Bayesian Network based Reliability Analysis in Edge Computing enabled Machine Vision System

2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) Pub Date : 2022-12-21 DOI:10.1109/IATMSI56455.2022.10119369

Himanshu Gauttam, K.K. Pattanaik, Saumya Bhadauria, Garima Nain

{"title":"Bayesian Network based Reliability Analysis in Edge Computing enabled Machine Vision System","authors":"Himanshu Gauttam, K.K. Pattanaik, Saumya Bhadauria, Garima Nain","doi":"10.1109/IATMSI56455.2022.10119369","DOIUrl":null,"url":null,"abstract":"Industry 4.0 (I4.0) solutions are realizing the goal of intelligent factories using digital transformation of the manufacturing and production industries. The Machine Vision System (MVS) ensures the required quality measures of vision-based inspection tasks in smart factories. The recent studies fused various trending technologies such as Industrial IoT (IIoT), Edge Computing, Artificial Intelligence, etc., to improve the performance of MVS in terms of reduced latency, improved inspection accuracy, etc. However, these studies did not focus on the reliability aspect and its impact on system performance when component(s) of MVS becomes faulty. Hence, this work proposes a Bayesian network-based framework for identifying defective component(s) in MVS. Analysis reveals that the proposed solution is suitable for reliability analysis and faulty component(s) identification of MVS to ensure the quality control in vision-based industrial applications.","PeriodicalId":221211,"journal":{"name":"2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IATMSI56455.2022.10119369","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

Industry 4.0 (I4.0) solutions are realizing the goal of intelligent factories using digital transformation of the manufacturing and production industries. The Machine Vision System (MVS) ensures the required quality measures of vision-based inspection tasks in smart factories. The recent studies fused various trending technologies such as Industrial IoT (IIoT), Edge Computing, Artificial Intelligence, etc., to improve the performance of MVS in terms of reduced latency, improved inspection accuracy, etc. However, these studies did not focus on the reliability aspect and its impact on system performance when component(s) of MVS becomes faulty. Hence, this work proposes a Bayesian network-based framework for identifying defective component(s) in MVS. Analysis reveals that the proposed solution is suitable for reliability analysis and faulty component(s) identification of MVS to ensure the quality control in vision-based industrial applications.

查看原文本刊更多论文

基于贝叶斯网络的边缘计算机器视觉系统可靠性分析

工业4.0 (I4.0)解决方案正在通过制造和生产行业的数字化转型实现智能工厂的目标。机器视觉系统(MVS)确保智能工厂中基于视觉的检测任务所需的质量措施。最近的研究融合了各种趋势技术，如工业物联网(IIoT)，边缘计算，人工智能等，以提高MVS在减少延迟，提高检测精度等方面的性能。然而，这些研究并没有关注MVS组件故障时可靠性方面及其对系统性能的影响。因此，这项工作提出了一个基于贝叶斯网络的框架来识别MVS中的缺陷成分。分析表明，该解决方案适用于基于视觉的工业应用中MVS的可靠性分析和故障部件识别，以保证质量控制。

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

2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)

自引率

0.00%

发文量