High resolution weld semantic defect detection algorithm based on integrated double U structure

Abstract As a key industrial equipment, the welding quality of pressure vessels is directly related to the operation safety, and X-ray nondestructive testing is an important means to evaluate the weld quality. In this study, a high-resolution semantic segmentation algorithm based on a double U-shape...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyan Li, Yi Wei, Zhigang Lv, Peng Wang, Liangliang Li, Mengyu Sun, Chu Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02421-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731811024830464
author Xiaoyan Li
Yi Wei
Zhigang Lv
Peng Wang
Liangliang Li
Mengyu Sun
Chu Wang
author_facet Xiaoyan Li
Yi Wei
Zhigang Lv
Peng Wang
Liangliang Li
Mengyu Sun
Chu Wang
author_sort Xiaoyan Li
collection DOAJ
description Abstract As a key industrial equipment, the welding quality of pressure vessels is directly related to the operation safety, and X-ray nondestructive testing is an important means to evaluate the weld quality. In this study, a high-resolution semantic segmentation algorithm based on a double U-shaped network was proposed to meet the requirements of pressure vessel weld defect detection, and accurate detection was realized through innovative three-stage processing flow. Firstly, the weld area was automatically extracted from the original X-ray films (3000+×800 + pixels) by the Gaussian positioning algorithm. Then, a multi-image hybrid stitching technology was proposed to reconstruct the long weld into a standard size of 1500 × 1500, which not only expanded the WSCR data set, but also effectively improved the data imbalance problem. In terms of model architecture, by improving U2Netp and UNet networks, MC-SPP module (multi-connection spatial pyramid pooling), RMAG module (residual multi-add gating recurrent unit), HDC-CBAM module (hybrid dilated convolution-convolutional block attention) and CCM module (cross-layer connection fusion) were integrated to form a cascade network with multi-level feature fusion capability. The experimental results showed that the model could effectively segment the defects such as cracks, pores, slag inclusion, incomplete fusion and incomplete penetration in the weld film, and the mIOU value reached 78.1, which was significantly superior to the existing methods, and provided an efficient and reliable solution for welding defect detection of pressure vessels, which had important engineering application value.
format Article
id doaj-art-a485709e2aba444391d2eb0648a5e4d5
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a485709e2aba444391d2eb0648a5e4d52025-08-20T03:08:25ZengNature PortfolioScientific Reports2045-23222025-05-0115111810.1038/s41598-025-02421-0High resolution weld semantic defect detection algorithm based on integrated double U structureXiaoyan Li0Yi Wei1Zhigang Lv2Peng Wang3Liangliang Li4Mengyu Sun5Chu Wang6School of Electronics and Information Engineering, Xi’an Technological UniversitySchool of Electronics and Information Engineering, Xi’an Technological UniversitySchool of Electronics and Information Engineering, Xi’an Technological UniversitySchool of Institute for Interdisciplinary and Innovation Research, Xi’an Technological UniversitySchool of Institute for Interdisciplinary and Innovation Research, Xi’an Technological UniversitySchool of Opto-electronical Engineering, Xi’an Technological UniversitySchool of Electronics and Information Engineering, Xi’an Technological UniversityAbstract As a key industrial equipment, the welding quality of pressure vessels is directly related to the operation safety, and X-ray nondestructive testing is an important means to evaluate the weld quality. In this study, a high-resolution semantic segmentation algorithm based on a double U-shaped network was proposed to meet the requirements of pressure vessel weld defect detection, and accurate detection was realized through innovative three-stage processing flow. Firstly, the weld area was automatically extracted from the original X-ray films (3000+×800 + pixels) by the Gaussian positioning algorithm. Then, a multi-image hybrid stitching technology was proposed to reconstruct the long weld into a standard size of 1500 × 1500, which not only expanded the WSCR data set, but also effectively improved the data imbalance problem. In terms of model architecture, by improving U2Netp and UNet networks, MC-SPP module (multi-connection spatial pyramid pooling), RMAG module (residual multi-add gating recurrent unit), HDC-CBAM module (hybrid dilated convolution-convolutional block attention) and CCM module (cross-layer connection fusion) were integrated to form a cascade network with multi-level feature fusion capability. The experimental results showed that the model could effectively segment the defects such as cracks, pores, slag inclusion, incomplete fusion and incomplete penetration in the weld film, and the mIOU value reached 78.1, which was significantly superior to the existing methods, and provided an efficient and reliable solution for welding defect detection of pressure vessels, which had important engineering application value.https://doi.org/10.1038/s41598-025-02421-0Defect detectionSemantic segmentationWelding seam extractionData enhancement
spellingShingle Xiaoyan Li
Yi Wei
Zhigang Lv
Peng Wang
Liangliang Li
Mengyu Sun
Chu Wang
High resolution weld semantic defect detection algorithm based on integrated double U structure
Scientific Reports
Defect detection
Semantic segmentation
Welding seam extraction
Data enhancement
title High resolution weld semantic defect detection algorithm based on integrated double U structure
title_full High resolution weld semantic defect detection algorithm based on integrated double U structure
title_fullStr High resolution weld semantic defect detection algorithm based on integrated double U structure
title_full_unstemmed High resolution weld semantic defect detection algorithm based on integrated double U structure
title_short High resolution weld semantic defect detection algorithm based on integrated double U structure
title_sort high resolution weld semantic defect detection algorithm based on integrated double u structure
topic Defect detection
Semantic segmentation
Welding seam extraction
Data enhancement
url https://doi.org/10.1038/s41598-025-02421-0
work_keys_str_mv AT xiaoyanli highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure
AT yiwei highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure
AT zhiganglv highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure
AT pengwang highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure
AT liangliangli highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure
AT mengyusun highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure
AT chuwang highresolutionweldsemanticdefectdetectionalgorithmbasedonintegrateddoubleustructure