Multigrade Artificial Neural Network for the Design of Finite Periodic Arrays

To solve the restriction of prior knowledge in artificial neural networks (ANNs) for the modeling of finite periodic arrays, a new multigrade ANN model is proposed in this paper. Considering mutual coupling and array environment, the proposed model is designed with two sub-ANNs, element-ANN and array-ANN. Based on the relationship between the geometrical variables and the electromagnetic (EM) behavior of elements in an array, element-ANN is built to provide prior knowledge for the modeling of array-ANN. Then, in a review of mutual coupling and array environment, array-ANN is modeled to obtain the EM response of the whole array from the nonlinear superposition of the element responses. Three numerical examples of a linear phased array, a six-element printed dipole array, and a U-slot microstrip array are employed to verify the effectiveness of the proposed model.

Duke Scholars

Author William T. Joines Electrical and Computer Engineering