Single-pass corner milling is common in machining process. Machining quality and cost are the two most important goals for machining process. Machining quality is greatly affected by deformation and mechanical property. Cutting temperature has a very important effect on tool wear, mechanical property, deformation and machining precision. In this paper, cost per volume (CPV) and machining temperature are selected as objectives. To reduce the cost of research, AdvantEdge simulation software was used to simulating the machining process and examined for its accuracy. Comparing the result of AdvantEdge with physical experiments, it showed an average 8% error on CPV and a 6% error on temperature. Given this comparison, simulation data were used to train Kriging model as the surrogate model. Kriging model manifested high accuracy, showing mean error of 6% and 3% in terms of CPV and temperature on validation points. To solve the multi-objective problem, a K-means particle swarm optimization (PSO) was constructed, which outperformed traditional adaptive gird algor (AGA) by finding the better optimal solutions, meanwhile consuming lesser time. Optimization result showed that corner milling should have a low-level spindle speed to ensure low cost and low temperature. High feed rate, cutting depth and cutting width will result in low cost along with high temperature. Optimal parameters should be chosen from Pareto set according to different practical needs. This integrated method manifested its applicability in solving multi-objective problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.