Semi-supervised transfer learning-based automatic weld defect detection and visual inspection

Abstract

Welding is the most used fusing technology in the fabrication process of engineering structures including buildings, industrial facilities, bridges, and vital pipelines. Regular inspection of these welds is important for their overall safety and reliable usage. The need for fully automated, highly efficient structural health monitoring has encouraged researchers to invest their focus on new technologies involving artificial intelligence and computer vision. In this paper, a novel Semi-supervised Transfer learning based Multi-domain learning (ST-MDL) network is proposed for automatic weld image segmentation. Six traditional segmentation models based on U-net architecture have been utilized for comparative analysis with the proposed ST-MDL approach. The best performing model is employed for semantic segmentation of weld images to identify and measure the weld porosity inside a weld image. A novel end-to-end fully automated weld visual inspection framework (W-VIF) has also been proposed, where the measurements of segmented weld images are compared with the American welding society handbook of visual inspection standards to fully automate the process of visual inspection. The results demonstrate that the trained models are capable of identifying and quantifying weld defects, and hence a practical fully automated weld visual inspection procedure is created.