M. P. Planche, A. F. Kanta, P. C. Coddet, University of Technology Belfort-Montbeliard, Belfort Cedex, France; G. Montavon, SPCTS - UMR CNRS 6638, Faculty of Sciences, Limoges cedex, France
In thermal spray process, the particle parameters such as particle size, velocity and temperature influence significantly the time of flight as well as the melting time of these particles, then the splat formation and finally the coating properties. Thus, the knowledge of the interactions between the process parameters and the in-flight particles is very important in the optimization approach of the deported coating. The artificial neural network (ANN) concept was used to predict the in-flight particle velocity and temperature considering the case of alumina (Al2O3-TiO2) coatings. The database of the in-flight particle characteristics (diameter, velocity and temperature) versus power process parameters (current, hydrogen rate, plasma gas composition) was collected from the literatures. The ANN was trained with the database to establish the relationships which link particle diameter and power process parameters to particle velocity and temperature.
Then, the established ANN relationships allowed to determine the in-flight particle velocity and temperature versus their diameter for given power process parameters. These velocity and temperature data were then used to determine the time for complete particle melting and the fly time of the particle before impact by analytical method for given operating conditions.
Summary: The artificial neural network (ANN) concept was used to predict the in-flight particle velocity and temperature considering the case of alumina (Al2O3-TiO2) coatings. The database of the in-flight particle characteristics (diameter, velocity and temperature) versus power process parameters (current, hydrogen rate, plasma gas composition) was collected from the literatures.
