Optimization of Machining Parameters for Cylindricity in CNC Turning of HSLA Steel using Response Surface Methodology and Genetic Algorithm

Abstract

The performance prediction of the surface finish, cylindricity and dimensional deviation is essential to ensure the quality of a machined work piece. The objective of the current study is to evaluate the functional relationship for the input parameters and the responses, develop the prediction models for the responses and the optimization of the output responses for CNC turning of DMR 292 steel. The current work is carried out at Defence Mettalurgical Research Laboratory, Hyderabad. In this current work, the neural network has been used for prediction of an output with a good accuracy. The study includes a central composite face-centered design methodology to design the test, and variance analysis is applied to check the fitting degree of the prediction model. The Neural-network-based methodology and the Response Surface Methodology are proposed for predicting the surface roughness, dimensional deviation and cylindricity in a CNC turning process. RSM prediction model defines the functional relationship which gives the various outputs for any inputs within the constraint. Thus GA solver gives the global optimized value in given search space.