Modeling of Electrical Discharge Machining Process Using Conventional Regression Analysis and Genetic Algorithms

An attempt was made to model input-output relationships of an electrical discharge machining process based on the experimental data (collected according to a central composite design) using multiple regression analysis. Three input parameters, such as peak current, pulse-on-time and pulse-duty-factor, and two outputs, namely, material removal rate (MRR) and surface roughness (SR) had been considered for the said modeling. The value of regression coefficient was determined for each model. The performances of the developed models were tested with the help of some test cases collected through the real experiments and were found to be satisfactory. It had been posed as an optimization problem and solved using a genetic algorithm to determine the set(s) of optimal parameters for ensuring the maximum MRR and minimum SR. It was also formulated as a multi-objective optimization problem and a Pareto-optimal front of solutions had been obtained.