EUVIMEDEUVIMED entdecken
Crossref

A hybrid HMM-RBFNN system using relevant and non-redundant features for bearing fault classification

Miloud Sedira, Ahmed Felkaoui

Comptes Rendus. Mécanique · 15.04.2026 · 354 (G1) · 365-395

DOI: 10.5802/crmeca.350 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Comptes Rendus. Mécanique, online erschienen am 15.04.2026. Verfasst von Miloud Sedira und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents an innovative hybrid approach that combines Hidden Markov Models (HMM) with Radial Basis Function Neural Networks (RBFNN) for the automatic classification of mechanical faults in rolling element bearings using vibration signal analysis. The signals are sourced from the well-established database ( https://engineering.case.edu/bearingdatacenter/welcome ), widely used in fault diagnosis research. Raw signals are preprocessed to extract relevant features across time, frequency, and time–frequency domains, including wavelet packet decomposition. To enhance classification robustness and reduce computational complexity, dimensionality reduction is performed using Principal Component Analysis (PCA), complemented by Fisher score-based feature selection. HMMs are trained to capture the temporal dynamics of the signals, while RBFNNs leverage the reduced feature space for fine-grained classification. A comprehensive performance comparison is conducted between standalone HMM and RBFNN models, as well as their integration within the hybrid HMM-RBFNN system. Experimental results demonstrate that the proposed hybrid method significantly improves classification accuracy, highlighting its potential for industrial predictive maintenance applications.

Zitieren

APA

Sedira, M., & Felkaoui, A. (2026). A hybrid HMM-RBFNN system using relevant and non-redundant features for bearing fault classification. Comptes Rendus. Mécanique, 354(G1), 365-395. https://doi.org/10.5802/crmeca.350

Vancouver

Sedira M, Felkaoui A. A hybrid HMM-RBFNN system using relevant and non-redundant features for bearing fault classification. Comptes Rendus. Mécanique. 2026;354(G1):365-395. doi:10.5802/crmeca.350

BibTeX
@article{Sedira2026,
  author = {Sedira, Miloud and Felkaoui, Ahmed},
  title = {A hybrid HMM-RBFNN system using relevant and non-redundant features for bearing fault classification},
  journal = {Comptes Rendus. Mécanique},
  year = {2026},
  volume = {354},
  number = {G1},
  pages = {365--395},
  doi = {10.5802/crmeca.350}
}
Kostenlos starten →