An Adaptive Preprocessing Module for ML/AI-Based SEL/ μ -SEL Detection in COTS Systems Without Physical Modification to the COTS System
IEEE Transactions on Nuclear Science · 2026-08 · 73 (8) · 3043-3052
DOI: 10.1109/tns.2026.3677548 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Nuclear Science, 2026-08. Verfasst von Junkai Zhao und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Gefördert von: Singapore Ministry of Education.
Abstract (Originalsprache)
In our envisioned “Chang’s Next Paradigm of New Space,” commercial-off-the-shelf (COTS) systems—embodying multiple COTS ICs—would be employed in space missions. When applied to COTS systems with power management ICs (including multiple voltage regulators), reported machine learning (ML)/AI-based single-event-latchup (SEL)/ $\mu $ -SEL detection approaches require access to the internal subpower rails (after regulators). This is because regulator-induced distortions significantly obscure SEL/ $\mu $ -SEL characteristics on the external power rail (before regulators). However, accessing internal rails requires physical modification, which is highly undesirable. In this article, we propose an adaptive preprocessing module that, for the first time, enables ML/AI-based SEL/ $\mu $ -SEL detection in COTS systems without physical modification. Specifically, by compensating for regulator-induced distortions, our proposed module allows ML/AI-based approaches to detect SELs/ $\mu $ -SELs by monitoring only the external power rail, thereby, very advantageously, without any physical modification to the COTS system. Integrated with this proposed module, our previous reported AI-based approach achieves a high average detection accuracy of 91.1%. This is a very worthy improvement of 11.1%–53.9% over reported approaches without our proposed module, while incurring modest hardware overhead.
Förderung
- Singapore Ministry of Education
Zitieren
APA
Zhao, J., Chong, K., Shu, W., & Chang, J. S. (2026). An Adaptive Preprocessing Module for ML/AI-Based SEL/ μ -SEL Detection in COTS Systems Without Physical Modification to the COTS System. IEEE Transactions on Nuclear Science, 73(8), 3043-3052. https://doi.org/10.1109/tns.2026.3677548
Vancouver
Zhao J, Chong K, Shu W, Chang JS. An Adaptive Preprocessing Module for ML/AI-Based SEL/ μ -SEL Detection in COTS Systems Without Physical Modification to the COTS System. IEEE Transactions on Nuclear Science. 2026;73(8):3043-3052. doi:10.1109/tns.2026.3677548
BibTeX
@article{Zhao2026,
author = {Zhao, Junkai and Chong, Kwen-Siong and Shu, Wei and Chang, Joseph S.},
title = {An Adaptive Preprocessing Module for ML/AI-Based SEL/ μ -SEL Detection in COTS Systems Without Physical Modification to the COTS System},
journal = {IEEE Transactions on Nuclear Science},
year = {2026},
volume = {73},
number = {8},
pages = {3043--3052},
doi = {10.1109/tns.2026.3677548}
}
EUVIMED