DSP-Based Industrial Defect Detection for Intelligent Manufacturing

IF 2 3区计算机科学 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer Supported Cooperative Work-The Journal of Collaborative Computing Pub Date : 2023-05-24 DOI:10.1109/CSCWD57460.2023.10152825

Han Yue, Rucen Wang, Yi Gao, Ailing Xia, Jianhua Zhang

{"title":"DSP-Based Industrial Defect Detection for Intelligent Manufacturing","authors":"Han Yue, Rucen Wang, Yi Gao, Ailing Xia, Jianhua Zhang","doi":"10.1109/CSCWD57460.2023.10152825","DOIUrl":null,"url":null,"abstract":"Internet of Things (IoT) based industrial defect detection has attracted more and more attention. As a key component of intelligent manufacturing, defect detection is very important. Although deep learning (DL) can reduce the cost of traditional manual inspection and improve accuracy and efficiency, it requires huge computing resources and cannot be simply deployed on IoT devices. Digital signal processor (DSP) is an important IoT device with the characteristics of small size, strong performance and low energy consumption, and has been widely used in intelligent manufacturing. In order to achieve accurate defect detection on DSP, we proposed a variety of optimization strategies, and then extended the model to run on multi-core using a parallel scheme, and further quantified the implementation of the model. We evaluated it on three datasets, i.e. NEUSDD, MTDD and RSDD. Experimental results show that our method achieves a faster speed than running the same CNN model on a mainstream desktop CPU, with slightly accuracy loss.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"58 1","pages":"1667-1672"},"PeriodicalIF":2.0000,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/CSCWD57460.2023.10152825","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}

引用次数: 0

Abstract

Internet of Things (IoT) based industrial defect detection has attracted more and more attention. As a key component of intelligent manufacturing, defect detection is very important. Although deep learning (DL) can reduce the cost of traditional manual inspection and improve accuracy and efficiency, it requires huge computing resources and cannot be simply deployed on IoT devices. Digital signal processor (DSP) is an important IoT device with the characteristics of small size, strong performance and low energy consumption, and has been widely used in intelligent manufacturing. In order to achieve accurate defect detection on DSP, we proposed a variety of optimization strategies, and then extended the model to run on multi-core using a parallel scheme, and further quantified the implementation of the model. We evaluated it on three datasets, i.e. NEUSDD, MTDD and RSDD. Experimental results show that our method achieves a faster speed than running the same CNN model on a mainstream desktop CPU, with slightly accuracy loss.

查看原文本刊更多论文

基于dsp的智能制造工业缺陷检测

基于物联网的工业缺陷检测技术越来越受到人们的关注。缺陷检测作为智能制造的关键组成部分，具有十分重要的意义。虽然深度学习可以降低传统人工检测的成本，提高准确性和效率，但它需要大量的计算资源，不能简单地部署在物联网设备上。数字信号处理器(DSP)是一种重要的物联网器件，具有体积小、性能强、能耗低等特点，在智能制造中得到了广泛的应用。为了在DSP上实现精确的缺陷检测，我们提出了多种优化策略，然后使用并行方案将模型扩展到多核上运行，并进一步量化了模型的实现。我们在NEUSDD、MTDD和RSDD三个数据集上对其进行了评估。实验结果表明，与在主流桌面CPU上运行相同的CNN模型相比，我们的方法获得了更快的速度，并且精度略有下降。

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

Computer Supported Cooperative Work-The Journal of Collaborative Computing COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-

CiteScore

6.40

自引率

4.20%

发文量

审稿时长

>12 weeks

期刊介绍： Computer Supported Cooperative Work (CSCW): The Journal of Collaborative Computing and Work Practices is devoted to innovative research in computer-supported cooperative work (CSCW). It provides an interdisciplinary and international forum for the debate and exchange of ideas concerning theoretical, practical, technical, and social issues in CSCW. The CSCW Journal arose in response to the growing interest in the design, implementation and use of technical systems (including computing, information, and communications technologies) which support people working cooperatively, and its scope remains to encompass the multifarious aspects of research within CSCW and related areas. The CSCW Journal focuses on research oriented towards the development of collaborative computing technologies on the basis of studies of actual cooperative work practices (where ‘work’ is used in the wider sense). That is, it welcomes in particular submissions that (a) report on findings from ethnographic or similar kinds of in-depth fieldwork of work practices with a view to their technological implications, (b) report on empirical evaluations of the use of extant or novel technical solutions under real-world conditions, and/or (c) develop technical or conceptual frameworks for practice-oriented computing research based on previous fieldwork and evaluations.