基于深度学习的光纤收卷机器视觉自动检测技术

doi:10.12068/j.issn.1005-3026.2021.01.011

东北大学学报（自然科学版） ›› 2021, Vol. 42 ›› Issue (1): 68-74.DOI: 10.12068/j.issn.1005-3026.2021.01.011

基于深度学习的光纤收卷机器视觉自动检测技术

刘宇，魏希来，王帅，戴丽

(东北大学机械工程与自动化学院，辽宁沈阳110819)

出版日期:2021-01-15 发布日期:2021-01-13
通讯作者: 刘宇
作者简介:刘宇(1980-)，男，宁夏中卫人，东北大学副教授.
基金资助:
国家自然科学基金资助项目(51875094); 中央高校基本科研业务费专项资金资助项目(N2003011).

Machine Vision Automatic Inspection Technology of Optical Fiber Winding Based on Deep Learning

LIU Yu， WEI Xi-lai， WANG Shuai， DAI Li

School of Mechanical Engineering & Automation， Northeastern University， Shenyang 110819， China.

Online:2021-01-15 Published:2021-01-13
Contact: LIU Yu
About author:-
Supported by:
-

摘要/Abstract

摘要： 已有的光纤收卷检测方法的泛化能力和环境适应性均较差，无法应用于工业生产.提出基于深度学习的机器视觉方法对收卷过程中的收卷图像进行分类来解决光纤收卷问题.通过考虑光纤收卷时光纤间力的作用，建立了光纤收卷模型，提出了光纤收卷时排线机构的速度表达式.使用相机采集大量光纤收卷图片形成数据集，搭建并训练神经网络模型用于对收卷情况进行分类.通过实验验证，该方法对间隙状态的识别正确率在94.67%以上，叠线状态识别正确率为100%，检测速度高于实际生产绕线速度，是一种可以和控制系统相结合替代人工收卷并实现自动精密绕线的良好方法.

关键词: 光纤收卷；深度学习；机器视觉；缺陷检测；自动检测

Abstract: Existing optical fiber winding inspection methods have poor generalization ability and environmental adaptability， and cannot be applied to industrial production. A machine vision method based on deep learning was proposed to classify the winding images during the winding process to solve the optical fiber winding problem. By considering the effect of the force between the optical fibers when the optical fiber was winding， the optical fiber winding model was established， and the speed expression of the arranging mechanism was proposed when the optical fiber was winding. The camera was used to collect a large number of optical fiber winding pictures to form a data set， and a neural network model was built and trained to classify the winding situation. Experimental verification showed that the accuracy of this method for gap state recognition is over 94.67%， and the accuracy of overlapped line recognition is 100%. The inspection speed is higher than the actual production winding speed. It is a favorable method that can be combined with the control system to replace manual winding and realize automatic precision winding.

Key words: optical fiber winding; deep learning; machine vision; defect detection; automatic detection

中图分类号:

TP399

刘宇，魏希来，王帅，戴丽. 基于深度学习的光纤收卷机器视觉自动检测技术[J]. 东北大学学报（自然科学版）, 2021, 42(1): 68-74.

LIU Yu， WEI Xi-lai， WANG Shuai， DAI Li. Machine Vision Automatic Inspection Technology of Optical Fiber Winding Based on Deep Learning[J]. Journal of Northeastern University(Natural Science), 2021, 42(1): 68-74.

参考文献

[1]郭晨霞，杨瑞峰.数字视觉精密测量光纤环绕制状态参数［J］.中北大学学报(自然科学版)，2014，35(3):337-341.(Guo Chen-xia，Yang Rui-feng.Parameter measurement of fiber coil winding based on digital vision［J］.Journal of North University of China(Natural Science Edition)，2014，35(3):337-341.)
[2]郭晨霞，杨瑞峰，张鹏.光纤环绕制监测图像清晰度评价方法［J］.兰州理工大学学报，2016，42(5):102-105.(Guo Chen-xia，Yang Rui-feng，Zhang Peng.Evaluation method of image clarity monitoring with fiber coil winding［J］.Journal of Lanzhou University of Technology，2016，42(5):102-105.)
[3]郭晨霞，杨瑞峰，赵洛彬.基于区域的光纤环绕制缺陷实时检测算法［J］.太原理工大学学报，2016，47(2):190-194.(Guo Chen-xia，Yang Rui-feng，Zhao Luo-bin.The defect detection algorithm of fiber coil winding based on winding region［J］.Journal of Taiyuan University of Technology，2016，47(2):190-194.)
[4]张万成，叶泽群.一种用于光纤精密绕线的视觉识别技术［J］.电子工艺技术，2015，36(3):172-174.(Zhang Wan-cheng，Ye Ze-qun.A design of visual identification technology for accurate winding of optical fiber［J］.Electronics Process Technology，2015，36(3):172-174.)
[5]杨瑞峰，丁清，郭晨霞，等.光纤环绕制缺陷动态检测方法研究［J］.实验室研究与探索，2017，36(10):36-40.(Yang Rui-feng，Ding Qing，Guo Chen-xia，et al.Research on dynamic detection method of winding defects of optical fiber coils［J］.Research and Exploration in Laboratory，2017，36(10):36-40.)
[6]Nyalala I，Okinda C，Nyalala L，et al.Tomato volume and mass estimation using computer vision and machine learning algorithms:cherry tomato model［J］.Journal of Food Engineering，2019，263:288-298.
[7]Wang J J，Fu P，Gao R X.Machine vision intelligence for product defect inspection based on deep learning and Hough transform［J］.Journal of Manufacturing Systems，2019，51:52-60.
[8]He K，Zhang X，Ren S，et al.Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas，2016:770-778.
[9]Howard A G，Zhu M，Chen B，et al.MobileNets:efficient convolutional neural networks for mobile vision applications［EB/OL］.(2017-04-17)［2019-10-08］.https://arxiv.org/abs/1704.04861
[10]Sandler M，Howard A，Zhu M，et al.MobileNetv2:inverted residuals and linear bottlenecks［C］//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018:4510-4520.
[11]Howard A，Sandler M，Chu G，et al.Searching for MobileNetv3［C］//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul，2019:1314-1324.
[12]Pulli K，Baksheev A，Kornyakov K，et al.Real-time computer vision with OpenCV［J］.Communications of the ACM，2012，55(6):61-69.
[13]Tan C，Sun F，Kong T，et al.A survey on deep transfer learning［C］//27th International Conference on Artificial Neural Networks.Rhodes，2018:270-279.
[14]Han D，Liu Q，Fan W.A new image classification method using CNN transfer learning and web data augmentation［J］.Expert Systems With Applications，2018，95:43-56.
[15]Kingma D P，Ba J.Adam:a method for stochastic optimization［EB/OL］.(2014-12-22)［2019-10-08］.https://arxiv.org/abs/1412.6980.

基于深度学习的光纤收卷机器视觉自动检测技术

Machine Vision Automatic Inspection Technology of Optical Fiber Winding Based on Deep Learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	牛大鹏，臧雅丽，贾明兴. 基于案例推理的湿法冶金全流程优化设定[J]. 东北大学学报:自然科学版, 2020, 41(1): 1-6.
[2]	赵海，徐进，陈星池，李雨喆. 基于手机摄像头的血压估计方法[J]. 东北大学学报:自然科学版, 2017, 38(8): 1075-1078.
[3]	吴刚，邱煜晶，王国仁. 基于隐马尔可夫模型和遗传算法的地图匹配算法[J]. 东北大学学报:自然科学版, 2017, 38(4): 472-475.
[4]	张锡哲，孟庆虎，张斌. 一种动态社交网络上的传播源点定位方法[J]. 东北大学学报:自然科学版, 2017, 38(2): 219-223.
[5]	徐久强，宋佳，何璇，赵海. 基于节点汇聚的地震序列分析方法[J]. 东北大学学报:自然科学版, 2016, 37(3): 319-322.
[6]	李晗，赵海，陈星池，李大舟. 基于鉴相器的手机瞬时心率监测软件设计[J]. 东北大学学报:自然科学版, 2016, 37(2): 174-178.
[7]	赵海，张娅，何璇，赵楠. 基于时空影响域的地震网络动力学演化特征分析[J]. 东北大学学报:自然科学版, 2015, 36(9): 1232-1236.
[8]	张聿博，张锡哲，张斌. 基于观察点的信息源定位方法的准确率分析[J]. 东北大学学报:自然科学版, 2015, 36(3): 350-353.
[9]	贾思媛，许勇，赵海，艾均. DBLP科研合作网络的建模与拓扑特征分析[J]. 东北大学学报(自然科学版), 2013, 34(10): 1396-1399.
[10]	李晗，赵海，朱剑，李大舟. 基于容积脉搏波的收缩压测量方法[J]. 东北大学学报(自然科学版), 2013, 34(8): 1078-1081.