Light spot detection of diamond wire based on deep learning

FENG Zongqiang; YING Yipeng; ZHANG Fujun; YU Yongbo; LIU Yi

doi:10.37188/OPE.20233115.2260

您当前的位置：

首页 >

文章列表页 >

Light spot detection of diamond wire based on deep learning

Information Sciences | 更新时间：2023-08-28

- Light spot detection of diamond wire based on deep learning
- Optics and Precision Engineering Vol. 31, Issue 15, Pages: 2260-2272(2023)
- 作者机构：
  
  1.燕山大学机械工程学院，河北秦皇岛 066004
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233115.2260
  CLC：
扫描看全文
FENG Zongqiang, YING Yipeng, ZHANG Fujun, et al. Light spot detection of diamond wire based on deep learning. [J]. Optics and Precision Engineering 31(15):2260-2272(2023)
DOI：

FENG Zongqiang, YING Yipeng, ZHANG Fujun, et al. Light spot detection of diamond wire based on deep learning. [J]. Optics and Precision Engineering 31(15):2260-2272(2023) DOI： 10.37188/OPE.20233115.2260.

摘要

金刚线断线检测是金刚线生产过程中的重要环节。针对现有接触式检测敏感度低、断线反馈滞后等问题，提出了一种基于机器视觉检测强光下金刚线反射的光斑点的非接触式断线检测方法。在金刚线光斑点检测的嵌入式平台上，针对传统图像处理的光斑点检测操作复杂、易受外部光照影响的局限性，研究了基于深度学习的光斑点目标检测，对多种Yolo系列模型进行了训练部署，针对原有模型网络层次较深、模型体积较大，在嵌入式设备中存在检测实时性较差的问题，提出了一种基于Yolox改进的轻量化目标光斑点检测模型MCA-Yolox，利用MobileNetV3轻量化特征提取网络替换Yolox模型的主干特征提取网络，对模型进行轻量化改进，然后利用深度可分离卷积和倒残差结构对加强特征提取网络进行了轻量化改进。结合CA注意力机制提高了轻量化模型的检测精度。最后，将改进后的模型部署于嵌入式平台。实验结果表明，改进后模型MCA-Yolox的大小和运算量减小到Yolox模型的1/3以下，与同样规模的Yolox-Tiny和Yolov4-Tiny相比具有更高的检测精度，模型的mAP提升了1%以上，加速优化后检测速度可达30 frame/s，提供了一种基于深度学习检测金刚线断线的完整工业检测方案。

Abstract

Break detection is an important part of the diamond wire production process. To address the problems of low sensitivity and lag feedback of existing contact detection， a non-contact wire break detection method is proposed based on machine vision detection of light spots reflected by diamond lines under strong light. Here， the study addresses the limitations of complex spot detection operation and ease of influence from external illumination of traditional image processing by investigating spot target detection on the embedded platform of diamond line spot detection using deep learning. A variety of Yolo-type models were trained and deployed. The problem of poor real-time detection in embedded devices due to the deep network level and large model volume of the original model was also addressed through a lightweight target spot detection model MCA-Yolox based on Yolox. The MobileNetV3 lightweight feature extraction network was used to replace the backbone feature extraction network of the Yolox model， and the model was lightweighted. Then， the enhanced feature extraction network was lightweight using the deep separable convolution and inverted residual structures. Then， combined with the CA attention mechanism， the detection accuracy of the lightweight model was improved. Finally， the improved model was deployed on the embedded platform. The experimental results show that the size and computation amount of the improved model， MCA-Yolox， are reduced to less than 1/3 those of the Yolox model， and compared with Yolox-Tiny and Yolov4-Tiny of the same scale， it has higher detection accuracy. The mAP of the model increased by more than 1%， and the detection speed can reach 30 frames/s after accelerated optimization. In summary， this paper presents a complete industrial detection scheme based on deep learning to detect diamond wire breaks.

关键词

机器视觉金刚线断线检测光斑点深度学习嵌入式

Keywords

machine visiondiamond wiredetection of broken wirelight spotdeep learningembedded type

references

王宝玉，宋为，张太超. 电镀金刚线技术探讨［J］. 金属制品， 2018， 44（3）： 10-13. doi: 10.2166/wcc.2018.167http://dx.doi.org/10.2166/wcc.2018.167

WANG B Y， SONG W， ZHANG T CH. Discussion on electroplating diamond wire technology［J］. Metal Products， 2018， 44（3）： 10-13.（in Chinese）. doi: 10.2166/wcc.2018.167http://dx.doi.org/10.2166/wcc.2018.167

孟雪，李和胜. 太阳能硅片切割用金刚线发展评述［J］. 超硬材料工程， 2019， 31（1）： 46-51. doi: 10.3969/j.issn.1673-1433.2019.01.009http://dx.doi.org/10.3969/j.issn.1673-1433.2019.01.009

MENG X， LI H SH. Review on diamond wires for slicing solar silicon wafers［J］. Superhard Material Engineering， 2019， 31（1）： 46-51.（in Chinese）. doi: 10.3969/j.issn.1673-1433.2019.01.009http://dx.doi.org/10.3969/j.issn.1673-1433.2019.01.009

赵雷，李欢，胡孝伟. 金刚线在硅晶体切割领域的应用研究［J］. 电子工业专用设备， 2019， 48（3）： 33-36. doi: 10.3969/j.issn.1004-4507.2019.03.009http://dx.doi.org/10.3969/j.issn.1004-4507.2019.03.009

ZHAO L， LI H， HU X W. Research on the application of diamond wire in single polysilicon cutting［J］. Equipment for Electronic Products Manufacturing， 2019， 48（3）： 33-36.（in Chinese）. doi: 10.3969/j.issn.1004-4507.2019.03.009http://dx.doi.org/10.3969/j.issn.1004-4507.2019.03.009

ZHANG M， LIU Z D， PAN H W， et al. Experimental research on combined processing of diamond wire saw and molybdenum twisted wire［J］.The International Journal of Advanced Manufacturing Technology， 2019， 101（9/10/11/12）： 2751-2759. doi: 10.1007/s00170-018-3010-xhttp://dx.doi.org/10.1007/s00170-018-3010-x

梁志敏. 视频图像质量检测技术研究与实践［D］. 北京：北京邮电大学， 2013： 5-80.

LIANG ZH M. Research and Practice of Video Image Quality Detection Technology［D］. Beijing： Beijing University of Posts and Telecommunications， 2013： 5-80.（in Chinese）

葛乃红. 二维斑点追踪超声心动图与心电图对心肌梗死的诊断价值对比［J］. 影像研究与医学应用， 2021， 5（23）： 154-155. doi: 10.3969/j.issn.2096-3807.2021.23.070http://dx.doi.org/10.3969/j.issn.2096-3807.2021.23.070

GE N H. Comparison of diagnostic value between two-dimensional speckle tracking echocardiography and electrocardiogram in myocardial infarction［J］. Journal of Imaging Research and Medical Applications， 2021， 5（23）： 154-155.（in Chinese）. doi: 10.3969/j.issn.2096-3807.2021.23.070http://dx.doi.org/10.3969/j.issn.2096-3807.2021.23.070

唐沐恩，林挺强，文贡坚. 遥感图像中舰船检测方法综述［J］. 计算机应用研究， 2011， 28（1）： 29-36. doi: 10.3969/j.issn.1001-3695.2011.01.007http://dx.doi.org/10.3969/j.issn.1001-3695.2011.01.007

TANG M E， LIN T Q， WEN G J. Overview of ship detection methods in remote sensing image［J］. Application Research of Computers， 2011， 28（1）： 29-36.（in Chinese）. doi: 10.3969/j.issn.1001-3695.2011.01.007http://dx.doi.org/10.3969/j.issn.1001-3695.2011.01.007

XU Y Z， WU T， GAO F， et al. Improved small blob detection in 3D images using jointly constrained deep learning and Hessian analysis［J］. Scientific Reports， 2020， 10： 326. doi: 10.1038/s41598-019-57223-yhttp://dx.doi.org/10.1038/s41598-019-57223-y

张轩宇. 遥感影像海上船舶检测技术研究［D］. 大连：大连理工大学， 2021： 5-15. doi: 10.3934/mbe.2021063http://dx.doi.org/10.3934/mbe.2021063

ZHANG X Y. Research on Detection Technology of Remote Sensing Images for Ships at Sea［D］. Dalian： Dalian University of Technology， 2021： 5-15.（in Chinese）. doi: 10.3934/mbe.2021063http://dx.doi.org/10.3934/mbe.2021063

CAO C Q， WU J， ZENG X D， et al. Research on airplane and ship detection of aerial remote sensing images based on convolutional neural network［J］. Sensors， 2020， 20（17）： 4696. doi: 10.3390/s20174696http://dx.doi.org/10.3390/s20174696

范丽丽，赵宏伟，赵浩宇，等. 基于深度卷积神经网络的目标检测研究综述［J］. 光学精密工程， 2020， 28（5）： 1152-1164.

FAN L L， ZHAO H W， ZHAO H Y， et al. Survey of target detection based on deep convolutional neural networks［J］. Opt. Precision Eng.， 2020， 28（5）： 1152-1164.（in Chinese）

REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： unified， real-time object detection［C］. 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）.2730，2016， Las Vegas， NV， USA. IEEE， 2016： 779-788. doi: 10.1109/cvpr.2016.91http://dx.doi.org/10.1109/cvpr.2016.91

马立，巩笑天，欧阳航空. Tiny YOLOV3目标检测改进［J］. 光学精密工程， 2020， 28（4）： 988-995. doi: 10.3788/OPE.20202804.0988http://dx.doi.org/10.3788/OPE.20202804.0988

MA L， GONG X T， OUYANG H K. Improvement of Tiny YOLOV3 target detection［J］. Opt. Precision Eng.， 2020， 28（4）： 988-995.（in Chinese）. doi: 10.3788/OPE.20202804.0988http://dx.doi.org/10.3788/OPE.20202804.0988

AHMAD T， CHEN X N， SAQLAIN A S， et al. EDF-SSD： an improved feature fused SSD for object detection［C］. 2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics （ICCCBDA）.2426，2021， Chengdu， China. IEEE， 2021： 469-473. doi: 10.1109/icccbda51879.2021.9442501http://dx.doi.org/10.1109/icccbda51879.2021.9442501

王宸，张秀峰，刘超，等. 改进YOLOv3的轮毂焊缝缺陷检测［J］. 光学精密工程， 2021， 29（8）： 1942-1954. doi: 10.37188/OPE.20212908.1942http://dx.doi.org/10.37188/OPE.20212908.1942

WANG CH， ZHANG X F， LIU CH， et al. Detection method of wheel hub weld defects based on the improved YOLOv3［J］. Optics and Precision Engineering， 2021， 29（8）： 1942-1954.（in Chinese）. doi: 10.37188/OPE.20212908.1942http://dx.doi.org/10.37188/OPE.20212908.1942

KUMAR A， KALIA A， SHARMA A， et al. A hybrid tiny YOLO v4-SPP module based improved face mask detection vision system［J］. Journal of Ambient Intelligence and Humanized Computing， 2023， 14（6）： 6783-6796. doi: 10.1007/s12652-021-03541-xhttp://dx.doi.org/10.1007/s12652-021-03541-x

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lightweight deep learning network for accurate localization of optical image components

Visual composite positioning for precision microassembly

Review of multi-view stereo reconstruction methods based on deep learning

Bump height measurement of chip packaging based on white light triangulation

Small sample data augmentation and abundances inversion of minerals hyperspectral

Related Author

No data

Related Institution

College of Mathematics and Statistics， Chongqing University

Chang Chun Champion Optics Co.， Ltd.

School of Mechanical Engineering， Dalian University of Technology

School of Science， Jiangxi University of Science and Technology

School of Electrical Engineering and Automation， Jiangxi University of Science and Technology

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰