Remaining Useful Life Prediction of Aerial Bundled Cables in Coastal Areas Using Thermal and Corrosion Degradation Models

Binyousuf, Waleed; Khan, Tariq Amin; Tariq, Syed Muhammad Talha; Hassan, Mohsan; Shah, Abad

doi:10.1109/tpwrd.2021.3112081

Cited by 5 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [7] a range of power system equipment inspection data are used to predict the failure rate, which resolve the bias from the conventional average reliability model in an economical way; a follow on study [7] [8] developed a condition assessment method for reclosers with condition data. Additionally, conventional lifetime estimation for low-value assets normally consider physics based models, such as [9] [10], which are impractical for large asset fleets. However, none of these worked on end-life anticipation with raw periodic inspection data, typically the only data available on such assets, and consequently did not have to address the problem of missing test values.…”

Section: Introductionmentioning

confidence: 99%

A Gaussian Process Based Fleet Lifetime Predictor Model for Unmonitored Power Network Assets

Stephen

Chandarasupsang

et al. 2023

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

This paper proposes the use of Gaussian Process Regression to automatically identify relevant predictor variables in a formulation of a remaining useful life model for unmonitored, low value power network assets. Reclosers are used as a proxy for evaluating the efficacy of this method. Distribution network reclosers are typically high-volume assets without on-line monitoring, leading to an insufficient understanding of which factors drive their failures. The ubiquity of reclosers, and their lack of monitoring, prevents the tracking of their individual remaining life, and, confirms their use in validating the proposed process. As an alternative to monitoring, periodic inspection data is used to evaluate asset risk level, which is then used in a predictive model of remaining useful life. Inspection data is often variable in quality with a number of features missing from records. Accordingly, missing inputs are imputed by the proposed process using samples drawn from an advanced form of joint distribution learned from test records and reduced to its conditional form. This work is validated on operational data provided by a regional distribution network operator, but conceptually is applicable to unmonitored fleets of assets of any power network.

show abstract

Section: Introductionmentioning

confidence: 99%