Weld Defect Detection From Imbalanced Radiographic Images Based on Contrast Enhancement Conditional Generative Adversarial Network and Transfer Learning

When a sensor data-based detection method is used to detect the potential defects of industrial products, the data are normally imbalanced. This problem affects improvement of the robustness and accuracy of the defect detection system. In this work, welding defect detection is taken as an example: based on imbalanced radiographic images, a welding defect detection method using generative adversarial network combined with transfer learning is proposed to solve the data imbalance and improve the accuracy of defect detection. First, a new model named contrast enhancement conditional generative adversarial network is proposed, which is creatively used as a global resampling method for data augmentation of X-ray images. While solving the limitation of feature extraction due to low contrast in some images, the data distribution in the images is balanced, and the number of the image samples is expanded. Then, the Xception model is introduced as a feature extractor in the target network for transfer learning, and based on the obtained balanced data, fine-tuning is performed through frozen-unfrozen training to build the intelligent defect detection model. Finally, the defect detection model is used to detect five types of welding defects, including crack, lack of fusion, lack of penetration, porosity, and slag inclusion; an F1-score of 0.909 and defect recognition accuracy of 92.5% are achieved. The experimental results verify the effectiveness and superiority of the proposed defect detection method compared to conventional methods. For other similar applications to defect detection, the proposed method has promotional value.

Automated summary

In this study, a welding defect detection method using generative adversarial network combined with transfer learning is proposed to address the issue of data imbalance in industrial product defect detection. A new contrast enhancement conditional generative adversarial network model is introduced for global resampling of X-ray images, balancing data distribution and expanding sample size. By utilizing the Xception model for feature extraction and fine-tuning through frozen-unfrozen training, an intelligent defect detection model is built, achieving an F1-score of 0.909 and defect recognition accuracy of 92.5% for detecting five types of welding defects. Experimental results validate the effectiveness and superiority of the proposed method for defect detection applications.