Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms

The welding quality of industrial pipelines directly impacts structural safety. X-ray non-destructive testing (NDT), known for its non-invasive and efficient characteristics, is widely used for weld defect detection. However, challenges such as low contrast between defects and background, as well as...

Full description

Saved in:
Bibliographic Details
Main Authors: Guanli Su, Xuanhe Su, Qunkai Wang, Weihong Luo, Wei Lu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4519
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183784629010432
author Guanli Su
Xuanhe Su
Qunkai Wang
Weihong Luo
Wei Lu
author_facet Guanli Su
Xuanhe Su
Qunkai Wang
Weihong Luo
Wei Lu
author_sort Guanli Su
collection DOAJ
description The welding quality of industrial pipelines directly impacts structural safety. X-ray non-destructive testing (NDT), known for its non-invasive and efficient characteristics, is widely used for weld defect detection. However, challenges such as low contrast between defects and background, as well as large variations in defect scales, reduce the accuracy of existing object detection models. To address these, an optimized detection model based on You Only Look Once (YOLO) v5 is proposed. Firstly, the Efficient Multi-Scale Attention (EMA) attention mechanism is integrated into the first Cross Stage Partial (C3) module of the backbone to enhance the model’s receptive field and the initial feature extraction. Secondly, the Efficient Channel Attention (ECA) attention mechanism is embedded before the Spatial Pyramaid Pooling Fast (SPPF) layer to enhance the model’s ability to extract small targets and key features. Finally, the Complete Intersection over Union (CIoU) loss is replaced with Wise Intersection over Union (WIoU) to improve localization accuracy and multi-scale detection performance. The experimental results show that the optimized model achieves a precision of 94.1%, a recall of 89.2%, and an mAP@0.5 of 94.6%, representing improvements by 11.5%, 5.4%, and 6.9%, respectively, over the original YOLOv5. The optimized model also outperforms several mainstream object detection models in weld defect detection. In terms of mAP@0.5, the optimized YOLOv5 model shows improvements of 14.89%, 13.02%, 6.1%, 19.37%, 7.1%, 7.5%, and 10.7% compared with the Faster-RCNN, SSD, RT-DETR, YOLOv3, YOLOv8, YOLOv9, and YOLOv10 models, respectively. This optimized model significantly enhances X-ray weld defect detection accuracy, meeting industrial application requirements and offering another high-precision solution for weld defect detection.
format Article
id doaj-art-3671309053834c00a5229abb30533787
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-3671309053834c00a5229abb305337872025-08-20T02:17:14ZengMDPI AGApplied Sciences2076-34172025-04-01158451910.3390/app15084519Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention MechanismsGuanli Su0Xuanhe Su1Qunkai Wang2Weihong Luo3Wei Lu4School of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaNatural Gas Branch of SINOPEC, Beijing 100029, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaThe welding quality of industrial pipelines directly impacts structural safety. X-ray non-destructive testing (NDT), known for its non-invasive and efficient characteristics, is widely used for weld defect detection. However, challenges such as low contrast between defects and background, as well as large variations in defect scales, reduce the accuracy of existing object detection models. To address these, an optimized detection model based on You Only Look Once (YOLO) v5 is proposed. Firstly, the Efficient Multi-Scale Attention (EMA) attention mechanism is integrated into the first Cross Stage Partial (C3) module of the backbone to enhance the model’s receptive field and the initial feature extraction. Secondly, the Efficient Channel Attention (ECA) attention mechanism is embedded before the Spatial Pyramaid Pooling Fast (SPPF) layer to enhance the model’s ability to extract small targets and key features. Finally, the Complete Intersection over Union (CIoU) loss is replaced with Wise Intersection over Union (WIoU) to improve localization accuracy and multi-scale detection performance. The experimental results show that the optimized model achieves a precision of 94.1%, a recall of 89.2%, and an mAP@0.5 of 94.6%, representing improvements by 11.5%, 5.4%, and 6.9%, respectively, over the original YOLOv5. The optimized model also outperforms several mainstream object detection models in weld defect detection. In terms of mAP@0.5, the optimized YOLOv5 model shows improvements of 14.89%, 13.02%, 6.1%, 19.37%, 7.1%, 7.5%, and 10.7% compared with the Faster-RCNN, SSD, RT-DETR, YOLOv3, YOLOv8, YOLOv9, and YOLOv10 models, respectively. This optimized model significantly enhances X-ray weld defect detection accuracy, meeting industrial application requirements and offering another high-precision solution for weld defect detection.https://www.mdpi.com/2076-3417/15/8/4519X-ray nondestructive testingweld defectsattention mechanismloss functionYOLO
spellingShingle Guanli Su
Xuanhe Su
Qunkai Wang
Weihong Luo
Wei Lu
Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms
Applied Sciences
X-ray nondestructive testing
weld defects
attention mechanism
loss function
YOLO
title Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms
title_full Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms
title_fullStr Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms
title_full_unstemmed Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms
title_short Research on X-Ray Weld Defect Detection of Steel Pipes by Integrating ECA and EMA Dual Attention Mechanisms
title_sort research on x ray weld defect detection of steel pipes by integrating eca and ema dual attention mechanisms
topic X-ray nondestructive testing
weld defects
attention mechanism
loss function
YOLO
url https://www.mdpi.com/2076-3417/15/8/4519
work_keys_str_mv AT guanlisu researchonxraywelddefectdetectionofsteelpipesbyintegratingecaandemadualattentionmechanisms
AT xuanhesu researchonxraywelddefectdetectionofsteelpipesbyintegratingecaandemadualattentionmechanisms
AT qunkaiwang researchonxraywelddefectdetectionofsteelpipesbyintegratingecaandemadualattentionmechanisms
AT weihongluo researchonxraywelddefectdetectionofsteelpipesbyintegratingecaandemadualattentionmechanisms
AT weilu researchonxraywelddefectdetectionofsteelpipesbyintegratingecaandemadualattentionmechanisms