ARTIFICIAL NEURAL NETWORK AND PARTICLE SWARM OPTIMIZATION HYBRID INTELLIGENCE FOR PREDICTING CUTTING FORCE DURING HARD TURNING OF H13 TOOL STEEL WITH MINIMAL CUTTING FLUID APPLICATION

The manufacturing industry in the modern era is striving and thriving hard to be cost competitive and efficient by employing innovative techniques. One such strategy which can make improved operational performance is hard turning. Hard turning process allows a shop floor to turn heat-treated workpiece with hardness over 45 HRC directly to the final size and shape. Hard turning requires a huge supply of cutting fluid to enhance its cutting performance. Petroleum-based emulsions are in regular use for metal cutting as these fluids improve the quality of the finished products and increase productivity by cooling and lubricating but their uses are being questioned nowadays as they create several environmental and health issues. Hence, from the ecological and health point of view, dry machining is the best logical alternative as it is free from the health issues related to operators in the shop floor and the contamination of water and air. However, dry machining is not efficient for many metal cutting operations as it affects surface finish and reduces tool life. Under such circumstances, the concept of minimal cutting fluid application (MCFA) proves itself as a possible solution. The present study aims to investigate the effect of minimal cutting fluid application while hard turning of H13 tool steel. An Artificial Neural Network (ANN) model was developed for the prediction of cutting force and its ability to predict cutting force (Fz) was analyzed. An effort has also been made to optimize the cutting parameters using Particle Swarm Optimization (PSO) to achieve minimum cutting force.