Image processing and geometrical analysis for profile detection during pulsed gas metal arc welding

Abstract

This article describes an image analysis algorithm used to detect profiles during arc welding processes. The new algorithm is an aggregation of image processing (segmentation, filtering), computational geometry (alpha shape) and graph theory (cycle detection). It allows to extract precise geometrical profile entities, whether open or closed contours, that could be used for the monitoring of the welding process. The algorithm is shown to be really efficient and could be used for real-time monitoring of gas metal arc welding process.

An extended framework for knowledge modelling and reuse in reverse engineering projects

“…Three segmentation techniques are commonly used. 4,5 First, the region-based technique utilises spatial coherence to organise the mesh into meaningful groups. The best techniques are based on region-group approximation and allow the recognition of simple forms such as planes and cylinders, and spherical and conical surfaces.…”

In situ experimental measurement of temperature field and surface tension during pulsed GMAW

“…It is based on canny numerical filter. Then, an algorithm of geometrical treatment (alpha-shape and graph theory) transforms points to segment and segments to a polygon [11]. This allows getting the virtual center of the drop and so the experimental radius R exp measured at each point of the contour.…”

Transient behaviour of deposition of liquid metal droplets on a solid substrate

“…On Fig. 2, the evolution of the base radius (position of the contact line) of the macro-drop was scanned thanks to image detection of the fluid phase [13]. The first rapid advance of the contact line (in the first 1 s) is mainly due to the creation of the weld pool due to the arc.…”