Abstract (EN):
In this paper an Artificial Neural Network (ANN) aiming the efficient modeling of a set of
machining conditions in the orthogonal cutting of composite materials is presented. The
experimental procedure considers process parameters as cutting speed and feed rate, the type
of insert of the tool and the type of workpiece material in order to obtain a set of results used
for ANN learning. The supervised learning of the ANN is based on a genetic algorithm with
an elitist strategy. Input, hidden and output layers model the topology of the ANN. The
weights of the synapses, the bias for the hidden and output nodes and the number of neural
nodes of the hidden layer are used as design variables. Sigmoid activation functions are used
in hidden and output layers. The square error between experimental and numerical results is
used to monitoring the learning process aiming to obtain the completeness of modeling of the
machining process.
Idioma:
Inglês
Tipo (Avaliação Docente):
Científica
Nº de páginas:
10