Reliability-Aware Machine Learning Prediction for Multi-Cycle Long-Term PMOS NBTI Degradation in Robust Nanometer ULSI Digital Circuit Design
Year: 2025
Type: conference-paper
Abstract: This paper focuses on enhancing the reliability of robust nanometer Ultra Large Scale Integrated (ULSI) digital circuits by employing a machine learning approach for predicting multi-cycle, long-term PMOS Negative Bias Temperature Instability (NBTI) degradation. The study utilizes the 32nm technology node at temperatures of 300K and 400K, employing the HSPICE MOSRA tool. Support Vector Regression, Random Forest, K-Nearest Neighbor, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference Systems are employed for training and testing datasets. Results reveal the significant impact of NBTI degradation on threshold voltage and subsequent effects on circuit performance. The proposed machine learning models exhibit reliability-aware predictions with over 99% accuracy, providing valuable insights for robust ULSI digital circuit design.
Authors: Karan Singh, Shruti Kalra
Institution: Jaypee Institute of Information Technology
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4409759840