Application of neural network to visual sensing of weld line and automatic tracking in robot welding

摘要

In order to make a robust control system to detect weld line and to track the weld line automatically by welding robot with visual sensor, a new control system applied artificial neural network was constructed. Before the image taken was applied to neural network, the LOG filter was applied to an original image to enhance the weld line image, and then a binary image was generated. The binary image was applied to the artificial neural network, and weld line direction was detected. Then the seam tracking was performed using the weld line direction. Because the neural network was used for detecting process of weld line, more robust control system was obtained. Moreover, as the result of seam tracking experiment, the applicability of the system to an automatic welding was confirmed.