Prediction and optimization of process parameters in wire cut electric discharge machining for High-speed steel (HSS)

Abstract

This paper investigates the effect of parameters such as discharge current, power, cutting speed, and spark gap on surface roughness for different thickness of high-speed steel plates in wire cut electric discharge machining. Experiments were performed at different levels of discharge current on different levels of plate thickness and experimental results of surface roughness, spark gap, and cutting speed were taken. Optimum process parameters were found for each thickness of plate experimentally and validated with the Artificial Neural Network (ANN) and Supporting Vector Machines (SVM) models. The ANN and SVM models were developed separately and trained with experimental data. The models were used to predict current, cutting speed and spark gap for required surface roughness and thickness of the plate. The maximum error between the experimental and predicted values was found to be less than 5% for the two models.