ANN and RSM Prediction of Water Uptake of Recycled HDPE Biocomposite Reinforced with Treated Palm Waste W. filifera

Abstract

This study examined the water uptake (WU) behavior of recycled high-density polyethylene (RHDPE). The biocomposites made of palm waste Washingtonia (PWW) fibers were treated with 3% sodium bicarbonate (NaHCO3) for 24 h. Several RHDPE materials reinforced with different concentrations of PWW fibers (5 to 30 wt.%) until saturation, or roughly 25 days, were developed to investigate the WU kinetics and diffusion in biocomposites. An artificial neural network (ANN) and the response surface methodology (RSM) methods were applied to model the behavior of uptake measured in experiments and optimize the immersion period and PWW fiber content in RHDPE/PWW biocomposite WU. The WU moved swiftly during the first test phase and was completed after 400 h of soaking. The outcomes demonstrated a perfect fit between the observed and anticipated data. Findings showed that the ANN models’ training, test, and validation correlation coefficients were 0.9984, 0.9955, and 0.9723, respectively, for predicting WU. Concerning accuracy and reliability, the ANN model outperformed the RSM model, making it suitable for various industrial uses. The results offer helpful information for professionals to consider when developing and implementing PWW fiber biocomposites.