A novel nbti-aware chip remaining lifetime prediction framework using machine learning

Yu Guang Chen, Ing Chao Lin, Yong Che Wei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Negative-Bias Temperature Instability (NBTI) poses serious threats to modern ICs and may lead to timing and functional failure. If these failures occur in industrial automated production systems, the malfunctioning system can cause significant economic losses due to unacceptable fabrication quality and yield. Although preventive maintenance is a useful way to avoid such a situation, executing preventive maintenance on a frequent basis will also introduce significant production line downtime. To accurately execute the preventive maintenance just before circuit failure occurs, a chip remaining lifetime estimation method is in demand. In this paper, we propose a framework for predicting the remaining lifetime of the chip. This framework can adapt to changes in the process and operating voltage. The framework tracks representative aging indicators through machine learning methods in order to predict the remaining lifetime of the chip. In addition, we also investigate the impact of changes in hyperparameters, such as training sample sizes, on prediction performance. The experimental results show that the proposed framework achieves an average accuracy and precision of 97.3% and 97.2%, respectively, and the accuracy is 2.54% higher than the strategy used to determine chip health level in a previous work.

Original languageEnglish
Title of host publicationProceedings of the 22nd International Symposium on Quality Electronic Design, ISQED 2021
PublisherIEEE Computer Society
Pages476-481
Number of pages6
ISBN (Electronic)9781728176413
DOIs
Publication statusPublished - 2021 Apr 7
Event22nd International Symposium on Quality Electronic Design, ISQED 2021 - Santa Clara, United States
Duration: 2021 Apr 72021 Apr 9

Publication series

NameProceedings - International Symposium on Quality Electronic Design, ISQED
Volume2021-April
ISSN (Print)1948-3287
ISSN (Electronic)1948-3295

Conference

Conference22nd International Symposium on Quality Electronic Design, ISQED 2021
Country/TerritoryUnited States
CitySanta Clara
Period21-04-0721-04-09

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'A novel nbti-aware chip remaining lifetime prediction framework using machine learning'. Together they form a unique fingerprint.

Cite this