Poster + Paper
20 June 2024 Method for detecting defects in direct metal deposition using a neural network
Author Affiliations +
Conference Poster
Abstract
Research of literature dedicated to neural networks and artificial intelligence was made. The topicality of the research in this area was proven. Neural network models most using in computer vision were chosen. The possibility of using a method to detect defects during the process of direct metal deposition based on neural network application was proven. Three neural network models based on U-Net, ResUNet and VGG-16 architectures were trained. The best of three models was chosen. Goals for future researches were set.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
P. Pivkin, N. Khodanovich, S. Grigoriev, and P. Peretyagin "Method for detecting defects in direct metal deposition using a neural network", Proc. SPIE 13005, Laser + Photonics for Advanced Manufacturing, 1300511 (20 June 2024); https://doi.org/10.1117/12.3022863
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neural networks

Education and training

Defect detection

Artificial neural networks

Metals

Image processing

COVID 19

Back to Top