<![CDATA[The compression molding behavior of plantain–bamboo fiber reinforced high-density polyethylene (HDPE) composites was studied through an integrated multivariate analysis and neural network modelling framework. The study utilized materials for fiber extraction and composite production, including water, alkali (NaOH), acetic acid, acetic anhydride, maleic anhydride grafted PE, hydrogen peroxide, hypochlorite, and caustic soda. The composite matrix was high-density polyethylene with density (0.96 g/cm³), reinforced with activated plantain and bamboo fibers. Methods involved mechanical extraction, chemical treatment using alkali solutions, neutralization, bleaching, and stabilization. Fibers were oven-dried, milled, and sieved to (75 μm) before composite formation. Process variables such as fiber fraction (10–50%) and temperature (150–190°C) informed the experimental design. A feed-forward neural network (5-5-5) was used for modelling system performance. The multivariate analysis used predictive neural network models to study combined process-variable effects during compression molding. Interaction plots were generated by varying fiber volume fraction (VF) against other variables. Results showed that high yield stress near (90 MPa) occurred at low VF (10–20%) when bamboo fiber ratio (BFR) was maintained at (40–60%). Pure plantain fiber outperformed pure bamboo at (0) and (1.0 BFR). Optimal molding temperature ranged (166–174°C), producing high yield stress even at VF (10%). At low temperatures (150°C) and VF (30%), yield stress exceeded (80 MPa). Maximum strength required holding times (>17 min) and low clamping force (<1900 N). Neural network predictions aligned closely with experimental data, demonstrating strong predictive reliability. This integrated statistical–computational approach provides valuable insights for optimizing natural fiber composite manufacturing and reducing experimental cost.]]>
Copyrights © 2025
