A Machine Learning-Driven Optimization of Machining Parameters for Nanoclay-Glass Fiber Polymer-Reinforced Composites for Performance Prediction and Process Enhancement

Abstract The optimization of machining parameters for glass fiber-reinforced polymer (GFRP) composites is critical due to their widespread applications in aerospace, automotive, and structural engineering. This study investigates the effect of montmorillonite (MMT) nanoclay reinforcement on the machining performance of GFRP composites and employs advanced machine learning (ML) models to optimize key machining parameters. Experimental results indicate that incorporating 3 wt% MMT nanoclay enhances the mechanical integrity of GFRP composites by improving tensile, flexural, and interlaminar shear strengths while increasing thermal stability. Machining trials conducted on a computer numerical control (CNC) vertical machining center identify cutting speed and cutting depth as the most influential parameters affecting surface roughness (Ra) and material removal rate (MRR). SHAP (SHapley Additive exPlanations) analysis highlights cutting depth as the dominant factor for Ra prediction, contributing 76.47%, while for MRR, cutting depth and speed account for 53.82% and 43.22%, respectively. Gradient boosting, CatBoost, and XGBoost models are employed to establish predictive frameworks linking machining parameters to performance metrics, with statistical validation using analysis of variance (ANOVA) confirming their hierarchical influence. The findings demonstrate that ML-assisted optimization enhances machining efficiency while reducing reliance on extensive experimental trials. The integration of data-driven modeling with experimental validation provides a novel methodology for optimizing machining strategies in nanocomposite processing, bridging the gap between nanofiller reinforcement and intelligent machining parameter selection. This research advances precision manufacturing by enabling the development of high-performance, sustainable composite materials for industrial applications.