Nondestructive Evaluation of Thermal Barrier Coatings Thickness Using Terahertz Technique Combined with PCA–GA–ELM Algorithm

Thermal barrier coatings (TBCs) are usually used in high temperature and harsh environment, resulting thinning or even spalling off. Hence, it is vital to detect the thickness of TBCs. In this study, a hybrid machine learning model combined with terahertz time-domain spectroscopy technology was designed predict The signals were obtained from samples prepared laboratory actual turbine blade. principal component analysis (PCA) method decrease data dimensions. Finally, an extreme (ELM) proposed establish TBCs prediction model. Genetic algorithm (GA) selected optimize make more accurate. results showed that root correlation coefficient (R2) exceeded 0.97 errors (root mean square error absolute percentage error) less than 2.57. This study proposes PCA–GA–ELM accurate feasible for evaluating