Process Modelling and Optimization using ANN and RSM during WSEM of Ni51.59Ti48.41 shape memory alloy

Abstract

Shape memory Ti-Ni alloys have fascinated significantly in recent years since these types of material are intelligent, shape memory and functional materials. These materials find many applications in the engineering and medical fields. In the current study, ‘Ni-Ti’ shape memory alloy (SMA) has been processed by wire spark erosion machining (WSEM). This research article explores the effects of controllable machining variables such as spark on-time, spark off-time, wire feed and servo voltage on productivity, i.e., material removal rate (MRR) and surface integrity. To assess the impact of WSEM controllable factor, a statistical analysis is done. Mathematical modelling and ANOVA study have been conducted after performing 29 experiments based on Box-Behnken design (BBD) of response surface methodology (RSM) technique. Artificial neural network (ANN) modelling technique is used for further prediction of the response. The predicted values obtained from the ANN model shows excellent agreement with experimental outcomes. In this study, the correlation coefficient (R) value is 0.9919, which is very close to unity. It is clearly showing that the prediction accuracy of ANN model is high. Furthermore, scanning electron microscope (SEM) is utilized to assess the microstructure and composition of the WSEMed surfaces. After a critical study, it has been noticed that machined surfaces contain debris, cracks, craters and spherical droplets. In addition, energy dispersive spectroscopy (EDS) analysis has been performed to check the elemental composition on the machined surface.