Data-Driven Method for Porosity Measurement of Thermal Barrier Coatings Using Terahertz Time-Domain Spectroscopy

Accurate measurement of porosity is crucial for comprehensive performance evaluation thermal barrier coatings (TBCs) on aero-engine blades. In this study, a novel data-driven predictive method based terahertz time-domain spectroscopy (THz-TDS) was proposed. By processing and extracting features from signals, multivariate parameters were composed to characterize the porosity. Principal component analysis, which enabled effective representation complex signal information, introduced downscale dimensionality data. Additionally, average power spectral density frequency spectrum extreme points first-order derivative phase extracted. These extracted collectively form set that accurately Subsequently, used as inputs construct an learning machine (ELM) model optimized by sparrow search algorithm (SSA) predicting Based experimental results, it evident accuracy SSA-ELM significantly higher than basic ELM. Furthermore, robustness evaluated through K-fold cross-validation final regression coefficient 0.92, indicates excellent model. introducing use THz-TDS employing advanced techniques, provided solution rapid accurate detection in TBCs. The findings study offer valuable references researchers practitioners field TBCs inspection, opening up new avenues improving overall assessment these coatings.