Statistical Evaluation of Machining Parameters in Drilling of Glass Laminate Aluminum Reinforced Epoxy Composites using Machine Learning Model

Glass laminate aluminum reinforced epoxy (GLARE), which is used in the aerospace industry, is being researched as a primary fiber reinforced metal composite material. This work presented attempts to construct empirical correlations to predict the thrust force in drilling GLARE composites with a commercial 10 mm solid carbide drill. The empirical correlations were created using multiple linear regression models, the most basic and simplest type of machine learning (ML) model. Response surface methodology's face-centered central composite design is used as the base for experimental design. Machining parameters considered are speed (rpm) and feed rate (mm/min). The results revealed that combining a low drilling speed with a low feed rate minimizes the thrust forces while drilling GLARE composites. Furthermore, the provided machine learning-based linear regression model can be utilized to accurately estimate the thrust force in drilling GLARE composites within the parameters and restrictions presented.