Quantitative Acoustic Resonance Testing based on Synthetic Training Data

Acoustic resonance testing (ART) is a nondestructive testing method based on the analysis of intentionally excited natural vibrations of the parts to be inspected. ART leverages the fact that structural anomalies or macroscopic defects are reflected in the natural vibration characteristics of defective test objects. The corresponding test decisions are typically made using a specific classifier, which has been derived from training data generated by measurements on several representative parts. However, the experimental generation of suitable training data is often time-consuming and, due to various practical limitations, the number of data sets may be too small, and the distribution of component properties may be poorly conditioned.