Neuro-fuzzy predictive model for surface roughness and cutting force of machined Al–20 Mg2Si–2Cu metal matrix composite using additives

Abstract

Today’s metal matrix composites are widely used due to their excellent properties, which are useful for high-performance applications in the automotive and aerospace industries. Furthermore, improving the machinability of these composites is vital for improving product quality in the manufacturing process. In this research, various adaptive network-based fuzzy inference systems (ANFISs) were introduced to evaluate the effect of the feed rate, the cutting speed and the particle size on the machinability of Al–20 Mg2Si metal matrix composite. Two ANFIS models were selected as the most precise models for predicting surface roughness and cutting force. Results show that the proposed ANFIS models have an adequate accuracy in predicting the machinability of metal matrix composites.