An active vision sensing method for welded seams location using “circle–depth relation” algorithm

Abstract

In order to meet the requirement of welded seams location and seam tracking, vision sensor based on circular laser trajectory has been developed and three-dimensional information of welded seams can be calculated in real- time, escaping from shortcomings of less information, explain ambiguity and single tracking direction for “spot” or “line” laser vision sensors. We put forward three vital angles (cone angle α, deflection angle β, and off-axis angle γ) so that welded seams could be described using three-dimensional information. On this basis, a mathematical model of depth recovery according to “circle–depth relation” algorithm is constructed. The relation of depth values and off-axis angle γ under gas tungsten arc welding (GTAW) experiment condition is addressed by real experiment and the characteristic points of welded seams is described and located. Mean square error (MSE) was used to analyze the recovery precision. The results show: (1) Depth recovery for butt joint with V-groove (60°), butt joint with gap, lap joint, corner joint (120°), circular welded seams and ramp welded seams are realized and the recovery accuracy is compulsory for GTAW process; (2) Welded seams can be located very well using proposed vision sensor based on circular laser trajectory; and proposed vision sensor manifested a promising result with high precision and high efficiency.