Surface Roughness Prediction Model for Ball End Milling Operation Using Artificial Intelligence

Abstract

Surface roughness is an index which determines the quality of machined products. In this study the average surface roughness value (Ra) for Aluminum after ball end milling operation has been measured. 84 experiments have been conducted varying cutter axis inclination angle (φ degree), spindle speed (S rpm), feed rate (fy mm/min), radial depth of cut (fx mm) and axial depth of cut (t mm) in order to find Ra. This data has been divided into two sets on a random basis. 68 data sets have been used for training different ANFIS model for Ra prediction. 16 test data sets have been used to validate the models. Better ANFIS model has been selected based on the minimum value of root mean square error (RMSE) which is constructed with three Gaussian membership functions (gaussMF) for each inputs and a linear membership function for output. The Selected ANFIS model has been compared with theoretical model and Response Surface Methodology (RSM). This comparison is done based on RMSE and mean absolute percentage error (MAPE). The comparison shows that the selected ANFIS model gives better result for training and testing data. Here ANFIS model has been used further for predicting surface roughness of a typical die made by ball end milling operation. An algorithm was developed to determine the feasible solutions for the cutting parameters in order to obtain a desired surface roughness for the three dimensional die. This algorithm was used to show how a near optimal combination of machining parameters can be determined for a targeted level of surface finish.

Key words: Aluminium; Surface; Manufacturing; Quality; Milling; ANFIS; Machining; AI