Predicting failure loads of graphene incorporated adhesively bonded single lap joints fabricated with short glass fibre reinforced polylactic acid using ANN approach

Additive manufacturing has been prominent for making complicated polymeric structures, with PLA being preferred for its biodegradability, ease of use, and wide 3D printing compatibility. The present study aims to explore the effects of graphene-integrated adhesive on shear properties, failure modes, and vibrational response of adhesively joined bonded joints prepared with 3D printed short glass fibre-reinforced polylactic acid (PLA) adherents. Field emission scanning electron microscopy (FESEM) was used to analyse fracture surfaces, while artificial neural networks (ANN) predicted failure modes using a backpropagation algorithm. Tensile testing of bulk samples indicated that samples printed with 0º raster orientation have higher tensile strength (30.7 MPa) than samples printed with 45º (26.7 MPa) and 90º (23.4 MPa) raster orientations. Shear test results demonstrate that incorporating 1.0 wt.% of graphene into the adhesive enhances the adhesive joint's shear properties, leading to a 19.51% increase in shear strength compared to neat samples. The free vibrational analysis avowed that the addition of graphene up to 1.0 wt.% increases natural frequencies due to improved stiffness from its well-dispersed state within the epoxy matrix. Furthermore, the failure load was accurately predicted using an artificial neural network trained on data from stress-strain curves. The R² value of 0.9861 indicates that the results are reliable and show a good correlation. Thereby, this study demonstrated how graphene-integrated epoxy adhesives enhance the mechanical and vibrational properties of adhesively bonded lap joints prepared with 3D printed short glass fibre-reinforced PLA adherents, while also using artificial neural networks to predict failure modes, providing a novel approach to optimise the performance of adhesively joined 3D printed components.