Monitoring manufacturing systems using AI: A method based on a digital factory twin to train CNNs on synthetic data

IF 4.6 2区 工程技术 Q2 ENGINEERING, MANUFACTURING CIRP Journal of Manufacturing Science and Technology Pub Date : 2024-03-27 DOI:10.1016/j.cirpj.2024.03.005
Marcello Urgo , Walter Terkaj , Gabriele Simonetti
{"title":"Monitoring manufacturing systems using AI: A method based on a digital factory twin to train CNNs on synthetic data","authors":"Marcello Urgo ,&nbsp;Walter Terkaj ,&nbsp;Gabriele Simonetti","doi":"10.1016/j.cirpj.2024.03.005","DOIUrl":null,"url":null,"abstract":"<div><p>Modern cyber–physical production systems provide advanced solutions to enhance factory throughput and efficiency. However, monitoring its behaviour and performance becomes challenging as the complexity of a manufacturing system increases. Artificial Intelligence (AI) provides techniques to manage not only decision-making tasks but also to support monitoring. The integration of AI into a factory can be facilitated by a reliable Digital Twin (DT) that enables knowledge-based and data-driven approaches. While computer vision and convolutional neural networks (CNNs) are crucial for monitoring production systems, the need for extensive training data hinders their adoption in real factories. The proposed methodology leverages the Digital Twin of a factory to generate labelled synthetic data for training CNN-based object detection models. Regarding their position and state, the focus is on monitoring entities in manufacturing systems, such as parts, components, fixtures, and tools. This approach reduces the need for large training datasets and enables training when the actual system is unavailable. The trained CNN model is evaluated in various scenarios, with a real case study involving an industrial pilot plant for repairing and recycling Printed Circuit Boards (PCBs).</p></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1755581724000361/pdfft?md5=9367de29c3c31b4b7cb60d9a4027c53e&pid=1-s2.0-S1755581724000361-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CIRP Journal of Manufacturing Science and Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1755581724000361","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

Abstract

Modern cyber–physical production systems provide advanced solutions to enhance factory throughput and efficiency. However, monitoring its behaviour and performance becomes challenging as the complexity of a manufacturing system increases. Artificial Intelligence (AI) provides techniques to manage not only decision-making tasks but also to support monitoring. The integration of AI into a factory can be facilitated by a reliable Digital Twin (DT) that enables knowledge-based and data-driven approaches. While computer vision and convolutional neural networks (CNNs) are crucial for monitoring production systems, the need for extensive training data hinders their adoption in real factories. The proposed methodology leverages the Digital Twin of a factory to generate labelled synthetic data for training CNN-based object detection models. Regarding their position and state, the focus is on monitoring entities in manufacturing systems, such as parts, components, fixtures, and tools. This approach reduces the need for large training datasets and enables training when the actual system is unavailable. The trained CNN model is evaluated in various scenarios, with a real case study involving an industrial pilot plant for repairing and recycling Printed Circuit Boards (PCBs).

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
利用人工智能监控制造系统:基于数字工厂孪生系统的方法,在合成数据上训练 CNN
现代网络物理生产系统提供了先进的解决方案,以提高工厂的生产能力和效率。然而,随着生产系统复杂性的增加,对其行为和性能的监控也变得具有挑战性。人工智能(AI)不仅提供了管理决策任务的技术,还提供了支持监控的技术。可靠的数字孪生(DT)可实现基于知识和数据的方法,从而促进人工智能与工厂的整合。虽然计算机视觉和卷积神经网络(CNN)对监控生产系统至关重要,但它们需要大量的训练数据,这阻碍了它们在实际工厂中的应用。所提出的方法利用工厂的数字孪生系统生成标注合成数据,用于训练基于 CNN 的物体检测模型。关于它们的位置和状态,重点是监控制造系统中的实体,如零件、组件、夹具和工具。这种方法减少了对大型训练数据集的需求,并能在实际系统不可用时进行训练。经过训练的 CNN 模型在各种场景中进行了评估,其中一个实际案例研究涉及印刷电路板 (PCB) 维修和回收的工业试验工厂。
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
CIRP Journal of Manufacturing Science and Technology
CIRP Journal of Manufacturing Science and Technology Engineering-Industrial and Manufacturing Engineering
CiteScore
9.10
自引率
6.20%
发文量
166
审稿时长
63 days
期刊介绍: The CIRP Journal of Manufacturing Science and Technology (CIRP-JMST) publishes fundamental papers on manufacturing processes, production equipment and automation, product design, manufacturing systems and production organisations up to the level of the production networks, including all the related technical, human and economic factors. Preference is given to contributions describing research results whose feasibility has been demonstrated either in a laboratory or in the industrial praxis. Case studies and review papers on specific issues in manufacturing science and technology are equally encouraged.
期刊最新文献
Resilience compass navigation through manufacturing organization uncertainty – A dynamic capabilities approach using mixed methods A structured digital twinning approach to improve decision-making in manufacturing SMEs Numerical simulation of molten pool flow behavior in ultrasonic vibration-assisted gas tungsten arc welding of low-alloy high-strength steel Hybrid FE-ML model for turning of 42CrMo4 steel Study on the effect of variable laser power on residual stress distribution in laser directed energy deposition of Ti6Al4V
×
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