Method and device for detecting and identifying X-ray image defects of welding seam

Abstract

The invention provides a method and a device for detecting and identifying X-ray image defects of a welding seam. The method comprises the following steps: scanning with vision, performing central-peripheral difference operation, obtaining a grey saliency map, searching focus of attention, and determining a dubious area; and enabling a pixel grey-scale signal in the dubious area to directly pass through a trained layered network depth model by adopting deep learning, and directly identifying by obtaining substantive characteristics in the dubious defection area. According to the invention, image objects are selected and identified in series from strong to weak visual saliency; the efficiency and the accuracy for analyzing and identifying images are increased; and the method is strong in adaptation and good in universality.

Description

technical field [0001] The invention relates to radiography and non-destructive testing, in particular to a method and device for detecting and identifying defects in X-ray images of welds. Background technique [0002] At present, welding is one of the important process methods in the manufacturing field. With the rapid introduction of computer technology, automatic control technology, and information and software technology into the welding field, automation and intelligence of welding production have become an important direction for the development of welding technology in the 21st century. Computer vision technology has been widely used in the field of welding defect detection due to its large amount of information, high precision, and large detection range. X-ray inspection is one of the important methods commonly used in conventional non-destructive testing, and its inspection results will be used as an important judgment basis for weld defect analysis and quality as...

AI Technical Summary

Problems solved by technology

Welding images are ever-changing and defect images vary greatly, how to improve the adaptability and generality of defect detection and recognition methods, etc.; (5) the problem of welding defect classification and recognition methods, there are still many problems in the neural network and support vector machine methods currently used , the correct recognition rate in the experiments of all methods is usually about 85%. If it is aimed at pictures with strong noise and low contrast (such as X-ray welding images), and the defect area is small (such as welding defects), and the experimental Due to the difference between the environment and the actual production environment, the recognition accuracy rate is lower

[0007] Therefore, for the above-mentioned problems existing in related technologies, effective solutions have not yet been proposed

Images