Citation

A, Ibrar Jahan M and S, Jamuna and Bharti, Gaurav Kumar and R, Kavya and Khushi, Khushi and Ibrahim@Ghazali, Siti Azlida and Amphawan, Angela (2025) Design and Simulation of Radiation-Hardened Conductive-Bridge RAM Cell Towards Durable Artificial Intelligence Chips. In: 2025 Multimedia University Engineering Conference (MECON), 21-23 July 2025, Cyberjaya, Malaysia.

Full text not available from this repository.

Abstract

Advanced computer memory is crucial for artificial intelligence, machine learning and pattern recognition. As the demand for high-density, low-power, and non-volatile memory grows, conductive-bridge RAM (CBRAM) has emerged as a promising alternative to conventional memory technologies. CBRAM operates by forming and dissolving metallic filaments, enabling resistive switching between a low-resistance state (LRS) and a high-resistance state (HRS). However, its susceptibility to radiation-induced failures limits its use in harsh environments, such as in aerospace, oil and gas and defense applications. To address this, we propose a radiation-hardened CBRAM cell using Triple Modular Redundancy (TMR) to enhance fault tolerance. A 1T1R (one-transistor, one-resistor) architecture was implemented for controlled switching, and a 4×4 CBRAM array was developed to evaluate its scalability. Analyzing SET and RESET operations under transient conditions, a Verilog-A model was simulated in Cadence Virtuoso. The results show that TMR effectively reduces single-cell failures, achieving 100% fault coverage through a majority-voter circuit, and also improving data integrity and reliability in radiation-prone environments. Also, challenges such as leakage currents and power overhead were analyzed, highlighting the importance of further optimization. Overall, our research demonstrates that CBRAM, when boosted with TMR, is a strong and radiation-resistant memory option, suitable for use in demanding environments.

Item Type:	Conference or Workshop Item (Other)
Uncontrolled Keywords:	Machine Learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	17 Apr 2026 02:55
Last Modified:	17 Apr 2026 02:55
URII:	http://shdl.mmu.edu.my/id/eprint/15715

Downloads

Edit (login required)