The selection of milling parameters by the PSO-based neural network modeling method

During the past decade, polymer nanocomposites have emerged relatively as a new and rapidly developing class of composite materials and attracted considerable investment in research and development worldwide. An increase in the desire for personalized products has led to the requirement of the direct machining of polymers for personalized products. In this work, the effect of cutting parameters (spindle speed and feed rate) and nanoclay (NC) content on machinability properties of polyamide-6/nanoclay (PA-6/NC) nanocomposites was studied by using high speed steel end mill. This paper also presents a novel approach for modeling cutting forces and surface roughness in milling PA-6/NC nanocomposite materials, by using particle swarm optimization-based neural network (PSONN) and the training capacity of PSONN is compared to that of the conventional neural network. In this regard, advantages of the statistical experimental algorithm technique, experimental measurements artificial neural network and particle swarm optimization algorithm, are exploited in an integrated manner. The results indicate that the nanoclay content on PA-6 significantly decreases the cutting forces, but does not have a considerable effect on surface roughness. Also the obtained results for modeling cutting forces and surface roughness have shown very good training capacity of the proposed PSONN algorithm in comparison to that of a conventional neural network.