TU Darmstadt / ULB / TUprints

Hybrid Modeling of Lithium-Ion Battery: Physics-Informed Neural Network for Battery State Estimation

Singh, Soumya ; Ebongue, Yvonne Eboumbou ; Rezaei, Shahed ; Birke, Kai Peter (2023)
Hybrid Modeling of Lithium-Ion Battery: Physics-Informed Neural Network for Battery State Estimation.
In: Batteries, 2023, 9 (6)
doi: 10.26083/tuprints-00024089
Article, Secondary publication, Publisher's Version

[img] Text
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (5MB)
Item Type: Article
Type of entry: Secondary publication
Title: Hybrid Modeling of Lithium-Ion Battery: Physics-Informed Neural Network for Battery State Estimation
Language: English
Date: 19 June 2023
Place of Publication: Darmstadt
Year of primary publication: 2023
Publisher: MDPI
Journal or Publication Title: Batteries
Volume of the journal: 9
Issue Number: 6
Collation: 19 Seiten
DOI: 10.26083/tuprints-00024089
Corresponding Links:
Origin: Secondary publication DeepGreen

Accurate forecasting of the lifetime and degradation mechanisms of lithium-ion batteries is crucial for their optimization, management, and safety while preventing latent failures. However, the typical state estimations are challenging due to complex and dynamic cell parameters and wide variations in usage conditions. Physics-based models need a tradeoff between accuracy and complexity due to vast parameter requirements, while machine-learning models require large training datasets and may fail when generalized to unseen scenarios. To address this issue, this paper aims to integrate the physics-based battery model and the machine learning model to leverage their respective strengths. This is achieved by applying the deep learning framework called physics-informed neural networks (PINN) to electrochemical battery modeling. The state of charge and state of health of lithium-ion cells are predicted by integrating the partial differential equation of Fick’s law of diffusion from a single particle model into the neural network training process. The results indicate that PINN can estimate the state of charge with a root mean square error in the range of 0.014% to 0.2%, while the state of health has a range of 1.1% to 2.3%, even with limited training data. Compared to conventional approaches, PINN is less complex while still incorporating the laws of physics into the training process, resulting in adequate predictions, even for unseen situations.

Uncontrolled Keywords: Li-ion battery, battery modeling, state estimation, state of health (SOH), state of charge (SOC), hybrid modeling, physics-informed neural network (PINN), single-particle model (SPM)
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-240897
Additional Information:

This article belongs to the Special Issue The Precise Battery—towards Digital Twins for Advanced Batteries

Classification DDC: 600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
600 Technology, medicine, applied sciences > 660 Chemical engineering
Divisions: 11 Department of Materials and Earth Sciences > Material Science > Mechanics of functional Materials
Date Deposited: 19 Jun 2023 13:14
Last Modified: 02 Oct 2023 08:13
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/24089
PPN: 511990626
Actions (login required)
View Item View Item