Operando impedance-based battery cell internal temperature estimation under non-stationarity and non-linearity conditions

Title data

Hackmann, Tobias ; Emir, Yunus ; Danzer, Michael A.:
Operando impedance-based battery cell internal temperature estimation under non-stationarity and non-linearity conditions.
In: Energy and AI. Vol. 21 (2025) . - 100569.
ISSN 2666-5468
DOI: https://doi.org/10.1016/j.egyai.2025.100569

Official URL:

Abstract in another language

Electrochemical impedance spectroscopy, a method for battery diagnostics, is used to estimate the internal temperature of a lithium-ion battery cell during highly dynamic load profiles. For the first time, a recurrent neural network is trained and evaluated with operando impedance data for temperature estimation. Furthermore, an approach is considered that guides the training process of the neural network by incorporating physical constraints. The model’s development based on an extensive series of measurements with different load profiles, tested under realistic conditions on large-format lithium-ion cells. The estimation accuracy of the data-driven approach is evaluated and compared against model-based methods, including the extended Kalman filter. An impedance correction model is proposed, which leads to a significant enhancement of the model-based estimation. The recurrent neural network under consideration achieves a mean square error of 1.07 °C for the investigated testing profiles in the temperature range up to 60 °C.

Further data

Item Type:	Article in a journal
Refereed:	Yes
Keywords:	Temperature estimation; Recurrent neural network; Extended Kalman filter; Electrochemical impedance spectroscopy (EIS); Non-stationarity; Non-linearity
Institutions of the University:	Faculties Faculties > Faculty of Engineering Science Faculties > Faculty of Engineering Science > Chair Electrical Energy Systems Faculties > Faculty of Engineering Science > Chair Electrical Energy Systems > Chair Electrical Energy Systems - Univ.-Prof. Dr.-Ing. Michael Danzer Research Institutions > Central research institutes > Bayerisches Zentrum für Batterietechnik - BayBatt
Result of work at the UBT:	Yes
DDC Subjects:	600 Technology, medicine, applied sciences 600 Technology, medicine, applied sciences > 620 Engineering
Date Deposited:	05 Aug 2025 10:41
Last Modified:	07 Aug 2025 11:12
URI:	https://eref.uni-bayreuth.de/id/eprint/94426