Process Modelling and Optimization using ANN and RSM during WSEM of Ni_51.59Ti_48.41 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.

An energy efficiency-based optimization of the rough honing process of hardened 5150 alloy

“…Step 2: The EF, SR, and MRR models are developed regarding process parameters by means of the ANN. 22,23 The ANN approach is named as an advanced processing and modeling technique for the obtained data, in which the biological behaviors of the human brain are simulated and reproduced. The ANN requires a number of layers and neurons, which are connected to produce the neural network.…”

“…Step 2: The EF , SR , and MRR models are developed regarding process parameters by means of the ANN. 22,23…”

Modeling and optimization of WEDM of monel 400 alloy using ANFIS and snake optimizer: A comparative study

“…Raju et al 27 experiments combined the Taguchi technique with a genetic algorithm to predict the WEDM's machining parameters and found that wire feed is the most significant influencing factor on material removal rate and surface roughness. Singh et al 28 used mathematics, ANOVA modeling, 29 tests carried out using the RSM technique, and artificial neural networks to predict the machining parameters. In a similar vein, Rajput et al 29 devised a combination of RSM and a genetic algorithm to evaluate the surface roughness in the hybrid-chemical magnetorheological finishing process.…”