Novel method of in-situ ultrasonic test of aircraft parts

Aerial in-situ test is an important constituent of modern aerial maintenance and repairing technology, which can detect the performance of aircraft structure quickly. Aiming at the low efficiency of the present in-situ test methods, the paper proposed a novel method of in-situ ultrasonic test of aircraft parts. Hilbert-Huang transform (HHT) and support vector machine (SVM) were applied in the method to extract features and classify different defects accurately. The relationship between key parameter C (cost) and sigma (sigma) of SVM and the classification accuracy were calculated, therefore the optimized results were got. Experiments of classification were made and the results illustrated that the features extracted through HHT of the system had good divisibility. The method could classify typical aircraft defects effectively, which had its special advantages on the short training time cost. This would have a promising application in rapid in-situ aircraft test.