Research on in-situ monitoring method for ceramic additive manufacturing process based on YOLOv3

Jia Xinjian; Liu Bingshan; Hu Chuanqi; Liu Xiaodong; Li Xin; Wang Gong

doi:10.1117/12.3032822

5 July 2024 Research on in-situ monitoring method for ceramic additive manufacturing process based on YOLOv3

Jia Xinjian, Liu Bingshan, Hu Chuanqi, Liu Xiaodong, Li Xin, Wang Gong

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 131845Y (2024) https://doi.org/10.1117/12.3032822
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

To address the consistency issues in the ceramic additive manufacturing process, a solution is proposed involving the use of computer vision to acquire monitoring images of the manufacturing surface. The obtained image data is then input into the YOLOv3 model for training, aiming to detect and eliminate defects during the manufacturing process. To tackle the problem of uneven illumination at different positions on the large-scale manufacturing surface, a method using homomorphic filtering is proposed to remove the illumination components from the images. The parameters of the Gaussian-type homomorphic filter are determined through theoretical analysis and experimental validation. The results demonstrate that after homomorphic filtering, the detection rate for bubble defects increased by 6.7% and the detection rate for pit defects increased by 2.3%.

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

Citation Download Citation

Jia Xinjian, Liu Bingshan, Hu Chuanqi, Liu Xiaodong, Li Xin, and Wang Gong "Research on in-situ monitoring method for ceramic additive manufacturing process based on YOLOv3", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 131845Y (5 July 2024); https://doi.org/10.1117/12.3032822

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