Effective Artificial Neural Network Framework for Time-Modulated Arrays Synthesis

The antenna array synthesis problem has long been known as a tough issue, which attracts considerable interest to explore high-performance low-complexity optimization techniques. In this article, an efficient artificial neural network (ANN) for time-modulated arrays (TMAs) synthesis is proposed. By defining the equivalent excitation properly, TMA synthesis can be first transformed to a generalized phased array optimization. Next, a two-stage ANN framework composed of two encoders and a universal decoder is established to optimize the equivalent excitation, and then a single-input single-output (SISO) sinc−1-ANN is proposed to solve inverse of
$\text {sinc}\left ({\cdot }\right)$
efficiently. To achieve fast and accurate pattern prediction, the decoder is pretrained to be a real-time array analyzer, while the encoder is designed as an array synthesizer to develop online training. By minimizing the loss function related to radiation pattern and equivalent excitation, the desired pattern can be achieved. Then, with the help of the pretrained SISO sinc−1-ANN, the static excitation coefficient, switch-on duration, and starting time are acquired. Simulation results of different types of desired TMA patterns are provided to verify the superiority, effectiveness, and efficiency of the proposed approach.