Leveraging CMOS Aging for Efficient Microelectronics Design

Martinez, Antonio Leonel Hernandez; Khursheed, Saqib; Rossi, Daniele

doi:10.1109/iolts50870.2020.9159742

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, many online applications demand implementation of global indicators of RUL along with warning indication about imminent failure. For such applications, this paper proposes a RUL prediction methodology, based on support vector machine regression (SVMR) [6], [7] that can provide a reliable prediction of RUL, which was introduced in [8]. This enables the system to produce warnings, thus avoiding catastrophic events.…”

Section: Introductionmentioning

confidence: 99%

Online Remaining Useful Lifetime Prediction Using Support Vector Regression

Hernadezmartinez

Khursheed

Alnuayri

et al. 2022

IEEE Trans. Emerg. Topics Comput.

Self Cite

View full text Add to dashboard Cite

An accurate prediction of remaining useful lifetime (RUL) in high reliability and safety electronic systems is required due to its wide use in industrial applications. In this paper, we propose a novel methodology for online RUL prediction, using support vector regression (SVR) model. Through Cadence simulations with 22nm CMOS technology library, we demonstrate that frequency degradation follows a trackable path and depends on temperature, voltage and aging. This characteristic is exploited for training the SVR model, validated over 20 years of aging degradation. Our methodology is capable of highly accurate RUL estimation, requiring a ring oscillator (RO), temperature sensor and trained SVR software model. Using a supply voltage of 0.9 V and variation in temperature from 0°C to 100°C, 13 and 21 stage RO show 90% cases with a RUL prediction deviation of ±0.2 years, and the remaining between ±0.75 and ±0.8 years, respectively. Furthermore, with voltage variation from 0.7 to 0.9V, with steps of 0.05V and four representative temperatures (25, 50, 75 and 100 °C), the 13-RO shows 52% cases between ±0.2 years, 21-RO has 80.5% cases concentrated between ±0.2 years of RUL prediction deviation and remaining cases for both ROs are located between ±0.8 years.

show abstract

Section: Introductionmentioning

confidence: 99%