The widespread adoption of EVs is limited by their reliance on batteries with presently low energy and power densities compared to liquid fuels and are subject to aging and performance deterioration over time. For this reason, monitoring the battery state of charge and state of health during the EV lifetime is a very relevant problem. This work proposes the structure of a battery digital twin designed to reflect battery dynamics at the run time accurately. To ensure a high degree of correctness concerning non-linear phenomena, the digital twin relies on data-driven models trained on traces of battery evolution over time: a state of health model, repeatedly executed to estimate the degradation of maximum battery capacity, and a state of charge model, retrained periodically to reflect the impact of aging. The proposed digital twin structure will be exemplified on a public dataset to motivate its adoption and prove its effectiveness, with a high degree of accuracy and inference and retraining times compatible with onboard execution.

A Machine Learning-based Digital Twin for Electric Vehicle Battery Modeling / Alamin, KHALED SIDAHMED SIDAHMED; Chen, Yukai; Macii, Enrico; Poncino, Massimo; Vinco, Sara. - ELETTRONICO. - (2022), pp. 1-6. (Intervento presentato al convegno IEEE International Conference on Omin-Layer Intelligent Systems (COINS) tenutosi a Barcelona (Spagna) nel 1-3 August 2022) [10.1109/COINS54846.2022.9854960].

A Machine Learning-based Digital Twin for Electric Vehicle Battery Modeling

Khaled Sidahmed Sidahmed Alamin;Yukai Chen;Enrico Macii;Massimo Poncino;Sara Vinco
2022

Abstract

The widespread adoption of EVs is limited by their reliance on batteries with presently low energy and power densities compared to liquid fuels and are subject to aging and performance deterioration over time. For this reason, monitoring the battery state of charge and state of health during the EV lifetime is a very relevant problem. This work proposes the structure of a battery digital twin designed to reflect battery dynamics at the run time accurately. To ensure a high degree of correctness concerning non-linear phenomena, the digital twin relies on data-driven models trained on traces of battery evolution over time: a state of health model, repeatedly executed to estimate the degradation of maximum battery capacity, and a state of charge model, retrained periodically to reflect the impact of aging. The proposed digital twin structure will be exemplified on a public dataset to motivate its adoption and prove its effectiveness, with a high degree of accuracy and inference and retraining times compatible with onboard execution.
2022
978-1-6654-8356-8
978-1-6654-8355-1
File in questo prodotto:
File Dimensione Formato  
Battery_DT___IEEE_coins (16).pdf

accesso aperto

Descrizione: Accepted manuscript version
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 678.67 kB
Formato Adobe PDF
678.67 kB Adobe PDF Visualizza/Apri
A_Machine_Learning-based_Digital_Twin_for_Electric_Vehicle_Battery_Modeling.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.37 MB
Formato Adobe PDF
1.37 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2968469