International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Based Fault Prediction and Self-Healing Mechanism in VLSI Circuits |
|---|---|
| ABSTRACT | The increasing complexity and miniaturization of Very Large Scale Integration (VLSI) circuits have significantly improved computational capability and energy efficiency; however, these advancements have also introduced serious reliability challenges. As technology nodes continue to scale into the deep submicron and nanometer regimes, VLSI systems become highly susceptible to a wide range of faults, including permanent faults due to manufacturing imperfections, transient faults caused by radiation and noise, and progressive faults resulting from aging phenomena such as bias temperature instability, hot carrier injection, and electromigration. Conventional fault detection and fault-tolerant techniques, which primarily rely on static redundancy, offline testing, or predefined correction strategies, are often insufficient to handle the dynamic and unpredictable nature of these faults. In this work, an AI-based fault prediction and self-healing framework for VLSI circuits is proposed to enhance system reliability and operational longevity. The proposed approach employs machine learning algorithms to continuously observe and analyze critical internal and environmental parameters such as supply voltage variations, power consumption patterns, timing slack, temperature profiles, and switching activity. By learning complex correlations and degradation trends from both historical and real-time data, the AI model is capable of predicting impending faults at an early stage, enabling proactive intervention before catastrophic failure occurs. The proposed oscilloscope provides user-controlled settings such as time division and voltage division, enabling better visualization of different types of input signals. Triggering functionality is also included to stabilize repetitive waveforms. For data storage and further analysis, the system supports SD card logging, which allows captured waveforms to be saved and reviewed later. Extensive simulation-based evaluation demonstrates that the proposed AI-driven methodology significantly improves fault prediction accuracy, reduces recovery time, and enhances overall system robustness when compared to traditional fault management techniques. Furthermore, the self-healing capability effectively extends circuit lifetime and ensures reliable operation in safety-critical and mission-critical environments. The proposed framework is scalable and flexible, making it suitable for integration into next-generation VLSI architectures used in applications such as automotive electronics, aerospace systems, high-performance computing, and Internet of Things (IoT) devices. |
| AUTHOR | PROF. DR. CHETHAN S, SHAMBHULINGAPPA, SHAREEF SAB, SHREEDHAR HOSUR Department of Electronics Communication and Engineering, Dr. Ambedkar Institute of Technology, Bengaluru, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312065 |
| pdf/65_AI-Based Fault Prediction and Self-Healing Mechanism in.pdf | |
| KEYWORDS | |
| References | 1. Khalil, K. M. A., Eddash, O., Kumar, A., & Bayoumi, M. A. “Intelligent Fault-Prediction Assisted Self-Healing for Embryonic Hardware,” IEEE Transactions on Biomedical Circuits and Systems, vol. 14, no. 3, pp. 583–595, 2020. https://doi.org/10.1109/TBCAS.2020.2985460 2. Ojha, A. K. “AI-Augmented Fault Detection and Diagnosis in VLSI Circuits: A Step Toward Intelligent Chip Design,” Journal of Artificial Intelligence, Machine Learning and Neural Network, vol. 4, no. 6, pp. 145–154, 2024. https://jaimlnn.org/articles/2024-vlsi-fault-ai 3. Singh, R., & Singh, R. “Review and Analysis of Fault Detection in Self-Healing Hardware System,” International Journal of Analog Integrated Circuits, vol. 11, no. 1, pp. 33–42, 2025 https://ijanalogcircuits.org/articles/vlsi-self-healing-review 4. Meyyappan, S., & Alamelumangai, V. “VLSI-Based Self-Healing Solution for Fault-Tolerant Digital Circuits,” International Journal of Development Research, vol. 5, no. 11, pp. 5947–5951, 2015. https://www.journalijdr.com/vlsi-based-self-healing-solution-fault-tolerant-digital-circuits 5. Anonymous “Machine Learning-Based Approach for Transistor-Level Fault Prediction in Hardware Systems,” IEEE Transactions on Circuits and Systems, 2020. https://ieeexplore.ieee.org/document/9124562 6. Moness, M., Gaber, L., Hussein, A. I., & Ali, H. M. “Automated Design Error Debugging of Digital VLSI Circuits sing Semi-Supervised Learning,” Springer VLSI Design Series, 2021. https://link.springer.com/article/10.1007/s10470-021-01835-x 7. Balasubramanian, A., & Gurushankar, N. “AI-Powered Hardware Fault Detection and Self-Healing Mechanisms,” International Journal of Core Engineering & Management, vol. 6, no. 4, pp. 50–56,2019. https://ijcem.org/articles/aifault-vlsi-systems 8. GTKWave – VCD Viewer Tool Used for waveform analysis in digital simulations. https://gtkwave.sourceforge.net 9.Cadence Xcelium / NC-Sim Used for Verilog simulation and VCD generation. https://www.cadence.com/en_US/home/tools/digital-design-and-signoff/simulation/xcelium-parallel-simulator.html 10.Scikit-learn Documentation – Machine Learning in Python https://scikit-learn.org/stable/user_guide.html |
