Prediction and optimization of surface roughness in thermal drilling using integrated ANFIS and GA approach

In the recent decade, thermal drilling is becoming popular in aerospace and automobile industries because of its unique advantages over conventional twist drilling process. Surface finish of the thermally drilled hole along with its bushing, is a major concern in all crucial applications and it is worthy of investigation. In the present study, the surface roughness of the thermally drilled hole on galvanized steel is predicted and then optimization is carried out, employing an integrated adaptive network-based fuzzy inference system (ANFIS) and genetic algorithm (GA) approach. Experimentation is based on Taguchi L27 orthogonal array and significant parameters such as spindle speed, angle of tool and workpiece thickness are varied in different levels keeping feed rate as constant. Using the experimental results, an ANFIS model is developed for prediction of surface roughness. An objective function is then formulated on minimization of surface roughness with the help of predicted results of the ANFIS model. Then this objective function was imported into GA toolbox of MATLAB software to optimum values of surface roughness of thermally drilled hole. High degree of closeness is observed between the experimental and predicted results. It is also found that the spindle speed and angle of tool play a significant role on the surface roughness of drilled holes in galvanized steel.