Research Progress on Rapid Optimization Design Methods of Metamaterials Based on Intelligent Algorithms

Abstract

At present, research on metamaterials is continuously advancing to engineering applications, and great progress is being achieved in the areas of physical mechanisms and effects, design theory and methods, and fabrication and measurement. However, traditional metamaterials design mainly relies on artificial design and optimization. In the face of large-scale engineering applications, it is impossible to realize the rapid overall design of a large number of metamaterial structural units. In recent years, the proportion of intelligent algorithms covering traditional heuristic algorithms and neural network algorithms in metamaterials design has increased gradually. Metamaterials design based on intelligent algorithms can surpass the limitation of traditional methods in different substrate systems, frequency variation, and different performance indicators, offering the unique advantages of rapid design and architectural innovation. This paper summarizes the application of several typical intelligent algorithms, including the genetic algorithm, Hopfield network algorithm, and deep learning algorithm in metamaterials design, which include forward designs and an inverse design. The use of intelligent algorithms can achieve the rapid design of frequency selective surfaces under different performance indexes, multi-mechanisms composite absorber metamaterials, flat focusing, and abnormal reflection metasurfaces, providing the necessary support for design methods while promoting the engineering applications of metamaterials.

Keywords

• metamaterials
• heuristic algorithm
• neural network algorithm
• frequency selective surface
• phase gradient metasurface
• sub-wavelength