Material Removal Rate Optimization Under ANN and QRCCD

Numerical analysis is a significant aspect of the manufacturing process. This process is used to study the performance of lubricants and cutting parameters during machining operations. Material removal rate (MRR) is an important factor to consider to enhance the machining and production processes of manufacturing components. Using an artificial neural network (ANN) and a quadratic rotatable central composite design (QRCCD), this study focuses on the numerical analysis of the copra oil-based TiO₂ nano-lubricant performance with the machining parameters on the material removal rate during the end-milling machining operation. This study considered five machining parameters that are the control factors, such as spindle speed, feed rate, length-of-cut, cutting depth, and helix angle, on the response known as MRR under end-milling of AA8112 alloy. The measured experimental result from the end-milling machining operation is used to develop a model for the MRR to predict the performance of the nano-lubricant with the machining parameters. The ANN model developed could predict the surface roughness with 99.85% accuracy and the MRR with 98.7%. The results also show that increasing the spindle speed reduced surface roughness, which increased the material removal rate slightly during the machining process.