Design of a Substrate Integrated Waveguide power divider that uses a neural network

Abstract

One of the problem in Substrate Integrated Waveguide (SIW) power dividers design is that the simulation often needs plenty of calculation, so it tends to take a long time to optimize the parameters. This paper provides a new approach for the design of substrate integrated waveguide power dividers based on a back-propagation neural network. The design of a 10GHz SIW power divider is presented, and we introduce a BP neural network to optimize the parameters. The results show that the neural network can help to optimize parameters and make the design more efficiently.