Optimization of Surface Roughness Based on Multi-Linear Regression Model and Genetic Algorithm

Abstract

During the high-speed milling operations of 7050-T7451 aluminum alloy using solid carbide end mills, helical angle, axial and radial depth-of-cut have significant effects on the milling uniformity. A surface roughness predictive model of work-piece was developed by using a full-factorial experimental design and multi-linear regression technology. Genetic algorithm was utilized to optimize the helical angle and cutting parameters by means of a series of operations of selection, crossover and mutation based on genetics. The result shows that it is possible to select optimum axial depth-of-cut, radial depth-of-cut and helical angle for obtaining minimum cutting force and reasonably good metal removal rate.