Vision-based online measurement method for weld joint forming characteristics of thick plate T-shaped joint

Abstract

The invention provides a vision-based online measurement method for weld joint forming characteristics of a thick plate T-shaped joint. Fusion depth, fusion width and sectional area of weld joint forming can be measured on line. The method comprises steps as follows: firstly, according to an extracted weld joint contour, designing a weld joint contour characteristic point recognition algorithm based on a slope mutation and supervision method, and realizing detection for characteristic points; secondly, proposing a method based on cubic exponential smoothing to carry out fault diagnosis by aiming at the influence of various random interferences in welding on weld joint contour characteristic point detection, and further obtaining effective characteristic points; and finally, calculating thefusion depth, the fusion width and the sectional area of the weld joint on line by using the weld contour and the characteristic points extracted before welding and during welding and adopting a high-order nonlinear fitting method. By effectively measuring the weld joint forming characteristics, weld joint forming can be controlled, and then online monitoring for the welding quality is realized.The method has the advantages of time consumption reduction, high measurement precision, high robustness and the like.

Description

technical field [0001] The invention relates to a vision-based on-line measurement method for weld formation characteristics of thick plate T-shaped joint welding, and belongs to the technical field of multi-layer and multi-pass weld formation detection. Background technique [0002] One of the keys to welding quality is to control the shape of the weld to achieve the required filling. Weld formation is related to multiple heterogeneous influencing factors. In a specific welding scenario, welding process parameters are the key factors affecting weld formation. The automatic and intelligent robot welding process needs to adjust the welding process parameters according to the weld forming characteristics, so as to realize the online monitoring of welding quality. Therefore, the effective measurement of weld forming characteristics helps to promote the automation and intelligence of the welding process. [0003] At present, the online measurement of weld forming features most...

AI Technical Summary

Problems solved by technology

The feature points of the weld seam contour, the shape of the weld seam and the filling area of ​​the thick plate T-shaped joint are variable, and the detection of the seam shape features based on the visual method is easily disturbed by the electromagnetic field, strong arc light and welding torch vibration. presents a challenge to current methods to accurately obtain weld shape features

Images