Research on milling chatter identification of thin-walled parts based on incremental learning and multi-signal fusion

Chatter is a kind of self-excited vibration that often occurs in the milling process of thin-walled parts. It has become the main factor restricting production efficiency and quality. Due to the occurrence of chatter, the signal becomes more complex and unstable. To realize milling chatter detection of thin-walled parts, a method based on variational modal decomposition (VMD) and nonlinear dimensionless index is proposed by using the multi-sensor signal fusion and complementarity method to analyze the characteristics of signals from the time-frequency domain. Firstly, VMD decomposes the force signal and acceleration signal to obtain a series of intrinsic mode function (IMF) components. When chatter occurs, the energy is transferred to the chatter frequency band. Each IMF signal's nonlinear energy entropy (EE) is extracted to construct the feature vector. A chatter identification model is established based on multi-sensor signal fusion and support vector machine. To solve the problem of model updating, supervised learning and unsupervised learning are combined to provide a method for chatter detection.