CNN-Vit: A Hybrid CNN–Vision Transformer Framework for Accurate and Real-Time Welding Defect Classification With GAN-Based Data Augmentation
The American Journal of Engineering and Technology · 10.04.2026 · 08 (04) · 1-11
DOI: 10.37547/tajet/volume08issue04-01 ↗Kurz gefasst
Fachartikel in der Zeitschrift The American Journal of Engineering and Technology, online erschienen am 10.04.2026. Verfasst von Satar Jabbar Kadhim.
Abstract (Originalsprache)
Deep learning–based welding defect classification often faces challenges such as limited training data, class imbalance, and high model complexity, which restrict real-time industrial applications. To address these issues, this paper proposes a hybrid CNN–Vision Transformer framework with GAN-based data augmentation for welding defect classification. First, welding images acquired using a wide dynamic range visual sensor are preprocessed through binarization, median filtering, morphological dilation, and cropping to enhance defect features. A Generative Adversarial Network (GAN) is then employed to generate synthetic samples and alleviate dataset imbalance. A lightweight CNN extracts local spatial features and reduces feature dimensionality, after which the resulting feature maps are converted into tokens and processed by a Vision Transformer encoder to capture global contextual relationships via self-attention. The proposed model classifies welding images into four categories: normal, burn-through, undercut, and welding collapse. Experimental results demonstrate that the hybrid architecture achieves improved classification accuracy and computational efficiency compared with conventional lightweight CNN models. In addition, the model attains 98.25% accuracy on the MNIST dataset, validating the effectiveness of the proposed framework.
Zitieren
APA
Kadhim, S. J. (2026). CNN-Vit: A Hybrid CNN–Vision Transformer Framework for Accurate and Real-Time Welding Defect Classification With GAN-Based Data Augmentation. The American Journal of Engineering and Technology, 08(04), 1-11. https://doi.org/10.37547/tajet/volume08issue04-01
Vancouver
Kadhim SJ. CNN-Vit: A Hybrid CNN–Vision Transformer Framework for Accurate and Real-Time Welding Defect Classification With GAN-Based Data Augmentation. The American Journal of Engineering and Technology. 2026;08(04):1-11. doi:10.37547/tajet/volume08issue04-01
BibTeX
@article{Kadhim2026,
author = {Kadhim, Satar Jabbar},
title = {CNN-Vit: A Hybrid CNN–Vision Transformer Framework for Accurate and Real-Time Welding Defect Classification With GAN-Based Data Augmentation},
journal = {The American Journal of Engineering and Technology},
year = {2026},
volume = {08},
number = {04},
pages = {1--11},
doi = {10.37547/tajet/volume08issue04-01}
}
EUVIMED