首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221502--1)

基于线阵图像深度学习的电池组焊缝瑕疵检测

Weld Defect Inspection of Battery Pack Based on Deep Learning of Linear Array Image

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为实现对激光焊缝质量的高效检测,引入了线阵图像传感解决在线检测问题,提出了一种基于深度学习的焊缝瑕疵快速检测方法。首先,针对激光焊缝瑕疵,优化了基于YOLO(You only look once)的深度学习网络。其次,在实验数据集中加入了合适的锚框,以提高检测框定位信息的准确度,并通过多尺度特征融合技术提高了瑕疵的识别准确度。最后,制作数据集并提出了一种数据集预处理方法训练网络,提升了瑕疵的识别效果。实验结果表明,本方法对焊缝单孔、穿孔、凹槽瑕疵的总识别率大于94%,对尺寸为4096pixel×4000pixel的单张工件图像的检测时间为0.97s,相比传统超声、射线图像检测方法在检测速度方面有明显提升。

Abstract

In order to realize efficient inspection of laser welding quality, this paper introduces linear array image sensing to address online inspection, and proposes a fast inspection method of weld defect based on deep learning. First, aiming at the laser weld defect, a deep learning network based on Yolo (You only look once) is optimized. Then, an appropriate anchor frame is added to the experimental data set to improve the accuracy of detection frame positioning information, and multi-scale feature fusion technology is used to improve the accuracy of defect recognition, Finally, the data set is made and a data set preprocessing method is proposed to train the network, which improves the recognition effect of defects. Experimental results show that the total recognition rate of single hole, perforation and groove defect is more than 94%, and the detection time of single workpiece image with size of 4096pixel×4000pixel is 0.97s, which is significantly faster than traditional ultrasonic and radiographic image detection methods.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TH705, TP391.4

DOI:10.3788/LOP57.221502

所属栏目:机器视觉

基金项目:国家自然科学基金;

收稿日期:2020-02-09

修改稿日期:2020-03-27

网络出版日期:2020-11-01

作者单位    点击查看

吴桐:天津大学精密测试技术及仪器国家重点实验室, 天津 300072
杨金成:天津大学精密测试技术及仪器国家重点实验室, 天津 300072
廖瑞颖:天津大学精密测试技术及仪器国家重点实验室, 天津 300072
杨凌辉:天津大学精密测试技术及仪器国家重点实验室, 天津 300072

联系人作者:杨凌辉(icelinker@tju.edu.cn)

备注:国家自然科学基金;

【1】Guo Z Q, Lai H Q. Causes and control measures of body-in-white laser weld defects [J]. Welding Technology. 2017, 46(1): 43-46.
郭志强, 赖鸿群. 白车身激光焊缝缺陷的成因分析及控制措施 [J]. 焊接技术. 2017, 46(1): 43-46.
Guo Z Q, Lai H Q. Causes and control measures of body-in-white laser weld defects [J]. Welding Technology. 2017, 46(1): 43-46.
郭志强, 赖鸿群. 白车身激光焊缝缺陷的成因分析及控制措施 [J]. 焊接技术. 2017, 46(1): 43-46.

【2】Liu M N. Welding process analysis of NEV battery pack lower shell Automobile Technology & Material[J]. 0, 2018(12): 37-39, 42.
刘美娜. 新能源汽车电池包下壳体焊接工艺分析 汽车工艺与材料[J]. 0, 2018(12): 37-39, 42.

【3】Geng L B. Research on laser welding technology for car battery covers [D]. Harbin: Harbin Institute of Technology. 2017.
耿立博. 汽车动力电池盖板激光焊接工艺研究 [D]. 哈尔滨: 哈尔滨工业大学. 2017.

【4】Cai Y X, Lu L G, Shen P, et al. Online weld breakage diagnosis for the battery of electric vehicle: a data-driven approach . [C]∥2016 IEEE Vehicle Power and Propulsion Conference (VPPC), October 17-20, 2016, Hangzhou, China. New York: IEEE. 2016, 1-5.

【5】Zhou L, Li X Y, Liu S X. Elimination of car body laser penetration welding defect and process optimization [J]. Foundry Technology. 2015, 36(9): 2336-2339.
周丽, 李兴阳, 刘双喜. 车身激光深熔焊焊缝的缺陷消除与工艺优化研究 [J]. 铸造技术. 2015, 36(9): 2336-2339.

【6】Non-destructive Testing Editorial Department. nondestructive testing special report plan [J]. Nondestructive Testing. 2020, 2020(1): 4.
年《无损检测》专题报道计划 [J]. 无损检测. 2020, 2020(1): 4.

【7】Wang D L. Application of ultrasonic inspection technology in detecting welding joint defects [J]. Welding Technology. 2017, 46(12): 82-86.
王东林. 超声波检测技术在白车身焊点缺陷检测中的应用 [J]. 焊接技术. 2017, 46(12): 82-86.

【8】Chen D P, Li X L, Li Y H, et al. Ultrasonic infrared thermography testing for the quality of laser welded seams [J]. Nondestructive Testing. 2008, 30(10): 747-749.
陈大鹏, 李晓丽, 李艳红, 等. 超声红外热像技术检测激光焊缝质量 [J]. 无损检测. 2008, 30(10): 747-749.

【9】Wang Y, Guo H. Application of support vector machine in weld defect detection and recognition of X-ray images [J]. Computer Aided Drafting, Design and Manufacturing. 2014, 24(3): 22-26.

【10】Zhu Q D, Ai X T. The defect detection algorithm for tire X-ray images based on deep learning . [C]∥2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), June 27-29, 2018, Chongqing, China. New York: IEEE. 2018, 138-142.

【11】Li D J, Song H, Xu L H. A real-time welding seam detection technology based on laser vision [J]. Laser & Infrared. 2019, 49(7): 818-823.
李东洁, 宋贺, 徐立航. 一种基于激光视觉的焊缝实时检测技术研究 [J]. 激光与红外. 2019, 49(7): 818-823.

【12】Lu R S, Wu A, Zhang T D, et al. Review on automated optical (visual) inspection and its applications in defect detection [J]. Acta Optica Sinica. 2018, 38(8): 0815002.
卢荣胜, 吴昂, 张腾达, 视觉, 等. 检测技术及其在缺陷检测中的应用综述 [J]. 光学学报. 2018, 38(8): 0815002.

【13】Wang G H, Qian K M. Review on line-scan camera calibration methods [J]. Acta Optica Sinica. 2020, 40(1): 0111011.
王国珲, 钱克矛. 线阵相机标定方法综述 [J]. 光学学报. 2020, 40(1): 0111011.

【14】Lien P C, Zhao Q F. Product surface defect detection based on deep learning . [C]∥2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech), August 12-15, 2018, Athens, Greece. New York: IEEE. 2018, 250-255.

【15】Everingham M. Eslami S M A, van Gool L, et al. The pascal visual object classes challenge: a retrospective [J]. International Journal of Computer Vision. 2015, 111(1): 98-136.

【16】Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection [J]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 779-788.

【17】Girshick R. Fast R-CNN [2020-01-30].https:∥arxiv.[2020-01-30]. 0, org/abs/1504: 08083.

【18】Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector [M]. ∥Leibe B, Matas J, Sebe N, et al. Computer Vision-ECCV 2016. Lecture Notes in Computer Science. Cham: Springer. 2016, 9905: 21-37.

【19】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.

【20】Guo J X, Liu L B, Xu F, et al. Airport scene aircraft detection method based on YOLO v3 [J]. Laser & Optoelectronics Progress. 2019, 56(19): 191003.
郭进祥, 刘立波, 徐峰, 等. 基于YOLO v3的机场场面飞机检测方法 [J]. 激光与光电子学进展. 2019, 56(19): 191003.

【21】Chen T M, Fu G Y, Li S Y, et al. Typical target detection for infrared homing guidance based on YOLO v3 [J]. Laser & Optoelectronics Progress. 2019, 56(16): 161502.
陈铁明, 付光远, 李诗怡, 等. 基于YOLO v3的红外末制导典型目标检测 [J]. 激光与光电子学进展. 2019, 56(16): 161502.

【22】Gidaris S, Komodakis N. LocNet: improving localization accuracy for object detection . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 789-798.

【23】Tian Z, Gui Z G, Zhang P C, et al. Faster_RCNN for industrial spark plug image weld defect inspection [J]. Journal of Test and Measurement Technology. 2020, 34(1): 34-40.
田珠, 桂志国, 张鹏程, 等. Faster_RCNN用于工业火花塞图像焊缝缺陷检测 [J]. 测试技术学报. 2020, 34(1): 34-40.

【24】Liu H, Guo R Y. Detection and identification of SAWH pipe weld defects based on X-ray image and CNN [J]. Chinese Journal of Scientific Instrument. 2018, 39(4): 247-256.
刘涵, 郭润元. 基于X射线图像和卷积神经网络的石油钢管焊缝缺陷检测与识别 [J]. 仪器仪表学报. 2018, 39(4): 247-256.

引用该论文

Wu Tong,Yang Jincheng,Liao Ruiying,Yang Linghui. Weld Defect Inspection of Battery Pack Based on Deep Learning of Linear Array Image[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221502

吴桐,杨金成,廖瑞颖,杨凌辉. 基于线阵图像深度学习的电池组焊缝瑕疵检测[J]. 激光与光电子学进展, 2020, 57(22): 221502

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF