The present paper presents a method for weld location extraction in radiographic images. Images are processed line by line by applying fuzzy reasoning based on local pixel characteristics. For each pixel, values of spatial contrast and spatial variance are computed for evaluating the edge fuzzy membership value. The method proposed uses the machine learning approach for knowledge acquisition, which automatically generates fuzzy rules by learning from examples. Using this method, all welds are successfully extracted from 101 radiographic images taken from aluminium alloy welding parts.

No abstract

No abstract

No abstract

To research the feasibility of magneto-optical imaging (MOI) in detecting small and complex defects and to explore the imaging process of MOI detection, the MOI system is used to detect defects with small and complex shapes. And the magnetic field energy accumulation of defects is simulated by Maxwell 3D. Finally, the defect profile is reconstructed according to the magnetic field distribution obtained. Research results show that the reconstructed defect images are basically consistent with the actual magneto-optical images. And there is special magnetic field energy accumulation at the intersection point, inflection point and end point of the complex-shaped defects. MOI is feasible in the detection of complex shapes, and the simulated imaging method has a certain theoretical assistance for MOI detection.