Hilbert–Huang Transform-Based Emitted Sound Signal Analysis for Tool Flank Wear Monitoring

This paper presents an emitted sound signal analysis technique for tool flank wear monitoring based on the Hilbert–Huang Transform (HHT). HHT is a new signal processing technique suitable for analyzing non-stationary and non-linear signals like emitted sound. The need for HHT in this analysis and its principle are explained. The entire experiment was done on a conventional turning machine using carbide insert tools and mild steel work piece. The emitted sound signal during turning process of a fresh tool, a slightly worn tool with 0.2 mm flank wear and a severely worn tool with 0.4 mm flank wear were recorded separately using a highly sensitive microphone under different cutting conditions. Each emitted sound signal is decomposed into several intrinsic mode functions (IMFs) using empirical mode decomposition (EMD). The Hilbert transform is then applied on each IMF to obtain the instantaneous frequencies with time and their amplitudes. Finally, the marginal and the Hilbert spectrums of fresh, slightly worn and severely worn tool sound signals were produced using selected IMFs. From these spectrums, it is found that the increase in tool flank wear resulted in an increase of the sound pressure amplitude. This is also found true for all the different cutting conditions. The results show that the HHT-based emitted sound signal analysis can also be considered as a simple and reliable method for tool flank wear monitoring.