Seam tracking algorithm based on multi-information sensor of vision and arc

Abstract

With the rapid development of weld sensor technology and signal processing technology,more and more researchers begin to pay attention to the research of the welding process quality control.The multi-sensor information fusion technology is an important method for welding quality control.The technology is applied to the automatic control process of MIG pulse welding quality.This paper captured different description information for the effective feature extraction and transmission with the vision sensor and the arc sensor,which used in multi-sensor information fusion algorithm for seam tracking.The vision sensor obtained image information by industrial Charg-Coupled Device(CCD) for the lateral deviation information of the weld torch,the arc sensor obtained current information by data acquisition card for the height complementary deviation information and lateral redundancy information of the weld torch.The complementary and redundant information of two sensors were used to sensor information fusion on feature level for lateral and height deviation control.The redundant information fusion achieved visual image de-noising,while the complementary information fusion can further improve the seam tracking precision.The experimental results show that the proposed algorithm can improve the welding quality,and thus verify its efficiency and rationality.