SELF-HEALING VLSI CIRCUITS: A NEW PARADIGM FOR FAULT-TOLERANT DESIGNS IN IOT DEVICES

Authors

  • Dr.D.R.V.A.Sharath Kumar, D.A.Kiran Kumar Author

Keywords:

Self-restoration circuits, fault-tolerant VLSI, IoT safety, Silicon Carbide (SiC), neuromorphic computing, system studying, cyber–physical resilience.

Abstract

The integration of self-restoration capability in Very Large-Scale Integration (VLSI) circuits is revolutionizing fault-tolerant designs in Internet of Things (IoT) gadgets, ensuring resilience against failures and cyber threats. This examine explores the development of self-restoration VLSI circuits, leveraging system mastering for actual-time anomaly detection, fault alerting, and automated remediation. By incorporating neuromorphic computing and spiking neural networks, the proposed approach enhances system adaptability and power performance, allowing independent healing from faults and safety breaches. The Process Design Kit (PDK) evolved for Silicon Carbide (SiC)-based totally low-electricity circuits ensures robustness in extreme environments, with a hit implementation of combinational and sequential circuits running at temperatures up to 500°C. Additionally, electricity-green safety answers which includes lightweight encryption, common sense obfuscation, and novel transistor technologies like tunnel subject-impact transistors (TFETs) and all-spin common sense gadgets are examined. The findings spotlight self-healing as a transformative paradigm for cyber–bodily systems, enhancing reliability in clever grids, medical gadgets, and commercial automation. Future advancements will attention on AI-driven predictive maintenance, deep-gaining knowledge of-based totally protection improvements, and actual-time variation to evolving threats, paving the manner for autonomous, fault-tolerant IoT ecosystems.

 

Downloads

Published

2025-05-13

Issue

Section

Articles

How to Cite

SELF-HEALING VLSI CIRCUITS: A NEW PARADIGM FOR FAULT-TOLERANT DESIGNS IN IOT DEVICES. (2025). Machine Intelligence Research, 19(1), 419-434. https://machineintelligenceresearchs.com/index.php/mir/article/view/257