EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Federated Multi‐Source Data Fusion for Semi‐Supervised Fault Detection in District Heating Substations

Jonne van Dreven, Sadi Alawadi, Abbas Cheddad, Ahmad Nauman Ghazi, Jad Al Koussa, Dirk Vanhoudt

Expert Systems · 2026-02 · 43 (2)

DOI: 10.1111/exsy.70194 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Expert Systems, online erschienen am 01.01.2026. Verfasst von Jonne van Dreven und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fault detection in district heating (DH) substations is critical for energy efficiency and reliability. However, it is challenged by scarce fault labels, low‐frequency data, privacy concerns, and battery‐constrained gateways. We propose a novel hybrid semi‐supervised federated domain adaptation architecture for fault detection in DH. We use a one‐class variational autoencoder (VAE) to leverage heterogeneous sensor streams from 434 distributed substations. First, we perform cross‐network unsupervised pre‐training on multi‐sourced data from two independent real‐world DH networks, fusing their return temperature dynamics into a robust shared manifold. Second, we leverage maintenance metadata to selectively allow verified‐normal clients for per‐round fine‐tuning of the model. Third, we drastically reduce uplink costs by compressing each client's weight delta using 10% top‐ k sparsification and demonstrate that our pipeline enables robust few‐shot finetuning with 20% of the normal operational data while retaining high detection performance. By strategically training, our method achieves F 1 and G‐mean scores of up to 97% and an AUC ≥ 99% on real‐world DH data. To our knowledge, this is the first work to study cross‐domain data fusion in the DH field for fault detection, aiming to enhance and enable effective, scalable, and energy‐efficient monitoring of substations.

Zitieren

APA

Dreven, J. V., Alawadi, S., Cheddad, A., Ghazi, A. N., Koussa, J. A., & Vanhoudt, D. (2026). Federated Multi‐Source Data Fusion for Semi‐Supervised Fault Detection in District Heating Substations. Expert Systems, 43(2). https://doi.org/10.1111/exsy.70194

Vancouver

Dreven JV, Alawadi S, Cheddad A, Ghazi AN, Koussa JA, Vanhoudt D. Federated Multi‐Source Data Fusion for Semi‐Supervised Fault Detection in District Heating Substations. Expert Systems. 2026;43(2). doi:10.1111/exsy.70194

BibTeX
@article{Dreven2026,
  author = {Dreven, Jonne van and Alawadi, Sadi and Cheddad, Abbas and Ghazi, Ahmad Nauman and Koussa, Jad Al and Vanhoudt, Dirk},
  title = {Federated Multi‐Source Data Fusion for Semi‐Supervised Fault Detection in District Heating Substations},
  journal = {Expert Systems},
  year = {2026},
  volume = {43},
  number = {2},
  doi = {10.1111/exsy.70194}
}
Kostenlos starten →