EUVIMEDEUVIMED entdecken
Crossref

AI-Assisted Design of FISO CFP-DEMOS Devices via Transfer Learning and Multiobjective Optimization

Xiaoyun Huang, Yixian Song, Hongyu Tang, Yan Pan, Yiting Ye, Boying Meng, Shuang Wang, Zenan Wang, Dawei Gao, Kai Xu

IEEE Transactions on Electron Devices · 2026-05 · 73 (5) · 2680-2688

DOI: 10.1109/ted.2026.3674877 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Electron Devices, 2026-05. Verfasst von Xiaoyun Huang und 9 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: Zhejiang Province Key Research and Development Programs, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drain-extended metal–oxide–semiconductor (DEMOS) devices are critical components in power management integrated circuits (PMICs), yet their optimization faces significant challenges, including prohibitive experimental costs, limited datasets, and inadequate modeling of process variations. This research presents an AI-assisted device design framework for optimizing fully isolated contact field plate DEMOS (FISO CFP-DEMOS) devices. The framework employs a modular architecture integrating two key components: a pretraining and fine-tuning neural network for performance prediction, and an adaptive multiobjective optimization algorithm. The predictive model leverages uncalibrated simulation data during pretraining to learn fundamental device physics, followed by fine-tuning with minimal experimental measurements to capture real fabrication conditions. This transfer learning approach achieves mean absolute percentage errors (MAPEs) of 3.53% for breakdown voltage ( $V_{\text {BD}}$ ) and 3.08% for specific on-resistance ( $R_{\text {on},\text {SP}}$ ) using only 1% of available experimental data. The sequential optimization algorithm then systematically optimizes process and structural parameters across multiple voltage ratings (9–40 V) while ensuring fabrication feasibility. Experimental validation demonstrates figure-of-merit (FOM) improvements up to 52.01% compared to baseline devices. This methodology significantly reduces development cycles and experimental costs while maintaining high prediction accuracy and practical manufacturability, establishing an efficient pathway for next-generation power semiconductor device development.

Förderung

  • Zhejiang Province Key Research and Development Programs
  • National Natural Science Foundation of China

Zitieren

APA

Huang, X., Song, Y., Tang, H., Pan, Y., Ye, Y., Meng, B., Wang, S., Wang, Z., Gao, D., & Xu, K. (2026). AI-Assisted Design of FISO CFP-DEMOS Devices via Transfer Learning and Multiobjective Optimization. IEEE Transactions on Electron Devices, 73(5), 2680-2688. https://doi.org/10.1109/ted.2026.3674877

Vancouver

Huang X, Song Y, Tang H, Pan Y, Ye Y, Meng B, et al. AI-Assisted Design of FISO CFP-DEMOS Devices via Transfer Learning and Multiobjective Optimization. IEEE Transactions on Electron Devices. 2026;73(5):2680-2688. doi:10.1109/ted.2026.3674877

BibTeX
@article{Huang2026,
  author = {Huang, Xiaoyun and Song, Yixian and Tang, Hongyu and Pan, Yan and Ye, Yiting and Meng, Boying and Wang, Shuang and Wang, Zenan and Gao, Dawei and Xu, Kai},
  title = {AI-Assisted Design of FISO CFP-DEMOS Devices via Transfer Learning and Multiobjective Optimization},
  journal = {IEEE Transactions on Electron Devices},
  year = {2026},
  volume = {73},
  number = {5},
  pages = {2680--2688},
  doi = {10.1109/ted.2026.3674877}
}
Kostenlos starten →