The Application Of Artificial Neural Networks And Genetic Algorithms In Microwave Design

Artificial neural networks(ANN) and genetic algorithm(GA) based on biology have been used widely because of their superiority. This thesis focuses on the application of ANN and GAto microwave design.Electromagnetic absorbers are of great value. The effect of EM wave incidence on the surface of multilayer medium is studied. GA is used to optimize the parameters of the medium and the combination mode of different ferrite absorbers. Several design results are given. In addition, the absorbing characteristic of the material loaded by resistors is given.Furthermore, the application of ANN and GAto microwave circuit CAD is discussed. ANN models of microstrip gap and microstrip interdigital capacitor(IDC) are established. The training samples come from FDTD simulation. Different training algorithms, namely Levenburg-Marquart algorithm and the gradient-based algorithm with an adaptive learning rate and momentum, are compared in this paper. According to the engineering requirement, dimensions of IDC can be designed using the trained ANN model and GA. The design procedure is proved to be time saving and of high accuracy...