arrow
Return

An automatic welding defect location algorithm based on deep learning

delete2021-06-01
delete79
PRE
AI
杨
杨雷 (Lei Yang)
H
Huaixin Wang
B
Benyan Huo
F
Fangyuan Li
刘
刘嫣红 (Yanhong Liu) *
DOI:10.1016/j.ndteint.2021.102435delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Welding production has a pivotal role in the modern manufacturing industry. However, welding defects are frequently generated during the complex welding production process which will bring a certain effect to the welding quality. Therefore, the issue of welding defect detection has received considerable critical attention. However, traditional methods, based on handcrafted features or shallow-learning techniques could only detect welding defects under specific detection conditions or priori knowledge. In this paper, to serve the evaluation of the harmfulness of welding defects to different objects, based on the strong feature expression ability of deep learning, an automatic welding defect location method is proposed based on the improved U-net network from digital X-ray images which includes data augmentation and welding defect location. To acquire better location performance, the data augmentation is realized to enlarge the data set of welding defects to serve the network training. On the basis, a defect location method based on the improved U-net network is proposed to realize automatic and high-precision welding defect location. Experiments show that the proposed method could acquire the detection precision up to 88.4% on the public data set (GDXray Set) which shows a remarkable location performance compared with other related detection methods.
Keywords:
Welding defects
Defect location
X-ray images
Data augmentation
Semantic segmentation

Journal

N
NDT and E International
IF:
4.5
Papers:
3.1K
Citations:
1.1W

Organization

Zhengzhou University cover
Zhengzhou University
Scholars:
5.8K
Papers: 1.6K
Citations: 3.5W
Cited Papers

Cited Papers

errShare
errSave
Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA
err2015-04-01
err242
PREAI
errShukur, Osamah Basheer; Lee, Muhammad Hisyam
errShare
errSave
errShare
errSave
Flow-volume curves and sleep-disordered breathing: therapeutic implications.
err1983-08-01
err0
errOAAI
errE F Haponik; P L Smith; J Kaplan; E R Bleecker
errShare
errSave
Automated control of welding penetration based on audio sensing technology
err2017-12-01
err79
PREAI
errLv, Na; Xu, Yanling; Li, Sichen; Yu, Xinwen; Chen, Shanben
errShare
errSave
Activity pattern study of Asiatic black bear (Ursus thibetanus) in the Qinling Mountains, China, by using infrared camera traps
err2021-01-15
err0
PREAI
errBabar Zahoor; Xuehua Liu; Pengfen Wu; Wanlong Sun; Xiaodong Jia; Zixin Lv; Xiangyu Zhao; Xiangbo He; Baishuo He; Qiong Cai; Melissa Songer
errShare
errSave
researcher View more