A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation - Université de Lorraine Access content directly
Journal Articles SN Applied Sciences Year : 2023

A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation

Abstract

Abstract Feature selection is a difficult but highly important preliminary step for bearings remaining useful life (RUL) estimation. To avoid the weights setting problem in hybrid metric, this work devotes to conduct feature selection by using a single metric. Due to noise and outliers, an existing feature selection metric, called monotonicity, used for estimating bearings RUL, requires data smoothing processing before adequate implementation. Such a smoothing process may remove significant part of meaningful information from data. To overcome this issue, a mixture distribution analysis-based feature selection metric is proposed. Moreover, based on this new metric, a feature selection approach for bearings RUL estimation is proposed. Numerical experiments benchmarking the proposed method and the existing metric monotonicity method on available real datasets highlight its effectiveness.
s42452-023-05518-1.pdf (1.29 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Licence : CC BY - Attribution

Dates and versions

hal-04470889 , version 1 (22-03-2024)

Licence

Attribution

Identifiers

Cite

Fei Huang, Alexandre Sava, Kondo Hloindo Adjallah, Dongyang Zhang. A mixture distributions analysis based feature selection approach for bearing remaining useful life estimation. SN Applied Sciences, 2023, 5 (11), pp.302. ⟨10.1007/s42452-023-05518-1⟩. ⟨hal-04470889⟩
13 View
2 Download

Altmetric

Share

Gmail Facebook X LinkedIn More