Efficient optimization of process parameters in 2.5 D end milling using neural network and genetic algorithm

Abstract

The study aims at design and development of an integrated system to model and optimize the cutting parameters for identifying and controlling the parameters so as to achieve high level performance and quality in the 2.5 D end milling process. Taguchi’s method is used for experimental design to find out the critical parameters in the 2.5 D end milling process. An optimized artificial neural network (ANN) based on feed-forward back propagation was used to establish the model between 2.5 D end milling parameters and responses. Genetic algorithm (GA) was utilized to find the best combination of cutting parameters providing lower temperature rise in the work piece (Al 6061 T6). As fitness function of GA the output of ANN is used in the study. Cutting parameters include speed, feed, depth of cut and step over. Parameters found out by GA were able to lowers the minimum temperature rise from 19.7 to 17.2 °C with almost 13% decrease. Both the modeling and optimization process was found satisfactory. Also the GA has emerged as an effective tool to optimize 2.5 D end milling process parameters. © 2018, The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden.