Either to obtain desirable microstructures by adjusting processing parameters or to predict the properties of a thermal barrier coating (TBC) according to its microstructure, fast and reliable quantitation of the microstructure is imperative. In this research, a machine-learning-based approach—a deep convolution neural network (DCNN)—was established to accurately quantify the microstructure of air-plasma-sprayed (APS) TBCs based on 2D images. Four scanning electron microscopy (SEM) images (view field: 150 μm × 150 μm, image size: 3072 pixel × 3072 pixel) were taken and labeled to train the DCNN. After training, the DCNN could recognize correctly 98.5% of the pixels in the SEM images of typical APS TBCs. This study demonstrated that a small dataset of SEM images could be enough to train a DCNN, making it a powerful and feasible method for quantitively characterizing the microstructure osf APS TBCs.

(La_0.2Yb_0.2Sm_0.2Eu_0.2Gd_0.2)₂Zr₂O₇ (HEZ) has shown considerable promise as a novel thermal barrier coating material for temperatures exceeding 1300 °C. This study systematically investigates the interfacial stability of (La_0.2Yb_0.2Sm_0.2Eu_0.2Gd_0.2)₂Zr₂O₇ with yttria-stabilized zirconia (YSZ), which is of paramount importance for its application in double-layer thermal barrier coatings. Our findings highlight that rare earth elements with a smaller radius diffuse more easily into the YSZ lattice, resulting in a broader diffusion zone. Simultaneously, the incorporation of rare earth elements into the YSZ lattice inhibits tetragonal-to-monoclinic phase transformation. Compared to La₂Zr₂O₇/YSZ, HEZ/YSZ demonstrates superior high-temperature stability, which could be attributed to the higher fracture toughness and lower thermal expansion coefficient of HEZ, the absence of t-m transformation and the formation of a continuous gradient diffusion layer that minimizes interface stress. This study offers a practical strategy for designing materials for durable double-layer thermal barrier coating systems.