Research on welding spot defect detection of spacecraft thermistor based on Yolov5

Lei Huang; Mingyu Guo; Guanghui Fu; Yue Yu; Li Yang

doi:10.1117/12.2640831

24 October 2022 Research on welding spot defect detection of spacecraft thermistor based on Yolov5

Lei Huang, Mingyu Guo, Guanghui Fu, Yue Yu, Li Yang

Proceedings Volume 12289, International Conference on Intelligent Manufacturing and Industrial Automation (CIMIA 2022); 122890N (2022) https://doi.org/10.1117/12.2640831
Event: International Conference on Intelligent Manufacturing and Industrial Automation (CIMIA 2022), 2022, Kunming, China

Abstract

In order to improve the detection efficiency and accuracy of spacecraft thermistor wire solder joint detection and defect identification, yolov5 neural network model is studied and optimized, ECA attention module is introduced, infrared thermal imager and microscope lens are used, temperature control fixture and optical fiber coupled semiconductor laser are used to realize the detection of micro holes in its solder joint Infrared image signal acquisition and quality detection of cracks and other defects.

Citation Download Citation

Lei Huang, Mingyu Guo, Guanghui Fu, Yue Yu, and Li Yang "Research on welding spot defect detection of spacecraft thermistor based on Yolov5", Proc. SPIE 12289, International Conference on Intelligent Manufacturing and Industrial Automation (CIMIA 2022), 122890N (24 October 2022); https://doi.org/10.1117/12.2640831

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