Exploring the Efficacy of Python-Driven Automated Machine Vision Algorithms for Inspection in Sheet Metal Forming

IF 1.9 4区 工程技术 Q3 ENGINEERING, MECHANICAL
Pratheesh Kumar S,  Nharguna Nangai M B
{"title":"Exploring the Efficacy of Python-Driven Automated Machine Vision Algorithms for Inspection in Sheet Metal Forming","authors":"Pratheesh Kumar S,&nbsp; Nharguna Nangai M B","doi":"10.1007/s40799-024-00773-2","DOIUrl":null,"url":null,"abstract":"<div><p>This research explores the application of Python-driven automated machine vision algorithms for inspection in sheet metal forming, a critical manufacturing process. The study addresses the need for advanced, reliable, and efficient inspection techniques to enhance quality control, thereby improving product performance and manufacturing efficiency. The methodology used in this research involves inspecting formed sheet metal products using Python-based methods, namely the Structural Similarity Index Measure (SSIM) and Normalized Cross Correlation (NCC), along with MATLAB for image correlation, are applied directly for contour inspection. In addition to contour inspection, feature detection, which includes dimensional measurement, is also carried out as a critical part of assessing the quality and performance of the formed sheet metal products. This research integrates machine vision algorithms with Python, offering a comprehensive inspection of sheet metal products. The use of Python-based methods and the Hough Transform (HT) algorithm for inspecting sheet metal formed components introduces a novel approach with immense potential for enhancing efficiency in the quality control of the sheet metal inspection process. This signifies a notable breakthrough in automated inspection within the sheet metal forming industry, allowing comprehensive inspection of both features and dimensional measurements. By adopting the most effective method, manufacturers in the sheet metal fabrication field can enhance inspection efficiency and accuracy, thereby improving product quality and operational performance.</p></div>","PeriodicalId":553,"journal":{"name":"Experimental Techniques","volume":"49 4","pages":"703 - 726"},"PeriodicalIF":1.9000,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Experimental Techniques","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s40799-024-00773-2","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

Abstract

This research explores the application of Python-driven automated machine vision algorithms for inspection in sheet metal forming, a critical manufacturing process. The study addresses the need for advanced, reliable, and efficient inspection techniques to enhance quality control, thereby improving product performance and manufacturing efficiency. The methodology used in this research involves inspecting formed sheet metal products using Python-based methods, namely the Structural Similarity Index Measure (SSIM) and Normalized Cross Correlation (NCC), along with MATLAB for image correlation, are applied directly for contour inspection. In addition to contour inspection, feature detection, which includes dimensional measurement, is also carried out as a critical part of assessing the quality and performance of the formed sheet metal products. This research integrates machine vision algorithms with Python, offering a comprehensive inspection of sheet metal products. The use of Python-based methods and the Hough Transform (HT) algorithm for inspecting sheet metal formed components introduces a novel approach with immense potential for enhancing efficiency in the quality control of the sheet metal inspection process. This signifies a notable breakthrough in automated inspection within the sheet metal forming industry, allowing comprehensive inspection of both features and dimensional measurements. By adopting the most effective method, manufacturers in the sheet metal fabrication field can enhance inspection efficiency and accuracy, thereby improving product quality and operational performance.

Abstract Image

探索蟒蛇驱动的自动机器视觉算法在钣金成形检测中的有效性
本研究探讨了python驱动的自动机器视觉算法在钣金成形检测中的应用,这是一个关键的制造过程。本研究探讨了先进、可靠、高效的检验技术,以加强质量控制,从而提高产品性能和制造效率。本研究中使用的方法包括使用基于python的方法,即结构相似指数度量(SSIM)和归一化互相关(NCC),以及MATLAB图像相关,直接用于轮廓检测,检测成形钣金产品。除了轮廓检测外,包括尺寸测量在内的特征检测也是评估成形钣金产品质量和性能的关键部分。本研究将机器视觉算法与Python相结合,提供对钣金产品的全面检查。使用基于python的方法和霍夫变换(HT)算法来检测钣金成形部件,为提高钣金检测过程的质量控制效率提供了一种具有巨大潜力的新方法。这标志着在钣金成形行业的自动化检测方面的一个显著突破,允许对特征和尺寸测量进行全面检查。通过采用最有效的方法,钣金加工领域的制造商可以提高检测效率和准确性,从而提高产品质量和操作性能。
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 求助全文
来源期刊
Experimental Techniques
Experimental Techniques 工程技术-材料科学:表征与测试
CiteScore
3.50
自引率
6.20%
发文量
88
审稿时长
5.2 months
期刊介绍: Experimental Techniques is a bimonthly interdisciplinary publication of the Society for Experimental Mechanics focusing on the development, application and tutorial of experimental mechanics techniques. The purpose for Experimental Techniques is to promote pedagogical, technical and practical advancements in experimental mechanics while supporting the Society''s mission and commitment to interdisciplinary application, research and development, education, and active promotion of experimental methods to: - Increase the knowledge of physical phenomena - Further the understanding of the behavior of materials, structures, and systems - Provide the necessary physical observations necessary to improve and assess new analytical and computational approaches.
×
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:604180095
Book学术官方微信