EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Metric-Driven Evaluation Framework for Remaining Useful Life Prognosis with Quantified Uncertainty

Govind Vashishtha iD, Sumika Chauhan iD, Merve Ertarğın iD

Sensors · 03.04.2026 · 26 (7) · 2230

DOI: 10.3390/s26072230 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.04.2026. Verfasst von Govind Vashishtha und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Geoengineering, Mining and Geology, Wroclaw University of Science and Technology, Na Grobli 15, 50-421 Wroclaw, Poland. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper introduces a novel metric-driven evaluation framework for Remaining Useful Life (RUL) prognosis in rotating machinery, featuring robust uncertainty quantification. Accurate RUL prediction is vital for optimizing maintenance and preventing failures, but existing methods often struggle with complex nonlinear degradation or lack reliable uncertainty estimates. Our proposed framework integrates a probabilistic Deep State Space Model (DSSM) with a variational inference approach to model complex, non-linear degradation trends and inherent aleatoric uncertainty. A key innovation is the use of the Slime Mold Algorithm (SMA) for efficient hyperparameter optimization, ensuring maximum accuracy. Furthermore, an online adaptation mechanism, governed by a heuristic reinforcement learning agent, allows the model to continuously update its knowledge and adapt to concept drift in real-time. Experimental validation on the IMS bearing dataset demonstrates superior RUL prediction accuracy, evidenced by the lowest Root Mean Square Error (RMSE) of 8.1829 cycles, and a PICP of 0.59416. This dual capability makes the framework highly suitable for real-world predictive maintenance, enhancing safety and reliability.

Schlagwörter

Stichwörter der Autor:innen

deep state space modellong short-term memoryremaining useful lifeslime mold optimizationuncertainty quantification

Autor:innen und Institutionen

  • Faculty of Geoengineering, Mining and Geology, Wroclaw University of Science and Technology, Na Grobli 15, 50-421 Wroclaw, Poland.
  • Department of Mechanical Engineering, Graphic Era Deemed to Be University, Dehradun 248002, India.
  • Department of Electrical and Electronics Engineering, University of Munzur, Tunceli 62000, Turkey.

ORCID-Profile: Govind Vashishtha, Sumika Chauhan, Merve Ertarğın

Zitieren

APA

Vashishtha, G., Chauhan, S., & Ertarğın, M. (2026). A Metric-Driven Evaluation Framework for Remaining Useful Life Prognosis with Quantified Uncertainty. Sensors, 26(7), 2230. https://doi.org/10.3390/s26072230

Vancouver

Vashishtha G, Chauhan S, Ertarğın M. A Metric-Driven Evaluation Framework for Remaining Useful Life Prognosis with Quantified Uncertainty. Sensors. 2026;26(7):2230. doi:10.3390/s26072230

BibTeX
@article{Vashishtha2026,
  author = {Vashishtha, Govind and Chauhan, Sumika and Ertarğın, Merve},
  title = {A Metric-Driven Evaluation Framework for Remaining Useful Life Prognosis with Quantified Uncertainty},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2230},
  doi = {10.3390/s26072230}
}
Kostenlos starten →