Study on tool wear and optimization of machining parameters in laser-assisted fast tool servo machining of glass-ceramic

Abstract

Glass-ceramic is difficult to be ultra precision machined due to its high hardness and brittleness. Laser-assisted fast tool servo machining (LAFTSM) of glass-ceramic optical free-form surface was carried out with tool wear as the characteristic value to study the machining quality of glass-ceramic. Orthogonal experiments on LAFTSM were conducted using the Taguchi method (TM). The range of tool wear reduction obtained by comparing laser-assisted machining (LAM) with fast tool servo (FTS) machining is 48.83%–64.12%. The order of contribution of each machining parameter obtained through variance analysis to the reduction of tool wear is: spindle speed > laser power > feed rate > piezoelectric frequency. The optimal combination of machining parameters that can minimize tool wear obtained through signal-to-noise ratio (S/N) analysis is: spindle speed 55 rpm, feed rate 0.01 mm/rev, piezoelectric frequency 8 Hz, laser power 75 W. Artificial neural network (ANN) and genetic algorithm (GA) were used to fit and optimize the machining parameters and experimental results in TM orthogonal experiments. The fitting values of ANN are highly consistent with the orthogonal experimental results. The optimal combination of machining parameters obtained after GA optimization analysis is: spindle speed 50 rpm, feed rate 0.015 mm/rev, piezoelectric frequency 4 Hz, laser power 75 W. Experiments were conducted using the optimal combination of machining parameters of TM and ANN, the results showed that ANN performs better than TM in predicting minimum tool wear and optimizing machining parameters. This study provides a reference for LAFTSM and the research methods of tool wear.