Intelligent control welding system based on vision measurement

Abstract

The invention discloses an intelligent control welding system based on visual measurement. An action execution module of the system comprises a robot used for carrying a welding gun to move and conduct welding operation and a positioner used for bearing a weldment. A monocular stereoscopic vision measurement module comprises a first industrial camera and a marking light-emitting strip used for being arranged on the weldment to mark a welded joint. A line laser vision sensor module comprises a line laser transmitter for transmitting laser stripes to the welding site of the weldment and a second industrial camera of which the camera shooting focus rightly faces the welding site irradiated by the laser stripes. The first industrial camera, the second industrial camera and the line laser transmitter are all installed at the execution tail end of the robot. A control unit of the system controls the execution unit. The two welded joint coarse positioning methods based on the model and monocular double-station stereoscopic vision are provided, the problem that welded joint fine positioning and on-line tracking need to manually teach starting point work is solved, and the method is suitable for most of weldments and scenes.

Description

technical field [0001] The invention belongs to the technical field of robot welding, and in particular relates to an intelligent control welding system based on vision measurement. Background technique [0002] As one of the very important technological means in industrial production, welding technology has been widely used in many fields. With the rapid development of science and technology such as computer technology and artificial intelligence, the requirements for the automation and intelligence of welding technology in industrial sites continue to increase, and the use of automatic welding processing systems with welding robots as the main body is increasing. However, limited by the intelligence level of current robots, most robots mainly use "teaching and reproduction" and offline programming when performing welding operations. There are two main disadvantages: [0003] (1) Poor flexibility and heavy workload, it is only suitable for a single welding environment or w...

AI Technical Summary

Problems solved by technology

[0003] (1) Poor flexibility and heavy workload, it is only suitable for a single welding environment or workpiece, if one of the two is changed, it needs to be taught again;

[0004] (2) Poor adaptability, lack of automatic measurement and adjustment capabilities for weld seam changes (such as errors caused by workpiece clamping errors, vibration shifts, welding thermal deformation, etc.) during the welding process, robot teaching or offline programming trajectory and There is a large error between the actual weld trajectory, which affects the welding quality and accuracy

[0008] (3) For weldments with discontinuous or multiple welds, the spatial position of each weld cannot be independently identified;

Images