Tool wear status seriously affects the dimensional accuracy and surface quality of the machined parts. Therefore, tool condition monitoring (TCM) is essential in the milling process of aerospace structural parts due to the use of difficult-to-cut materials and complex cutting trajectories. The Higher order spectrum (HOS) was first employed to analyze the vibration signals, and then bispectral features extracted from de-noised signals were used to characterize the tool wear status. The improved Pearson’s correlation coefficient was used for feature selection to reduce the influence of periodic components on feature selection process. Furthermore, a novel objective function was proposed to guide the hyperparameters optimization process of support vector machine based on Bayesian optimization algorithm, in which the effect of imbalanced data on the recognition rates was considered. To demonstrate the effectiveness of the proposed method, a structural part milling experiment was performed on a vertical machining center and vibration signals of spindle were collected. Based on this, an online TCM model was established. The present study suggests that the proposed TCM system is accurate and robust.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.