Study On The Visual Model Theory And Experiments For Measurement Of The Weld Seam Deviation During The Arc Welding Process

Seam tracking technology is one of the important research issues in the field of theautomation of arc welding process, and accurate seam tracking can improve the weld quality.The technology of seam deviation detection, which is the deviation between the seam center andthe arc, is one of the key to realize accurate seam tracking. Nowadays there are many sensorsapplied in weld automation, and the machine vision sensor has become the most prospectivesensor for its special advantage.The traditional method of seam tracking based on machine vision is to catch weld imagereal time by CCD (Charge Couple Device) vision, and the information between the weld poolcenter and the seam has been acquired through image processing, whose dispersion reflects thedeviation between the arc and the seam at the moment. The thesis, which is different from thetraditional method getting the seam deviation information only by image processing, chooses aweld pool process region which includes the foreside of weld pool and the seam in front of thepool. Then the centroid of weld pool image is made as the characteristic parameter to analyze theseam deviation. And the new method is researched on how to set up the seam deviationmeasurement visual model by the pool characteristic parameters.The thesis has been researched by a set of seam tracking experiment apparatus, whichincludes the CCD sensor, the working platform, and the step drive control system and so on.Firstly the thesis researches the seam recognition technology of welding images. And theposition of the seam has been acquired by the morphology, which can supply the bases to realizethe demonstration welding.However, there are some disadvantages in the demonstration weld seam tracking system.So the thesis researches new methods to realize the real time seam tracking. Several experimentsunder different welding conditions have been undertaken in order to analyze the relation betweenthe centroid's dispersion of the process region and seam deviation. The relation model betweenthem has been set up using the linear regression analysis. And the model's salience andgenerality have been tested.In order to analyze other factors' influence to seam deviation, the weld pool characteristic parameters, which are the dispersion of pool centroid, the centroid's displacement and thecentroid's speed, have been chosen as input data. And the visual model between the seamdeviation and weld pool characteristic parameters has been set up using the neural networktechnology. Finally, the visual measurement model's accuracy and generality have been tested,and the result shows that the method has the signification of the theory and the realism.