EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unsupervised Anomaly Detection for Cars CAN Sensors Time Series Using Small Recurrent and Convolutional Neural Networks

Yann Cherdo, Benoit Miramond, Alain Pegatoquet iD, Alain Vallauri

Sensors · 23.05.2023 · 23 (11) · 5013

DOI: 10.3390/s23115013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.05.2023. Verfasst von Yann Cherdo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Renault Software Labs, 2600 Route des Crêtes, Sophia Antipolis, 06560 Valbonne, France. Hauptthemen laut MEDLINE: Automobiles, Neural Networks, Computer. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Renault and the ANRT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictive maintenance in the car industry is an active field of research for machine learning and anomaly detection. The capability of cars to produce time series data from sensors is growing as the car industry is heading towards more connected and electric vehicles. Unsupervised anomaly detectors are therefore very adapted to process those complex multidimensional time series and highlight abnormal behaviors. We propose to use recurrent and convolutional neural networks based on unsupervised anomaly detectors with simple architectures on real, multidimensional time series generated by the car sensors and extracted from the Controller Area Network bus (CAN). Our method is then evaluated through known specific anomalies. As the computational costs of Machine Learning algorithms are a rising issue regarding embedded scenarios such as car anomaly detection, we also focus on creating anomaly detectors that are as small as possible. Using a state-of-the-art methodology incorporating a time series predictor and a prediction-error-based anomaly detector, we show that we can obtain roughly the same anomaly detection performance with smaller predictors, reducing parameters and calculations by up to 23% and 60%, respectively. Finally, we introduce a method to correlate variables with specific anomalies by using anomaly detector results and labels.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AutomobilesNeural Networks, ComputerTime FactorsIndustryAlgorithms

Stichwörter der Autor:innen

Controller Area Network busInternet of Thingsanomaly detectionanomaly likelihoodcarcomputational costsconvolutional neural networkgated recurrent unitlong short-term memoryrecurrent neural networksensorstime seriesunsupervised

Autor:innen und Institutionen

  • Renault Software Labs, 2600 Route des Crêtes, Sophia Antipolis, 06560 Valbonne, France.
  • LEAT (CNRS), Bât. Forum, Campus SophiaTech 930 Route des Colles, 06903 Sophia Antipolis, France.

ORCID-Profile: Alain Pegatoquet

Förderung

  • Renault and the ANRT

Zitieren

APA

Cherdo, Y., Miramond, B., Pegatoquet, A., & Vallauri, A. (2023). Unsupervised Anomaly Detection for Cars CAN Sensors Time Series Using Small Recurrent and Convolutional Neural Networks. Sensors, 23(11), 5013. https://doi.org/10.3390/s23115013

Vancouver

Cherdo Y, Miramond B, Pegatoquet A, Vallauri A. Unsupervised Anomaly Detection for Cars CAN Sensors Time Series Using Small Recurrent and Convolutional Neural Networks. Sensors. 2023;23(11):5013. doi:10.3390/s23115013

BibTeX
@article{Cherdo2023,
  author = {Cherdo, Yann and Miramond, Benoit and Pegatoquet, Alain and Vallauri, Alain},
  title = {Unsupervised Anomaly Detection for Cars CAN Sensors Time Series Using Small Recurrent and Convolutional Neural Networks},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {11},
  pages = {5013},
  doi = {10.3390/s23115013}
}
Kostenlos starten →