Recognition and prediction of SMT solder joint defects based on YOLOV5

Jianyu Ma; Zhenhai Li; Tao Liu

doi:10.1117/12.3032827

5 July 2024 Recognition and prediction of SMT solder joint defects based on YOLOV5

Jianyu Ma, Zhenhai Li, Tao Liu

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 131846F (2024) https://doi.org/10.1117/12.3032827
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

PCB (Printed circuit board) is an important electronic component. It is also the carrier of electronic components and metal wires. With the rapid development of science and technology, the production of PCB board has become more refined and the structure has become more complex. At the same time, the appearance of SMT technology has greatly improved the integration of the circuit board, but SMT technology also has defects, such as "monument", "tin bead", "bridge", etc., which leads to short circuit fracture. Based on the research of solder joint defect detection based on YOLOV5, this paper designs an automatic recognition and prediction system for SMT solder joint defects based on YOLOV5 to solve the problems of low accuracy, slow speed and high cost of current solder joint defect detection technology. Real-time image preprocessing was performed on the collected images, and the possible steles, Wuxi, multi-tin, bridge and broken holes were detected. Defect detection in the system is divided into three main parts: image processing, motion control and human-computer interaction. The system has the advantages of simple operation, accurate detection and fast detection speed.

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

Citation Download Citation

Jianyu Ma, Zhenhai Li, and Tao Liu "Recognition and prediction of SMT solder joint defects based on YOLOV5", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 131846F (5 July 2024); https://doi.org/10.1117/12.3032827

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