Online weld joint rectification method for arc welding robot based on structured light visual sensing

Abstract

The invention discloses an online weld joint rectification method for an arc welding robot based on structured light visual sensing. The method comprises the following steps: S1, in a welding process,carrying out filter smoothing treatment on a weld joint point detected by a structured light visual sensor to obtain a smooth detection track; S2, establishing a rectification triangle according to atarget point searching criterion, and calculating a deviation value between the current point position of a robot spray gun and the position of the detected weld joint point; and S3, outputting a controlled quantity through a fuzzy controller and the deviation value to obtain a rectification value of the current point of the robot along the weld joint perpendicular direction, wherein the robot isrectified in position according to the rectification value. According to the method disclosed by the invention, the dynamic property of rectifying the tail end of the spray gun can be controlled according to the deviation value, the speed along the weld joint direction is steady, and relatively high response is available in the direction perpendicular to the weld joint. In the rectification process, the gesture of the robot is not changed, and the gesture of the robot is kept consistent with the initially demonstrated gesture, so that the continuity, stability and instantaneity of the gesturein the online rectification process are guaranteed.

Description

technical field [0001] The invention relates to the field of robot control, in particular to an online deviation correction method for arc welding robots based on structured light vision sensing. Background technique [0002] Industrial robots are widely used, among which welding robots are one of the most important application fields. At present, welding robots are still mainly based on teaching and offline programming, which are suitable for welding tasks with standard size and shape and accurate positioning of workpieces. However, for workpieces with complex welding trajectories, large dimensional deviations, and poor positioning accuracy, the traditional teaching programming method cannot meet the requirements of welding quality and welding efficiency. The sensor-assisted welding method is currently the main means to solve this problem, and the structured light vision sensor is a better solution. [0003] Structured light vision sensing is a non-contact sensing method ...

AI Technical Summary

Problems solved by technology

However, for workpieces with complex welding trajectories, large dimensional deviations, and poor positioning accurac

Images