通过卷积神经网络 (CNN) 从传统弯管机的声音信号监测运行和生产率

IF 1.9 4区 工程技术 Q2 Engineering
Eunseob Kim, Daeseong Mun, Martin B. G. Jun, Huitaek Yun
{"title":"通过卷积神经网络 (CNN) 从传统弯管机的声音信号监测运行和生产率","authors":"Eunseob Kim, Daeseong Mun, Martin B. G. Jun, Huitaek Yun","doi":"10.1007/s12541-024-01018-3","DOIUrl":null,"url":null,"abstract":"<p>This study introduces a non-invasive approach to monitor operation and productivity of a legacy pipe bending machine in real-time based on a lightweight convolutional neural network (CNN) model and internal sound as input data. Various sensors were deployed to determine the optimal sensor type and placement, and labels for training and testing the CNN model were generated through the meticulous collection of sound data in conjunction with webcam videos. The CNN model, which was optimized through hyperparameter tuning via grid search and utilized feature extraction using Log-Mel spectrogram, demonstrated notable prediction accuracies in the test. However, when applied in a real-world manufacturing scenario, the model encountered a significant number of errors in predicting productivity. To navigate through this challenge and enhance the predictive accuracy of the system, a buffer algorithm using the inferences of CNN models was proposed. This algorithm employs a queuing method for continuous sound monitoring securing robust predictions, refines the interpretation of the CNN model inferences, and enhances prediction outcomes in actual implementation where accuracy of monitoring productivity information is crucial. The proposed lightweight CNN model alongside the buffer algorithm was successfully deployed on an edge computer, enabling real-time remote monitoring.</p>","PeriodicalId":14359,"journal":{"name":"International Journal of Precision Engineering and Manufacturing","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Operation and Productivity Monitoring from Sound Signal of Legacy Pipe Bending Machine via Convolutional Neural Network (CNN)\",\"authors\":\"Eunseob Kim, Daeseong Mun, Martin B. G. Jun, Huitaek Yun\",\"doi\":\"10.1007/s12541-024-01018-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>This study introduces a non-invasive approach to monitor operation and productivity of a legacy pipe bending machine in real-time based on a lightweight convolutional neural network (CNN) model and internal sound as input data. Various sensors were deployed to determine the optimal sensor type and placement, and labels for training and testing the CNN model were generated through the meticulous collection of sound data in conjunction with webcam videos. The CNN model, which was optimized through hyperparameter tuning via grid search and utilized feature extraction using Log-Mel spectrogram, demonstrated notable prediction accuracies in the test. However, when applied in a real-world manufacturing scenario, the model encountered a significant number of errors in predicting productivity. To navigate through this challenge and enhance the predictive accuracy of the system, a buffer algorithm using the inferences of CNN models was proposed. This algorithm employs a queuing method for continuous sound monitoring securing robust predictions, refines the interpretation of the CNN model inferences, and enhances prediction outcomes in actual implementation where accuracy of monitoring productivity information is crucial. The proposed lightweight CNN model alongside the buffer algorithm was successfully deployed on an edge computer, enabling real-time remote monitoring.</p>\",\"PeriodicalId\":14359,\"journal\":{\"name\":\"International Journal of Precision Engineering and Manufacturing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-04-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Precision Engineering and Manufacturing\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s12541-024-01018-3\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Precision Engineering and Manufacturing","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s12541-024-01018-3","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

摘要

本研究介绍了一种基于轻量级卷积神经网络(CNN)模型和内部声音作为输入数据的非侵入式方法,用于实时监控传统弯管机的运行和生产率。我们部署了各种传感器,以确定最佳传感器类型和位置,并通过细致收集声音数据和网络摄像头视频,生成用于训练和测试 CNN 模型的标签。CNN 模型通过网格搜索超参数调整进行了优化,并利用 Log-Mel 频谱进行了特征提取,在测试中取得了显著的预测精度。然而,当应用于现实世界的制造场景时,该模型在预测生产率时遇到了大量错误。为了应对这一挑战并提高系统的预测准确性,我们提出了一种使用 CNN 模型推论的缓冲算法。该算法采用了一种队列方法来进行连续的声音监测,以确保稳健的预测,完善了对 CNN 模型推论的解释,并在实际应用中提高了预测结果,因为在实际应用中,监测生产率信息的准确性至关重要。提出的轻量级 CNN 模型和缓冲算法已成功部署在边缘计算机上,实现了实时远程监控。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Operation and Productivity Monitoring from Sound Signal of Legacy Pipe Bending Machine via Convolutional Neural Network (CNN)

Operation and Productivity Monitoring from Sound Signal of Legacy Pipe Bending Machine via Convolutional Neural Network (CNN)

This study introduces a non-invasive approach to monitor operation and productivity of a legacy pipe bending machine in real-time based on a lightweight convolutional neural network (CNN) model and internal sound as input data. Various sensors were deployed to determine the optimal sensor type and placement, and labels for training and testing the CNN model were generated through the meticulous collection of sound data in conjunction with webcam videos. The CNN model, which was optimized through hyperparameter tuning via grid search and utilized feature extraction using Log-Mel spectrogram, demonstrated notable prediction accuracies in the test. However, when applied in a real-world manufacturing scenario, the model encountered a significant number of errors in predicting productivity. To navigate through this challenge and enhance the predictive accuracy of the system, a buffer algorithm using the inferences of CNN models was proposed. This algorithm employs a queuing method for continuous sound monitoring securing robust predictions, refines the interpretation of the CNN model inferences, and enhances prediction outcomes in actual implementation where accuracy of monitoring productivity information is crucial. The proposed lightweight CNN model alongside the buffer algorithm was successfully deployed on an edge computer, enabling real-time remote monitoring.

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
CiteScore
4.10
自引率
10.50%
发文量
115
审稿时长
3-6 weeks
期刊介绍: The International Journal of Precision Engineering and Manufacturing accepts original contributions on all aspects of precision engineering and manufacturing. The journal specific focus areas include, but are not limited to: - Precision Machining Processes - Manufacturing Systems - Robotics and Automation - Machine Tools - Design and Materials - Biomechanical Engineering - Nano/Micro Technology - Rapid Prototyping and Manufacturing - Measurements and Control Surveys and reviews will also be planned in consultation with the Editorial Board.
×
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