Application of RBF Network for Forecasting Characteristics of In-Flight Particles by Plasma Spraying

Abstract

The main factors that influence the deposition efficiency and forming quality are the state of in-flight particles, which are directly effected by process parameter during plasma spray forming. In this study, plasma spraying of ZrO2 powder was employed according to the method of orthogonal experiments, and the relationship between spray parameters and characteristics of in-flight particles, which were monitored by an optical monitoring system of CCD camera, were investigated. Radial basis function (RBF) neural network model had been designed to forecast the temperature and velocity of in-flight particles, and optimized spray parameter. The comparison of the simulations with the experimental results shows the validity of the model.