Thermal barrier coatings (TBCs) are usually used in high temperature and harsh environment, resulting in thinning or even spalling off. Hence, it is vital to detect the thickness of the TBCs. In this study, a hybrid machine learning model combined with terahertz time-domain spectroscopy technology was designed to predict the thickness of TBCs. The terahertz signals were obtained from the samples prepared in laboratory and actual turbine blade. The principal component analysis (PCA) method was used to decrease the data dimensions. Finally, an extreme learning machine (ELM) was proposed to establish the thickness of TBCs prediction model. Genetic algorithm (GA) was selected to optimize the model to make it more accurate. The results showed that the root correlation coefficient (R2) exceeded 0.97 and the errors (root mean square error and mean absolute percentage error) were less than 2.57. This study proposes that terahertz time-domain technology combined with PCA–GA–ELM model is accurate and feasible for evaluating the thickness of the TBCs.
High-emissivity coatings are often used on the surfaces of solar probes to block heat from the sun. Therefore, improving the thermal control ability is the standard for determining the quality of the coatings. In this study, MgO was doped into Al2O3 to improve the thermal control ability of the coatings and to analyse the effect of different MgO doping contents. The solar absorptivity to infrared (IR) emissivity ratio (α/ε) was used to evaluate the thermal control ability of the coatings. The results showed that 5 wt.% MgO doping content is the best choice. The main reason for the change in α/ε is related to the doping of MgO, which affects the grain size of Al2O3.