A method for detect welding quality of component arc weld

Abstract

A method for detect welding quality of electric arc weld of component features that a plurality of pictures of different types of weld joints of same component are collected and a sample library is established. One part of the sample library is used as training set and the other part as test set. Template Matching Algorithm Based on Spatial Correlation Method Extracts the Pictures of Target WeldedJoint Areas in samples from Training Set and Test Set; Define the welding joint quality types, label the welding joint quality types of all the pictures in the training set manually, build convolution neural network based on tensorflow frame, input the pictures of all the target welding joint areas in the training set into the convolution neural network, and train the machine learning classifier;Finally, the images of the target welded joint area in each sample image of S test set are classified by the trained machine learning classifier, and the classification result is the corresponding quality type of the welded joint. The invention can quickly find out the quality problem of the component arc welding in the picture.

Description

technical field [0001] The invention relates to the technical field of welding quality detection, in particular to a method for detecting welding quality of component arc welding. Background technique [0002] The welding quality inspection of components refers to the inspection of welding results, the purpose is to ensure the integrity, reliability, safety and usability of the welding structure. [0003] Traditional manual inspection needs to be inspected according to welding structure instructions, technical standards, process documents, construction drawings, etc. The inspection of appearance quality mainly includes dimension inspection, geometric shape inspection, and appearance flaw inspection. Radiographic flaw detection and ultrasonic testing can be used Flaw detection, coloring inspection and other methods for auxiliary detection. [0004] However, there are many deficiencies in the traditional manual detection and classification. Only relying on human eyes and some...

AI Technical Summary

Problems solved by technology

[0004] However, there are many deficiencies in the traditional manual detection and classification. Only relying on human eyes and some inspection rules for detection and classification will inevitably lead to many errors and consume a lot of time and labor on repetitive work.

Auxiliary detection methods such as radiographic flaw detection may have higher costs, so efficient and intelligent component welding quality detection and classification methods have become an important demand in current actual production

Images