This paper proposes an optimization methodology for the selection of best process parameters in electro-discharge machining. Regular cutting experiments are carried out on die-sinking machine under different conditions of process parameters. The system model is created using counter-propagation neural network using experimental data. This system model is employed to simultaneously maximize the material removal rate as well as minimize the surface roughness using simulated annealing scheme. Finally consistency of the method is tested with several initial trail values. Results are shown in the form of tables and figures.