EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Time Shift Multiscale Ensemble Fuzzy Dispersion Entropy and Its Application in Bearing Fault Diagnosis

Juntong Li, Shunrong Chen, Yuting Shi, Rou Guan, Hua Chen, Shi Yang, Jingyuan Ma, Qilin Wu, Chengjiang Zhou

Coatings · 02.07.2025 · 15 (7) · 779

DOI: 10.3390/coatings15070779 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Coatings, online erschienen am 02.07.2025. Verfasst von Juntong Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, PhD research startup foundation of Yunnan Normal University, Fundamental Research Program of Yunnan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate detection of surface defects such as wear, cracks, and flaws in metallic components is critical for equipment reliability and longevity, representing a core challenge in surface integrity engineering. To solve the information loss, low estimation accuracy and poor noise immunity associated with Multiscale Dispersion Entropy (MDE) are utilized to address the sensitivity to parameter selection and overfitting susceptibility of the Least Squares Twin Support Vector Machines (LSTSVM). A brand new fault diagnosis method which combined Time Shift Multiscale Ensemble Fuzzy Dispersion Entropy (TSMEFuDE) with binary tree LSTSVM (BT LSTSVM) was proposed. Firstly, a time shift method based on Higuchi Fractal Dimension was introduced to TSMEFuDE, resolving the continuity loss between coarse-grained levels. Second, four mapping techniques, linear, NCDF, tansig and logsig, are introduced. This synergetic combination of each advantage results in the improvement of entropy output stability. Furthermore, triangular and trapezoidal membership functions are incorporated into dispersion patterns and abolished in the round function, therefore enhancing the boundaries between the classes after signal mapping to discrete classes. Lastly, the proposed BT LSTSVM algorithm decomposes the multi-classification problem to a binary classification problem, which promotes the robustness of the algorithm. Simulation experiments maintain that TSMEFuDE has stronger adaptability, higher stability, and better noise resistance. In the fault diagnosis experiment, when compared to the Multiscale Fuzzy Dispersion Entropy (MFuDE) combined with the BT TSVM method, the TSMEFuDE combined with BT LSTSVM method improved the accuracy of bearing fault diagnosis by 5.65% and 2.82%.

Förderung

  • National Natural Science Foundation of China
  • PhD research startup foundation of Yunnan Normal University
  • Fundamental Research Program of Yunnan Province
  • Project of Educational Commission of Yunnan Province of China
  • University-Industry Collaborative Education Program

Zitieren

APA

Li, J., Chen, S., Shi, Y., Guan, R., Chen, H., Yang, S., Ma, J., Wu, Q., & Zhou, C. (2025). Time Shift Multiscale Ensemble Fuzzy Dispersion Entropy and Its Application in Bearing Fault Diagnosis. Coatings, 15(7), 779. https://doi.org/10.3390/coatings15070779

Vancouver

Li J, Chen S, Shi Y, Guan R, Chen H, Yang S, et al. Time Shift Multiscale Ensemble Fuzzy Dispersion Entropy and Its Application in Bearing Fault Diagnosis. Coatings. 2025;15(7):779. doi:10.3390/coatings15070779

BibTeX
@article{Li2025,
  author = {Li, Juntong and Chen, Shunrong and Shi, Yuting and Guan, Rou and Chen, Hua and Yang, Shi and Ma, Jingyuan and Wu, Qilin and Zhou, Chengjiang},
  title = {Time Shift Multiscale Ensemble Fuzzy Dispersion Entropy and Its Application in Bearing Fault Diagnosis},
  journal = {Coatings},
  year = {2025},
  volume = {15},
  number = {7},
  pages = {779},
  doi = {10.3390/coatings15070779}
}
Kostenlos starten →