DROPS

Document

DOI: 10.4230/OASIcs.DX.2026.2

An Explainable GNN Framework for Component-Level Anomaly Diagnosis

Authors: Sena Ozgunay, Louise Travé-Massuyès, Jean-Michel Loubes, and Raul Sena Ferreira

Published in: OASIcs, Volume 148, 37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026)

Abstract

Industrial processes are complex systems composed of multiple interacting sensors that generate multivariate time series (MTS). Detecting anomalies in such systems is critical for reliability and safety, yet understanding their origin is equally important. Existing Graph Neural Network (GNN)-based methods for anomaly detection primarily focus on sensor-level deviations and either attribute anomalies directly to the deviating sensors. When diagnosis is attempted, generally, the most deviated sensor is identified as a root cause of a system fault. However, in many industrial systems, anomalies do not arise from faulty sensors but from disruptions in the influences governing the system dynamics. We propose an explainable GNN-based anomaly detection framework that shifts the perspective from sensor-level anomalies to component-level diagnosis, hypothesizing that anomalous measurements are symptoms of altered inter-sensor influences. Experiments show that the method effectively identifies and prioritizes the true faulty components, providing interpretable insights into system failures.

Cite as

Sena Ozgunay, Louise Travé-Massuyès, Jean-Michel Loubes, and Raul Sena Ferreira. An Explainable GNN Framework for Component-Level Anomaly Diagnosis. In 37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026). Open Access Series in Informatics (OASIcs), Volume 148, pp. 2:1-2:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{ozgunay_et_al:OASIcs.DX.2026.2,
  author =	{Ozgunay, Sena and Trav\'{e}-Massuy\`{e}s, Louise and Loubes, Jean-Michel and Ferreira, Raul Sena},
  title =	{{An Explainable GNN Framework for Component-Level Anomaly Diagnosis}},
  booktitle =	{37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026)},
  pages =	{2:1--2:17},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-455-0},
  ISSN =	{2190-6807},
  year =	{2026},
  volume =	{148},
  editor =	{Pill, Ingo and Zanella, Marina and Provan, Gregory},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2026.2},
  URN =		{urn:nbn:de:0030-drops-278163},
  doi =		{10.4230/OASIcs.DX.2026.2},
  annote =	{Keywords: Anomaly Detection, Fault Diagnosis, Graph Neural Networks, Time Series}
}

Search Results

Documents authored by Ferreira, Raul Sena

An Explainable GNN Framework for Component-Level Anomaly Diagnosis

Abstract

Cite as

Thanks for your feedback!

Could not send message