Data-Driven Thermal Modelling for Anomaly Detection in Electric Vehicle Charging Stations

Pere Izquierdo Gomez, Alberto Barragan Moreno, Jun Lin, Tomislav Dragicevic

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

20 Downloads (Pure)

Abstract

The rapid growth of the electric vehicle (EV) sector is giving rise to many infrastructural challenges. One such challenge is its requirement for the widespread development of EV charging stations which must be able to provide large amounts of power in an on-demand basis. This can cause large stresses on the electrical and electronic components of the charging infrastructure—negatively affecting its reliability as well as leading to increased maintenance and operation costs. This paper proposes a human-interpretable data-driven method for anomaly detection in EV charging stations, aiming to provide information for the condition monitoring and predictive maintenance of power converters within such a station. To this end, a model of a high-efficiency EV charging station is used to simulate the thermal behaviour of EV charger power converter modules, creating a data set for the training of neural network models. These machine learning models are then employed for the identification of anomalous performance.
Original languageEnglish
Title of host publicationProceedings of 2022 IEEE Transportation Electrification Conference & Expo (ITEC)
Number of pages6
PublisherIEEE
Publication date2022
Pages1005-1010
ISBN (Print)978-1-6654-0561-4
ISBN (Electronic)978-1-6654-0560-7
DOIs
Publication statusPublished - 2022
Event2022 IEEE Transportation Electrification Conference and Expo - Westin Anaheim Resort, Anaheim, United States
Duration: 15 Jun 202217 Jun 2022
https://itec-conf.com/

Conference

Conference2022 IEEE Transportation Electrification Conference and Expo
LocationWestin Anaheim Resort
Country/TerritoryUnited States
CityAnaheim
Period15/06/202217/06/2022
Internet address
Series2022 Ieee Transportation Electrification Conference and Expo (itec)
ISSN2377-5483

Keywords

  • Electric vehicle (EV)
  • Electric vehicle charging station (EVCS)
  • Anomaly detection
  • Outlier identification
  • Condition monitoring
  • Machine learning
  • Neural network
  • Time series analysis

Fingerprint

Dive into the research topics of 'Data-Driven Thermal Modelling for Anomaly Detection in Electric Vehicle Charging Stations'. Together they form a unique fingerprint.

Cite this