|本期目录/Table of Contents|

[1]夏正洪,何琥,吴建军,等.基于深度学习的航空铆钉分类及异常情况检测*[J].中国安全生产科学技术,2023,19(6):199-205.[doi:10.11731/j.issn.1673-193x.2023.06.028]
　XIA Zhenghong,HE Hu,WU Jianjun,et al.Aviation rivet classification and abnormal situation detection based on deep learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(6):199-205.[doi:10.11731/j.issn.1673-193x.2023.06.028]
点击复制

基于深度学习的航空铆钉分类及异常情况检测*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年6期
页码:
199-205
栏目:
职业安全卫生管理与技术
出版日期:
2023-06-30

文章信息/Info

Title:
Aviation rivet classification and abnormal situation detection based on deep learning
文章编号:
1673-193X(2023)-06-0199-07
作者:
夏正洪; 何琥; 吴建军; 魏汝祥
(1.中国民用航空飞行学院 空中交通管理学院，四川 广汉 618307；
2.中国民用航空华北地区管理局，北京 100621；
3.安阳学院 航空工程学院，河南 安阳 455000)
Author(s):
XIA Zhenghong;  HE Hu;  WU Jianjun;  WEI Ruxiang
(1.School of Air Traffic Management,Civil Aviation Flight University of China,Guanghan Sichuan 618307,China;
2.Civil Aviation Administration of North China,Beijing 100621,China;
3.School of Aviation Engineering,Anyang University,Anyang Henan 455000,China)
关键词:
深度学习; 航空铆钉; 目标检测; 精确率; 召回率
Keywords:
deep learning;  aviation rivet;  target detection;  precision;  recall rate
分类号:
X949；V355.1
DOI:
10.11731/j.issn.1673-193x.2023.06.028
文献标志码:
A
摘要:
针对航空铆钉小目标检测准确率较低、速率较慢等问题，提出1种基于深度学习的航空铆钉分类及异常情况检测方法。首先，根据钉头外观对航空铆钉进行分类，制作航空铆钉数据集；然后，构建航空铆钉分类及异常情况检测模型；最后，从置信度、召回率r、精确率p、平均精度值AP、全类平均精度mAP等指标对检测结果进行评价，并将该算法与YOLOx-s、YOLOx-m、YOLOv5、YOLOv4检测结果进行对比。研究结果表明：该算法可以实现对航空铆钉的分类及异常情况检测，检测结果的置信度约为90%，精确率、召回率、AP值分别在95%，85%，88%以上；本文所涉及铆钉分类及异常情况检测效果由好到坏顺序依次为：开槽盘头自攻铆钉、十字槽头铆钉、半圆头铆钉、平头铆钉、沉头铆钉、抽芯铆钉、异常情况；与其他算法相比，基于深度学习的航空铆钉分类及异常情况的检测，其效果和速度均有一定优势。研究结果可为减小航空铆钉松动和脱落风险、减轻飞机重量、防止金属疲劳和提升飞行可靠性及稳定性提供参考。
Abstract:
Aiming at the low accuracy problem of small target detection for aviation rivet,a method of aviation rivet classification and abnormal situation detection based on deep learning was proposed.Firstly,the aviation rivet was classified according to the appearance of rivet head,and the data set of aviation rivet was made.Secondly,the aviation rivet classification and abnormal situation detection models were constructed.Finally,the detection results were evaluated from the indexes such as confidence,recall rate r,precision p,average precision AP and mean average precision mAP,and the algorithm was compared with the detection results of YOLOx-s,YOLOx-m,YOLOv5 and YOLOv4.The results showed that the algorithm can realize the classification and abnormal situation detection of aviation rivet,the confidence of the detection results is about 90%,and the precision,recall rate and AP value are above 95%,85% and 88% respectively.The order of rivet classification and abnormal situation detection effect from good to bad is: slotted pan head self-tapping rivet,cross slot head rivet,half-round head rivet,flat head rivet,countersunk head rivet,core pulling rivet and abnormal situation.Compared with other algorithms,the aerial rivet classification and abnormal situation detection based on deep learning have advantages in effect and speed.The research results can provide reference value and important significance for reducing the risk of aviation rivet loosening and detachment,reducing aircraft weight,preventing metal fatigue.

参考文献/References:

［1］ZENG Z W,LIU X,DENG Y M,et al.A parametric study of magnetooptic imaging using finite-element analysis applied to aircraft rivet site inspection［J］.IEEE Transactions on Magnetics,2006,42(11):3737-3744.
［2］HE Y Z,LUO F L,PAN M C,et al.Pulsed eddy current technique for defect detection in aircraft riveted structures［J］.NDT & E International,2010,43(2):176-181.
［3］UCHANIN V.Detection of the fatigue cracks initiated near the rivet holes by eddy current inspection techniques［J］.Transactions on Aerospace Research,2020(2):47-58.
［4］高庆吉,胡丹丹,牛国臣,等.基于磁光图像的飞机铆钉缺陷识别［J］.中国图像图形学报,2007，12(12):2179-2183. GAO Qingji,HU Dandan,NIU Guochen,et al.Defect recognition of aircraft rivet based on magnetooptical image［J］.Journal of Image and Graphics,2007,12(12):2179-2183.
［5］OVERTON G.Structured-light 3D scanner speeds aircraft rivet inspection［J］.Laser Focus World:The Magazine for the Photonics & Optoelectronics Industry,2013,49(7):14-16.
［6］李红卫.基于三维点云的飞机机体结构铆钉轮廓提取算法研究［J］.机电工程,2020,37(6):719-723. LI Hongwei.Algorithm of rivet contour extraction for aircraft body structure based on 3D point cloud ［J］.Journal of Mechanical & Electrical Engineering,2020,37(6):719-723.
［7］毕超,张超,周鹏.飞机蒙皮铆钉孔的位置与法矢检测技术研究［J］.中国测试,2022,48(6):32-38. BI Chao,ZHANG Chao,ZHOU Peng.Research on inspection technology for positions and normal vectors of rivet holes on aircraft surface ［J］.China Measurement & Test,2022,48(6):32-38.
［8］杨飞,罗建桥,李柏林,等.结合噪声估计的NRLBP铆钉表面缺陷检测［J］.机械设计与制造,2021(4):56-61. YANG Fei,LUO Jianqiao,LI Bolin,et al.Rivet surface defect detection based on NRLBP combined with noise estimation ［J］.Machinery Design & Manufacture,2021(4):56-61.
［9］陈健飞,蒋刚,杨剑锋,等.基于SVM的铆接件识别及特征参数研究分析［J］.机械设计与制造,2017(1):65-68. CHEN Jianfei,JIANG Gang,YANG Jianfeng,et al.Research and analysis on recognition and characteristic parameters of riveted parts based on SVM ［J］.Machinery Design & Manufacture,2017(1):65-68.
［10］喻强,庄志炜,田威,等.基于单目视觉的散堆铆钉识别与定位技术［J/OL］.计算机集成制造系统:1-20［2023-03-25］.http://kns.cnki.net/kcms/detail/11.5946.TP.20211029.1927.016.html.
［11］邢雪亮,甘文波,蒋朝根.基于机器视觉的航空铆钉尺寸检测技术［J］.计量学报,2020,41(5):518-523. XING Xueliang,GAN Wenbo,JIANG Chaogen.Technology of size detection of air rivets based on machine vision ［J］.Acta Metrologica Sinica,2020,41(5):518-523.
［12］田清廉,熊天辰,黄翔,等.一种基于散乱点云的铆钉孔孔位提取方法［J］.航空制造技术,2022,65(7):83-89. TIAN Qinglian,XIONG Tianchen,HUANG Xiang,et al.An extracting method for center of rivet holes based on scattered point cloud ［J］.Aeronautical Manufacturing Technology,2022,65(7):83-89.
［13］李华,王岩彬,益朋,等.基于深度学习的复杂作业场景下安全帽识别研究［J］.中国安全生产科学技术,2021,17(1):175-181. LI Hua,WANG Yanbin,YI Peng,et al.Research on recognition of safety helmets under complex operation scenes based on deep learning ［J］.Journal of Safety Science and Technology,2021,17(1):175-181.
［14］罗会兰,陈鸿坤.基于深度学习的目标检测研究综述［J］.电子学报,2020,48(6):1230-1239. LUO Huilan,CHEN Hongkun.Survey of object detection based on deep learning ［J］.Acta Electronica Sinica,2020,48(6):1230-1239.
［15］何超,陈果,王雨薇.基于深度学习的航空发动机内部损伤实时检测方法［J/OL］.航空动力学报:1-9［2023-03-25］.https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTDCdPD656v2WvdV0bJ_J3L_1uLWxGjO6Ix7oPnb1OH3X47DwhqdFuSsn8p64L&uniplatform=NZKPT.

相似文献/References:

[1]涂思羽,彭平安,蒋元建.基于深度学习的井下环境异常工况智能识别技术研究[J].中国安全生产科学技术,2018,14(11):58.[doi:10.11731/j.issn.1673-193x.2018.11.009]
　TU Siyu,PENG Pingan,JIANG Yuanjian.Research on intelligent recognition technology of abnormal operating conditions in underground environment based on deep learning method[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(6):58.[doi:10.11731/j.issn.1673-193x.2018.11.009]
[2]刘欣宜,张宝峰,符烨,等.基于深度学习的污染场地作业人员着装规范性检测[J].中国安全生产科学技术,2020,16(7):169.[doi:10.11731/j.issn.1673-193x.2020.07.027]
　LIU Xinyi,ZHANG Baofeng,FU Ye,et al.Detection on normalization of operating personnel dressing at contaminated sites based on deep learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(6):169.[doi:10.11731/j.issn.1673-193x.2020.07.027]
[3]毕东月.基于深度学习的输煤皮带故障视觉检测方法研究[J].中国安全生产科学技术,2021,17(8):84.[doi:10.11731/j.issn.1673-193x.2021.08.013]
　BI Dongyue.Research on visual detection method for fault of coal conveyor belt based on deep learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(6):84.[doi:10.11731/j.issn.1673-193x.2021.08.013]
[4]崔铁军,王凌霄.YOLOv4目标检测算法在煤矿工人口罩佩戴监测工作中的应用研究*[J].中国安全生产科学技术,2021,17(10):66.[doi:10.11731/j.issn.1673-193x.2021.10.010]
　CUI Tiejun,WANG Lingxiao.Research on application of YOLOv4 object detection algorithm in monitoring on masks wearing of coal miners[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(6):66.[doi:10.11731/j.issn.1673-193x.2021.10.010]
[5]刘超,雷晨,李树刚,等.基于CNN-GRU的瓦斯浓度预测模型及应用*[J].中国安全生产科学技术,2022,18(9):62.[doi:10.11731/j.issn.1673-193x.2022.09.009]
　LIU Chao,LEI Chen,LI Shugang,et al.Prediction model of gas concentration based on CNN-GRU and its application[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(6):62.[doi:10.11731/j.issn.1673-193x.2022.09.009]
[6]曹亚利,李振雷,刘旭东,等.基于卷积神经网络的冲击地压预警方法研究*[J].中国安全生产科学技术,2022,18(10):101.[doi:10.11731/j.issn.1673-193x.2022.10.015]
　CAO Yali,LI Zhenlei,LIU Xudong,et al.Research on early-warning method of rockburst based on convolutional neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(6):101.[doi:10.11731/j.issn.1673-193x.2022.10.015]
[7]李子奇,蒋柱虎,王力,等.基于深度学习的工程结构损伤识别研究进展[J].中国安全生产科学技术,2022,18(12):43.[doi:10.11731/j.issn.1673-193x.2022.12.006]
　LI Ziqi,JIANG Zhuhu,WANG Li,et al.Research progress in damage identification of engineering structure based on deep learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(6):43.[doi:10.11731/j.issn.1673-193x.2022.12.006]
[8]唐豪,奉鑫鑫,高曙,等.基于视频分析的空管员违规行为识别方法*[J].中国安全生产科学技术,2023,19(1):196.[doi:10.11731/j.issn.1673-193x.2023.01.029]
　TANG Hao,FENG Xinxin,GAO Shu,et al.Violations recognition method of air traffic controllers based on video analysis[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(6):196.[doi:10.11731/j.issn.1673-193x.2023.01.029]
[9]黄鹏,房志明,朱曼,等.基于SSD网络的电梯内电动自行车检测研究*[J].中国安全生产科学技术,2023,19(2):167.[doi:10.11731/j.issn.1673-193x.2023.02.023]
　HUANG Peng,FANG Zhiming,ZHU Man,et al.Research on detection of electric bicycles in elevator based on SSD network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(6):167.[doi:10.11731/j.issn.1673-193x.2023.02.023]
[10]叶万军,成炜康,陈笑楠,等.砂卵石地层大直径盾构工程地表沉降深度学习预测*[J].中国安全生产科学技术,2023,19(8):124.[doi:10.11731/j.issn.1673-193x.2023.08.018]
　YE Wanjun,CHENG Weikang,CHEN Xiaonan,et al.Deep learning and prediction on surface subsidence of large-diameter shield project in sandy cobble stratum[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(6):124.[doi:10.11731/j.issn.1673-193x.2023.08.018]

备注/Memo

备注/Memo:
收稿日期： 2022-12-19
* 基金项目： 四川省科技计划项目（2022YFG0196）；高校基本科研项目（J2023-046）
作者简介： 夏正洪，硕士，教授，主要研究方向为航空运行安全风险评价。
更新日期/Last Update: 2023-07-09