Automated weld defect classification from ultrasonic signals using statistical moments on normal distribution curves of wavelet co-efficient

Ultrasonic Testing is a highly reliable Non-Destructive Testing Technique for weld defect characterization. Defects occur either high frequency components (Porosity, Sidewall crack) or as low frequency components (Root, Lack of Fusion, Lack of penetration, slag) in the UT signal. Manual interpretation of these signals is subjective in nature and is dependent on the expertise of the individual. Hence it is necessary to develop automated signal analysis system that classifies the defect. As defect classification is non-linear in nature, neural network based classification techniques are cited in literature. However neural network based techniques are computationally complex and has prediction error. Hence in this paper, an effective range based classification system using statistical moments is proposed. Performance of the proposed technique is measured in terms sensitivity and specificity.