A Novel and Fast Method to Design Metamaterial Absorbers Based on RBF-PSO Algorithm

A novel and fast method based on radial basis function (RBF) neural network and particle swarm optimization (PSO) algorithm is proposed in designing metamaterial absober (MA). The nonlinear relationship between geometric parameters and frequency response of MA is built by RBF neural network, which has the characteristic of accurate approximation and good generalization. The PSO algorithm is chosen as the optimizer to obtain the best geometric dimensions based on desired requirements. Through the combination of the neural network and optimization technique, the complexity of designing absorbing structure could be reduced significantly. The accuracy of the proposed method is verified through the comparisons between the outputs of neural network and simulation under the same optimized parameters. The results show that designing an absorbing structure with the proposed method is an efficient way.