Cutting sound signal processing for tool breakage detection in face milling based on empirical mode decomposition and independent component analysis

Owing to the inherent complexity and variability of the machining process, the sound signals of the cutting process are usually polluted by chip breakage signals and environmental noise which makes it very difficult for tool breakage detection based on sound signals. An approach based on empirical mode decomposition (EMD) and independent component analysis (ICA) is presented to deal with the blind source separation problem of cutting sound signals in face milling with the objective of separating cutting oriented sound signals from those background noises. The advantage of EMD is its ability to adaptively decompose an arbitrary complicated time series into a set of components, called intrinsic mode functions (IMFs). With EMD, cutting sound signals in face milling process are composed into a set of IMFs. Using fast ICA to analyze these series, some independent components are obtained, from which different types of sound signals can be extracted. Experimental results show that the proposed EMD-ICA method is capable of separating cutting sound signals in face milling, where different source components related to a normal insert and a broken one are extracted successfully. This makes tool breakage detection possible.