EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-Gradient-Descent-Integrated Physics-Informed Autoencoder for Sensor Fault Detection in Data Center Chillers

Xinyue Shen, Pan Li, Chen Xu, Chengliang Xu

Sensors · 11.05.2026 · 26 (10) · 3025

DOI: 10.3390/s26103025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.05.2026. Verfasst von Xinyue Shen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Urban Construction, Wuhan University of Science and Technology, Wuhan 430065, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The operating status of chillers in data centers critically affects temperature stability and energy efficiency, imposing stringent requirements on the accuracy, robustness, and adaptability of sensor fault detection systems. Existing Physics-Informed Autoencoders (PIAE) for chiller fault detection face challenges such as gradient conflicts and limited generalization, especially under complex fault scenarios like sensor drift, stuck faults, and precision attenuation. To address these limitations, we propose a Multi-Gradient Descent Algorithm-integrated PIAE (MGDA-PIAE), which embeds the chiller thermal balance equation as a hard constraint and dynamically determines Pareto-optimal weights between data reconstruction and physical consistency. By unifying feature learning with physical law constraints, the model achieves improved generalization and stable performance across diverse operational conditions. Validation using operational data from a data center in Guangzhou demonstrates that MGDA-PIAE significantly outperforms conventional AE and PIAE models: the average recall increases by approximately 20% and the F1-score by 10%, while for flow sensor faults, the F1-score improves by over 80% compared with AE and 20% compared with PIAE. Further tests on multiple sensor types confirm that the model maintains high-precision detection with low false negatives under varying operating modes. By adjusting a single physical threshold, MGDA-PIAE can flexibly meet different fault detection requirements, providing a practical and reliable solution for maintaining the efficient, stable, and safe operation of data center refrigeration systems.

Schlagwörter

Stichwörter der Autor:innen

chillerdata centermultiple gradient descent algorithmphysics-informed autoencodersensor fault detection

Autor:innen und Institutionen

  • School of Urban Construction, Wuhan University of Science and Technology, Wuhan 430065, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Shen, X., Li, P., Xu, C., & Xu, C. (2026). A Multi-Gradient-Descent-Integrated Physics-Informed Autoencoder for Sensor Fault Detection in Data Center Chillers. Sensors, 26(10), 3025. https://doi.org/10.3390/s26103025

Vancouver

Shen X, Li P, Xu C, Xu C. A Multi-Gradient-Descent-Integrated Physics-Informed Autoencoder for Sensor Fault Detection in Data Center Chillers. Sensors. 2026;26(10):3025. doi:10.3390/s26103025

BibTeX
@article{Shen2026,
  author = {Shen, Xinyue and Li, Pan and Xu, Chen and Xu, Chengliang},
  title = {A Multi-Gradient-Descent-Integrated Physics-Informed Autoencoder for Sensor Fault Detection in Data Center Chillers},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3025},
  doi = {10.3390/s26103025}
}
Kostenlos starten →