Skip to content

Drilling behavior and ANN-based optimization of Pinus roxburghii fiber–reinforced PLA composites

Sep 2026 · Engineering Research Express · Vol 8 · 0 citations · 50 references
Physics

Abstract

Pinus roxburghii fibers offer an attractive reinforcement for PLA due to their low density, renewability, and biodegradability. In this study, PLA/Pinus roxburghii composite laminates were fabricated via compression molding, and their drilling behavior was assessed in terms of thrust force and torque. Drilling experiments using two tool geometries (twist drill and end mill) were performed to evaluate the influence of cutting parameters on hole formation. Experimental results showed that the end mill generated a minimum thrust force of 60.35 N and a maximum torque of 0.191 Nm, while the twist drill produced a thrust force of 63.08 N, indicating approximately 4.32% higher thrust force under identical machining conditions. Analysis of variance revealed that drill geometry was the most significant factor influencing drilling performance. Experimental trends were analyzed using response surface methodology, confirming that the end mill produced lower drilling forces and reduced damage compared to the twist drill. To enhance process optimization, an artificial neural network (ANN) model was developed to predict drilling responses under varying conditions. The model exhibited strong predictive capability, with correlation coefficients (R) of 0.9196, 0.7791, 0.9934, and 0.9094 for the training, validation, testing, and overall datasets, respectively. Cross-validation further confirmed the robustness and reliability of the ANN model for predicting machining behavior in PLA-based biocomposites.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.