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.

Due to fire protection regulations, a minimum number of fire extinguishers must be available depending on the surface area of each building, industrial establishment or workplace. There is also a set of rules that establish where the fire extinguisher should be placed: always close to the points that are most likely to be affected by a fire and where they are visible and accessible for use. Fire extinguishers are pressure devices, which means that they require maintenance operations that ensure they will function properly in the case of a fire. The purpose of manual and periodic fire extinguisher checks is to verify that their labeling, installation and condition comply with the standards. Security seals, inscriptions, hose and other seals are thoroughly checked. The state of charge (weight and pressure) of the extinguisher, the bottle of propellant gas (if available), and the state of all mechanical parts (nozzle, valves, hose, etc.) are also checked. To ensure greater safety and reduce the economic costs associated with maintaining fire extinguishers, it is necessary to develop a system that allows monitoring of their status. One of the advantages of monitoring fire extinguishers is that it will be possible to understand what external factors affect them (for example, temperature or humidity) and how they do so. For this reason, this article presents a system of soft agents that monitors the state of the extinguishers, collects a history of the state of the extinguisher and environmental factors and sends notifications if any parameter is not within the range of normal values.The results rendered by the SmartFire prototype indicate that its accuracy in calculating pressure changes is equivalent to that of a specific data acquisition system (DAS). The comparative study of the two curves (SmartFire and DAS) shows that the average error between the two curves is negligible: 8% in low pressure measurements (up to 3 bar) and 0.3% in high pressure (above 3 bar).