Multi-objective optimization of cutting parameters in turning process using differential evolution and non-dominated sorting genetic algorithm-II approaches


Optimization techniques using evolutionary algorithm (EA) are becoming more popular in engineering design and manufacturing activities because of the availability and affordability of high-speed computers. In this work, an attempt was made to solve multi-objective optimization problem in turning by using multi-objective differential evolution (MODE) algorithm and non-dominated sorting genetic algorithm(NSGA-II). Optimization in turning means determination of the optimal set of machining parameters to satisfy the objectives within the operational constraints. These objectives may be minimum tool wear, maximum metal removal rate or any weighted combination of both. The main machining parameters which are considered as variables of the optimization are cutting speed, feed rate, and depth of cut. The optimum set of these three input parameters is determined for a particular job-tool combination of EN24 steel and tungsten carbide during a single-pass turning which minimizes the tool wear and maximizes the metal removal rate after satisfying the constraints of temperature and surface roughness. The regression models, developed for tool wear, temperature, and surface roughness were used for the problem formulation. The non-dominated solution set obtained from MODE was compared with NSGA-II using the performance metrics and reported.