Welding crack detection based on eddy current infrared thermography

Xin Yan; Xiangdong Gao

doi:10.1117/12.3011246

1 November 2023 Welding crack detection based on eddy current infrared thermography

Xin Yan, Xiangdong Gao

Proceedings Volume 12917, International Conference on Precision Instruments and Optical Engineering (PIOE 2023); 129170G (2023) https://doi.org/10.1117/12.3011246
Event: 3rd International Conference on Precision Instruments and Optical Engineering (PIOE 2023), 2023, Shanghai, China

Abstract

Welding defect detection is an important means to ensure the quality of welding, and also an essential part of manufacturing quality inspection. In order to improve the flexibility of weld quality inspection, this study adopts two different object detection algorithms, YOLOv5 and YOLOv7, to detect cracks in the collected datasets of spot welding crack using Eddy Current Infrared Thermography. The performance metrics are used to evaluate the model's effectiveness and determine the most suitable detection model for weld crack detection. The experiments show that YOLOv7 is more suitable as the detection model for spot welding crack detection, which can achieve better results in terms of detection accuracy and detection speed, and meets the requirements of high detection accuracy and fast detection speed in practical industrial applications.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xin Yan and Xiangdong Gao "Welding crack detection based on eddy current infrared thermography", Proc. SPIE 12917, International Conference on Precision Instruments and Optical Engineering (PIOE 2023), 129170G (1 November 2023); https://doi.org/10.1117/12.3011246

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