A methodology based on an optimized surrogate model and Non-dominated Sorting Genetic Algorithm III(NSGA-III) algorithm is proposed to address the long design cycle issues that conventional antennas encounter, with fast multiple parameters processing capability. A Temporal Convolutional Network (TCN) network model with high fitting efficiency and a simple structure is first developed as a surrogate model for antenna performance prediction, taking antenna dimensional parameters as input and outputting the reflection coefficient (S11) and gain of the antenna. Then, an adaptive NSGA-III algorithm with enhanced search efficiency is presented. By combing it with the prior TCN surrogate model, the parameter optimization for a 5G millimeter-wave antenna design is realized. Results show that the proposed method achieves a remarkable reduction in Mean Squared Error (MSE) by 12.489 % and 3.277 % respectively, while also presents a decreased running time by 2.670 % and 70.419 % respectively, as compared to the Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) network models. The proposed method can rapidly and accurately perform the optimization task of multiple antenna parameters, demonstrating its feasibility and effectiveness for antenna applications requiring wide bandwidth, low loss and high gain.
Read full abstract