Time-Frequency Distribution and Nonlinear Model-Based Virtual Torsional Vibration Sensor for Milling Insert Wear Assessment

Abstract

This study establishes the utility of torsional vibration, time-frequency analysis, and neural networks for on-line estimation of the extent of flank wear in a milling insert. First, a time-frequency distribution, i.e., a Choi-Williams distribution, is calculated from the torsional vibration of a milling machine spindle. Second, scattering matrices and orthogonalization are employed to identify the time-frequency components that are best correlated to the extent of wear. Third, a neural network is trained to estimate the extent of wear from these critical time-frequency components. To reduce the cost of the system, a nonlinear model-based virtual sensor is developed to eliminate the need for a permanent torsional vibration sensor, which is more expensive and bulky than the translational vibration sensor. Experimental results have shown the usefulness of the proposed solution.