Abstract
Worldwide, environmental groups and policymakers are focusing on waste recycling to create economic value and on the decomposition of waste by leveraging on scarce resources. This work, therefore, explores the thermal decomposition of enhanced biodegradable polymer matrices made from a mixture of discarded Phoenix dactylifera L./high-density polyethylene (PD/HDPE) using the machine learning analysis of experimental data. The experimental results of these samples were obtained via thermogravimetric (TGA) analysis under an oxidation-free environment, with heating rates of 10, 20, and 40 °C·min(-1) and a degradation temperature range from 25 to 600 °C. The TGA analyses revealed the continued dependence of the actual percentage weight loss by these materials as a test function of the degradation temperature, shifting thermograms to temperature maxima consistent with increasing heating rates. Although high-density polyethylene (HDPE) materials were found to be thermally more stable than Phoenix dactylifera L. (PD) materials, PD/HDPE composite materials contained a significant amount of residual ash. Using a machine learning deep neural network approach for this process, significantly improved learning algorithms have been developed, which reduces the overall cost function (residual error) to almost zero (0.025) after just over a million iterations (epochs) and provides predictions that overlap with the experimental results (R2~1). Learning algorithms, along with optimized synaptic weights and biases, were employed to predict the behaviour of PD materials based on experimental thermograms conducted at higher degradation temperatures, typically ranging between 600 and 1000 °C. Predicted data using the enhanced learning algorithms completely overlapped the experiments (R2~1) for these higher degradation temperatures with near unity correlation if the decomposition of the materials continued until the residue was attained. With this approach, it is possible to predict and optimize the thermal characteristics of PD and HDPE with greater efficiency, which reduces the need for multiple design iterations and experimentation.