Abstract:
Hybrid machining processes (HMPs) have attracted the attention of investigators from both academia and industry due to their enhanced process performance and capabilities while machining so-called difficult-to-cut materials. In this paper, the dual approach of Artificial Neural Network (ANN) and Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) was used to model and optimize a new HMP called as Abrasive Mixed Electro Discharge Diamond Grinding (AMEDDG). Due to complex nature of AMEDDG process, the choice of an appropriate coalition of input factors is an effortful job for machinist. The central composite rotatable design was used to plan the experiments and ANN model was established to observe the effect of input machining parameters viz. Wheel speed, powder concentration, pulse current, and pulse-on-time on material removal rate (MRR) and average surface roughness (Ra). The established ANN model was found to be capable of forecasting the output responses within tolerable limits for the chosen set of machining parameters. An ANN-NSGA-II based dual approach was applied for multi-objective optimization of control factors in AMEDDG, and experimental validation directs that optimal data was in tolerable limits.
