[1]王 青,吕绪山,党 帅,等.基于深度学习的纱管识别方法研究[J].机械与电子,2023,41(12):20-26.
　WANG Qing,LYU Xushan,DANG Shuai,et al.Research on Yarn Bobbin Detection Method Based on Deep Learning[J].Machinery & Electronics,2023,41(12):20-26.
点击复制

基于深度学习的纱管识别方法研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
41
期数:
2023年12期
页码:
20-26
栏目:
研究与设计
出版日期:
2023-12-30

文章信息/Info

Title:
Research on Yarn Bobbin Detection Method Based on Deep Learning
文章编号:
1001-2257 ( 2023 ) 12-0020-07
作者:
王 青; 吕绪山; 党 帅; 姜越夫; 梁高翔; 赵恬恬; 薛博文
西安工程大学机电工程学院,陕西 西安 710048
Author(s):
WANG Qing ;  LYU Xushan ;  DANG Shuai ;  JIANG Yuefu ;  LIANG Gaoxiang ;  ZHAO Tiantian ;  XUE Bowen
( College of Mechanical and Electrical Engineering , Xi ’an Polytechnic University , Xi ’an 710048 , China )
关键词:
纱管识别; 注意力机制; 深度学习;  YOLOv5
Keywords:
yarn bobbin detection ;  attention mechanism ;  deep learning ;  YOLOv5
分类号:
TP317.4
文献标志码:
A
摘要:
为提高自动络筒机的工作效率,视觉检测准确率的提升尤为重要,在 YOLOv5 的基础上提出了一种改进的纱管识别方法。将网络原有的 SiLU 激活函数替换为表现力更好的 Mish 激活函数。将 CIoU 定位损失函数替换为考虑了真实框和预测框之间方向匹配性的 SIoU 损失函数,使网络更快速地收敛。将原有的 C3 模块替换为嵌入了 CA 注意力机制的 CCA 模块,使网络在提取特征上具有更好的表现力。制作纱管数据集,并对数据集进行数据增强使模型具有更好的鲁棒性和泛化能力。通过试验得出,所提的改进 YOLOv5 网络在识别准确率上达到了 97.30% ,召回率达到了 98.17% , mAP_0.5 达到了 98.58% ,改进后的网络相较于原网络,在识别性能上有显著提升。
Abstract:
To improve the efficiency of automatic winding machines , it is particularly important to improve the accuracy of visual inspection.This paper proposes an improved yarn bobbin detection method based on YOLOv5.The original SiLU activation function of the network is replaced by the Mish activation function with better expressive power.The CIoU localization loss function is replaced with the SIoU loss function , which takes into account the directional matching between the true and predicted Bounding Box , allows the network to converge more quickly.The original C3 module is replaced with a CCA module embedded with a CA attention mechanism , which gives the network better performance in extracting features. Besides , the yarn bobbin dataset is produced and data augmentation is applied for better robustness and generalization of the model.Through the experiment , it was concluded that the improved YOLOv5 network proposed in this paper achieved 97.30% in recognition precision ; 98.17% in recall ; and 98.58% in mAP_0.5.The improved network has a significant improvement in recognition performance compared with the original network.

参考文献/References:

[ 1 ] WANG J G , ZHOU J , WANG L , et al.Detection of residual yarn on spinning bobbins based onsalient region detection [ J ] .The journal of the textile institute , 2019 , 110 ( 6 ): 838-846.

[ 2 ] YANG Y , MA X , HE Z , et al.A robust detection method of yarn residue for automatic bobbin management system [ C ] ∥2019 IEEE / ASME International Conference on Advanced Intelligent Mechatronics ( AIM ) .New York : IEEE , 2019 : 1075-1079.
[ 3 ] 高畅 . 基于机器视觉的纱管余纱量检测研究[ D ] . 无锡:江南大学,2019.
[ 4 ] ZHANG M , JIA Y.Color recognition model based on multiple SVMs for bobbin sorting machine [ C ] ∥International Symposium on Computational Intelligence and Design. New York : IEEE , 2012 : 218-221.
[ 5 ] JING J , LI H , ZHANG H , et al.Detection of bobbin yarn surface defects by visual saliency analysis [ J ] .Fibers and polymers , 2020 , 21 : 2685-2694.
[ 6 ] 马传旭,张宁,潘如如 . 基于支持向量机的筒子纱纱管品种检测[ J ] . 纺织学报, 2023 , 44 ( 1 ): 194-200.
[ 7 ] 张宁,杜金隆,张炜 . 基于机器视觉的送纱管同轴度检测研究[ J / OL ] . 机械设计与制造: 1-5 [ 2023-06-30 ] . https : ∥doi.org / 10.19356 / j.cnki.1001 3997.20230605.025.
[ 8 ] 贺文涛,黄学宇 . 工程应用中的目标识别方法评估研究[ J ] . 工业控制计算机, 2020 , 33 ( 11 ): 78-79 , 83.
[ 9 ] GIRSHICK R , DONAHUE J , DARRELL T , et al.Rich feature hierarchies for accurate object detection and semantic segmentation [ C ] ∥2014 IEEE Conference on Computer Vision and Pattern Recognition , 2014 : 580-587.
[ 10 ] GIRSHICK R.Fast R-CNN [ C ] ∥Proceedings of the IEEE International Conference on Computer Vision , 2015 : 1440-1448.
[ 11 ] REN S Q , HE K M , GIRSHICK R , et al.Faster R-CNN : towards real-time object detection with region proposal networks [ J ] .IEEE Transactions on pattern analysis and machine intelligence , 2017 , 39 ( 6 ): 1137-1149.
[ 12 ] LIU W , ANGUELOV D , ERHAN D , et al.SSD : single shotmultibox detector [ C ] ∥Computer Vision ECCV 2016 , 2016 : 21-37.
[ 13 ] ZHAO H X , LI J B , NIE J , et al.Identification method for cone yarn based on the improved faster R-CNN model [ J ] .Processes , 2022 , 10 ( 4 ): 634.
[ 14 ] WEI B , HAO K R , GAO L , et al.Detecting textile micro defects : a novel and efficient method based on visual gain mechanism [ J ] .Information sciences , 2020 , 541 :60-74.
[ 15 ] HU R , FU Z H , ZHU S W , et al.Detection of residual yarn in bobbin based on hough transform and BP neural network [ C ] ∥2021 IEEE 5th Advanced Information Technology , Electronic and Automation Control Conference ( IAEAC ), 2021 : 68-74.
[ 16 ] 徐健,吴曙培,刘秀平 . 基于改进深度神经网络的纱管分类[ J ] . 激光与光电子学进展, 2020 , 57 ( 10 ): 152-159.
[ 17 ] 张星星 . 基于机器视觉的管纱外观检测系统研究[ D ] . 西安:西安工程大学,2019.
[ 18 ] WANG K , TENG Z X , ZOU T Y.Metal defect detection based on YOLOv5 [ J ] .Journal of physics : conference series , 2022 , 2218 ( 1 ): 012050.
[ 19 ] HE K M , ZHANG X Y , REN S Q , et al.Spatial pyramid pooling in deep convolutional networks for visual recognition [ J ] .IEEE Transactions onpattern analysis and machine intelligence , 2015 , 37 ( 9 ): 1904-1916.
[ 20 ] LIN T Y , DOLL?R P , GIRSHICK R , et al.Feature pyramid networks for object detection [ C ] ∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2017 : 2117-2125.
[ 21 ] LIU S , QI L , QIN H F , et al.Path aggregation network for instance segmentation [ C ] ∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2018 : 8759-8768.
[ 22 ] HOU Q , ZHOU D , FENG J.Coordinate attention for efficient mobile network design [ C ] ∥Proceedings of the IEEE / CVF Conference on Computer Vision and Pattern Recognition , 2021 : 13713-13722.
[ 23 ] ZHENG Z H , WANG P , REN D W , et al.Enhancing geometric factors in model learning and inference for object detection and instance segmentation [ J ] .IEEE Transactions on cybernetics , 2021 , 52 ( 8 ): 8574-8586.

相似文献/References:

[1]杨永灿,刘 韬,柳小勤,等.基于注意力机制的一维卷积神经网络行星齿轮箱故障诊断[J].机械与电子,2021,(10):3.
　YANG Yongcan,LIU Tao,LIU Xiaoqin,et al.Fault Diagnosis of Planetary Gearbox Based on One-dimensional Convolutional Neural Network with Attention Mechanism[J].Machinery & Electronics,2021,(12):3.
[2]李文波,王 玉,王明泉,等.瞬态场景下基于光流法的红外视频插帧算法研究[J].机械与电子,2024,42(04):15.
　LI Wenbo,WANG Yu,WANG Mingquan,et al.Research on Infrared Video Frame Interpolation Algorithm Based on Optical Flow Method in Transient Scene[J].Machinery & Electronics,2024,42(12):15.
[3]王 凡,甄子洋,邓 敏.基于 CNN-GRU-Attention 的道岔故障诊断算法研究[J].机械与电子,2024,42(06):10.
　WANG Fan,ZHEN Ziyang,DENG Min.Research on Turnout Fault Diagnosis Algorithm Based on CNN-GRU-Attention[J].Machinery & Electronics,2024,42(12):10.
[4]鲍克鹏,许 涛,贾雪磊,等.基于改进双边分割网络的视觉测振方法[J].机械与电子,2025,(03):29.
　BAO Kepeng,XU Tao,JIA Xuelei,et al.Visual Vibration Measurement Method Based on an Improved Bilateral Segmentation Network[J].Machinery & Electronics,2025,(12):29.
[5]苑 超,丁晓森,朱 雷,等.基于改进 VMD 与 Transformer 的 GIS 局部放电信号识别[J].机械与电子,2025,(04):27.
　YUAN Chao,DING Xiaosen,ZHU Lei,et al.GIS Partial Discharge Signal Recognition Based on Improved VMD and Transformer[J].Machinery & Electronics,2025,(12):27.
[6]段耀斌,王城宇,张国谋,等.基于注意力机制的多向传感器数据融合齿轮箱故障诊断方法[J].机械与电子,2025,(07):3.
　DUAN Yaobin,WANG Chengyu,ZHANG Guomou,et al.Fault Diagnosis Method for Gearbox Based on Attention Mechanism and Multi-directional Sensor Data Fusion[J].Machinery & Electronics,2025,(12):3.
[7]杨吴奔,苏立鹏,郑建豹,等.基于 AAC-GAN 的起重机缺陷图像生成方法及其在缺陷分类中的应用[J].机械与电子,2025,(09):67.
　YANG Wuben,SU Lipeng,ZHENG Jianbao,et al.Crane Defect Image Generation Method Based on AAC-GAN and Its Application in Defect Classification[J].Machinery & Electronics,2025,(12):67.
[8]郭 庆,陈 川,季强东,等.基于改进 YOLOv11 的复杂环境下火焰目标检测[J].机械与电子,2025,(11):33.
　GUO Qing,CHEN Chuan,JI Qiangdong,et al.Flame Target Detection in Complex Environments Based on Improved YOLOv11[J].Machinery & Electronics,2025,(12):33.
[9]潘学华,梁炜皓,李金瑾,等.面向绝缘子微小缺陷的 YOLOv8s 的改进算法研究[J].机械与电子,2025,(12):10.
　PAN Xuehua,LIANG Weihao,LI Jinjin,et al.Research on Improved YOLOv8s Algorithm for Micro-defect Detection in Insulators[J].Machinery & Electronics,2025,(12):10.

备注/Memo

备注/Memo:
收稿日期: 2023-06-20
基金项目:陕西省重点研发计划项目( 2022GY-307 )
作者简介:王 青 ( 1985- ),女,陕西西安人,讲师,硕士研究生导师,研究方向为三维视觉下的位姿估计等;吕绪山 ( 1998- ),男,陕西安康人,硕士,研究方向为机器视觉。
更新日期/Last Update: 2024-01-10