The present article addresses a generation of predictive models that assesses the thickness and length of internal defects in additive manufacturing materials. These modes use data from the application of active transient thermography numerical simulation. In this manner, the raised procedure is an ad-hoc hybrid method that integrates finite element simulation and machine learning models using different predictive feature sets and characteristics (i.e., regression, Gaussian regression, support vector machines, multilayer perceptron, and random forest). The performance results for each model were statistically analyzed, evaluated, and compared in terms of predictive performance, processing time, and outlier sensibility to facilitate the choice of a predictive method to obtain the thickness and length of an internal defect from thermographic monitoring. The best model to predictdefect thickness with six thermal features was interaction linear regression. To make predictive models for defect length and thickness, the best model was Gaussian process regression. However, models such as support vector machines also had significative advantages in terms of processing time and adequate performance for certain feature sets. In this way, the results showed that the predictive capability of some types of algorithms could allow for the detection and measurement of internal defects in materials produced by additive manufacturing using active thermography as a non-destructive test.

Fused Filament Fabrication (FFF) has become a widely adopted additive manufacturing technology due to its cost-effectiveness, material versatility, and accessibility. However, optimizing process parameters, predicting material behavior, and ensuring structural reliability remain major challenges. This review analyzes state-of-the-art computational methods used in FFF, which are categorized into four main areas: melt flow dynamics, cooling and solidification, thermal–mechanical behavior, and material property characterization. Notably, the integration of Computational Fluid Dynamics (CFD) and Finite Element Analysis (FEA) has led to improved predictions of key phenomena, such as filament deformation, residual stresses, and temperature gradients. The growing use of fiber-reinforced filaments has further enhanced mechanical performance; however, this also introduces added complexity due to filler orientation effects and interlayer adhesion issues. A critical limitation across existing studies is the lack of standardized experimental validation methods, which hinders model comparability and reproducibility. This review highlights the need for unified testing protocols, more accurate multi-physics simulations, and the integration of AI-based process monitoring to bridge the gap between numerical predictions and real-world performance. Addressing these gaps will be essential to advancing FFF as a precise and scalable manufacturing platform.

This article makes a comparison between different Digital Image Correlation methods to determinate the main mechanical characteristics of composite materials. More specifically Carbon Fiber Reinforced Polymers. For this purpose, several tensile tests were carried out using the same camera and lens model. Different statistical methods as well as probabilistic numerical simulations were performed with the aim of evaluating the discrepancies between methods, and between different mechanical parameters. We want to highlight the consistency of the results, enabling the possibility of using 3D methods with non-planar specimen for determining the mechanical properties of Carbon Fiber Reinforced Polymers. In this case, the novelty is focused on the use of different configurations (2D and 3D) to study the differences in terms of results. the objective is not the specific characterization of CFRP, but to analyze the way in which the use of a dataset from DIC3D or, on the contrary, from DIC2D affects the final results. According to this, it is possible to concluded that significative differences arise in the evaluation of the elastic properties that could be assigned to the uncertainties of the methods. However, this significance does not appear in the results of the probabilistic simulation.

Smartvessel is an innovative fire extinguisher prototype supported by new materials and IoT technology that seeks to improve the functionality and efficiency of conventional fire extinguishers. Storage containers for gases and liquids are essential for industrial activity as they enable higher energy density. The main contributions of this new prototype are (i) innovation in the use of new materials that provide lighter and more resistant extinguishers, both mechanically and against corrosion in aggressive environments. For this purpose, these characteristics are directly compared in vessels made of steel, aramid fiber and carbon fiber with the filament winding technique. (ii) The integration of sensors that allow its monitoring and provide the possibility of predictive maintenance. The prototype is tested and validated on a ship, where accessibility is complicated and critical. For this purpose, different data transmission parameters are defined, verifying that no data are lost. Finally, a noise study of these measurements is carried out to verify the quality of each data. Acceptable coverage values are achieved with very low read noise, on average less than 1%, and a weight reduction of 30% is obtained.