Chatter Monitoring of Machining Center Using Head Stock Structural Vibration Analyzed with a 1D Convolutional Neural Network

Abstract

Real-time chatter detection is crucial for the milling process to maintain the workpiece surface quality and minimize the generation of defective parts. In this study, we propose a new methodology based on the measurement of machine head stock structural vibration. A short-pass lifter was applied to the cepstrum to effectively remove components resulting from spindle rotations and to extract structural vibration modal components of the machine. The vibration modal components include information about the wave propagation from the cutter impact to the head stock. The force excitation from the interactions between the cutter and workpiece induces structural vibrations of the head stock. The vibration magnitude for the rigid body modes was smaller in the chatter state compared to that in the stable state. The opposite variation was observed for the bending modes. The liftered spectrum was used to obtain this dependence of vibration on the cutting states. The one-dimensional convolutional neural network extracted the required features from the liftered spectrum for pattern recognition. The classified features allowed demarcation between the stable and chatter states. The chatter detection efficiency was demonstrated by application to the machining process using different cutting parameters. The classification performance of the proposed method was verified with comparison between different classifiers.