Finding the optimal design parameters for the target EM response of a metamaterial absorber is still a challenging task even if the layout of the absorber has been determined. To effectively address this issue, we introduce the idea of surrogate-based optimization into the area of metamaterial absorber design. This paper proposes a surrogate based optimization method combining artificial neural network (ANN) and trust region algorithm for metamaterial absorbers. Each optimization iteration utilizes the optimal solution from the previous iteration and the sample points surrounding it as the training dataset to build an effective ANN surrogate model. To improve the convergence of the optimization method for metamaterial absorbers based on ANN surrogate model, we incorporate a trust region algorithm. The proposed method employs a simple forward neural network architecture and requires less training data, leading to a quick convergence towards the target solution after only a few iterations. Compared to the three commonly used alternative methods, the proposed method can optimize geometric and material parameters more efficiently in the same time. The validity of the proposed method is demonstrated by two examples of electromagnetic optimizations of metamaterial absorbers.

Download full-text PDF

Source
http://dx.doi.org/10.1364/OE.503010DOI Listing

Publication Analysis

Top Keywords

metamaterial absorber
12
optimization method
12
neural network
12
metamaterial absorbers
12
proposed method
12
artificial neural
8
trust region
8
region algorithm
8
ann surrogate
8
surrogate model
8

Similar Publications

In conventional nondispersive infrared (NDIR) gas sensors, a wide-spectrum IR source or detector must be combined with a narrowband filter to eliminate the interference of nontarget gases. Therefore, the multiplexed NDIR gas sensor requires multiple pairs of narrowband filters, which is not conducive to miniaturization and integration. Although plasmonic metamaterials or multilayer thin-film structures are widely applied in spectral absorption filters, realizing high-performance, large-area, multiband, and compact filters is rather challenging.

View Article and Find Full Text PDF

Metamaterial absorbers have gained widespread applications in fields such as sensing, imaging, and electromagnetic cloaking due to their unique absorption characteristics. This paper presents the design and fabrication of a novel K-band polarization-sensitive metamaterial absorber, which operates in the frequency range of 20.76 to 24.

View Article and Find Full Text PDF

Carbon microspheres (CMSs) are recognized as highly effective microwave absorbers due to their exceptional wave absorption properties. In this study, 5,10,15,20-tetrakis(4-aminophenyl)porphyrin, a metamaterial, was chemically bonded to CMSs─considered a conjugated carbon structure─using a 1,3-dibromopropane linker to explore the synergistic properties and microwave absorption capabilities of the synthesized composite. The synthesized structures were characterized by using X-ray diffraction, FE-SEM, Fourier transform infrared, diffuse reflectance spectroscopy, and VNA analyses.

View Article and Find Full Text PDF
Article Synopsis
  • The article discusses an ultra-wideband nanoscale metamaterial absorber designed for applications in the visible spectrum, emphasizing its ultrathin and flexible characteristics.
  • The study highlights the effective absorption capabilities of the structure, achieving an impressive maximum absorption rate of 86.66%, with a peak absorption of 99.88% for a single unit cell.
  • The research utilizes numerical analysis methods, like the Finite Difference Time Domain (FDTD), to optimize dispersion and Fano resonance properties, making the metamaterial a promising candidate for applications such as solar energy harvesting and biochemical sensing.
View Article and Find Full Text PDF

Comparison of algorithms using deep reinforcement learning for optimization of hyperbolic metamaterials.

Sci Rep

December 2024

Division of Advanced Electrical and Electronics Engineering, Tokyo University of Agriculture and Technology, 2- 24-16 Naka-cho, Koganei-shi, Tokyo, 184-8588, Japan.

A hyperbolic metamaterial absorber has great potential for improving the performance of photo-thermoelectric devices targeting heat sources owing to its broadband absorption. However, optimizing its geometry requires considering numerous parameters to achieve absorption that aligns with the radiation spectrum. Here, we compare three algorithms using deep reinforcement learning for the optimization of a hyperbolic metamaterial absorber.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!