Search Results

Documents authored by Waxenegger-Wilfing, Günther

Document
DOI: 10.4230/OASIcs.DX.2024.11
Leveraging Causal Information for Multivariate Timeseries Anomaly Detection

Authors: Lukas Heppel, Andreas Gerhardus, Ferdinand Rewicki, Jan Deeken, and Günther Waxenegger-Wilfing

Published in: OASIcs, Volume 125, 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)

Abstract
Anomaly detection in multivariate timeseries is used in various domains, such as finance, IT, or aerospace, to identify irregular behavior in the used applications. Prior research in anomaly detection has focused on estimating the joint probability of all variables. Then, anomalies are scored based on the probability they receive. Thereby, the variables' dependencies are only considered implicitly. This work follows recent work in anomaly detection that integrates information about the causal relations between the variables in the timeseries into the detection mechanism. The causal mechanisms of the variables are then used to identify anomalies. An observation is identified as anomalous if at least one of the variables it contains deviates from its regular causal mechanism. These regular causal mechanisms are estimated via the conditional distribution of a variable given its causal parent variables, i.e., the variables having a causal influence on a variable. We further develop previous work by gathering information about the causal parents of the variables by applying causal discovery algorithms adapted to the timeseries setting. We apply Conditional Kernel Density Estimation and Conditional Variational Autoencoders to estimate the conditional probabilities. With this causal approach, we outperform methods that rely on the joint probability of the variables in our synthetically generated datasets and the C-MAPPS dataset, which provides simulation data of turbofan engines. Moreover, we investigate the causal approach’s inferred scores on the C-MAPPS dataset to gather insights into the measurements responsible for the prediction of anomalies. Furthermore, we investigate the influence of deviations from the true causal graph on the anomaly detection performance using synthetic data.
Cite as

Lukas Heppel, Andreas Gerhardus, Ferdinand Rewicki, Jan Deeken, and Günther Waxenegger-Wilfing. Leveraging Causal Information for Multivariate Timeseries Anomaly Detection. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 11:1-11:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{heppel_et_al:OASIcs.DX.2024.11,
  author =	{Heppel, Lukas and Gerhardus, Andreas and Rewicki, Ferdinand and Deeken, Jan and Waxenegger-Wilfing, G\"{u}nther},
  title =	{{Leveraging Causal Information for Multivariate Timeseries Anomaly Detection}},
  booktitle =	{35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
  pages =	{11:1--11:18},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-356-0},
  ISSN =	{2190-6807},
  year =	{2024},
  volume =	{125},
  editor =	{Pill, Ingo and Natan, Avraham and Wotawa, Franz},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.11},
  URN =		{urn:nbn:de:0030-drops-221034},
  doi =		{10.4230/OASIcs.DX.2024.11},
  annote =	{Keywords: Anomaly Detection, Causal Discovery, Multivariate Timeseries}
}
Document
DOI: 10.4230/OASIcs.DX.2024.15
Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems

Authors: Andrea Urgolo, Ingo Pill, Günther Waxenegger-Wilfing, and Manuel Freiberger

Published in: OASIcs, Volume 125, 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)

Abstract
Accommodating the dynamic and uncertain operational environments that are typical for aerospace applications, our work focuses on robust fault detection and accurate diagnosis in the context of Liquid Propellant Rocket Engines. To this end, we employ techniques based on learning temporal properties which are then dynamically adapted and refined based on observed behavior. Leveraging the capabilities of genetic programming, our methodology evolves and optimizes temporal properties that are validated through formal methods in order to ensure precise, interpretable real-time fault monitoring and diagnosis. Our integrated strategy enables us to enhance resilience, safety and reliability when operating rocket engines - due to the proactive detection and systematic analysis of operational deviations before they would escalate into critical failures. We demonstrate the effectiveness of our method via a rigorous evaluation across varied simulated fault conditions, in order to showcase its potential to significantly mitigate the fault-related risks in aerospace systems.
Cite as

Andrea Urgolo, Ingo Pill, Günther Waxenegger-Wilfing, and Manuel Freiberger. Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 15:1-15:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{urgolo_et_al:OASIcs.DX.2024.15,
  author =	{Urgolo, Andrea and Pill, Ingo and Waxenegger-Wilfing, G\"{u}nther and Freiberger, Manuel},
  title =	{{Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems}},
  booktitle =	{35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
  pages =	{15:1--15:20},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-356-0},
  ISSN =	{2190-6807},
  year =	{2024},
  volume =	{125},
  editor =	{Pill, Ingo and Natan, Avraham and Wotawa, Franz},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.15},
  URN =		{urn:nbn:de:0030-drops-221074},
  doi =		{10.4230/OASIcs.DX.2024.15},
  annote =	{Keywords: Machine learning, Runtime verification, Property learning, Monitoring, Fault detection, Diagnosis, Genetic programming, Explainable AI}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact