Poly(3-hydroxybutyrate-co-3-hydroxyhexanoate) (PHBHHx) is a biodegradable and biocompatible bacterial copolymer used in the biomedical and food industries. However, it displays low stiffness and strength for certain applications. This issue can be solved via reinforcement with nanofillers. In this work, PHBHHx-based bionanocomposites reinforced with different loadings of crystalline nanocellulose (CNC) and graphene oxide (GO) were developed by a green and straightforward solution casting technique. Their crystalline nature and surface topography were explored via X-ray diffraction (XRD) and field-emission scanning electron microscopy (FE-SEM), respectively, their composition was corroborated via Fourier-transformed infrared spectroscopy (FTIR), and their crystallization and melting behavior were determined via differential scanning calorimetry (DSC). The nanofillers had a nucleating role, raising the crystallization temperature of the polymer, whilst hardly any changes were found in the melting temperature. Further, significant enhancements in the stiffness, strength, and thermal stability of the PHBHHx matrix were observed with the incorporation of both nanofillers, which was attributed to a synergic effect. The mechanical properties for various concentrations of CNC and GO were accurately predicted using a machine learning (ML) model in the form of a support vector machine (SVM). The model performance was evaluated in terms of the mean absolute error (MAE), the mean square error (MSE), and the correlation coefficient (R2). These bio-based nanocomposites are a valuable alternative to conventional petroleum-based synthetic polymeric materials used nowadays for biomedicine and food packaging applications.
Keywords: bionanocomposites; graphene oxide; machine learning; mechanical properties; nanocellulose; polyhydroxyalcanoate.