This study analyzed acoustic emission (AE) signals generated during ultrasonic machining of SiC cathodes and evaluated classification performances of various machine learning models. AE data were collected in both waveform and hit formats, enabling signal characterization through statistical analysis and frequency domain examination. Various machine learning models, including XGBoost, KNN, Logistic Regression, SVM, and MLP, were applied to classify machining states. Results showed that XGBoost achieved the highest classification accuracy across all sensor positions, particularly at the upper part of the worktable with an accuracy of 98.35%. Additional experiments confirmed the consistency of these findings, highlighting the influence of sensor placement on classification performance. This study demonstrates the feasibility of monitoring AE-based machining state using machine learning and emphasizes the importance of sensor placement and signal analysis in improving classification accuracy. Future research should incorporate defect data and deep learning approaches to further enhance classification performance and process monitoring capabilities.

The guided ultrasonic wave has the advantage of diagnosis on a wide area within in a short time due to the long distance propagation characteristic. However, there are many difficulties in signal analysis due to the mode conversions in the reflection from the defect and boundaries. In the use of guided waves for structure monitoring, it is necessary to understand the relation between the propagation mode and the mode of variation according to the shape of the defect. In this study, the characteristics of induced ultrasonic mode conversion is analyzed in taper defects formed from the surface of an aluminum plate. The defect depths of the plate thickness are 20, 50, and 80% and the characteristics of the reflection and transmission modes are analyzed on various defect widths, depending on the angle of change of the tapered shape. The A0 and S0 modes were selected as the excitation mode of the guided waves, the transmission and reflection coefficient amplitudes are analyzed. It is confirmed that the wavelength of the excitation mode having a large influence on the amplitude of the transmission and reflection signals generated by the taper defects depend on the shape of the defect.