On Prediction And Optimization Of Laser Ablation Technology For PDPhSM Matrix Nanocomposite Thin Film Based Upon Artificial Neural Networks-Particle Swarm Algorithm

Some key factors in the process of polydiphenysilylenemethylene (PDPhSM) matrix nanocomposite thin film have been studied by a large amount of experiments in this paper, and the common rules of pulsed laser ablation technology has been obtained. The sample data was built by analyzing the experimental data collected during the experiments. A BP neural network and a RBF neural network models are developed to predict the polymerization efficiency for PDPhSM matrix nanocomposite thin film respectively. The results showed that the relative error between the expected value and predicted output of the network is less than 4%, which indicates that both BP and RBF models could be used to reveal the inherent disciplinarian between the parameters of synthesis technology and polymerization efficiency. However, the non-linear relationship has been approached more accurately, effectively and feasibly by using of RBF neural network than BP neural network.An artificial neural networks- particle swarm algorithm was firstly introduced to optimize the materials technology by using the constructed RBF neural network on the properties of pulsed laser ablation technology, and a satisfying result has been obtained, hence providing a brand-new way for materials technology optimization investigation. It is hopeful to be applied in the material technology optimization and material computer aided design field.