摘要
产品缺陷是工业生产过程中不可避免的问题,如果不能及时处理,会对产品的性能、美观以及安全性造成极大影响。传统的人工检测方法效率低,误检率及漏检率极高,而基于深度学习的缺陷检测技术可以有效改进,归纳总结近五年深度学习在工业产品缺陷检测领域的研究成果,分析国内外深度学习及缺陷检测技术的研究现状,阐述应用于工业产品缺陷检测深度学习网络模型的相关理论,比较主流深度学习缺陷检测技术的优缺点,指出现有深度学习缺陷检测技术存在的问题,并对未来的发展趋势进行展望。
Product defects are inevitable problems in the process of industrial production.If they cannot be handled in time,they will have a great impact on the performance,beauty and safety of products.Traditional manual detection methods have low efficiency,high false detection rate and high missed detection rate,but defect detection technology based on deep learning can effectively solve these problems.This paper summarizes the research results of deep learning in the field of industrial product defect detection in recent five years,analyzes the research status of deep learning and defect detection technology at home and abroad,expounds the related theory of deep learning network model applied in industrial product defect detection,compares the advantages and disadvantages of mainstream deep learning defect detection technology,and points out the existing problems of deep learning defect detection technology and the future development trend.
作者
金映谷
张涛
杨亚宁
王月
刘玉婷
JIN Ying-gu;ZHANG Tao;YANG Ya-ning;WANG Yue;LIU Yu-ting(School of Electromechanical Engineering,Dalian Minzu University,Dalian Liaoning 116605,China;School of Information and Communication Engineering,Dalian Minzu University,Dalian Liaoning 116605,China)
出处
《大连民族大学学报》
2020年第5期420-427,共8页
Journal of Dalian Minzu University
关键词
深度学习
缺陷检测
工业产品
deep learning
defect detection
industrial product