Type recognition of weld defects based on support vector machines

doi:10.16731/j.cnki.1671-3133.2017.10.020

Abstract

Abstract: For linear and circular two kinds of weld defects,proposed a method of weld defect type recognition algorithms based on Support Vector Machine (SVM).First of all,some image pre-processing algorithms such as fuzzy C means clustering,region filling algorithm,average filtering,edge detection,Otsu thresholding and inverse thresholding,to get the approximate location of weld defects.The information of the particular region will be extracted using segmentation based fractal texture analysis,SVM is used to classify the segmented defect as line or circular defects based on the extracted features lastly.The results showed that,the average accuracy rate is 97.5% for correcting identification of the type of weld defects,by 150 weld X-ray image is trained and 80 X-ray image weld test,which can meet industrial requirements.

Key words: weld, defect, image processing, Support Vector Machine(SVM)

CLC Number:

TP 391

Li Ning, Lu Ziguang. Type recognition of weld defects based on support vector machines[J]. Modern Manufacturing Engineering, 2017, 445(10): 106-109.

References

[1] 高炜欣,胡玉衡,穆向阳,等.埋弧焊X射线焊缝图像缺陷分割检测技术[J].仪器仪表学报,2011,32(6):1215-1224.
[2] 邵家鑫,都东,石涵,等.基于厚壁工件X射线实时成像的焊缝缺陷自动检测[J].清华大学学报(自然科学版),2013,53(2):150-154.
[3] 高炜欣,胡玉衡,武晓萌,等.埋弧焊X射线焊缝缺陷图像分类算法研究[J].仪器仪表学报,2016,37(3):518-524.
[4] VALAVANIS I,KOSMOPOULOS D.Multiclass defect detection and classification in weld radiographic images using geometric and texture features[J].Expert Systems with Applications,2010,37(12):6706-7614.
[5] SENTHIL Kumar G,NATARAJAN U,ANANTHAN S S.Vision inspection system for the identification and classification of defects in MIG welding joints[J].International Journal of Advanced Manufacturing Technology,2011,61(9-12):923-933.
[6] MUHTADAN R,WIDYAWAN R H,Amhar F.Weld defect classification in radiographic film using statistical texture and support vector machine[J].Advanced Materials Research,2014,89(6):695-700.
[7] 杜秀丽,沈毅,王艳.基于时频判别特征的焊缝超声检测缺陷分类[J].焊接学报,2008,29(2):89-92.
[8] 张晓光,林家骏.X射线检测焊缝的图像处理与缺陷识别[J].华东理工大学学报(自然科学版),2004,30(2).
[9] AREE C,LURSINSAP S,SOPHATSATHIT C,et al.Fuzzy C-Mean:A statistical feature classification of text and image segmentation method.Proceeding of international conference on Intelligent technology,Thailand,Assumption University Bangkok,Thailand[C].[S.l.]:[s.n.],2000:279-284.
[10] GONZALEZ R C,WOODS R E.Digital Image Processing[M].New York:Prentice Hall,2000.
[11] YAZID H,AROF H,AHMAD S,et al Discontinuities detection in welded joints based on inverse surface thresholding[J].NDT & E International,2011(44):563-570.
[12] COSTA A F,HUMPIRE-Mamani G,TRAINA A J M.An efficient algorithm for fractal analysis of textures.25th international conference on graphics,patterns and images[C].[S.l.]:[s.n.],2012:39-46.
[13] VAPNIK V.Statistical learning theory[M].New York:Wiley&Sons,1998.

[1]	DENG Zejian, YANG Miaosen, LIU Xiyang, DU Rongzhen, LIU Jianwei. Research on autonomous welding technology for curved workpieces based on structured light [J]. Modern Manufacturing Engineering, 2025, 538(7): 96-104.
[2]	WEI Shuhao, XU Hongwei, KE Haisen, LI Xiaolu, DING Jianxiong. The electromagnetic clutch end face defect detection of improved YOLOv8n [J]. Modern Manufacturing Engineering, 2025, 536(5): 126-134.
[3]	LI Jicun, ZHENG Peng, LI Yan, HE Qingze. Research on an aluminum profile surface defect detection algorithm integrating GhostBottleneck and attention mechanism [J]. Modern Manufacturing Engineering, 2025, 534(3): 115-123.
[4]	ZHOU Sicong, XIANG Feng, LI Hongjun, ZUO Ying. Industrial small target defect detection based on improved GAN data enhancement [J]. Modern Manufacturing Engineering, 2025, 533(2): 101-108.
[5]	HU Ming, HU Xiangtao, ZHAN Honghui. Development and application of robot weld adaptive correction grinding system based on model matching [J]. Modern Manufacturing Engineering, 2025, 532(1): 42-49.
[6]	ZHOU Xin, ZHAO Kaiyue, LIU Jia, CHEN Chengwei. Short-cycle arc stud welding quality inspection [J]. Modern Manufacturing Engineering, 2025, 532(1): 87-93.
[7]	SUN Tieqiang, QIN Yuanwei, SONG Chao, XIAO Pengcheng. The end face of steel coil defect detection based on improved YOLOv7 [J]. Modern Manufacturing Engineering, 2024, 526(7): 117-125.
[8]	CAO Jieqiang, LI Junli, LIU Gang, ZHANG Liqiang. Automatic fiber placement accuracy detection based on morphology [J]. Modern Manufacturing Engineering, 2024, 524(5): 15-22.
[9]	MA Tao, LI Jingzhao. Copper threaded part surface defect detection algorithm based on MFA-UNet [J]. Modern Manufacturing Engineering, 2024, 524(5): 113-120.
[10]	KANG Feng, XUE Ruilei, LIU Zeqing, LIU Hongsheng. Edge detection of pipeline GMAW molten pool based on improved Canny operator [J]. Modern Manufacturing Engineering, 2024, 524(5): 121-126.
[11]	ZENG Fei, LI Bin, ZHOU Jian, FAN Jiangfeng. Improved defect detection and geometric characterization of drainage pipes in YOLOv7 algorithm [J]. Modern Manufacturing Engineering, 2024, 522(3): 110-118.
[12]	XU Jianlong, XUE Ruilei, WU Libin, LI Xiaojuan, LIU Hongsheng. Analysis and identification of arc acoustic signal characteristics of occlusion defects in narrow gap GMAW [J]. Modern Manufacturing Engineering, 2024, 521(2): 137-141.
[13]	SUN Tieqiang, LIU Jun, SONG Chao, XIAO Pengcheng. A small target defect detection method for aluminum profile surface based on improved YOLOv8n [J]. Modern Manufacturing Engineering, 2024, 531(12): 120-129.
[14]	GONG Lükai, PENG Yili, CHEN Xubing, HAN Guirong, LI Huiyi. Research on weld feature recognition based on improved U-Net algorithm [J]. Modern Manufacturing Engineering, 2024, 530(11): 18-25.
[15]	LI Zhigang, YANG Xiang, ZHU Lin, WEI Chengfa. Collaborative planning strategy of welding robot based on Stateflow [J]. Modern Manufacturing Engineering, 2024, 530(11): 60-65.