陈国文,周先何,叶勇,魏中青,倪国民
CHEN Guo-wen,ZHOU Xian-he,YE Yong,WEI Zhong-qing,NI Guo-min

• 1:浙江盛元化纤有限公司

摘要(Abstract)：

盛元涤纶牵伸变形丝锭智能外检系统利用光电成像系统采集被控目标的图像，经计算机及专用的图像处理模块进行数字化处理，根据图像的像素分布、亮度和颜色等信息，来进行尺寸、形状、色泽等的疵点判别。将深度学习的神经网络算法应用到涤纶丝锭外观缺陷的数据特征学习和识别上，克服了人眼无法连续工作、人为误判及对人员经验和熟练度依赖的缺点，稳定地完成这些带有高度重复性和缺陷收集难的工作。
Photoelectric imaging system is used to collect the image of the controlled target in Shengyuan polyester fiber draw textured yarn(DTY) intelligent external inspection system, and then digital processing by computer and special image processing module is performed. According to the image pixel distribution,brightness and color information, the defect discrimination of size, shape and color is carried out. The neural network algorithm of deep learning is applied to the data feature learning and recognition of the appearance defects of polyester yarn bobbins, which overcomes the shortcomings of uncontinuous work of human eyes, artificial misjudgment and dependence on personnel experience and proficiency, and stably completes these tasks with high repeatability and difficult collection of defects.

关键词(KeyWords)： 涤纶丝锭;机器视觉;智能外检;深度学习;大数据
polyester bobbin;machine vision;intelligent external inspection;deep learning;big data

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 陈国文,周先何,叶勇,魏中青,倪国民
CHEN Guo-wen,ZHOU Xian-he,YE Yong,WEI Zhong-qing,NI Guo-min

DOI: 10.16090/j.cnki.hcxw.2022.12.013

参考文献(References)：

• [1]晋博,蔡念,夏皓,等.基于深度学习的工业视觉检测系统[J].计算机工程与应用, 2019, 55(2):266-270.
• [2]杨志红.机器视觉技术在工业控制领域中的应用[J].信息与电脑(理论版), 2018(17):87-88.
• [3]赵艳.左保齐.机器视觉在织物疵点检测上的应用研究综述[J].计算机工程与应用, 2020, 56(2):11-17.
• [4]李祥瑞.机器视觉研究进展及工业应用综述[J].数字通信世界,2021(11):79-80, 146.
• [5]畅攀人,王勇,汪灵瑶,等.智能外检系统在涤纶长丝自动化包装线中的应用[J].机械制造自动化, 2019, 41(4):156-158, 172.
• [6]潘俊.涤纶长丝卷外观在线检测系统研究[D].上海:东华大学,2018.