Modeling and optimization of turning process parameters during the cutting of polymer (POM C) based on RSM, ANN, and DF methods

The present work concerns an experimental study dealing with cutting parameters’ effects on the surface roughness, cutting force, cutting power, and productivity during turning of the polyoxymethylene (POM C) polymer. For that, a cutting tool made of cemented carbide was used. The work is divided into three steps. The first one deals with unifactorial tests, where the evolution of the machining parameters (roughness criteria, cutting force components, and cutting power) is investigated by varying cutting speed, feed rater, and depth of cut. The second part concerns the modeling of the output parameters: arithmetic roughness, cutting force, cutting speed, and material removal rate by using the results of a full factorial design (L₂₇). The second step concerns the adoption of the two modeling techniques, which are the response surface methodology (RSM) and the artificial neural network (ANN). The obtained results related to two both techniques are compared in order to discern the most efficient one. The last step of the present research work concerns the multi-objective optimization using the desirability function (DF). The optimization was carried out according to three approaches, which are the “quality optimization,” “productivity optimization,” and the combination between the quality and productivity.