A teaching-free welding position guidance method for fillet weld based on laser vision sensing and EGM technology

Abstract

Position guidance plays an essential role in guaranteeing welding quality. However, the current position guidance methods usually rely on the teaching trajectory or a similarly designed weld path. The innovation of this manuscript is to establish a teaching-free position guidance method combining the position detected by laser vision with the data bidirectionally sent by externally guided motion (EGM) at a high rate. A feature point extraction method based on Steger algorithm and slope determination is proposed. A dense zig-zag path is generated according to the position guidance based on EGM. Meanwhile, the position guidance experiments for fillet weld (horizontal deflection angle α = 9.2°, 13.3° and vertical deflection angle β = 5.5°, 9.2°) are finished. The mean absolute error (MAE) of position guidance in the Y-axis and Z-axis can be controlled in 0.21 and 0.13 mm, respectively. Moreover, the robot welding experiments for fillet weld in three different horizontal and vertical deflection angles (α = 30°, β = 25°, α = 30° and β = 25°) show that this method can obtain good weld surface morphology and metallographic morphology, and have a potential application value in industrial automation.