Artificial neural networks implementation in plasma spray process: Prediction of power parameters and in-flight particle characteristics vs. desired coating structural attributes

Artificial neural networks (ANN) were implemented to predict atmospheric plasma spraying (APS) process parameters to manufacture a coating with the desired structural characteristics. ecific case of predicting power parameters to manufacture grey alumina (Al2O3–TiO2, 13% by wt.) coatings was considered. Deposition yield and porosity were the coating structural characteristics. having defined, trained and tested ANN, power parameters (arc current intensity, total plasma gas flow, hydrogen content) and resulting in-flight particle characteristics (average temperature and velocity) were computed considering several scenarios. The first one deals at the same time with the two structural characteristics as constraints. The others one deals with one structural characteristic as constraint while the other is fixed at a constant value.