Search Results

Documents authored by Mukhtar, Adil

Document
DOI: 10.4230/OASIcs.DX.2024.14
One-Class Classification and Cluster Ensembles for Anomaly Detection and Diagnosis in Multivariate Time Series Data

Authors: Adil Mukhtar, Thomas Hirsch, and Gerald Schweiger

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

Abstract
Real-world automated systems such as building automation, power plants, and more have benefited from data-driven learning methodologies for anomaly detection and diagnosis. Typically, these methodologies heavily rely on prior knowledge related to abnormal operations, i.e., data points labeled as anomalies. However, in practice, such labelled data points are often unavailable which poses challenges in effective anomaly detection, particularly in diagnosis. In this paper, we propose One-class Classification Cluster ENsembles (OCCEN) anomaly detection and diagnosis approach for multivariate time series data. OCCEN utilizes one-class classification learning methods for anomaly detection followed by the decomposition of anomalies into multiple clusters. Then each cluster is treated as a binary classification problem and classifiers are trained to learn cluster representations. These trained models in combination with explainable AI models are used to generate a ranked list of diagnoses, i.e., features. Finally, we re-rank those features to account for temporal dependencies through the dynamic time-warping technique. The practical evaluation of OCCEN for air handling units (AHU) demonstrates its effectiveness in identifying faults. The framework consistently outperforms the baseline in fault diagnosis, as higher scores are observed for detection and diagnostic evaluation metrics, including F1 score, intersection over union, HitRate@k, and RootCause@k.
Cite as

Adil Mukhtar, Thomas Hirsch, and Gerald Schweiger. One-Class Classification and Cluster Ensembles for Anomaly Detection and Diagnosis in Multivariate Time Series Data. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 14:1-14:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{mukhtar_et_al:OASIcs.DX.2024.14,
  author =	{Mukhtar, Adil and Hirsch, Thomas and Schweiger, Gerald},
  title =	{{One-Class Classification and Cluster Ensembles for Anomaly Detection and Diagnosis in Multivariate Time Series Data}},
  booktitle =	{35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
  pages =	{14:1--14:19},
  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.2024.14},
  URN =		{urn:nbn:de:0030-drops-221064},
  doi =		{10.4230/OASIcs.DX.2024.14},
  annote =	{Keywords: Anomaly Detection and Diagnosis, Machine Learning, Explainable AI, One-class Classification}
}
Document
Short Paper
DOI: 10.4230/OASIcs.DX.2024.20
Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review (Short Paper)

Authors: Stan Muñoz Gutiérrez, Adil Mukhtar, and Franz Wotawa

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

Abstract
Traditional onboard vehicle diagnostics are rapidly evolving concomitant to the rise of electrified powertrains, digital transformation, and intelligent technologies for advanced system management. The big data now available in modern vehicles offers unprecedented opportunities for condition monitoring and prognosis, but also presents challenges in scaling and integrating multimodal sensor data across components with varying timescale dynamics. Machine learning techniques have proven particularly effective in implementing diagnostic functions within electrified vehicle powertrains. This study systematically reviews intelligent, data-driven techniques for health monitoring and prognosis of electrified powertrains. We categorize existing research based on diagnostic functions and machine learning methods, with a focus on approaches that do not require prior knowledge of faulty operational states. Our findings indicate that deep learning methods are state-of-the-art across several diagnostic functions, fault modes, system levels, and multimodal sensor integration.
Cite as

Stan Muñoz Gutiérrez, Adil Mukhtar, and Franz Wotawa. Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 20:1-20:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{munozgutierrez_et_al:OASIcs.DX.2024.20,
  author =	{Mu\~{n}oz Guti\'{e}rrez, Stan and Mukhtar, Adil and Wotawa, Franz},
  title =	{{Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review}},
  booktitle =	{35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
  pages =	{20:1--20:14},
  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.2024.20},
  URN =		{urn:nbn:de:0030-drops-221128},
  doi =		{10.4230/OASIcs.DX.2024.20},
  annote =	{Keywords: Diagnostic functions, Machine Learning, Powertrain, Electrified vehicles}
}
Document
Short Paper
DOI: 10.4230/OASIcs.DX.2024.29
Transformer-Based Signal Inference for Electrified Vehicle Powertrains (Short Paper)

Authors: Stan Muñoz Gutiérrez, Adil Mukhtar, and Franz Wotawa

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

Abstract
The scarcity of labeled data for intelligent diagnosis of non-linear technical systems is a common problem for developing robust and reliable real-world applications. Several deep learning approaches have been developed to address this challenge, including self-supervised learning, representation learning, and transfer learning. Due largely to their powerful attention mechanisms, transformers excel at capturing long-term dependencies across multichannel and multi-modal signals in sequential data, making them suitable candidates for time series modeling. Despite their potential, studies applying transformers for diagnostic functions, especially in signal reconstruction through representation learning, remain limited. This paper aims to narrow this gap by identifying the requirements and potential of transformer self-attention mechanisms for developing auto-associative inference engines that learn exclusively from healthy behavioral data. We apply a transformer backbone for signal reconstruction using simulated data from a simplified powertrain. Feedback from these experiments, and the reviewed evidence from the literature, allows us to conclude that autoencoder and autoregressive approaches are potentiated by transformers.
Cite as

Stan Muñoz Gutiérrez, Adil Mukhtar, and Franz Wotawa. Transformer-Based Signal Inference for Electrified Vehicle Powertrains (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 29:1-29:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{munozgutierrez_et_al:OASIcs.DX.2024.29,
  author =	{Mu\~{n}oz Guti\'{e}rrez, Stan and Mukhtar, Adil and Wotawa, Franz},
  title =	{{Transformer-Based Signal Inference for Electrified Vehicle Powertrains}},
  booktitle =	{35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
  pages =	{29:1--29:14},
  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.2024.29},
  URN =		{urn:nbn:de:0030-drops-221217},
  doi =		{10.4230/OASIcs.DX.2024.29},
  annote =	{Keywords: Signal Inference, Deep Learning, Self-Supervised Learning, Multimodal Transformer Autoencoder, Electric Vehicle, Powertrain, Electric Motor}
}
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