| This study establishes the utility of torsional vibration, order tracking, time-frequency analysis, neural networks, and a wear model for on-line estimation and prediction 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 synchronized averaged 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. Fourth, to reduce the cost of the system, a nonlinear model-based virtual sensor is developed to estimate torsional vibration from translational vibration. The virtual sensor eliminates the need for a permanent torsional vibration sensor, which is more expensive and bulky than the translational vibration sensor. Fifth, a future wear forecasting method integrating a wear model and a future state predictor is established. Experimental data from cutting tests is used throughout the study to validate and evaluate the proposed methods. |
