Effective approaches to extract features and classify echoes in long ultrasound signals for metal shafts

Abstract

A-scans from ultrasonic testing of long shafts are complex signals, thus the discrimination of different types of echoes is of importance for non-destructive testing and equipment maintenance. Research has focused on selecting features of physical significance or exploring classifier like Artificial Neural Networks and Support Vector Machines. This paper summarizes and reports on our comprehensive exploration on efficient feature extraction schemes and classifiers for shaft testing system and further on the diverse possibilities of heterogeneous and homogeneous ensembles.