RBF neural networks process model based optimization of aluminum powder particle size distribution

Nitrogen atomizing process is with nonlinearities, large time delay, strong coupling and severe uncertainty, and thus it is difficult to obtain the deterministic model by mechanistic method. In this paper, the process model based on RBF Neural Networks is presented to estimate the particle size distribution of aluminum powder by means of measurements of melted aluminum level and temperature, atomizing nitrogen temperature and pressure, and environment nitrogen temperature and pressure, and optimization of aluminum powder particle size distribution is implemented to improve the percentage of super-tiny aluminum powder. Comparisons of the aluminum powder particle size distribution before and after optimizing illustrate that the optimization of aluminum powder particle size distribution can improve the effect of nitrogen atomization and promote the percentage of super-tiny aluminum powder greatly.