Classification of Welding Defects in Austenitic Stainless Steel by Neural Pattern Recognition of Ultrasonic Signal

초음파신호의 신경망 형상인식법을 이용한 오스테나이트 스테인레스강의 용접부결함 분류에 관한 연구

The research for the classification of the natural defects in welding zone is performd using the neuro-pattern recognition technology. The signal pattern recognition package including the user's defined function is developed to perform the digital signal processing, feature extraction, feature selection and classifier selection, The neural network classifier and the statistical classifiers such as the linear discriminant function classifier and the empirical Bayesian calssifier are compared and discussed. The neuro-pattern recognition technique is applied to the classificaiton of such natural defects as root crack, incomplete penetration, lack of fusion, slag inclusion, porosity, etc. If appropriately learned, the neural network classifier is concluded to be better than the statistical classifiers in the classification of the natural welding defects.