On-line chatter recognition and supression in milling based on smart CNC

The development tendency of manufacturing will be dominated by advanced machine tools which integrate intelligent machining technology. In this paper, the function of signal processing and intelligent control in smart CNC is proposed with the aim of on-line chatter recognition and suppression. To effectively recognize chatter, the algorithm of Estimation of Signal Parameters via Rotational Invariance Techniques (ESPRIT) is used to get the frequency characteristics of acceleration signals, and cutting process could be divided into different states. The model of chatter recognition is built by training a Hidden Markov Model. To implement real-time chatter suppression in CNC kernel, the algorithm of fuzzy control is used to determine the relationship between cutting force and spindle speed, and related cutting parameters could be adjusted timely once the chatter is identified. The model of chatter recognition and proposed smart CNC system are experimentally validated.