Tool wear condition monitoring based on continuous wavelet transform and blind source separation

Prognostics and health management (PHM) for condition monitoring systems have been proposed for predicting faults and estimating the remaining useful life (RUL) of components. In fact, in order to produce quickly, economically, with high quality and reduce machine tool downtime, a new intelligent method for tool wear condition monitoring is based on continuous wavelet transform (CWT) and blind source separation (BSS) techniques. CWT is one of the most powerful signal processing methods and has been widely applied in tool wear condition monitoring. The CWT used to transform one set of one-dimensional series into multiple sets of one-dimensional series for preprocessing. After that, BSS was applied to analyze the wavelet coefficients. The signal energy evolution of each independent source obtained by BSS was used for health assessment and RUL estimation, the idea is based on the computation of a nonlinear regression function in a high-dimensional feature space where the input data were mapped via a nonlinear function. Experimental results show that the proposed CWT-BSS method can reflect effectively the performance degradation of cutting tools for the milling process. The proposed method is applied on real-world RUL estimation for a given wear limit based on extracted features.