Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy

On, H.; Jeong, Leekyo; Jung, Minseok; Kang, Dong-Joong; Park, Jun-Hyub; Lee, Hak‐Joo

doi:10.1016/j.matdes.2021.110266

Cited by 19 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, our proposed model usually requires a large amount of training data for effective training. It may require the collection of a large amount of sample data, increasing the time cost of data collection, especially for complex metasurface [42]. Second, the internal mechanisms of our proposed model are complex and it is difficult to explain and understand the decision process of the model, which limits the interpretation of the predicted parameters [43].…”

Section: Discussionmentioning

confidence: 99%

Inverse design of electromagnetically induced transparency(EIT) metasurface based on deep convolutional generative adversarial network

Zhu,

Zhang,

Dong

et al. 2023

Phys. Scr.

View full text Add to dashboard Cite

With the increasing complexity of electromagnetically induced transparency (EIT) metasurface structure and the limitations of traditional optimization methods, there is an urgent need for an advanced design approach to accelerate the design of complex EIT metasurface. In this study, we propose an improved deep learning model based on deep convolutional generative adversarial network (DCGAN) to simplify the design process of EIT metasurface. The proposed model enables the optimization of metasurface with eight structural parameters, obtaining single-band or dual-band EIT effects for y polarization incidence. The training of the network model achieves convergence with a mean square error (MSE) of 0.2 for the generator and 0.41 for the discriminator. The average errors between the predicted results and the target parameters are within 0.6 μm. The relative spectral error (RSE) is utilized to quantify the deviation between the simulated spectra obtained from the predicted structures and the target spectra, exhibiting a minimum RSE of 6.26%. Furthermore, comparisons between the proposed model and two other convolutional neural networks validate the superior prediction capability and higher accuracy of our proposed model.

show abstract

Section: Discussionmentioning

confidence: 99%

Inverse design of electromagnetically induced transparency(EIT) metasurface based on deep convolutional generative adversarial network

Zhu,

Zhang,

Dong

et al. 2023

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…In addition, another structural design method is to adjust the order and thickness of the different materials for the improvements of impedance matching [26]. To achieve a satisfactory compromise between the absorbing properties and the total thickness, several optimization approaches have been presented, including genetic algorithm (GA) [27][28][29], deep neural network (NAA) [30,31], particle swarm optimization (PSO) [32,33], and artificial bee colony (ABC) [34]. For instance, a DNN has been proposed to forecast the reflection coefficients based on the structural parameters, which can obtain the optimal configuration efficiently [30].…”

Section: Introductionmentioning

confidence: 99%

Optimal design of multilayer radar absorbing materials: a simulation-optimization approach

Yao

Yang

et al. 2023

Adv Compos Hybrid Mater

View full text Add to dashboard Cite

Multilayer radar absorbing materials with light weight, strong absorption, and wide absorption bandwidth are urgently demanded with the increase of electromagnetic pollution. However, the current design methods with only simulation operation or optimization strategy are not comprehensive. Here, a simulation-optimization approach including electromagnetic simulation and numerical calculation is proposed based on the interaction between different software, in which the homogeneous medium substitution method is presented to simplify the complicated structures. Besides, return loss and impedance matching of different layer structures are investigated. From the simulated results, it can be found that the structures with better impedance matching have superior absorbing performance. The optimal method shows the advantages of fast and efficient, which has tremendous potential for various applications, such as military stealth and electromagnetic wave elimination.

show abstract

“…It is also a popular interdisciplinary subject to introduce machine-learning technology as a tool in assisting the efficient and rapid design of metasurfaces [ 34 , 35 , 36 ]. Various neural networks have been used for designing metasurfaces, including multilayer perceptron (MLP) [ 37 ], deep neural networks [ 38 ], convolutional neural networks (CNN) [ 39 ], auto-encoders [ 40 ], and generative adversarial networks [ 41 ]. Machine learning is also helpful in designing metasurface absorbers.…”

Section: Introductionmentioning

confidence: 99%

“…The forward prediction of the reflective spectra and inverse design of the microwave absorption metasurfaces could be achieved by building different machine-learning models. For example, variational autoencoder and covariance matrix-adaptation evolution strategies are utilized to find the optimal absorber in the X band [ 40 ]. Recent research about the intelligent design of metasurfaces that utilize machine-learning methods are focusing on the geometrical design.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Machine-Learning Model for Efficient Design of Graphene-Based Microwave Metasurfaces for Versatile Absorption Performance

Chen

Zhu

2023

Nanomaterials

View full text Add to dashboard Cite

Graphene, as a widely used nanomaterial, has shown great flexibility in designing optically transparent microwave metasurfaces with broadband absorption. However, the design of graphene-based microwave metasurfaces relies on cumbersome parameter sweeping as well as the expertise of researchers. In this paper, we propose a machine-learning network which enables the forward prediction of reflection spectra and inverse design of versatile microwave absorbers. Techniques such as the normalization of input and transposed convolution layers are introduced in the machine-learning network to make the model lightweight and efficient. Particularly, the tunable conductivity of graphene enables a new degree in the intelligent design of metasurfaces. The inverse design system based on the optimization method is proposed for the versatile design of microwave absorbers. Representative cases are demonstrated, showing very promising performances on satisfying various absorption requirements. The proposed machine-learning network has significant potential for the intelligent design of graphene-based metasurfaces for various microwave applications.

show abstract

Optimal design of microwave absorber using novel variational autoencoder from a latent space search strategy

Cited by 19 publications

References 33 publications

Inverse design of electromagnetically induced transparency(EIT) metasurface based on deep convolutional generative adversarial network

Inverse design of electromagnetically induced transparency(EIT) metasurface based on deep convolutional generative adversarial network

Optimal design of multilayer radar absorbing materials: a simulation-optimization approach

Lightweight Machine-Learning Model for Efficient Design of Graphene-Based Microwave Metasurfaces for Versatile Absorption Performance

Contact Info

Product

Resources

About