壳体电子束焊缝无损检测信息管理系统的设计与实现
Design and Realization of Nondestructive Testing Information Management System for Shell Electron Beam Welds
DOI: 10.12677/SEA.2022.115103, PDF,  被引量   
作者: 赵 爽, 安东阳, 王耀宗:北京星航机电装备有限公司,北京;龙 陵, 张海玲, 梁 昊*:中国科学院声学研究所,北京;金 珊:北京市科学技术研究院科技情报研究所,北京
关键词: X射线焊缝图像信息管理系统小波包滤波图像相似度检索智能缺陷检测X-Ray Weld Images Information Management System Wavelet Packet Filtering Image Similarity Detection Intelligent Defect Detection
摘要: 本文根据壳体电子束焊缝无损检测的具体检测工序和实际应用需求,提出了面向壳体电子束焊缝的无损检测信息管理系统。该管理系统集成了用户委托申请信息、检测工序信息、原始检测信息、无损检测报告信息等信息管理模块;重点研发了面向X射线图像的小波包滤波功能。基于TOP K Hash值的图像相似度快速检索功能和YOLOv5模型的人工智能的缺陷自动识别功能,可有效提高焊缝缺陷信息管理的办公效率和检测效率。
Abstract: According to the specific detection process and practical application requirements of nondestructive testing of shell electron beam welds, this paper proposes a nondestructive testing information management system for shell electron beam welds. The management system integrates information modules such as user entrusted application information, testing process information, original testing information, non-destructive testing report information, etc. and focuses on developing the function of wavelet packet filtering for X-ray images. The function of rapid retrieval of image similarity based on TOP K Hash value and the automatic identification function of defects based on artificial intelligence can effectively improve the office efficiency and detection efficiency of weld defects.
文章引用:赵爽, 龙陵, 安东阳, 王耀宗, 张海玲, 梁昊, 金珊. 壳体电子束焊缝无损检测信息管理系统的设计与实现[J]. 软件工程与应用, 2022, 11(5): 1005-1016. https://doi.org/10.12677/SEA.2022.115103

参考文献

[1] 魏明贤, 邬冠华, 王俊涛, 张方洲. 激光焊缝无损检测技术研究现状[J]. 无损探伤, 2022, 46(1): 25-30.
[2] 吕淳威. 造船项目质量管理的改进研究[J]. 广东造船, 2012, 31(6): 94-96+44.
[3] 陈彩霞, 丁益, 董建军. 工程项目管理系统的设计与实现[J]. 科技视界, 2021(30): 155-156.
[4] Yahaghi, E. and Movafeghi, A. (2019) Contrast Enhancement of Industrial Radiography Images by Gabor Filtering with Automatic Noise Thresholding. Russian Journal of Nondestructive Testing, 55, 73-79. [Google Scholar] [CrossRef
[5] Zhang, L., Zhang, Y.J., Dai, B.C., Chen, B. and Li, Y.F. (2019) Welding Defect Detection Based on Local Image Enhancement. IET Image Processing, 13, 2647-2658. [Google Scholar] [CrossRef
[6] Gharsallah, M.B., Mhammed, I.B., Braiek, E.B. and Braiek, E.B. (2018) Improved Geometric Anisotropic Diffusion Filter for Radiography Image Enhancement. Intelligent Automation and Soft Computing, 24, 231-240. [Google Scholar] [CrossRef
[7] Muthukumaran, M., Prabaharan, L., Sivapathi, A. and Gopalakrishnan, S. (2017) A Comparative Analysis of an Anisotropic Diffusion Image Denoising Methods on Weld X-Radiography Images. Far East Journal of Electronics and Communications, 17, 267-281. [Google Scholar] [CrossRef
[8] Yahaghi, E. and Hosseiniashrafi, M. (2019) Enhanced Defect Detectionin Radiography Images of Welded Objects. Nondestructive Testing and Evaluation, 34, 13-22. [Google Scholar] [CrossRef
[9] 付思琴, 邱涛, 王权顺, 黄德丰, 余华云. 基于改进YOLOv4的焊接件表面缺陷检测算法[EB/OL]. 包装工程, 1-12.
http://kns.cnki.net/kcms/detail/50.1094.TB.20220706.0852.002.html, 2022-07-19.
[10] 谭志彬, 柳纯录. 信息系统项目管理师教程[M]. 第3版. 北京: 清华大学出版社, 2018.
[11] 吴强. CBIR中特征提取技术的比较研究[D]: [硕士学位论文]. 杭州: 浙江理工大学, 2017.
[12] 薛正元. Top-k选择理论及其在图数据处理中的应用研究[D]: [博士学位论文]. 武汉: 华中科技大学, 2018.