Prediction of EDM process parameters by using Artificial Neural Network (ANN) - A Prediction Technique

Electrical discharge machining (EDM) process, at present is still an experience process, where the selected parameters are often far from the optimum, and at the same time selecting optimization parameters is costly and time consuming.The process parameters include duty cycle, pulse current, pulse on time, electrode type and gap voltage. Experiments were conducted using Taguchi L18 orthogonal array. An Artificial Neural Network (ANN) model which adapts Levenberg-Marquardt algorithm has been set up to represent the relationship between output parameters and input parameters so that optimization results are obtained.The results showed that the ANN model can be used easily for prediction of output parameters and hence helps in optimum selection of machining parameters for the purpose of process planning and optimization of machining parameters in EDM.