To The Study of Flushable Sensors for Classification of Tool Conditions

The machine learning techniques used for the purpose of classifying tool conditions. Using these techniques, we can choose the best classifier for time domain vibration and AE signature and evaluate the classification efficiency. The time domain signatures acquired at the first stage of the inquiry do not include the frequency data. These wavelet coefficients are used in machine learning techniques for tool condition classification. To determine the frequency content, the original AE and vibration signals are first converted from the time domain to the frequency domain using Fast Fourier Transform. The statistical data is derived from the frequency domain features of vibration and acoustic emission. improving the reliability of machine learning systems using sensor fusion technologies. Acoustic emission signals and vibrations are combined at the feature level to enhance the classification performance using Machine Learning algorithms.