Efficient Industrial Casting Inspection using Deep Transfer Learning
Journal of Informatics and Advanced Data Science · 21.04.2026 · 1 (01) · 52-61
DOI: 10.66849/jiads.v1i1.8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Informatics and Advanced Data Science, online erschienen am 21.04.2026. Verfasst von Qusay Shihab Hamad.
Abstract (Originalsprache)
Aluminum alloy castings have become vital elements of numerous contemporary sectors and their structural integrity directly influences the mechanical safety. It is due to this that quality control throughout the manufacturing process is of importance. In this paper, it is proposed to use deep learning to identify the defects in cast products using digital images. A transfer learning approach with a VGG-19 architecture was used to address the difficulties of large-data demands and sophisticated tuning of hyperparameters. The model was also tested on a large data set of 8,012 images including normal and defective samples. We have found that the model has a test accuracy of 99.251 and a recall of 99.265. These results indicate that the presented transfer learning model is a very accurate and robust one which can provide a practical solution to the quality control in real-time within the industrial setting.
Zitieren
APA
Hamad, Q. S. (2026). Efficient Industrial Casting Inspection using Deep Transfer Learning. Journal of Informatics and Advanced Data Science, 1(01), 52-61. https://doi.org/10.66849/jiads.v1i1.8
Vancouver
Hamad QS. Efficient Industrial Casting Inspection using Deep Transfer Learning. Journal of Informatics and Advanced Data Science. 2026;1(01):52-61. doi:10.66849/jiads.v1i1.8
BibTeX
@article{Hamad2026,
author = {Hamad, Qusay Shihab},
title = {Efficient Industrial Casting Inspection using Deep Transfer Learning},
journal = {Journal of Informatics and Advanced Data Science},
year = {2026},
volume = {1},
number = {01},
pages = {52--61},
doi = {10.66849/jiads.v1i1.8}
}
EUVIMED