[1]陆 晓,高 超,蒋承伶,等.基于双注意力机制和级联检测框架的金具螺栓缺陷检测研究[J].机械与电子,2024,42(01):63-70.
　LU Xiao,GAO Chao,JIANG Chengling,et al.Research on Bolt Defect Detection Based on Dual-attention Mechanism and Cascade Detection Framework[J].Machinery & Electronics,2024,42(01):63-70.
点击复制

基于双注意力机制和级联检测框架的金具螺栓缺陷检测研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年01期
页码:
63-70
栏目:
机电一体化
出版日期:
2024-01-25

文章信息/Info

Title:
Research on Bolt Defect Detection Based on Dual-attention Mechanism and Cascade Detection Framework
文章编号:
1001-2257 ( 2024 ) 01-0063-08
作者:
陆 晓 1 ; 高 超 1 ; 蒋承伶 1 ; 王茂飞 2
1. 国网江苏省电力有限公司,江苏 南京 210024 ;
2. 国网江苏泰州供电公司,江苏 泰州 225300
Author(s):
LU Xiao1 ;  GAO Chao1 ;  JIANG Chengling1 ;  WANG Maofei2
( 1.State Grid Jiangsu Electric Power Co. , Ltd. , Nanjing 210024 , China ;
2.State Grid Jiangsu Taizhou Power Supply Company , Taizhou 225300 , China )
关键词:
金具螺栓; 缺陷检测; 多尺度注意力; 级联; 知识引导; 图像增广
Keywords:
gauge bolts ;  defect detection ;  multi-scale attention ;  cascade ;  knowledge guiding ;  image augmentation
分类号:
TP391.41 ; TM75
文献标志码:
A
摘要:
针对传统输电线路金具上的螺栓缺陷检测存在精度低和效率低的问题,提出一种基于双注意力机制和级联检测框架的螺栓缺陷检测模型。首先,构建了螺栓缺陷检测的级联框架并通过基于 GridMask 图像增广方法实现数据集的扩充;其次,为了提高螺栓缺陷检测精度,提出了基于知识引导的输电线金具检测模型,通过隐式和显示模块的构建,实现第 1 级金具的检测;然后,将金具检测结果输入到第 2 级螺栓的缺陷检测网络中,同时提出一种基于双注意力机制的螺栓缺陷检测模型来进行螺栓缺陷检测,通过多尺度注意力模块的设计,融合空间注意力图,实现螺栓全局视野上的特征增强,提高检测的精度;最后,通过实验进行验证,实验结果表明,所提模型的螺栓缺陷检测平均准确度高、检测速度快,具有良好的实用性和鲁棒性,有一定的应用前景。
Abstract:
The traditional bolt defect detection on transmission lines suffers from low accuracy and efficiency , and this paper proposes a bolt defect detection model based on dual-attention mechanism and cascade detection framework.Firstly , a cascade framework for bolt defect detection is constructed and the dataset is expanded by an image augmentation method based on the GridMask ; secondly , in order to improve the accuracy of bolt defect detection , a knowledge-guided detection model for power line fittings is proposed , the detection of the first level of gold fixtures is realized through the construction of implicit and display modules ; then , the results of the gold fixture detection are inputted into the defect detection network for bolts at the second level , while a bolt defect detection model based on dual-attention mechanism is proposed for bolt defect detection , through the design of the multi-scale attention module , the spatial attention map is fused to realize the feature enhancement on the global field of view of the bolt and improve the accuracy of detection ; finally , it is validated by experiments , which show that the average accuracy of bolt defect detection of the model proposed in this paper is high and the detection speed is fast.The model has good practicality , robustness and certain application prospects.

参考文献/References:

[ 1 ] 王鹏,盛宇军,高笃良,等 . 架空输电线路巡检机器人系统设计[ J ] . 电子测量技术, 2022 , 45 ( 21 ): 117-122.

[ 2 ] JIAO R H , LIU Y Z , HE H , et al.A deep learning model for small-size defective components detection in power transmission tower [ J ] .IEEE Transactions on power delivery , 2022 , 37 ( 4 ): 2551-2661.
[ 3 ] 龙珊珊,信瑞山 . 基于人工智能图像识别的输电线路巡检研究[ J ] . 电子测量技术, 2023 , 46 ( 6 ): 116-121.
[ 4 ] ZHANG M D , SUN Y H , WANG S J , et al.A servo control method of bolt tightening robot for power transmission lines [ C ]// 2021 International Conference on Computer , Communication , Control , Automation and Robotics ( CCCAR 2021 ), 2021 , 1976 : 012055.
[ 5 ] RODRIGUES R S D , FADEL F L M , MCCLURE G , et al.Reli-ability assessment of existing transmission line towers considering mechanical model uncertainties [ J ] .Engineering structures , 2021 , 237 : 112016.
[ 6 ] 宋涛,李丹,路宁 . 基于分层强化学习的数字化输电线路路径规划研究[ J ] . 电测与仪表, 2022 , 59 ( 4 ): 91-97.
[ 7 ] 刘兰兰,万旭东,汪志刚,等 . 基于超分辨率重建与多尺度特征融合的输电线路缺陷检测方法[ J ] . 电子测量与仪器学报,2023 , 37 ( 1 ): 130-139.
[ 8 ] LIANG H G , ZUO C , WEI W M.Detection and evaluation method of transmission line defects based on deep learning [ J ] .IEEE Access , 2020 , 8 ( 2 ): 38448-38458.
[ 9 ] ZHOU X Y , ZHUO J C , KR?HENB?HL P.Bottom up object detection by grouping extreme and center points [ C ]// 2019 IEEE / CVF Conference on Computer Vision and Pattern Recognition.New York : IEEE , 2020 : 850-859.
[ 10 ] 赵振兵,李延旭,甄珍,等 . 结合 KL 散度和形状约束 的 Faster R-CNN典型金具检测方法[ J ] . 高电压技术,2020 , 46 ( 9 ): 3018-3026.
[ 11 ] LI Y F , DAI L G , NI H X , et al.Focus on local : transmission line defect detection via feature refinement [ J ] .Signal , image and video processing , 2023 , 17 : 31-37.
[ 12 ] NI H X , WANG M Z , ZHAO L Y.An improved faster R-CNN for defect recognition of key components of transmission line [ J ] .Mathematical biosciences and engineering , 2021 , 18 ( 4 ):4679-4695.
[ 13 ] QIU Z B , ZHU X , LIAO C B , et al.Detection of transmission line insulator defects based on an improved lightweight YOLOv4 model [ J ] .Applied sciences.2022 , 12 ( 3 ): 1207-1214.
[ 14 ] 高强,廉启旺 . 航拍图像中绝缘子目标检测的研究[ J ] . 电测与仪表, 2019 , 56 ( 5 ): 119-123.?
[ 15 ] LI F , XIN J B , CHEN T , et al.An automatic detection method of bird ’s nest on transmission line tower based on faster RCNN [ J ] .IEEE Access , 2020 , 8( 3 ): 164214-164221.
[ 16 ] HAO K , CHEN G K , ZHAO L , et al.An insulator defect detection model in aerial images based on multiscale feature pyramid network [ J ] .IEEE Transactions on instrumentation and measurement , 2022 , 71 : 3522412.
[ 17 ] 戚银城,江爱雪,赵振兵,等 . 基于改进 SSD 模型的输电线路巡检图像金具检测方法 [ J ] . 电测与仪表,2019 , 56 ( 22 ): 7-12 , 43.
[ 18 ] LIU M , LI Z , LI Y C , et al.A fast and accurate method of power line intelligent inspection based on edge computing [ J ] .IEEE Transactions on instrumentation and measurement , 2022 , 71 : 3506512.
[ 19 ] CHEN S B , SU C , KUANG Z X , et al.Insulator fault detection in aerial images based on the mixed grouped fire single-shot multibox detector [ J ] .Jour- nal of imaging science and technology , 2021 , 65( 6 ): 030402.
[ 20 ] ZHAO Z B , QI H Y , QI Y C , et al.Detection method based on automatic visual shape clustering for pin missing defect in transmission lines [ J ] .IEEE Transactions on instrumentation and measurement , 2020 , 69 ( 9 ): 6080-6091.
[ 21 ] LOU W S , ZHANG K , XIAO Y J , et al.PAformer : visually indistinguishable bolt defect recognition based on bolt position and attributes [ C ] ∥2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference ( APSIPA ASC ) . New York : IEEE , 2022 : 884-889.
[ 22 ] LUO P , WANG B , WANG H X , et al.An ultrasmall bolt defect detection method for transmission line inspection [ J ] .IEEE Transactions on instrumentation and measurement , 2023 , 72 : 5006512.
[ 23 ] ZHAO Z B , WANG R , LI Y X , et al.A new multilabel recognition framework for transmission lines bolt defects based on the combination of semantic knowledge and structural knowledge [ J ] .IEEE Transactions on instrumentation and measurement , 2022 , 71 : 5020211.
[ 24 ] CHEN P G , LIU S , ZHAO H S , et al.Gridmask data augmentation [ J / OL ] .arXiv : 2001.04086 [ 2023-06-03 ] .https :// doi.org / 10.48550 / arXiv.2001.04086.
[ 25 ] CHO K , MERRIENBOER B V , GULCEHRE C , et al. Learning phrase representations using rnn encoderdecoder for statistical machine translation [ C ] ∥The 2014 Conference on Empirical Methods in Natural Language Processing , 2014 : 1724-1734.

相似文献/References:

[1]赖肖强,胡 泓.基于机器视觉算法和改进 MobileNetV2 的晶圆缺陷检测研究[J].机械与电子,2025,(01):34.
　LAI Xiaoqiang,HU Hong.Research on Wafer Defect Detection Based on Machine Vision Algorithms and Improved MobileNetV2[J].Machinery & Electronics,2025,(01):34.
[2]黄心玥,王明泉,耿宇杰,等.基于 YOLOv8 的铝合金铸造轮毂缺陷检测算法研究与分析[J].机械与电子,2025,(02):26.
　HUANG Xinyue,WANG Mingquan,GENG Yujie,et al.Research and Analysis of Defect Detection Algorithm for Aluminum Alloy Casting Wheels Based on YOLOv8[J].Machinery & Electronics,2025,(01):26.
[3]曹振锋,王明泉,路宇鹏,等.基于 YOLOv8 的轻量化轮毂缺陷检测算法研究[J].机械与电子,2025,(06):31.
　CAO Zhenfeng,WANG Mingquan,LU Yupeng,et al.Research on the Lightweight Wheel Hub Defect Detection Algorithm Based on YOLOv8[J].Machinery & Electronics,2025,(01):31.
[4]刘 骞,陈茂林.基于深度学习的少样本光伏边框划痕检测[J].机械与电子,2025,(08):47.
　LIU Qian,CHEN Maolin.Few-shot Scratch Detection on Photovoltaic Frame Based on Deep Learning[J].Machinery & Electronics,2025,(01):47.
[5]王立杰,高嘉伟,徐相龙,等. 基于SDA-YOLOv8的PCBA 缺陷检测算法研究[J].机械与电子,2026,44(01):45.
　WANG Lijie,GAO Jiawei,XU Xianglong,et al. Research on PCBA Defect Detection Algorithm Based on SDA -YOLOv8[J].Machinery & Electronics,2026,44(01):45.

备注/Memo

备注/Memo:
收稿日期: 2023-07-21
基金项目:国网江苏电力有限公司科技项目资助( J2022004 )
作者简介:陆 晓 ( 1968- ),男,江苏南京人,博士,高级工程师,研究方向为电力系统调度运行及数字化建设管理;高 超 ( 1983- ),男,河南洛阳人,博士,高级工程师,研究方向为输电线路巡检;蒋承伶 ( 1986- ),男,重庆人,博士,高级工程师,研究方向为电气自动化、计算机通信;王茂飞 ( 1991- ),男,江苏泰州人,硕士,工程师,研究方向为智能运检技术,通信作者。
更新日期/Last Update: 2024-01-16