Optimization Process to Develop Tungsten Carbide Reinforced with Aluminium MMCs Using Surface Plots and ANN

Material selected for this study is A356 and four percentage of tungsten carbide (WC) powder for the fabrication of metal matrix composites. In this paper, a methodology is identified to find the co-relating higher order and the interactive influences of different input parameters affecting performance characteristics such as MRR, tool wear rate and surface roughness in wire electric discharge machining process using surface plots and artificial neural network. Voltage, flushing pressure, pulse on time and discharge current are the process parameters needed to be optimized to achieve optimum material removal rate, surface roughness and tool wear rate. Finding the ideal set of process parameters is achieved using artificial neural network which is a supervised machine learning algorithm and results are compared with RSM method. Results show that supervised machine learning technique (ANN) is performing better than the Response surface methodology (RSM) in terms of performance predictions.