An automatic flaw classification method of ultrasonic nondestructive testing for pipeline girth welds

As flaw classification is normally manual determination in ultrasonic nondestructive testing field, an automatic identification of flaw type based on Lifted Wavelet Transform (LWT) and BP neural network (BPN) is introduced in this paper. LWT is proposed to extract flaw feature from ultrasonic echo signals, ideally matched local characteristics of original signals. The computational speed and flaw classification efficiency is increased. Then a feature library is constructed. A modified BPN is followed as a classifier, trained by the library. And then when feature is extracted from any other flaw echo, the feature eigenvector is sent to the trained BPN. The output of the BPN is the input flaw signal´s type, realizing automatic flaw classification. For comparison, a Radial Basis Function neural network (RBFN) is tested under the same condition as BPN. Experiment results prove the proposed method, LWT with BPN, is fit for automatic flaw classification.