Literatur vom gleichen Autor/der gleichen Autor*in
plus bei Google Scholar

Bibliografische Daten exportieren
 

State of health estimation of lithium-ion batteries with a temporal convolutional neural network using partial load profiles

Titelangaben

Bockrath, Steffen ; Lorentz, Vincent ; Pruckner, Marco:
State of health estimation of lithium-ion batteries with a temporal convolutional neural network using partial load profiles.
In: Applied Energy. Bd. 329 (2023) . - 120307.
ISSN 1872-9118
DOI: https://doi.org/10.1016/j.apenergy.2022.120307

Volltext

Link zum Volltext (externe URL): Volltext

Angaben zu Projekten

Projekttitel:
Offizieller Projekttitel
Projekt-ID
H2020 Project: LIBERTY - “LIghtweight Battery System for Extended Range at Improved SafeTY”
963522
H2020 Project: SEABAT - “Solutions for largE bAtteries for waterBorne trAnsporT”
963560
H2020 Project: AI4DI - “Artificial Intelligence for Digitizing Industry”
826060

Projektfinanzierung: Andere
Part of the research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 963522 (LIBERTY - “LIghtweight Battery System for Extended Range at Improved SafeTY”). Part of the research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 963560 (SEABAT - “Solutions for largE bAtteries for waterBorne trAnsporT”). Part of the research leading to these results has received funding from the ECSEL Joint Undertaking under grant agreement No. 826060 (AI4DI - “Artificial Intelligence for Digitizing Industry”). This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation program and the ECSEL member states (i.e., BMBF in Germany).

Abstract

An accurate aging forecasting and state of health estimation is essential for a safe and economically valuable usage of lithium-ion batteries. However, the non-linear aging of lithium-ion batteries is dependent on various operating and environmental conditions wherefore the degradation estimation is a complex challenge. Moreover, for on-board estimations where only limited memory and computing power are available, a state of health estimation algorithm is needed that is able to process raw sensor data without complex preprocessing. This paper presents a data-driven state of health estimation algorithm for lithium-ion batteries using different segments of partial discharge profiles. Raw sensor data is directly input to a temporal convolutional neural network without the need of executing feature engineering steps. The neural network is able to process raw sensor data and estimate the state of health of battery cells for different aging and degradation scenarios. After executing Bayesian hyperparameter tuning together with a stratified cross validation approach for splitting the training and test data, the achieved generalized aging model estimates the state of health with an overall root mean squared error of 1.0%.

Weitere Angaben

Publikationsform: Artikel in einer Zeitschrift
Begutachteter Beitrag: Ja
Keywords: Lithium-ion battery; State of health estimation; Deep learning; Temporal convolutional network
Institutionen der Universität: Forschungseinrichtungen > Zentrale wissenschaftliche Einrichtungen > Bayerisches Zentrum für Batterietechnik - BayBatt
Forschungseinrichtungen
Forschungseinrichtungen > Zentrale wissenschaftliche Einrichtungen
Titel an der UBT entstanden: Nein
Themengebiete aus DDC: 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften
Eingestellt am: 22 Nov 2022 06:29
Letzte Änderung: 06 Nov 2023 12:48
URI: https://eref.uni-bayreuth.de/id/eprint/72870