FDM Process Using Prediction of Mechanical Properties of Borophene-Reinforced Polymer Nanocomposites

Polymer nanocomposites are utilized in various technical fields, including packaging, automotive, aerospace, and production, when nanoscale reinforcement is added to the polymer matrix. This paper gives a hybrid approach for the prediction of mechanical properties (MPs) of borophene-reinforced polymer nanocomposites by the fused deposition modeling (FDM) process. The proposed hybrid technique is the joint execution of both the election optimizer algorithm (EOA) and fuzzy-stranded neural network (FSNN), termed the EOA-FSNN approach. The primary objective is to assess the mechanical property improvement of borophene-reinforced polymer nanocomposites fabricated via the FDM process. The EOA algorithm is used to optimize the rheological features of polymers and their composites for FDM. The FSNN is used to predict the MP of borophene-reinforced polymer nanocomposites. The proposed method is assessed and compared to other existing approaches using MATLAB. The proposed approach shows better results compared to existing methods such as polynomial chaos expansion (PCE), artificial neural network (ANN), and genetic algorithm (GA). The integration of EOA with FSNN enables the proposed method to achieve superior performance, yielding a higher tensile strength of 33 MPa and a lower mean square error (MSE) of 0.318 compared to existing approaches. This hybrid approach not only enhances the MP of nanocomposites but also provides a reliable and efficient predictive framework for future advancements in polymer engineering.