An inclusive parametric study for performance improvement in WEDM process of pure titanium using Naive Bayes classifier

Abstract

Abstract Titanium alloys have exceptional hardness and high toughness, which can cause significant challenges in traditional machining. Wire-electrical discharge machining (WEDM) process offers excellent accuracy and high precision compared to conventional machines. Design of experimental (DOE) technique provides a systematic way to conduct the experimental runs with the least trials by saving time and cost. Thus, the current work focuses on the modelling of WEDM process at numerous input process environments using Taguchi and BBD-RSM approach. The variable input factors of WEDM process include pulse-on-time (Ton), pulse current (Ip), and pulse-off-time (Toff), whereas the response measures of material removal rate (MRR) and surface roughness (SR) were taken. The performance and adequacy of Taguchi and BBD-RSM models were assessed by using ANOVA, coefficient of determination (R2), and residual plots. The effect of WEDM factors on performance measures was studied by using main effect plots. Based on Entropy criterion, the weights of MRR and SR response factors were computed to, in turn, 0.52 and 0.48. The practical tests defined in the DOE along with the MRR and SR were considered as inputs to the Naive Bayes (NB) predictive model. The prediction findings indicated the appropriate performance of the NB algorithm. The authors believe that the present study, which compares DOE techniques and their application in predicting process outcomes using Naive Bayes classifier, will be useful for users in different domains and various applications.