Wuhan Univ. J. Nat. Sci.
Volume 27, Number 6, December 2022
|Page(s)||489 - 498|
|Published online||10 January 2023|
CLC number: TP 183
Automatic Detection of Weld Defects in Pressure Vessel X-Ray Image Based on CNN
Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
2 Shanghai Engineering Research Center of Smart Energy, Shanghai 201103, China
3 Shanghai Aino Industrial Technology CO., LTD, Shanghai 201612, China
The visual automatic detection method based on artificial intelligence has attracted more and more attention. In order to improve the performance of weld nondestructive defect detection, we propose DRepDet (Dilated RepPoints Detector). First, we analyze the weld defect dataset in detail and summarize the distribution characteristics of weld defect data, that is, the defect scale is very different and the aspect ratio distribution range is large. Second, according to the distribution characteristics of defect data, we design DResBlock module, and introduce dilated convolution with different dilated rates in the process of feature extraction to expand the receptive field and improve the detection performance of large-scale defects. Based on DResBlock and anchor-free detection framework RepPoints, we design DRepDet. Extensive experiments show that our proposed detector can detect 7 types of defects. When using combined dilated rate convolution network in detection, the AP50 and Recall50 of big defects are improved by 3.1% and 3.3% respectively, while the performance of small defects is not affected, almost the same or slightly improved. The final performance of the whole network is improved a large margin, with 6% AP50 and 4.2% Recall50 compared with Cascade R-CNN and 1.4% AP50 and 2.9% Recall50 compared with RepPoints.
Key words: nondestructive testing / depth learning / weld defect detection / convolutional neural networks / dilated convolution
Biography: XIAO Wenkai, male, Ph. D. candidate, Senior Engineer, research direction: artificial intelligence. E-mail: firstname.lastname@example.org
© Wuhan University 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.