YOLOv7-based defect detection of automotive aluminium alloy lined carbon fibre fully winding hydrogen storage composite cylinder

Shutao Xiong; Feng He; Xue Wang; Yanjun Li

doi:10.1117/12.3032834

5 July 2024 YOLOv7-based defect detection of automotive aluminium alloy lined carbon fibre fully winding hydrogen storage composite cylinder

Shutao Xiong, Feng He, Xue Wang, Yanjun Li

Author Affiliations +

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 1318474 (2024) https://doi.org/10.1117/12.3032834
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

In order to address the problems of impact and low signal-to-noise ratio of layered defects in automotive aluminium alloylined carbon fibre fully-wound hydrogen storage composite cylinders, we propose a deep learning algorithm based on YOLOv7. The algorithm introduces the Swin-Transformer module into the YOLOv7 backbone network structure to capture the contextual information and global dependencies of steel surface defects at different scales to retain more feature information of small-scale targets, thus improving the detection accuracy of the model. At the same time, we use the ECA attention module to improve the network's attention to small targets, which effectively solves the problem of the original model's missed detection of small targets. Finally, partial convolution (PConv) is introduced in the neck network of the model to replace the regular convolution for lightweight improvement to reduce the number of parameters and computation of the model. The experimental results show that the detection accuracy of the algorithm reaches 98.3% on the infrared thermal imaging dataset of homemade automotive hydrogen storage composite gas cylinders, which is 6.2% higher than that of the original YOLOv7 algorithm, and the algorithm has better detection accuracy and detection rate, and it can play an important role in industrial applications

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shutao Xiong, Feng He, Xue Wang, and Yanjun Li "YOLOv7-based defect detection of automotive aluminium alloy lined carbon fibre fully winding hydrogen storage composite cylinder", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 1318474 (5 July 2024); https://doi.org/10.1117/12.3032834

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Detection and tracking algorithms

Carbon fibers

Convolution

Composites

Defect detection

Machine learning

Keywords/Phrases

Search In:

Publication Years