Ultrasonic flaw detection using Support Vector Machine classification

In this work, a Support Vector Machine (SVM) classifier is introduced for ultrasonic flaw detection based on features extracted from the output of the subband decomposition filters. SVM is a machine learning method used for classification and regression analysis of complex real-world problems that may be difficult to analyze theoretically. A dataset constituting feature vectors of ultrasonic signals containing flaw and no flaw, is created in order to train and test the SVM. A k-fold cross validation technique is then performed to choose the best parameters for classification. Experimental results, using A-scan data measurements from a steel block, show that a very high classification accuracy can be achieved. Robust performance of the classifier is due to proper selection of frequency-diverse feature vectors and successful training.