[1]王云涛,张尚安,徐瀛鹏,等.基于三维模型的航空电连接器插孔视觉识别方法[J].郑州大学学报(工学版),2025,46(03):143-152.[doi:10.13705/j.issn.1671-6833.2025.03.005]
　WANG Yuntao,ZHANG Shangan,XU Yingpeng,et al.3D Model-based Visual Recognition Method of Aviation Electrical Connector′s Contacts[J].Journal of Zhengzhou University (Engineering Science),2025,46(03):143-152.[doi:10.13705/j.issn.1671-6833.2025.03.005]
点击复制

基于三维模型的航空电连接器插孔视觉识别方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年03期
页码:
143-152
栏目:
出版日期:
2025-05-13

文章信息/Info

Title:
3D Model-based Visual Recognition Method of Aviation Electrical Connector′s Contacts
文章编号:
1671-6833(2025)03-0143-10
作者:
王云涛1;  张尚安2;  徐瀛鹏3;  耿俊浩1
1.西北工业大学 机电学院,陕西 西安 710072;2.中航西飞民用飞机有限责任公司,陕西 西安 710089;3.浙江大华技术股份有限公司,浙江 杭州 310053
Author(s):
WANG Yuntao1;  ZHANG Shang’an2;  XU Yingpeng3;  GENG Junhao1
1.School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an 710072, China; 2.AVIC XAC Commercial Aircraft Co., Ltd., Xi’an 710089, China; 3.Zhejiang Dahua Technology Co., Ltd., Hangzhou 310053, China
关键词:
电连接器;  三维模型;  视觉识别;  插孔定位;  插孔补全;  插孔排序
Keywords:
electrical connector;  3D model;  visual recognition;  contact positioning;  contact completion;  contact sorting
分类号:
TP391.4V242.4
DOI:
10.13705/j.issn.1671-6833.2025.03.005
文献标志码:
A
摘要:
基于增强现实或机械臂的航空电连接器智能插接辅助技术依赖于精准的插孔位置和排序等先验信息,而当前先验信息的获取完全依赖人工采集,精度和完整度不高。针对这些问题,提出了一种基于三维模型的航空电连接器插孔视觉识别方法。该方法将基于深度学习和基于图像处理的方法耦合,通过融合深度学习的两步插孔精确定位方法实现了针对航空电连接器三维模型插孔的精准检测和定位信息获取,然后基于环状分层思想对已定位的插孔进行补全和排序,最终实现了对复杂航空电连接器三维模型插孔的全自动智能化精准视觉识别,得到了精准的插孔位置及排序信息。实验结果表明:所提方法在识别率和定位精度上均优于单一深度学习方法,其中融合YOLOv7的效果最佳,平均识别率为97.85%,平均定位误差为0.025 mm,平均定位时间为69 ms,漏识别插孔补全率为100%,排序正确率为100%,能够为基于增强现实或机械臂的航空电连接器智能插接辅助提供精准有效的先验信息。
Abstract:
The intelligent insertion assistance technology of aviation electrical connectors based on augmented reality or robotic arms relied on precise prior information such as precise contact positions and sorting information. However, the current acquisition of prior information relied entirely on manual collection, with low accuracy and completeness. To address this issue, in this study, a 3D model-based visual recognition method of aviation electrical connector′s contacts was proposed. This method coupled deep learning and image processing methods. The precise detection and positioning information acquisition of the 3D model contact for aviation electrical connectors was achieved through a two-step contact precise positioning method based on deep learning. Then, based on the circular layering idea, the positioned contacts were completed and sorted. Finally, fully automated, intelligent, and precise visual recognition of complex aviation electrical connector model contacts was achieved, and accurate contact positions and sorting information were obtained. The experiment showed that the contact recognition method proposed in this study was superior to the single deep learning method in both recognition rate and positioning accuracy. Among them, the fusion of YOLOv7 had the best effect, with an average recognition rate of 97.85%, an average positioning error of 0.025 mm, an average positioning time of 69 ms, a missing contact completion rate of 100%, and a sorting accuracy rate of 100%. It could provide accurate and effective prior information for intelligent insertion assistance of aviation electrical connectors based on augmented reality or robotic arms.

参考文献/References:

[1]GENG J H, CHEN M B, ZHAO X Y, et al. A markerless AR guidance method for large-scale wire and cable laying of electromechanical products[J]. IEEE Transactions on Industrial Informatics, 2024, 20(3): 4007-4020. 

[2]ANGADI S V, JACKSON R L, PUJAR V, et al. A comprehensive review of the finite element modeling of electrical connectors including their contacts[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2020, 10(5): 836-844. 
[3]WEN B H, PAN J, QIAN P, et al. Research on the influence of the closing amount of electrical connector contacts on fretting wear under a vibration environment[J]. Electronics, 2023, 12(11): 2469. 
[4]唐健钧, 叶波, 耿俊浩. 飞机装配作业AR智能引导技术探索与实践[J]. 航空制造技术, 2019, 62(8): 22-27. 
TANG J J, YE B, GENG J H. Exploration and practice of aircraft assembly AR intelligent pilot technology[J]. Aeronautical Manufacturing Technology, 2019, 62(8): 22-27. 
[5]TIAN W, DING Y F, DU X D, et al. A review of intelligent assembly technology of small electronic equipment [J]. Micromachines, 2023, 14(6): 1126.
[6]GENG J H, ZHAO X Y, GUO Z X, et al. A marker-less monocular vision point positioning method for industrial manual operation environments[J]. The International Journal of Advanced Manufacturing Technology, 2022, 120(9): 6011-6027.
[7]黄炜, 刘超. 基于视觉技术的连接器孔位识别与定位装配[J]. 组合机床与自动化加工技术, 2020(2): 43-46. 
HUANG W, LIU C. Identification and positioning assembly of connector hole-position based on vision technology [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2020(2): 43-46.
[8]胡广华, 黄俊锋, 王宁, 等. 用于自动插线系统的连接器识别与定位算法[J]. 华南理工大学学报(自然科学版), 2021, 49(3): 17-24, 33. 
HU G H, HUANG J F, WANG N, et al. Identification and location algorithm of connectors for automatic wiring system[J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(3): 17-24, 33. 
[9]PAN R Z, LI C, HU B, et al. Research on the examination technology of connector pin skewing according to Blob analysis[J]. Measurement Science and Technology, 2024, 35(3): 035004. 
[10] LI S F, ZHENG P, ZHENG L Y. An AR-assisted deep learning-based approach for automatic inspection of aviation connectors[J]. IEEE Transactions on Industrial Informatics, 2021, 17(3): 1721-1731. 
[11]李树飞, 郑联语, 刘新玉, 等. 增强现实眼镜辅助的线缆连接器装配状态智能检错方法[J]. 计算机集成制造系统, 2021, 27(10): 2822-2836. 
LI S F, ZHENG L Y, LIU X Y, et al. Smart inspection for assembly states of connectors in wiring harness assisted by AR glasses[J]. Computer Integrated Manufacturing Systems, 2021, 27(10): 2822-2836. 
[12]汪嘉杰, 王磊, 范秀敏, 等. 基于视觉的航天电连接器的智能识别与装配引导[J]. 计算机集成制造系统, 2017, 23(11): 2423-2430. 
WANG J J, WANG L, FAN X M, et al. Vision based intelligent recognition and assembly guidance of aerospace electrical connectors[J]. Computer Integrated Manufacturing Systems, 2017, 23(11): 2423-2430. 
[13]汪嘉杰. 面向装配引导的航天电连接器视觉分类识别方法研究[D]. 上海: 上海交通大学, 2018. 
WANG J J. Research on visual classification and recognition method of aerospace electrical connectors oriented to assembly guidance[D].Shanghai: Shanghai Jiao Tong University, 2018. 
[14]WU W H, LI Q. Machine vision inspection of electrical connectors based on improved YOLOv3[J]. IEEE Access, 2020, 8: 166184-166196. 
[15] ZHAO Y L, LI J, ZHANG Q Y, et al. Simultaneous detection of defects in electrical connectors based on improved convolutional neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3511710. 
[16] ZHAO D L, KONG F F, DU F Z. Vision-based adaptive stereo measurement of pins on multi-type electrical connectors[J]. Measurement Science and Technology, 2019, 30(10): 105002. 
[17]周友行, 翟明龙, 杨文佳, 等. 改进GoogLeNet模型在光纤连接器端面缺陷识别中的应用[J]. 湘潭大学学报(自然科学版), 2023, 45(4): 41-49. 
ZHOU Y H X, ZHAI M L, YANG W J, et al. Application of improved GoogLeNet model in visual inspection of optical fiber connector end-face defects[J]. Journal of Xiangtan University (Natural Science Edition), 2023, 45 (4): 41-49. 
[18] ZHAO D L, XUE D, WANG X Y, et al. Adaptive vision inspection for multi-type electronic products based on prior knowledge[J]. Journal of Industrial Information Integration, 2022, 27: 100283. 
[19]洪钢, 朱柯屹, 张宇轩, 等. 基于AR眼镜的航空连接器型号图像匹配方法[J]. 装备制造技术, 2021(7): 57-60, 71. 
HONG G, ZHU K Y, ZHANG Y X, et al. A method for EWIS connector image identification in AR-based aircraft assembly process[J]. Equipment Manufacturing Technology, 2021(7): 57-60, 71.
[20] YAP W P, FOK S C. A case-based design system for the conceptual design of electrical connectors[J]. The International Journal of Advanced Manufacturing Technology, 2002, 20(11): 787-798. 
[21]中国人民解放军总装备部. 耐环境快速分离高密度小圆形电连接器通用规范: GJB 599B—2012[S]. 北京:中国人民解放军总装备部, 2012. 
General Armaments Department of the People′s Liberation Army. General specification for environment resistant quick disconnect high density miniature circular electrical connectors: GJB 599B—2012[S]. Beijing:General Armaments Department of the People′s Liberation Army,2012. 
[22] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]∥European Conference on Computer Vision. Cham: Springer, 2016: 21-37. 
[23] 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. 
[24]WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-theart for real-time object detectors[C]∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2023: 7464-7475. 
[25]廖晓辉, 谢子晨, 路铭硕. 基于YOLOv5s和Android部署的电气设备识别[J]. 郑州大学学报(工学版), 2024, 45(1): 122-128. 
LIAO X H, XIE Z C, LU M S. Electrical equipment identification based on YOLOv5s and Android deployment [J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(1): 122-128. 
[26]廖晓辉, 谢子晨, 辛忠良, 等. 基于轻量化YOLOv5的电气设备外部缺陷检测[J]. 郑州大学学报(工学版), 2024, 45(4): 117-124. LIAO X H, XIE Z C, XIN Z L, et al. Electrical equipment external defect detection based on lightweight YOLOv5[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(4): 117-124.

更新日期/Last Update: 2025-05-22