An intelligent approach for prediction of angular error in taper cutting using wire-EDM

Abstract

In the present work, a support vector regression (SVR) model is developed to predict the angular error in taper cutting using wire electrical discharge machining (WEDM) process. The model is developed based on the data obtained from experimentation. A set of six important input parameters such as taper angle, part thickness, discharge current, pulse duration, wire speed and wire tension is chosen to conduct the tapering operation in WEDM. The model accuracy is evaluated by the three performance criteria including root mean square error (RMSE), Nash–Sutcliffe efficiency co-efficient (E) and co-efficient of determination (R2). Results show that SVR is an effective and simple approach in comparison to traditional prediction methods. The model provides an inexpensive and time saving alternative to study the angular error in taper cutting before actual cutting operation.