KIT | KIT-Bibliothek | Impressum | Datenschutz

A Method of Developing Quantile Convolutional Neural Networks for Electric Vehicle Battery Temperature Prediction Trained on Cross-Domain Data

Billert, Andreas M. 1; Frey, Michael ORCID iD icon 1; Gauterin, Frank ORCID iD icon 1
1 Institut für Fahrzeugsystemtechnik (FAST), Karlsruher Institut für Technologie (KIT)

Abstract:

The energy consumption caused by battery thermal management of electric vehicles can
be reduced using predictive control. A predictive controller needs a prediction model of the battery
temperature, for example for different battery cooling and heating thresholds. In the proposed method,
cross-domain data from simulation, vehicle fleet and weather stations were analyzed and processed
as training data for a Convolutional Neural Network (CNN). The CNN took data from previous road
segments and predictions for following road segments as input and predicted the change in battery
temperature as quantile sequences over a prediction horizon. Properties of the collected cross-domain
data sets were analyzed and considered during preprocessing, before 150 models were trained, of which
the best performing model was further analyzed. Point-forecast metrics and quantile-related metrics were
used for model comparison and evaluation. For example, the median prediction achieved a mean absolute
error (MAE) of 0.27 ◦C and the true values were below the median prediction in 47% of the test data.
Possible improvements of the method such as increasing data size, using more complex architectures as
... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000149920
Veröffentlicht am 12.08.2022
Originalveröffentlichung
DOI: 10.1109/OJITS.2022.3177007
Scopus
Zitationen: 15
Dimensions
Zitationen: 13
Zugehörige Institution(en) am KIT Institut für Fahrzeugsystemtechnik (FAST)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2022
Sprache Englisch
Identifikator ISSN: 2687-7813
KITopen-ID: 1000149920
Erschienen in IEEE Open Journal of Intelligent Transportation Systems
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Band 3
Seiten 411–425
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Schlagwörter Battery temperature, convolutional neural network, cross-domain data, machine learning, quantile forecasting
Nachgewiesen in Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page