Intelligent pattern recognition and diagnosis of ultrasonic inspection of welding defects based on neural network and information fusion

Abstract

The detection of defects in real manual metal arc welds using ultrasonic non-destructive testing has been investigated. Twenty-six features, extracted from three domains, were applied for recognition of defect type. To increase the reliability and accuracy of identification and classification, statistical analysis was used to evaluate the features extracted from ultrasonic defect echoes. The subset of optimum feature was then selected using the method of discriminant analysis. An intelligent defect evaluation method derived from the study is presented. The results show that statistical analysis is an effective method for feature evaluation. The uncertainty of defect diagnosis can be decreased by the information fusion method, and for three specific defect types, defects were correctly identified in approximately 93% of cases.