Fatigue bending tests, under controlled displacement, were performed on a polymer matrix composite material reinforced with continuous Kevlar fibers. The samples were fabricated using the Fused Filament Fabrication (FFF) technique in a Markforged Two^® 3D printer. The static characterization delivered a flexural modulus of elasticity of 4.73 GPa and flexural strength of 110 MPa. The applied loading corresponded to 92.3, 88.5, 86.2, and 84.7% of the static flexural displacement, giving 15, 248, 460, and 711 cycles for failure. Additionally, two numerical models were created: one using orthotropic properties for static loading conditions; and a second one using isotropic in-bulk properties for fatigue modeling. The second model was able to reproduce the experimental fatigue results. Finally, morphological analysis of the fractured surface revealed fiber breakage, fiber tearing, fiber buckling, matrix cracking, and matrix porosity.

Continuous fiber-reinforced additive manufacturing (cFRAM) composites improve the mechanical properties of polymer components. Given the recent interest in their mechanical performance and failure mechanisms, this work aims to describe the principal failure mechanisms and compare the prediction capabilities for the mechanical properties, stiffness constants, and strength of cFRAM using two distinct predictive models. This work presents experimental tensile tests of continuous carbon fiber AM composites varying their reinforced fraction, printing direction, and fiber angle. In the first predictive model, a micromechanical-based model for stiffness and strength predicts their macroscopic response. In the second part, data-driven models using different machine learning algorithms for regression are trained to predict stiffness and strength based on critical parameters. Both models are assessed regarding their accuracy, ease of implementation, and generalization capabilities. Moreover, microstructural images are used for a qualitative evaluation of the parameters and their influence on the macroscopic response and failure surface topology. Finally, we conclude that although predicting the mechanical properties of cFRAM is a complex task, it can be carried on a Gaussian process regression and a micromechanical model, with good accuracy generalized onto different process parameters specimens.