Glass fiber-reinforced polymer composites (GFRPCs) are extensively utilized in the aerospace, automotive, and structural sectors; nevertheless, their heterogeneous and abrasive characteristics result in rapid tool wear during drilling. Drill flank wear among various wear mechanisms notably influences hole quality and dimensional accuracy. This research investigates the impact of spindle speed, feed rate, and drill diameter on flank wear during dry drilling of GFRPC laminates with high-speed steel (HSS) twist drills. A full-factorial design with 81 experiments is used to create a comprehensive dataset. ANOVA indicates that spindle speed is the dominant factor affecting wear changes, accounting for 74.43%, followed by feed rate (15.80%) and drill diameter (6.16%). A linear regression model demonstrates reasonable statistical sufficiency (R² = 0.964), but it falls short in reflecting nonlinear interactions. Hence, an artificial neural network (ANN) model is developed to improve prediction. The multilayer feed-forward ANN with a 3-10-6-1 architecture, trained using the Levenberg–Marquardt optimization algorithm, achieves excellent predictive accuracy, with high correlation and low root-mean-square error. Model validation was achieved through independent confirmation experiments, yielding a mean absolute percentage error of only 2.27%, with all predictions falling within the permissible wear range. The findings indicate that ANN-based modeling provides a reliable framework for capturing the complex nonlinear relationships governing tool wear in GFRPC drilling and serves as a viable soft sensor for tool condition monitoring, process optimization, and sustainable, data-driven manufacturing.

This research explores the water uptake behavior of glass fiber/epoxy composites filled with nanoclay and establishes an Artificial Neural Network (ANN) to predict water uptake percentage from experimental parameters. Composite laminates are fabricated with varying glass fiber $(40-60\text{wt}.\mathrm{\%})$ and nanoclay $(0-4\text{wt}.\mathrm{\%})$ contents. Water absorption is evaluated for 70 days of immersion following ASTM D570-98 standards. The inclusion of nanoclay reduces water uptake by creating a tortuous path for moisture diffusion due to its high aspect ratio and platelet morphology, thereby enhancing the composite’s barrier properties. The ANN model is developed with a 3–4–1 feedforward structure and learned through the Levenberg–Marquardt algorithm with soaking time (7 to 70 days), fiber content $(40,50,\text{and}60\text{wt}.\mathrm{\%})$ and nanoclay content $(0,2,\text{and}4\text{wt}.\mathrm{\%})$ as input parameters. The model’s output is the water uptake percentage. The model has high prediction efficiency, with a correlation coefficient $(R)$ of $0.998$ and a mean squared error of $1.38\times {10}^{-4}$. Experimental and predicted values are in excellent agreement, ensuring the reliability of the ANN for the simulation of nonlinear water absorption behavior. The results identify the synergistic capability of nanoclay and fiber concentration to reduce water absorption and prove the feasibility of ANN as a substitute for time-consuming testing in composite durability estimation.