Modelling of an artificial neural network for electrical discharge machining of hot pressed zirconium diboride-silicon carbide composites

Abstract

Modelling is carried out to map the relationship between the input process parameters and the output response, considered in the machining process. To represent real-world systems of considerable complexity, an artificial neural network (ANN) model is often utilized to replace the mathematical approximation of the relationship. This paper explains the methodological procedure and the outcome of the ANN modelling process. The percentage of SiC in the workpiece material, the product of thermal conductivity and the melting point of the tool material, the pulse on time, and the pulse off time are considered as input parameters, while the material removal rate (MRR), the tool wear rate (TWR), roughness, roundness, taper angle and overcut are considered as output responses. The network is trained initially with one neuron in the hidden layer, i.e.,-a 4-4-6 topology is considered for training. In the subsequent phases, the number of hidden neurons in the hidden layer is increased gradually and then the network is tested with two hidden layers with the same number of hidden neurons in the second hidden layer. A feed forward back propagation neural network model with one hidden layer having 35 neurons is found to be the optimum network model (4-35-35-6). The model has the mean correlation coefficient of 0.92408.