Skip to main content

Three-Stage Generative and Surrogate Modeling Framework for Efficient MIMO Antenna Decoupling in Vehicular Communications

Journal articles  - Journal Article
Wang, J; Li, J; Li, G; Liao, S; Joines, WT
Published in: IEEE Transactions on Vehicular Technology
September 1, 2026

This paper presents a data-efficient optimization framework for compact MIMO antenna decoupling in space-constrained vehicular communications. To address the challenges of mutual coupling and limited training data, a three-stage data generation pipeline is proposed, including a frequency-aware data partitioning, a multibranch encoder-assisted conditional generative adversarial network, and a dual-filtering strategy for quality assurance. High-fidelity generated data are used to train forward and inverse surrogate models, enabling fast and accurate antenna design optimization without repeated electromagnetic simulations. Applied to a broadband stacked patch antenna array, the optimized design achieves a measured isolation of -42.75 dB and meets bandwidth and reflection criteria. Compared with traditional simulation-based methods, the proposed framework reduces the full-wave simulation time for data generation by 83.43%. These results highlight the potential of combining generative modeling and surrogate learning for intelligent and efficient antenna design in next-generation vehicular MIMO systems.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

IEEE Transactions on Vehicular Technology

DOI

EISSN

1939-9359

ISSN

0018-9545

Publication Date

September 1, 2026

Volume

75

Issue

9

Start / End Page

20396 / 20408

Related Subject Headings

  • Automobile Design & Engineering
  • 46 Information and computing sciences
  • 40 Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, J., Li, J., Li, G., Liao, S., & Joines, W. T. (2026). Three-Stage Generative and Surrogate Modeling Framework for Efficient MIMO Antenna Decoupling in Vehicular Communications. IEEE Transactions on Vehicular Technology, 75(9), 20396–20408. https://doi.org/10.1109/TVT.2026.3689643
Wang, J., J. Li, G. Li, S. Liao, and W. T. Joines. “Three-Stage Generative and Surrogate Modeling Framework for Efficient MIMO Antenna Decoupling in Vehicular Communications.” IEEE Transactions on Vehicular Technology 75, no. 9 (September 1, 2026): 20396–408. https://doi.org/10.1109/TVT.2026.3689643.
Wang J, Li J, Li G, Liao S, Joines WT. Three-Stage Generative and Surrogate Modeling Framework for Efficient MIMO Antenna Decoupling in Vehicular Communications. IEEE Transactions on Vehicular Technology. 2026 Sep 1;75(9):20396–408.
Wang, J., et al. “Three-Stage Generative and Surrogate Modeling Framework for Efficient MIMO Antenna Decoupling in Vehicular Communications.” IEEE Transactions on Vehicular Technology, vol. 75, no. 9, Sept. 2026, pp. 20396–408. Scopus, doi:10.1109/TVT.2026.3689643.
Wang J, Li J, Li G, Liao S, Joines WT. Three-Stage Generative and Surrogate Modeling Framework for Efficient MIMO Antenna Decoupling in Vehicular Communications. IEEE Transactions on Vehicular Technology. 2026 Sep 1;75(9):20396–20408.

Published In

IEEE Transactions on Vehicular Technology

DOI

EISSN

1939-9359

ISSN

0018-9545

Publication Date

September 1, 2026

Volume

75

Issue

9

Start / End Page

20396 / 20408

Related Subject Headings

  • Automobile Design & Engineering
  • 46 Information and computing sciences
  • 40 Engineering