An Adaptive Neuro-Fuzzy Inference System modeling for material removal rate in stationary ultrasonic drilling of sillimanite ceramic

Ultrasonic drilling of hard and brittle ceramic materials is a mechanical material removal process which is complex in nature and generally characterised by comparatively slow material removal rates. A precise modeling approach is required to simulate the material removal of ceramics by ultrasonic drilling to recompense the affect of sluggish material removal rates. The present paper uses Adaptive Neuro-Fuzzy Inference System (ANFIS) technique to model and simulate the material removal rate in stationary ultrasonic drilling of sillimanite ceramic. Depth of penetration, time for penetration and penetration rate were taken as model’s input features. The model combined modeling function of fuzzy inference with the learning ability of artificial neural network; and a set of rules has been generated directly from experimental data. The proposed modeling approach is verified by comparing the predicted results with the actual practical results obtained by conducting the confirmation experiments. The application of χ2-test shows that the values of material removal rate predicted by proposed model are well in agreement with the experimental values at 0.1% level of significance.