Surface Morphology Reconstruction And Quality Detection Of Pipeline Weld

Now,pipeline automatic welding is generally equipped with structural light sensor for seam tracking.And weld forming quality detection is one of the key points in robotic welding.Therefore,research on weld forming quality detection based on linear structured light sensor has great practical value.However,the existing weld forming quality detection based on structured light is mostly carried out on each contour line,and the changes of adjacent contour lines are not properly utilized.For pipeline welds,it is difficult to guarantee the interval of adjacent contour lines when reconstructing the three-dimensional(3D)morphology of the weld surface by line structured light scanning.The weld edge,width and reinforcement extracted from each single contour also exists deviations due to the positioning error of detection platform.Aiming at these problems,this paper presents a weld forming quality inspection method based on 3D reconstruction.And we hope that our findings can be helpful for pipeline automatic welding production.In order to improve the extraction speed of centerline from structured light,it is necessary to extract the region of interest(ROI)according to the first and the last frame in the original image of N frames at the beginning.Then the ROI is corrected by random sampling to ensure that the feature region is always within the ROI in the acquisition process.After Gaussian filtering,median filtering,image binarization and morphological processing,the edge of structured light is extracted by Laplace operator,and the sub-pixel centerline of structured light is obtained by Gray centroid method.Then the mean value of each column is taken as the actual center line position.To calculate the deviation between the axis of the pipeline to be measured and the rotation center of the profiler,feature points were extracted by calculating the changing rate and piecewise fitting,according to the measured results of the profilometer in both horizontal and vertical state.After position and attitude of the platform were corrected and information on weld surface 3D morphology of the pipeline weld surface was reconstructed by numerical calculation and point cloud processing.Aiming at the point cloud outliers,the filtering algorithm is improved by setting the height threshold and outliers were reset.In order to facilitate the follow-up process,the circular seam is treated as a plane in 3D reconstruction.After the base metal plane was fitted by the improved least squares algorithm,the weld edge was extracted by calculating the deviation.The center line of weld is fitted according to the median value of left and right weld toe coordinates.Then move it along the base metal plane to obtain the allowable boundary of the weld edge.Finally,the idealized model was established according to the width and reinforcement of seam to detect the weld forming quality and identify defects,such as excessive weld metal,undercut,lack of fusion.The difficult problem of contour stitching in the reconstruction of the pipeline weld surface based on line structure light can be solved,by correcting the position-posture of the platform and perfecting the detection process.The closer the fitting parameters of the left and right base metal surfaces of the pipeline are,the better the butt joint will be.Compared with the weld edge extraction from each contour,the distribution of weld toe extracted from the 3D reconstruction model is closer to the same plane and more accurate.The closer the actual weld surface contour to the ideal model,the better the weld forming quality will be.When the weld edge is located within the maximum and minimum boundaries and the actual height is lower than the minimum surface of the ideal model,is undercut.In the weld zone,the actual height is higher than the maximum surface of ideal model,means over reinforcement.Ideal model established based on the measured results of 3D reconstruction of pipeline weld surface can be used to make a general assessment of the weld surface forming quality,identify reinforcement,undercut etc.Compared with the detection on the contour of each frame,forming quality measured on the reconstruction results performs well.