EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A fuzzy-neuro approach to predictive maintenance using vibration signature classification

Asokan Vasudevan, Mohammed El Khider, Yogeesh N, Puspanathan Doraisingam, Khan Sarfaraz Ali, A. Sathishkumar

Sound & Vibration · 31.03.2026

DOI: 10.59400/sv3950 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sound & Vibration, online erschienen am 31.03.2026. Verfasst von Asokan Vasudevan und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vibration-based predictive maintenance must remain reliable under variable speed/load and noise while delivering actionable, interpretable decisions. We propose a fuzzy-neuro framework that maps windowed vibration segments to class decisions and a calibrated risk score with uncertainty. Given a sampled signal , overlapping windows are formed and encoded into a learned signature . Physics-informed indicators (e.g., RMS, kurtosis, band-energy and short-horizon trend) are fused with to form . An end-to-end neuro-adaptive Takagi-Sugeno-Kang (TSK) layer produces a transparent maintenance risk enabling rule-level explanations via dominant firing strengths . To support safe decision-making near thresholds, we estimate an interval risk from predictive samples using quantiles , and width as confidence. Using leakage-safe, unit-aware temporal splitting, experiments on public rolling-bearing benchmarks achieve 0.956 accuracy, 0.952 macro-F1, and 0.941 MCC, while the full model improves calibration and yields sharper risk intervals (mean width 0.132), translating classifier evidence into auditable "monitor/schedule/urgent" actions. These results indicate that the proposed framework is accurate, interpretable, and decision-ready for predictive maintenance.

Zitieren

APA

Vasudevan, A., Khider, M. E., N, Y., Doraisingam, P., Ali, K. S., & Sathishkumar, A. (2026). A fuzzy-neuro approach to predictive maintenance using vibration signature classification. Sound & Vibration. https://doi.org/10.59400/sv3950

Vancouver

Vasudevan A, Khider ME, N Y, Doraisingam P, Ali KS, Sathishkumar A. A fuzzy-neuro approach to predictive maintenance using vibration signature classification. Sound & Vibration. 2026. doi:10.59400/sv3950

BibTeX
@article{Vasudevan2026,
  author = {Vasudevan, Asokan and Khider, Mohammed El and N, Yogeesh and Doraisingam, Puspanathan and Ali, Khan Sarfaraz and Sathishkumar, A.},
  title = {A fuzzy-neuro approach to predictive maintenance using vibration signature classification},
  journal = {Sound & Vibration},
  year = {2026},
  doi = {10.59400/sv3950}
}
Kostenlos starten →