Physics-supported Bayesian machine learning for chatter prediction with process damping in milling

Abstract

Chatter stability of milling operations is a complicated phenomenon causing serious productivity issues in the manufacturing industry, yet a shop-floor implementable solution is lacking. This paper follows a physics-supported Bayesian machine learning approach and incorporates the potential effect of process damping on the stability of the process. Using a likelihood function based on the Nyquist stability criterion, the learning system monitors the actual stability state of the process during arbitrary cuts and refines the underlying model parameter uncertainties in the structural dynamics, cutting force coefficients, as well as the process damping. The framework can operate with limited training data and display the remaining uncertainties in stability predictions to the machine operator. Experimental case studies show the effectiveness of the proposed method and highlight the importance of considering process damping for certain endmills.