Detection and Classification of Surface Cracks Using Deep Learning Based Autoencoders in Eddy Current Testing

Industrial equipment subjected to rigorous conditions of high speed and pressure leads to the development of cracks on metal surfaces. These cracks reduce the service life and threaten the safety of parts, and the deeper the crack, the greater the resulting damage. Crack detection and crack depth evaluation continue to take center stage in quantitative non-destructive testing and evaluation (NDT&E 4.0). The accuracy of the rotating uniform eddy current (RUEC) probe in achieving fast and efficient detection of surface cracks is corroborated by a comparison with previous experimental results. Next, accurate crack depth classification is achieved by building deep learning model based on a sparse autoencoder (SAE) and a multi-layer perceptron (MLP) model. These classifiers are combined with eddy current testing (ECT) data, including the normal magnetic component Bz. As a result, evaluation metrics such as accuracy increased by up to 100% with both precision and recall scores of 1 for the deep sparse autoencoder classifier compared to MLP performance. The originality of our approach is evident in the application of deep SAE, which achieves high classification accuracy. Furthermore, the integration of our high-resolution NDT&E RUEC probe with advanced machine learning models for depth classification is both novel and impactful. This unique combination offers a comprehensive framework for crack analysis, from precise detection to detailed characterization.