UTILIZATION OF ARTIFICIAL NEURAL NETWORKS TO PREDICT THE INFLUENCE OF MILLING TYPE ON THE QUALITY PRODUCT

Abstract

ABSTRACT: During the process milling of piece with complex surfaces, the choice of different CNC machining strategies by the software CAM leads to deviations from the workpiece machined with respect to the designed ideal surface. Knowledge of deviations generated with respect to the final geometry of the piece allows to develop correction in the software modules, based on the different machining strategies, enabling so the executor to generate appropriate corrections before manufacture, so that the finished products are within the design specifications. At the same time, the SIM work in manufacturing processes has been studied by means of the application of artificial neural networks (ANN) as a solution to non-linear problems and conflicting parameters. Therefore, this paper evaluates the influence of the geometry and surface finish of three different milling strategies suggested by CAM software in the manufacture of a product by means of RNA.