A Deep Learning-Based Weld Defect Classification Method Using Radiographic Images With a Cylindrical Projection

Abstract

Welding defect detection based on radiographic images plays a vital role in industrial nondestructive testing. It provides an effective guarantee with respect to welding quality in shipbuilding, chemical industry, and aerospace applications. A variety of related computer-based image processing technologies have been designed for the detection of weld defects. However, this is a challenging task because weld defects can exhibit different shapes, sizes, positions, and contrasts in radiographic images. This article proposes an end-to-end weld defect recognition method that mainly includes three steps. In the first step, we propose an improved algorithm based on deep belief network (DBN), which classifies weld feature curves extracted by applying infinite norm for detecting defective weld base on radiographic images. In the second step, a new cylindrical projection method is proposed to increase the proportion of defect parts in the images and solve the problem of loss of defects with small size. And in the third step, we propose an improved deep learning network that is based on SegNet to identify weld defects. Experimental verification shows that this method can realize end-to-end weld defect recognition and strong robustness. Compared with existing methods, this method exhibits obvious advantages and can effectively assist inspectors in welding defect detection and significantly improve the detection efficiency of industrial nondestructive testing.