APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO EVALUATE WELD DEFECTS OF NUCLEAR COMPONENTS

Artificial neural networks (anns) are computational representations based on the biological neural architecture of the brain. anns have been successfully applied to a wide range of engineering and scientific applications, such as signal, image processing and data analysis. although radiographic testing is widely used for welding defects, it is unsuccessful in identifying some welding defects because of the nature of image formation and quality. neoteric algorithms have been used for the purpose of weld defects identifications in radiographic images to replace the expert knowledge. the application of artificial neural networks in noise detection of radiographic films is used. radial basis (rb) and learning vector quantization (lvq) were applied. the method shows good performance in weld defects recognition and classification problems.