multi-objective optimization of surface roughness and material removal rate using an improved self-adaptive particle swarm optimization algorithm in milling process

Surface roughness is one of the main characteristics of a work piece in the quality control process. several parameters such as cutting tool material and geometry, cutting parameters, work piece material properties, machine tool and coolant type affect the surface quality. an important task of process planners is the proper selection of three main cutting parameters: cutting speed, feed rate, and depth of cut in order to have not only low surface roughness, but also to perform the process within a reasonable amount of time. in this paper, using full factorial experiment design, the multiple regression equation for the surface roughness in the climb milling process of din 1.4021 martensitic stainless steel has been obtained and then used as one of the objective functions in the multi-objective improved self- adaptive particle swarm optimization (misapso) algorithm. this algorithm has been used to obtain cutting parameters to achieve low surface roughness simultaneously with a high material removal rate. the relatively new algorithm misapso developed with some changes in the common particle swarm optimization (pso) technique, has been used in multi-objective optimization of machining processes and was shown to be able to help the process planners in selecting cutting parameters.