Modelling of the thrust force of the drilling operation on PA6-nanoclay nanocomposites using particle swarm optimization

This paper presents a new approach for modelling the thrust force in the drilling of PA6-nanoclay (NC) nanocomposite materials, by using a particle-swarm-optimization-based neural network (PSONN). In this regard, the advantages of the statistical experimental algorithm technique, experimental measurements, particle swarm optimization, and artificial neural network were exploited in an integrated manner. For this purpose, numerous experiments for PA6 and PA6-NC nanocomposites were conducted to obtain the thrust force values using a highspeed steel drill 2 mm in diameter with a 1188 point angle. Then, a predictive model for the thrust force was created using the PSONN algorithm. The training capacity of the PSONN was compared with that of the conventional neural network. The results indicate that, when the NC content in PA6 is increased, the thrust force of the drilling operation on this material is decreased significantly. Also, the results obtained about the modelling of the thrust force showed the good training capacity of the proposed PSONN algorithm, compared with that of a conventional neural network.