AI-Driven Analysis of Quadruple-Node-Upset Self-Recovery Latches (LQNTL)

المؤلفون

  • Fazal Shah المؤلف
  • Maryam Tariq المؤلف
  • Sahar Ali المؤلف
  • Abdulaziz Hani Aldali المؤلف

DOI:

https://doi.org/10.59992/IJCI.2026.v5n11p5

الكلمات المفتاحية:

Fault-tolerant latch، Quadruple-Node-Upset (QNU)، Single Event Upset (SEU)، Machine Learning، Reinforcement Learning، Soft Error Resilience، HSPICE Simulation، Monte Carlo Fault Injection، Markov Model، Power-Delay Trade off، Process-Voltage-Temperature (PVT) Variations، AI-Driven Fault Correction، Self-Recovery Mechanism، Low-Power Design، Radiation-Hardened Computing

الملخص

In particular, Single Event Upsets and Multiple Bit Upsets created by radiation lead to severe problems for mission critical computing systems such as aerospace, nuclear, as well as safety critical embedded processors. Although QNU remains the most severe error, TMR Latches [3], ECC Latches [4], and DICE [1] are no longer viable because while remaining low power consuming, they incur significant delay overhead to inject QNU. In this paper, the Quadruple Node Upset Self Recovery Latch (LQNTL) is proposed, a fault tolerant latch that employs multi feedback redundancy with machine learning based optimization aimed at soft error resilience improvement.

The methodology is evaluated in terms of the fault recovery efficiency through simulation using HSPICE and transistor level, and fault injection using MC; and using AI models based on LSTM, SVM and Random Forests networks. In the second category, Maskov Models are used to probabilistically model transitions between fault state and Reinforcement Learning (RL) algorithms are employed to choose the best self-recovery mechanism through RL in order to make transitions between fault states adaptively in real time.

Simulation shows that LQNTL is superior at PVT variations to conventional latches and has 95% recovery success, a much reduced Mean time to Recovery (MTTR) (~10–15ns vs. 20–30ns in conventional latches), and a much safer and more robust latch using state-of-the art processes. LQNTL consumes a factor of 10–20 % more power than LQNTL but has superior fault tolerance and capability to determine errors a la deterministic. This thesis contributes to a thorough literature review of previous fault tolerant latch implementation, the gaps in the current design and the future direction for fault tolerant latch design using AI driven optimizations for next generation of radiation hardened computing architecture. The results indicate that LQNTL could constitute a foundation for future fault tolerant microprocessors, FPGAs and memory architectures in such environments of extreme demand, low power and self-recovery. Adaptive power management, neuromorphic inspired fault prediction, as well as extensions for quantum error correction of latch reliability are all considered for future work.

السير الشخصية للمؤلفين

  • Fazal Shah

    PHD in Artificial Intelligence, School of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China

  • Maryam Tariq

    Masters in Computer Science and Engineering, School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, China

  • Sahar Ali

    PHD in Artificial Intelligence, School of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China

  • Abdulaziz Hani Aldali

    Masters in Artificial Intelligence, School of Artificial Intelligence Anhui University of Science and Technology, Huainan, China

المراجع

1. Hatefinasab, S. et al. (2022) “Highly reliable quadruple-node upset-tolerant D-latch,” IEEE access: practical innovations, open solutions, 10, pp. 31836–31850. Available at: https://doi.org/10.1109/access.2022.3160448.

2. Yan, A. et al. (2023) “Designs of two quadruple-node-upset self-recoverable latches for highly robust computing in harsh radiation environments,” IEEE transactions on aerospace and electronic systems, 59(3), pp. 2885–2897. Available at: https://doi.org/10.1109/taes.2022.3219372.

3. Yan, A. et al. (01 Jan-March 2022) “Novel quadruple-node-upset-tolerant latch designs with optimized overhead for reliable computing in harsh radiation environments,” IEEE transactions on emerging topics in computing, 10(1), pp. 404–413. Available at: https://doi.org/10.1109/tetc.2020.3025584.

4. Hao, L. et al. (2024) “Low-cost and highly robust quadruple node upset tolerant latch design,” IEEE transactions on very large scale integration (VLSI) systems, 32(5), pp. 883–896. Available at: https://doi.org/10.1109/tvlsi.2024.3357312.

5. Huang, Z. et al. (2024) “NEST: A quadruple-node upset recovery latch design and algorithm-based recovery optimization,” IEEE transactions on aerospace and electronic systems, 60(4), pp. 4590–4600. Available at: https://doi.org/10.1109/taes.2024.3379962.

6. Yan, A. et al. (2025) “Cost-optimized and highly robust latches providing complete quadruple-node-upset tolerance and recovery with algorithm based verifications,” IEEE transactions on aerospace and electronic systems, PP (99), pp. 1–14. Available at: https://doi.org/10.1109/taes.2024.3525448.

7. Alkady, G.I. et al. (2022) “Single event upset and single event transient detection in FPGA-based search and rescue systems,” in 2022 11th Mediterranean Conference on Embedded Computing (MECO). IEEE, pp. 1–5.

8. Sit, M.A., Koylu, C. and Demir, I. (2020) “Identifying disaster-related tweets and their semantic, spatial and temporal context using deep learning, natural language processing and spatial analysis: a case study of Hurricane Irma,” in Social Sensing and Big Data Computing for Disaster Management. Routledge, pp. 8–32.

9. Liu, S. et al. (2022) “A polarity-driven radiation-hardened latch design for single event upset tolerance,” in 2022 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT). IEEE, pp. 1–6.

10. Peng, C. et al. (2020) “A triple-thresholds pavement crack detection method leveraging random structured forest,” Construction and building materials, 263(120080), p. 120080. Available at: https://doi.org/10.1016/j.conbuildmat.2020.120080.

11. Xu, H. et al. (2023) “LQNTL: Low-overhead quadruple-node-upset self-recovery latch based on triple-mode redundancy,” Integration (Amsterdam, Netherlands), 91, pp. 126–135. Available at: https://doi.org/10.1016/j.vlsi.2023.03.008.

12. Xu, H. et al. (2024) “A highly reliable and low-overhead quadruple-node-upset tolerant latch design,” Microelectronics and reliability, 157(115413), p. 115413. Available at: https://doi.org/10.1016/j.microrel.2024.115413.

13. Xu, H., Liu, C., et al. (2024) “Hardened latch designs based on the characteristic of transistor for mitigating multiple-node-upsets in harsh radiation environments,” Microelectronics Journal, 143(106031), p. 106031. Available at: https://doi.org/10.1016/j.mejo.2023.106031.

14. Li, Q. et al. (2020) “Self-recovery tolerance latch design based on the radiation mechanism,” IEEE access: practical innovations, open solutions, 8, pp. 220152–220164. Available at: https://doi.org/10.1109/access.2020.3040189.

15. Huang, Z. et al. (2021) “LC-TSL: A low-cost triple-node-upset self-recovery latch design based on heterogeneous elements for 22 nm CMOS,” Microelectronics, 117(105281), p. 105281. Available at: https://doi.org/10.1016/j.mejo.2021.105281.

16. Peng, C. et al. (2024) “High-performance latch designs of double-node-upset self-recovery and triple-node-upset tolerance for aerospace applications,” IEEE transactions on aerospace and electronic systems, 60(5), pp. 6550–6561. Available at: https://doi.org/10.1109/taes.2024.3406311.

17. Li, H., Zhao, X. and Li, J. (2025) “Design of self-recovering low-cost multiple-node-upset-tolerant latch,” Integration (Amsterdam, Netherlands), 101(102342), p. 102342. Available at: https://doi.org/10.1016/j.vlsi.2024.102342.

18. Kumar, S. and Mukherjee, A. (2022) “A triple-node upset self-healing latch for high speed and robust operation in radiation-prone harsh-environment,” Microelectronics and reliability, 139(114857), p. 114857. Available at: https://doi.org/10.1016/j.microrel.2022.114857.

19. Huang, Z. et al. (2023) “Overhead optimized and quadruple-node-upset self-recoverable latch design based on looped C-element matrix,” IEEE transactions on aerospace and electronic systems, 59(6), pp. 9357–9367. Available at: https://doi.org/10.1109/taes.2023.3316998.

20. Singh, H.K. et al. (2024) “Self-healing email systems: Autonomous recovery from cyber attacks,” in 2024 International Conference on Knowledge Engineering and Communication Systems (ICKECS). IEEE, pp. 1–4.

21. Pan, X. et al. (2023) “Radial electromagnetic type unbalance vibration self-recovery regulation system for high-end grinding machine spindles,” Frontiers of Mechanical Engineering, 18(3). Available at: https://doi.org/10.1007/s11465-023-0763-1.

22. Thanasekhar, B. et al. (2019) “Fault and delay tolerance in deep learning framework under GPU,” in 2019 11th International Conference on Advanced Computing (ICoAC). IEEE, pp. 139–146.

23. Garcia Freitas, P., Rigoni, R. and Farias, M.C.Q. (2016) “Secure self-recovery watermarking scheme for error concealment and tampering detection,” Journal of the Brazilian Computer Society, 22(1). Available at: https://doi.org/10.1186/s13173-016-0046-3.

24. Tsang, G. and Xie, X. (2021) “Deep learning based sepsis intervention: The modelling and prediction of severe sepsis onset,” in 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, pp. 8671–8678.

25. Zhou, J. and Xu, H. (2023) A cross-coupled interlocked-storage-cells- based quadruple-node upsets self-recover- able latch design, Jos.ac.cn. Available at: http://arxiv.jos.ac.cn/fileJOSARXIV/journal/article/jos/arXiv/PDF/2021/12/00041.PDF

26. He, L. et al. (2024) “A low-cost quadruple-node-upsets resilient latch design,” IEEE transactions on very large scale integration (VLSI) systems, 32(10), pp. 1930–1939. Available at: https://doi.org/10.1109/tvlsi.2024.3430224.

27. Hao, L., Zhang, X., et al. (2024) “Soft-error-immune quadruple-node-upset tolerant latch based on polarity design and source-isolation technologies,” IEEE transactions on very large scale integration (VLSI) systems, 32(4), pp. 597–608. Available at: https://doi.org/10.1109/tvlsi.2023.3342982.

28. Yan, A., Zhou, C., et al. (2023) “Design of a novel latch with quadruple-node-upset recovery for harsh radiation hardness,” in 2023 IEEE International Test Conference in Asia (ITC-Asia). IEEE, pp. 1–6.

29. Hao, L. et al. (2025) “A low-cost and triple-node-upset self-recoverable latch design with low soft error rate,” IEEE transactions on very large scale integration (VLSI) systems, PP (99), pp. 1–10. Available at: https://doi.org/10.1109/tvlsi.2025.3528199.

30. Huang, Z., Chen, X., et al. (2024) “Design of radiation hardened latch with low delay and tolerance of quadruple-node-upset in 32 nm process,” Microelectronics Journal, 153(106428), p. 106428. Available at: https://doi.org/10.1016/j.mejo.2024.106428.

التنزيلات

منشور

2026-11-16

إصدار

القسم

المقالات

كيفية الاقتباس

Fazal Shah, Maryam Tariq, Sahar Ali, & Abdulaziz Hani Aldali. (2026). AI-Driven Analysis of Quadruple-Node-Upset Self-Recovery Latches (LQNTL). المجلة الدولية للحاسبات والمعلوماتية, 5(11). https://doi.org/10.59992/IJCI.2026.v5n11p5