Performance Study and Machine Learning Model Evaluation of Embedded Micro-Agglomerated Particle TBCs Based on Plasma-Spraying Process

The spraying process affects the microstructure and service life of thermal barrier coatings. In this work, by changing the plasma-spraying process, the second-phase micron-agglomerated particles were introduced to prepare embedded micron-agglomerated particle thermal barrier coatings. Conventional thermal barrier coatings and embedded micron-agglomerated particle thermal barrier coatings were prepared by setting spraying process parameters with different powder feeding rates and distances between powder feeders. Sintering experiments and thermal cycling experiments were carried out on conventional thermal barrier coatings and embedded micron-agglomerated particle thermal barrier coatings. The effects of spraying process parameters on the microstructure and thermal cycle life of embedded micron-agglomerated particle thermal barrier coatings were systematically studied. Three machine learning models of BP, SVM, and GA-SVM were established to evaluate the relationship between spraying parameters and coating microstructure and thermal cycle life. The results show that the sintering resistance of the new thermal barrier coating is 500% higher than that of the conventional thermal barrier coating. When the distance between the two powder feeders is 35 mm and the powder feeder 1 rate is 12 g/min, the thermal cycle life of the coating is the best. When using machine learning model evaluation, the evaluation results of the three machine learning models have certain accuracy. Among them, the GA-SVM machine learning model has the best prediction effect and the smallest prediction error. The results of this paper provide a new paradigm for further preparation of thermal barrier coatings with high performance and long life.