Automatic laser welding defect detection and classification using sobel-contour shape detection

This paper describes a detection of common defects in laser welding of structural aluminum alloy. to overcome these problems,a technique has been proposed to detect defects automatically and effectively using the image segmentation technique. although,this technique has been well developed,it does suffer from several disadvantages of radiographic images taken to be poor in quality,as well as the microscopic size of the defects together with poor orientation relatively to the small size and thickness of the evaluated parts. using image segmentation algorithm allows the defects to be automatically inspected and measured within the welded surface such as cracks,porosity and foreign inclusions,which may be weakening the welded parts. this paper proposes a system to automatically identifies and classifies the faults from the welding process by using the existing image segmentation algorithms. the output of the developed system produces a measured analysis which can be then used to describe the mechanical properties of welded part of the alloy such as its tensile and force. the benefits of this project will improve the welding process to reduce faults and defects for both constructing and manufacturing fields.