The purpose of this study is to examine the postprocessed wire tool surface using scanning electron microscopy and find out the streamlined conditions of input process variables using multi-objective optimization techniques to get minimum wire wear values.
A federated mode of response surface methodology (RSM) and artificial neural network (ANN) is used to optimize the process variables during the machining of a nickel-based superalloy.
The study explores that with the rise in spark-off time and spark gap voltage, the rate of wire tool consumption also escalates.
Most of the researchers used the RSM technique for the optimization of process variables. The RSM generates a second-order regression model during the modeling and optimization of a manufacturing process whose major limitation is to fit the collected data to a second-order polynomial. The leading edge of ANN on the RSM is that it has comprehensive approximation capability, i.e. it can approximate virtually all types of nonlinear functions, including quadratic functions also.
