Dual-stage artificial neural network (ANN) model for sequential LBMM-?EDM-based micro-drilling

A sequential process combining laser beam micromachining (LBMM) and micro electro-discharge machining (?EDM) for the micro-drilling purpose was developed to incorporate both methods’ benefits. In this process, a guiding hole is produced through LBMM first, followed by ?EDM applied that same more fine machining. This facilitates stable, efficient regime with faster processing (compared pure ?EDM) much better quality LBMMed holes). Studies suggest strong correlations exist between various input output parameters of process. However, mathematical model maps simultaneously predicts all these from yet be developed. Our experimental study observed finishing operation’s are influenced morphological condition holes. Hence, an artificial neural network (ANN)-based dual-stage modeling method predict process’s outputs. The first stage utilized outputs different parameters. Furthermore, in second stage, LBMM-predicted (such as pilot entry area, exit recast layer, heat-affected zone) were used final prediction (i.e., time ?EDM, stability during terms short circuit/arcing count, tool wear ?EDM). evaluated based on average RMSE (root mean square errors) values individual parameters’ complete set data, i.e., time, wear. mentioned earlier found 0.1272 (87.28% accuracy), 0.1085 (89.15% 0.097 (90.3% respectively.