Research on the Relationship Between the Microstructure of Embedded Micro-Agglomerated Particle TBCs and Their Sintering Resistance Based on a Data-Mechanism Hybrid Driving Model

The distribution morphology and density of micro-agglomerated particles are the main microstructural characteristics of embedded micro-agglomerated particle thermal barrier coatings. The study of their effect on the sintering resistance of coatings can help to further improve the service life of thermal barrier coatings. Strain tolerance and thermal insulation performance are important evaluation indicators for the sintering resistance of thermal barrier coatings. In this study, embedded micro-agglomerated particle thermal barrier coatings were prepared by plasma spraying, and the distribution morphology and density of micro-agglomerated particles were analyzed and counted. Different simulation models were established to analyze the compressive stress and thermal stress of the coating, as well as the influence of the microstructure characteristics on the strain tolerance and thermal insulation performance of the coating. A machine learning model was established to evaluate the nonlinear relationship between the microstructure characteristics of the coating and its strain tolerance and thermal insulation performance. The results show that the horizontal angle of the micro-agglomerated particles in the coating has the most significant effect on the sintering resistance and is predicted using the PSO-SVM machine learning model. The predicted effects are the most important, and the coefficients of determination for strain tolerance and thermal insulation are as high as 0.988 and 0.945, respectively, indicating a strong correlation between the predicted and actual values. This research technique used experimental research-simulation computation-machine learning can be used to optimize the microstructure of coatings and guide the preparation of high-performance thermal barrier coatings.