Shape-based defect classification for Non Destructive Testing
This work addresses defect classification in aerospace structures for non-destructive testing, but it is incremental as it applies existing machine learning methods to a specific domain with shape-based features.
The paper tackled the problem of classifying aerospace structure defects detected by eddy current non-destructive testing by using impedance plane analysis to extract shape-based features and testing with machine learning classifiers, achieving competitive results against existing descriptors as measured by accuracy, sensitivity, specificity, precision, and Matthews correlation coefficient.
The aim of this work is to classify the aerospace structure defects detected by eddy current non-destructive testing. The proposed method is based on the assumption that the defect is bound to the reaction of the probe coil impedance during the test. Impedance plane analysis is used to extract a feature vector from the shape of the coil impedance in the complex plane, through the use of some geometric parameters. Shape recognition is tested with three different machine-learning based classifiers: decision trees, neural networks and Naive Bayes. The performance of the proposed detection system are measured in terms of accuracy, sensitivity, specificity, precision and Matthews correlation coefficient. Several experiments are performed on dataset of eddy current signal samples for aircraft structures. The obtained results demonstrate the usefulness of our approach and the competiveness against existing descriptors.