A method is put forward to realize the recognition and guiding of initial welding position.The weld seams are marked with black lines, which simplify the computational complexity of imageprocessing greatly. A two-time template matching method has been advanced to search for the targetpoint, which is simple and has higher calculation speed. According to the depth computing principlewith the special point matching using binocular stereovision, the initial welding position can be con-firmed by calculating the middle point of the perpendicular line of two radials in the space. Taking thewelding of propellant fuel container for example, good results are obtained with the algorithms. Fi-nally, similar method for terminating welding position is also advanced.
Shape from shading(SFS)is an important domain in computer vision.The paper presented an improved algorithm of shape from shading based on a single image according to an existed one.The presented algorithm enhanced the boundary constraints to eliminate the rotation distortion on the border of reconstructed object and introduced the factor of brightness error to weaken the influence irradiance equation’s nonlinearity on reconstructed errors.The reconstructed results verify the performance improvement in terms of accuracy by the input image of a synthetic image and a real image of weld.
Modeling is essential, significant and difficult for the quality and shaping control of arc welding process. A generalized rough set based modeling method was brought forward and a dynamic predictive model for pulsed gas tungsten arc welding (GTAW) was obtained by this modeling method. The results show that this modeling method can well acquire knowledge in welding and satisfy the real life application. In addition, the results of comparison between classic rough set model and back-propagation neural network model respectively are also satisfying.
