Electric Vehicle Thermal Management System Modeling with Informed Neural Networks

Ekin Alp Bicer, Pascal A. Schirmer, Peter Schreivogel, Gabriele Schrag

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Proper modeling of Thermal Management System (TMS) in Electric Vehicles (EVs) is crucial in terms of designing the EV components. Data-driven methods come up as an alternative to the computationally intensive high-fidelity methods or reduced order models where the accuracy is sacrificed for performance. In this paper, two informed neural network approaches are benchmarked in EV TMS modeling: Analytical Feature Engineering, where new features are generated by using the physical processes that take place within the EV, and Feature Generation via Loss Maps where loss maps of the inverter and the electric engine are used to generate a new power loss feature. Results show that accuracy increased by 1.7% to 3.6% depending on applied features and the neural network architecture.

Original languageEnglish
Title of host publication2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9789075815412
DOIs
StatePublished - 2023
Event25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe - Aalborg, Denmark
Duration: 4 Sep 20238 Sep 2023

Publication series

Name2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe

Conference

Conference25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe
Country/TerritoryDenmark
CityAalborg
Period4/09/238/09/23

Keywords

  • Deep Neural Network
  • Electric Vehicle (EV)
  • Machine learning
  • System modeling
  • Thermal Management

Fingerprint

Dive into the research topics of 'Electric Vehicle Thermal Management System Modeling with Informed Neural Networks'. Together they form a unique fingerprint.

Cite this