Quality control plays a critical role in modern manufacturing. With the rapid development of electric vehicles, 5G communications, and the semiconductor industry, high-speed and high-precision detection of surface defects on silicon carbide (SiC) wafers has become essential. This study developed an automated inspection framework for identifying surface defects on SiC wafers during the coarse grinding stage. The complex machining textures on wafer surfaces hinder conventional machine vision models, often leading to misjudgment. To address this, deep learning algorithms were applied for defect classification. Because defects are rare and imbalanced across categories, data augmentation was performed using a Wasserstein generative adversarial network with gradient penalty (WGAN-GP), along with conventional methods. An improved YOLOv8-seg instance segmentation model was then trained and tested on datasets with different augmentation strategies. Experimental results showed that, when trained with WGAN-GP–generated data, YOLOv8-seg achieved mean average precision values of 87.0% (bounding box) and 86.6% (segmentation mask). Compared with the traditional WGAN-GP, the proposed model reduced Fréchet inception distance by 32.2% and multiscale structural similarity index by 29.8%, generating more realistic and diverse defect images. The proposed framework effectively improves defect detection accuracy under limited data conditions and shows strong potential for industrial applications.
Huang et al. (Thu,) studied this question.