OPTIMIZATION OF CUTTING FORCE AND TOOL TEMPERATURE USING ANN BASED MULTI OBJECTIVE GENETIC ALGORITHMS IN TURNING HEAT TREATED BERYLLIUM COPPER ALLOY

Economics of machining are mostly influenced by the cutting conditions [14]. The present study investigates the effect of cutting parameters- cutting speed, feed rate, depth of cut, and heat treatment of work material (Be cu alloy) in turning process using uncoated CBN cutting tool. Four outputs of the machining, among which heat treatment is categoric, studied. The outputs are cutting force and cutting tool temperature. Neural Network based Genetic Algorithm approach is used to study the performance characteristics and to find out the optimal cutting parameters of the turning process for heat treated Be-cu alloy. Annealed and hardened Beryllium Copper alloy are used for experiments. Feed rate and cutting speed play the key role in the process since the change of these parameters impart huge impact on cutting tool temperature change. Experimental results prove the effectiveness of this approach. In this study, the main cutting parameters that affect the cutting performance in turning operations and the best combination are determined.