Design Automation for Microwave Branch-line Couplers Using Artificial Neural Networks with Self-Adaptive Differential Evolution Algorithm

The traditional method for designing branch-line couplers relies on a time-consuming labor-intensive trial-and-error process with multiple EM simulation iterations. This paper introduces a novel framework combining artificial neural networks with a self-adaptive differential evolution algorithm (ANNs-SaDE) for automatic design. The effectiveness of this framework is demonstrated through the design of wideband three-stage couplers.