Defect Classification of Weld Metallographic Structure Based on Data Augmentation of Poisson Fusion

被引：0

作者：

Bai X. ^{[1
]}

Gong S. ^{[1
]}

Li X. ^{[1
,3
]}

Xu B. ^{[2
]}

Yang X. ^{[3
]}

Wang M. ^{[3
]}

机构：

[1] School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai

[2] SAIC Volkswagen Automotive Co.，Ltd., Shanghai

[3] Hunan Huayan Laboratory Co.，Ltd., Hunan, Xiangtan

来源：

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University | 2023年 / 57卷 / 10期

关键词：

data augmentation; defect classification; Poisson fusion; weld metallographic structure;

D O I：

10.16183/j.cnki.jsjtu.2022.202

中图分类号：

学科分类号：

摘要：

The classification of the defects in welding applications based on the metallographic structure images plays an important part in industrial welding quality inspections. In order to improve the classification performance of defects in the weld metallographic structure images with a small sample dataset available (the amount of samples being less than 30) ，a Poisson fusion method is used for data augmentation of the defect images and the ResNet18_PRO network is proposed. Both of the methods notably improve the defects classification performance. During data augmentation, the defect area is extracted from original defect samples via digital image processing, and the defect area is fused with normal samples by the Poisson fusion method to generate new defect samples, thus increasing the number of defect samples. The model in this paper is improved based on the ResNet18 network. The downsampling structure is improved to reduce the information loss in the original downsampling structure, and an improved space pyramid pooling structure is added at the end of the network to integrate multi-scale feature information. The classification performance before and after data augmentation is compared by different classification models, which verifies the significant effect of the data augmentation on the classification performance. Meanwhile, the ablation experiment of the ResNet18 _ PRO is conducted to verify the effectiveness of the improved network structure and the training strategy. It is found that the average classification accuracy of ResNet18_PRO reaches 98. 83% and the average F1-score reaches 98. 76%, which greatly improves the classification accuracy of metallographic structure defects. Finally, the network is trained and tested with another industrial defect dataset and obtains good classification results. These results show that the proposed network has a good robustness and practical application value. © 2023 Shanghai Jiao Tong University. All rights reserved.

引用

页码：1216 / 1328

页数：112

共 25 条

[1]

ZHOU Zhenggan, TENG Shenghua, JIANG Wei, Et al., Research on defect detection and evaluation in WeldS with X-rays, Transactions of the China Welding Institution, 23, 3, pp. 85-88, (2002)

[2]

SHAO Zhonghua, Research on extraction technology of weld defects in X-ray image, (2011)

[3]

WANG Siyu, GAO Weixin, ZHANG Xiangsong, Summary of defect detection algorithms for X-ray weld image [J], Hot Working Technology, 49, 15, pp. 1-8, (2020)

[4]

HU Dan, GAO Xiangdong, ZHANG Nanfeng, Et al., Review of status and prospect of weld defect detection, Journal of Mechanical & Electrical Engineering, 37, 7, pp. 736-742, (2020)

[5]

LIU Yuzong, Study on the influence of weld wire types on the quality of 6082-T6 aluminum alloy laserarc composite weld welds [J], Lamps & Lighting, 2021, 2, pp. 38-39

[6]

DUAN F, YINS F, SONG P P, Et al., Automatic welding defect detection of X-ray images by using cascade AdaBoost with penalty term[J], IEEE Access, 7, pp. 125929-125938

[7]

HOU W H, WEI Y, GUO J, Et al., Automatic detection of welding defects using deep neural network [J], Journal of Physics： Conference Series, 933, (2018)

[8]

AJMI C, ZAPATA J, MARTINEZ-ALVAREZ J J, Et al., Using deep learning for defect classification on a small weld X-ray image dataset[J], Journal of Nondestructive Evaluation, 39, 3, pp. 1-13, (2020)

[9]

YAN Yaodong, Research on defect classification of stainless steel welds based on deep learning, (2021)

[10]

LUO Aimin, SHEN Caihong, YI Bin, Et al., Method of multi-classification by improved binary tree based on SVM for welding defects recongnition, Transactions of the China Welding Institution, 31, 7, pp. 51-54, (2010)

← 1 2 3 →