Objective optimization of drilling of hybrid aluminium metal matrix composites using ANN NSGA- II hybrid approach

Drilling is an important manufacturing process used for hole generation. Drilling of composite materials incorporating with hard ceramic particles, is very difficult to machine. So, the optimization of drilling operations is one of the most effective ways to enhance machining efficiency. This work presents a comprehensive analysis on optimization of drilling process parameters using a metaheuristic optimization technique for the machining of Fly Ash-bagasse Ash-SiC reinforced hybrid aluminum composite fabricated using stir casting process. The holes are drilled using conventional machining techniques following the L27 Taguchi orthogonal experimental array. Neural network based predictive models were widely used to capture trends in the experimental space with high degrees of accuracy and reliability. In this present work, a feed forward artificial neural network (ANN) is used to develop a model of complex relationship between independent machining parameters and dependent responses like material removal rate (MRR) and surface roughness (SR). The best model is found based on mean square error (MSE) and R- square value. The best model is then used as the fitness function in genetic algorithm (GA) to predict optimal machining parameters to simultaneously optimize MRR and SR. Combining the best ANN model with the NSGA-II, 35 sets of optimal parameters were found. Operators can select any process parameters for performing drilling to get optimal output responses.