Nanofillers are currently the focus of the majority of research on natural fibres due to their high specific strength, strength-to-weight ratio, relatively low cost, and other advantages. Combining the Taguchi method with that of artificial neural networks (ANN) is the primary objective of the current research, with the intention of improving the mechanical properties of nanocomposites. In order to accomplish the aforementioned goals, the following parameters were chosen: (i) nano-SiO2 weight percent; (ii) banana fibre weight percent; (iii) compression pressure in MPa; and (iv) compression moulding temperature in degrees Celsius. When applying the Taguchi method to optimise the process parameters, an L16 orthogonal array was utilised as the primary tool. In accordance with the design of the experiment, various mechanical properties, including the ability to withstand tension, bending, and impact, were evaluated. The ANN was utilised to make predictions that resulted in optimal outcomes. The mechanical properties of hybrid composites exhibited a significant improvement when the fibre mat thickness of banana fibre and the weight ratio of nano-SiO2 were increased. The Taguchi method found that the most significant mechanical properties were a tensile force of 47.36 MPa, a flexural force of 64.48 MPa, and an impact energy of 35.33 kJ when the material was subjected to conditions of 5% SiO2, 19 MPa pressure, and 110 degrees Celsius. The ANN model accurately predicted the mechanical strength with a 95% degree of confidence. In comparison to the regression model and the experimental data, the ANN forecast had a higher degree of precision. The aforementioned nanobased hybrid composites are most commonly utilised for the purpose of catering to the requirements of the modern transportation industry.

Polymer matrix, banana fiber, nano-SiO2 , Epoxy