Two approaches to multi–criteria optimisation of steel alloys for crankshafts production

The paper presents the application of multi–criteria optimisation to steel alloy composition determination aimed at obtaining improved properties material for crankshafts production. Neural network model of steel mechanical characteristics in dependence on amounts of its alloying elements was used for simulation purpose. Two optimisation approaches were applied to find optimal alloys composition. In the first one, several Pareto optimal solutions were found based on those obtained by simulation numerous compositions in the investigated region of interest. The second one used Taguchi method for robust design. The obtained optimal solutions were compared and decision about further production experiments was taken.