Efficient RCS Prediction of the Conducting Target Based on Physics-Inspired Machine Learning and Experimental Design

Xiao, Donghai; Guo, Lixin; Liu, Wei; Hou, Muyu

doi:10.1109/tap.2020.3027594

Cited by 19 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with algorithms in similar literatures or other ML benchmark techniques, the RMSE of the SLICY model is reduced from 36.6% to 66.1%. In Table 3, the mono-RCS prediction capability of the proposed method for a single frequency point is compared with the physical-optics-inspired (POI) SVR [9], which is a physical-inspired method. As shown in the Table 2 gives the RMSE and cost time comparison of different models.…”

Section: B Mono-rcs Of the Slicy Modelmentioning

confidence: 99%

“…Researchers have proposed ML models for EM solver design [2], repairing damaged receivers' data [3], and low scattering meta-surface design [4], etc. ML has also been applied in RCS prediction [5][6][7][8][9][10], but the existing techniques still have some limitations. For instance, 8326 samples are required for a single frequency point in [5], which may not be applicable for computationally expensive EM problems.…”

Section: Introductionmentioning

confidence: 99%

“…The ML models in [6,7] are effective only when the direction of the incident wave varies in one direction (θ or ϕ direction), which ignore the mono-RCS variation in the entire space. The physicsinspired model in [9] is suitable for the mono-RCS estimation at a single frequency point, while its wideband performance is not further considered. [10] discusses the RCS prediction over a wide frequency band, but the aspect angle variation range is only 10 degrees, and the sampling interval is very close (0.2-degree step), which results in massive computational costs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wideband Monostatic RCS Prediction of Complex Objects using Support Vector Regression and Grey-wolf Optimizer

Zhang,

Wang,

2024

ACES Journal

View full text Add to dashboard Cite

This paper presents a method based on the support vector regression (SVR) model and grey wolf optimizer (GWO) algorithm to efficiently predict the monostatic radar cross-section (mono-RCS) of complex objects over a wide angular range and frequency band. Using only a small-size of the mono-RCS data as the training set to construct the SVR model, the proposed method can predict accurate mono-RCS of complex objects under arbitrary incident angle over the entire three-dimensional space. In addition, the wideband prediction capability of the method is significantly enhanced by incorporating the meta-heuristic algorithm GWO. Numerical experiments verify the efficiency and accuracy of the proposed SVR-GWO model over a wide frequency band.

show abstract

Section: B Mono-rcs Of the Slicy Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wideband Monostatic RCS Prediction of Complex Objects using Support Vector Regression and Grey-wolf Optimizer

Zhang,

Wang,

2024

ACES Journal

View full text Add to dashboard Cite

show abstract

“…AI techniques have been introduced into communications over the last two decades. They have addressed many bottlenecks that the conventional methods are not able to resolve, from communication system design to propagation channel research [18], [23]- [26], with the latter being the focus of this section 1 .…”

Section: B Application Of ML To Propagation Channelsmentioning

confidence: 99%

Artificial Intelligence Enabled Radio Propagation for Communications—Part I: Channel Characterization and Antenna-Channel Optimization

Huang

et al. 2022

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

To provide higher data rates, as well as better coverage, cost efficiency, security, adaptability, and scalability, the 5G and beyond 5G networks are developed with various artificial intelligence techniques. In this two-part paper, we investigate the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels. It firstly provides a comprehensive overview of ML for channel characterization and ML-based antenna-channel optimization in this first part, and then it gives a state-of-the-art literature review of channel scenario identification and channel modeling in Part II. Fundamental results and key concepts of ML for communication networks are presented, and widely used ML methods for channel data processing, propagation channel estimation, and characterization are analyzed and compared. A discussion of challenges and future research directions for MLenabled next generation networks of the topics covered in this part rounds off the paper.

show abstract

“…It predicts EM characteristics of any point in the design space, reducing the time needed for device design and optimization. Various machine learning methods, including support vector regression (SVR), gaussian process regression (GPR), Kriging, back propagation neural network (BPNN), and deep learning, are used for surrogate modeling [24][25][26][27][28][29]. Deep learning has been recently applied to metasurface design, allowing for more efficient and automated processes [30][31][32].…”

Section: Introductionmentioning

confidence: 99%

Inverse design of ultra-wideband transparent frequency selective surface absorbers based on evolutionary deep learning

Pan,

Dong,

Wang

et al. 2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

Conventional frequency selective surface (FSS) absorbers design is time-consuming, involving multiple electromagnetic (EM) simulations for parameter scanning. A novel reverse design method is proposed utilizing evolutionary deep learning (EDL) based on an improved bacterial foraging optimization (IBFO) algorithm and a deep belief network. It establishes the relationship between the geometric structure and EM response. The combination of IBFO and EDL facilitates an efficient optimization for structural parameters, mitigating the "one-to-many" problem and accelerating the design process. An optically transparent FSS absorber with an ultra-bandwidth of 8-18GHz is designed to verify the proposed method’s capability. The simulation and experimental results demonstrate that the absorber displays exceptional characteristics such as polarization insensitivity and robustness under a 45° oblique incidence angle, making it a suitable candidate for radar stealth and photovoltaic solar energy applications. The proposed method can be applied to the design and optimization of various absorbers and complex EM devices.

show abstract

Efficient RCS Prediction of the Conducting Target Based on Physics-Inspired Machine Learning and Experimental Design

Cited by 19 publications

References 36 publications

Wideband Monostatic RCS Prediction of Complex Objects using Support Vector Regression and Grey-wolf Optimizer

Wideband Monostatic RCS Prediction of Complex Objects using Support Vector Regression and Grey-wolf Optimizer

Artificial Intelligence Enabled Radio Propagation for Communications—Part I: Channel Characterization and Antenna-Channel Optimization

Inverse design of ultra-wideband transparent frequency selective surface absorbers based on evolutionary deep learning

Contact Info

Product

Resources

About