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.

The relationship between wood and its degree of humidity is one of the most important aspects of its use in construction and restoration. The wood presents a behavior similar to a sponge, therefore, moisture is related to its expansion and contraction. The nondestructive evaluation (NDE) of the amount of moisture in wood materials allows to define, e.g., the restoration procedures of buildings or artworks. In this work, an integrated study of two non-contact techniques is presented. Infrared thermography (IRT) was able to retrieve thermal parameters of the wood related to the amount of water added to the samples, while the interference pattern generated by speckles was used to quantify the expansion and contraction of wood that can be related to the amount of water. In twenty-seven wooded samples, a known quantity of water was added in a controlled manner. By applying advanced image processing to thermograms and specklegrams, it was possible to determine fundamental values controlling both the absorption of water and the main thermophysical parameters that link the samples. On the one hand, results here shown should be considered preliminary because the experimental values obtained by IRT need to be optimized for low water contents introduced into the samples. On the other hand, speckle interferometry by applying an innovative procedure provided robust results for both high and low water contents.