No abstract

No abstract

Surface roughness is a quality index for machined surfaces. In this study an algorithm has been developed to determine the feasible solutions for cutting parameters in order to obtain desired surface roughness for three dimensional dies. Here the average surface roughness values for a commercial die material EN24 after ball end milling operation have been measured after experiments with different cutting parameters. These datasets have been used for training and testing different prediction models like artificial neural network (ANN), response surface methodology (RSM), adaptive neuro-fuzzy inference system (ANFIS) and mathematical equation based on machining theories. ANFIS model has been selected as better prediction model because it has shown minimum value of root mean square error (RMSE) and mean absolute percentage error (MAPE) for training and testing datasets. This ANFIS model has been used further for predicting surface roughness of a typical die made of EN24 after ball end milling operation.

For efficient use of machine tools at optimum cutting condition, it is necessary to find a suitable optimization method, which can find optimum feasible solution rapidly and explain the constraints as well. As the actual turning process parameter optimization is highly constrained and nonlinear, a modified Genetic Algorithm with Self Organizing Adaptive Penalty (SOAP) strategy is used to find the optimum cutting condition and to get clear idea of constraints at the optimum condition. Unit production cost is the objective function while limits of the cutting force, power, surface finish, stability condition, tool-chip interface temperature and available rotational speed in the machine tool are considered as the constraints. The result shows that our approach of GA with SOAP converges quickly by focusing on the boundary of the feasible and infeasible solution space created by constraints and also identifies the critical and non-critical constraints at the optimum condition.

No abstract