN model. Consequently, the combination of prediction and grading using deep learning provides a new paradigm for roping analysis and control.</p></div>\",\"PeriodicalId\":7342,\"journal\":{\"name\":\"Advances in Manufacturing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2024-05-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in Manufacturing\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s40436-024-00499-9\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, MANUFACTURING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Manufacturing","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s40436-024-00499-9","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MANUFACTURING","Score":null,"Total":0}
引用次数: 0

摘要

起皱是变形铝合金板材中出现的一种严重的带状表面缺陷。对工业应用而言,精确的起筋预测和评级至关重要。最近,作者引入了一种人工神经网络(ANN)模型,以有效预测具有纹理梯度的大面积区域的厚度范围内的起筋行为。在本研究中,作者简要回顾了之前提出的用于碾压预测的人工神经网络模型,并开发了一种基于少量学习(FSL)的方法,用于在样本有限的情况下进行碾压分级。为了考虑碾压模式的方向性,从实验观测中构建的碾压数据集被转换到频域,以获得更紧凑的表征。通过流形混合正则化和 Sinkhorn 映射算法,进一步提出了一种基于转移的 FSL 方法,用于分级碾压。此外,还为数据处理实施了一种新的以分量为重点的表示法,利用了频域中的罗经和功率分布之间的密切关联。最终的 FSL 方法在每类只需五个训练样本的情况下,就能达到 95.65% 的最佳滚动分类准确率,优于四种典型的 FSL 方法。这种 FSL 方法可用于对 ANN 模型预测的绳索形态进行分级。因此,利用深度学习将预测和分级结合起来,为绳索分析和控制提供了一种新的范例。
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 roping defect analysis in aluminum alloy sheets: prediction and grading

Deep learning methods for roping defect analysis in aluminum alloy sheets: prediction and grading

Deep learning methods for roping defect analysis in aluminum alloy sheets: prediction and grading

Roping is a severe band-like surface defect that occurs in deformed aluminum alloy sheets. Accurate roping prediction and rating are essential for industrial applications. Recently, the authors introduced an artificial neural network (ANN) model to efficiently forecast roping behavior across the thickness of large regions with texture gradients. In this study, the previously proposed ANN model for roping prediction is briefly reviewed, and a few-shot learning (FSL)-based method is developed for roping grading with limited samples. To consider the directionality of the roping patterns, the roping dataset constructed from experimental observations is transformed into the frequency domain for more compact characterization. A transfer-based FSL method is further presented for grade roping with manifold mixup regularization and the Sinkhorn mapping algorithm. A new component-focused representation is also implemented for data-processing, exploiting the close correlation between roping and power distribution in the frequency domain. The ultimate FSL method achieved an optimal accuracy of 95.65% in roping classification with only five training samples per class, outperforming four typical FSL methods. This FSL approach can be applied to grade the roping morphologies predicted by the ANN model. Consequently, the combination of prediction and grading using deep learning provides a new paradigm for roping analysis and control.

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
Advances in Manufacturing
Advances in Manufacturing Materials Science-Polymers and Plastics
CiteScore
9.10
自引率
3.80%
发文量
274
期刊介绍: As an innovative, fundamental and scientific journal, Advances in Manufacturing aims to describe the latest regional and global research results and forefront developments in advanced manufacturing field. As such, it serves as an international platform for academic exchange between experts, scholars and researchers in this field. All articles in Advances in Manufacturing are peer reviewed. Respected scholars from the fields of advanced manufacturing fields will be invited to write some comments. We also encourage and give priority to research papers that have made major breakthroughs or innovations in the fundamental theory. The targeted fields include: manufacturing automation, mechatronics and robotics, precision manufacturing and control, micro-nano-manufacturing, green manufacturing, design in manufacturing, metallic and nonmetallic materials in manufacturing, metallurgical process, etc. The forms of articles include (but not limited to): academic articles, research reports, and general reviews.
×
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