Optimization Method of Microwave Devices Based on Improved Extreme Learning Machine

Abstract

With the rapid development of modern wireless technology, it is necessary to continuously optimize microwave devices to meet the higher requirements of communication systems. In this paper, we propose a microwave device optimization method based on extreme learning machine (ELM) and gray wolf optimizer (GWO). we adopt GWO to optimize the parameters of ELM and establish the mapping relationships between the microwave device design parameters and their responses. According to the inverse mapping of expected response, the expected design parameters of microwave devices are obtained. The numerical results show that the proposed method can improve the design efficiency of microwave devices and realize automatic optimization design compared with the existing method.