An Efficient Strategy for the Synthesis of Sparse Linear Arrays Based on Artificial Neural Network

Abstract

An efficient strategy for the synthesis of sparse linear arrays including mutual coupling and platform effects based on artificial neural network (ANN) is proposed. In this strategy, high-quality ANN surrogate models of arbitrary linear arrays are built to reduce the computational cost of array synthesis in the presence of coupling effects. The “curse of dimensionality” of ANNs caused by the large number of array elements can be tackled by grouping the surrogate models of subarrays together. The surrogate models of a complete group of subarrays with the given physical structures are built by several independent ANN s which are used to characterize the effects of mutual coupling on the active element patterns (AEPs) with variable location distributions. The example for synthesizing sparse linear arrays with cosecant square-shaped beam pattern is demonstrated to validate the effectiveness of the proposed strategy. Due to the mutual coupling effects are accounted for in the synthesis process, the proposed method exhibits practical value in sparse array synthesis.