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.

In this study, acoustic emission (AE) signals associated with the behavior of materials in the magnesium alloy (Mg AZ31B) tensile test were analyzed. The AE sensor was attached with the material to measure the AE signals. During the tensile experiment, the AE sensor measured the elastic waves generated inside the specimen. The AE parameters, such as, the signal energy, duration, and frequency centroid, were studied. We also analyzed the effect of the materials size and tensile speed on the AE signals. As a result, the lowest frequency centroid value occurred at the yield and fracture points. As the width and length of the specimen increased, the number of hit counts increased and the peak frequency occurred. Other AE parameters, such as, the duration and frequency centroid, were not affected. As the tensile speed increased, the hit decreased and the frequency centroid decreased in the elastic region. It was found that in the detection of the yield and fracture deformation, the number of counts, and frequency centroid were appropriate.