FREQUENCY INVARIANT CLASSIFICATION OF ULTRASONIC WELD INSPECTION SIGNALS

Automated signal classification systems are finding increasing use in many applications for the analysis and interpretation of large volumes of signals. Such systems show consistency of response and help reduce the effect of variabilities associated with human interpretation. Thi s paper deals with the analysis of ultrasonic NDE signals obtained dur ing weld inspection of piping in boiling water reactors. The overall a pproach consists of three major steps, namely, frequency invariance, m ultiresolution analysis, and neural network classification. The data a re first preprocessed whereby signals obtained using different transdu cer center frequencies are transformed to an equivalent reference freq uency signal. Discriminatory features are then extracted using a multi resolution analysis technique, namely, the discrete wavelet transform (DWT). The compact feature vector obtained using wavelet analysis is c lassified using a multilayer perceptron neural network. Two different databases containing weld inspection signals have been used to test th e performance of the neural network. Initial results obtained using th is approach demonstrate the effectiveness of the frequency invariance processing technique and the DWT analysis method employed for feature extraction.