Imagen de Portada

Generation of WAAM Defect Images Using a Hybrid CVAE-CGAN: A Data Augmentation Strategy for Small and Imbalanced Datasets

Guardado en:
Publicado en:The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1-6
Autor principal: Yang, Junle
Otros Autores: Yuan, Lei, Mu, Haochen, He, Fengyang, Ding, Donghong, Pan, Zengxi, Li, Huijun
Publicado:
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Materias:
Datasets
Data augmentation
Image resolution
Machine learning
Defects
Intelligent manufacturing systems
Melt pools
Economic
Acceso en línea:Citation/Abstract
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Conference Title: 2025 IEEE 15th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)Conference Start Date: 2025 July 15Conference End Date: 2025 July 18Conference Location: Shanghai, ChinaIn industrial Wire Arc Additive Manufacturing (WAAM)., the scarcity and imbalance of labeled defect images limit the effectiveness of deep learning-based quality inspection systems. This paper presents a hybrid CVAE-CGAN framework designed to generate high-resolution., class-conditional molten pool images for data augmentation in small-sample settings. By combining a conditional variational autoencoder with adversarial training and integrating VGG19-based perceptual loss and sub-pixel convolution, the proposed model produces visually realistic and diverse synthetic defect images. Extensive experiments on a nine-class WAAM defect dataset demonstrate the model's ability to enhance classification performance, especially for underrepresented categories, offering a scalable solution to mitigate data limitations in intelligent manufacturing.
DOI:10.1109/CYBER67662.2025.11168313
Fuente:Science Database