Prediction of mechanical properties is an essential part of material design. State-of-the-art simulation-based prediction requires data on microstructure and inter-component interactions of material. However, due to high costs and time limitations, such parameters, which are especially required for the simulation of advanced properties, are not always available. This paper proposes a data-driven approach to predicting the labor-consuming fracture toughness based on a series of standard, easy-to-measure mechanical characteristics. Three supervised machine-learning (ML) models (artificial neural networks, a random forest algorithm, and gradient boosting) were designed and tested for the prediction of mechanical properties of pultruded composites. A considerable dataset of mechanical properties was acquired as results of standard tensile, compression, flexure, in-plane shear, and Charpy tests and utilized as the input to predict the fracture toughness. Furthermore, this study investigated the correlations between the obtained mechanical characteristics. Analysis of ML performance showed that fracture toughness had the highest correlations with longitudinal bending and transverse tension and a strong correlation with the longitudinal compression modulus and tensile strength. The gradient boosting decision tree-based algorithms demonstrated the best prediction performance for fracture toughness, with an MSE less than 10% of the average value, providing a prediction within the range of experimental error. The ML algorithms showed potential in terms of determining which macro-level parameters can be used to predict micro-level material characteristics and how. The results provide inspiration for future pultruded composite material design and can enhance the numerical simulations of material.

3D printing using fused composite filament fabrication technique (FFF) allows prototyping and manufacturing of durable, lightweight, and customizable parts on demand. Such composites demonstrate significantly improved printability, due to the reduction of shrinkage and warping, alongside the enhancement of strength and rigidity. In this work, we use polypropylene filament reinforced by short glass fibers to demonstrate the effect of fiber orientation on mechanical tensile properties of the 3D printed specimens. The influence of the printed layer thickness and raster angle on final fiber orientations was investigated using X-ray micro-computed tomography. The best ultimate tensile strength of 57.4 MPa and elasticity modulus of 5.5 GPa were obtained with a 90° raster angle, versus 30.4 MPa and 2.5 GPa for samples with a criss-cross 45°, 135° raster angle, with the thinnest printed layer thickness of 0.1 mm.

Fibre breaks govern the strength of unidirectional composite materials under tension. The progressive development of fibre breaks is studied using in situ X-ray computed tomography, especially with synchrotron radiation. However, even with synchrotron radiation, the resolution of the time-resolved in situ images is not sufficient for a fully automated analysis of continuous mechanical deformations. We therefore investigate the possibility of increasing the quality of low-resolution in situ scans by means of super-resolution (SR) using 3D deep learning techniques, thus facilitating the subsequent fibre break identification. We trained generative neural networks (GAN) on datasets of high—(0.3 μm) and low-resolution (1.6 μm) statically acquired images. These networks were then applied to a low-resolution (1.1 μm) noisy image of a continuously loaded specimen. The statistical parameters of the fibre breaks used for the comparison are the number of individual breaks and the number of 2-plets and 3-plets per specimen volume. The fully automated process achieves an average accuracy of 82% of manually identified fibre breaks, while the semi-automated one reaches 92%. The developed approach allows the use of faster, low-resolution in situ tomography without losing the quality of the identified physical parameters.

High residual stresses (RS) in laser powder bed fusion (PBF-LB) components present significant structural challenges, yet traditional characterization techniques are cost- and time-intensive. This study introduces three rapid mechanical testing methodologies to estimate longitudinal RS in PBF-LB 316L stainless steel by using the premature micro-yielding of pre-tensioned near-surface regions in cylindrical geometries. The proposed methods evaluate RS through: (I) plastic work density calculated from cyclic loading-unloading, (II) virtual unloading mathematically projected from standard monotonic tensile data, and (III) the detection of a macroscopic micro-yielding threshold (0.01% strain). Estimations were quantitatively validated against neutron diffraction (ND) measurements across multiple heat treatment conditions (as-built to 1000 °C). The energy-based approaches (Proposed Methods I and II) demonstrated linear proportionality with relative ND stress reductions (R2= 0.82 and 0.77, respectively). Furthermore, by subtracting the empirical micro-yielding threshold from condition-specific macroscopic yield strengths, Proposed Method III tracked absolute RS relaxation. Electron backscatter diffraction (EBSD) analysis physically validated these techniques, confirming that the initial non-linear macroscopic mechanical response is governed by localized geometrically necessary dislocation (GND) accumulation prior to bulk yielding. These findings establish the proposed mechanical methods as highly accessible alternatives for evaluating stress mitigation strategies in additive manufacturing.