Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102847 - 102847
Published: Oct. 1, 2024
Language: Английский
Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102847 - 102847
Published: Oct. 1, 2024
Language: Английский
IET Science Measurement & Technology, Journal Year: 2025, Volume and Issue: 19(1)
Published: Jan. 1, 2025
Abstract Due to the untimely deployment of sensors and early retirement high‐voltage circuit breakers, life‐cycle data is missing, leading an inability accurately predict mechanical performance degradation trend. A new modelling prediction method breakers considering censored was proposed. Firstly, multiple imputation by chained equations used impute missing values in dataset breaker closing time, creating interpolated dataset. Secondly, Nadaraya–Watson kernel regression employed smoothly estimate eliminate measurement errors. Then, functional principal component analysis utilized extract common trend deviation construct model. Finally, Bayesian inference applied dynamically update model parameters breaker. The results showed that proposed capable achieving better interpolation accuracy under condition different time breakers. Moreover, as progressed, dynamic effect improved. research can be provide effective decision‐making basis for operation maintenance strategy
Language: Английский
Citations
1Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102847 - 102847
Published: Oct. 1, 2024
Language: Английский
Citations
4