TRACKSIM: A Multi-Level Simulation Framework for Near-Life Battery Data Generation

Nicolai André Weinreich; Xin Sui; Remus Teodorescu; Kim Guldstrand Larsen

TRACKSIM: A Multi-Level Simulation Framework for Near-Life Battery Data Generation

Nicolai André Weinreich, Xin Sui, Remus Teodorescu, Kim Guldstrand Larsen

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

18 Downloads (Pure)

Abstract

Data-driven methods in the battery intelligence field are highly dependent on data similar to the targeted application. This paper introduces the multi-level simulation framework TRACKSIM as a tool to generate realistic synthetic battery cell data for training data-driven models. A use-case for State-Of-Health (SOH) estimation is presented.

Original language	English
Title of host publication	The 26th European Conference on Power Electronics and Applications
Publication status	Accepted/In press - 2025

Keywords

Batteries
Artifical Intelligence
Automotive applications
Simulation
Health assessment

Access to Document

Weinreich2025_TRACKSIMAccepted author manuscript, 4.13 MB

Cite this

@inproceedings{5e9c482a93cf43288efb9bcece8d8af9,

title = "TRACKSIM: A Multi-Level Simulation Framework for Near-Life Battery Data Generation",

abstract = "Data-driven methods in the battery intelligence field are highly dependent on data similar to the targeted application. This paper introduces the multi-level simulation framework TRACKSIM as a tool to generate realistic synthetic battery cell data for training data-driven models. A use-case for State-Of-Health (SOH) estimation is presented.",

keywords = "Batteries, Artifical Intelligence, Automotive applications, Simulation, Health assessment",

author = "Weinreich, {Nicolai Andr{\'e}} and Xin Sui and Remus Teodorescu and Larsen, {Kim Guldstrand}",

year = "2025",

language = "English",

booktitle = "The 26th European Conference on Power Electronics and Applications",

}

TY - GEN

T1 - TRACKSIM: A Multi-Level Simulation Framework for Near-Life Battery Data Generation

AU - Weinreich, Nicolai André

AU - Sui, Xin

AU - Teodorescu, Remus

AU - Larsen, Kim Guldstrand

PY - 2025

Y1 - 2025

N2 - Data-driven methods in the battery intelligence field are highly dependent on data similar to the targeted application. This paper introduces the multi-level simulation framework TRACKSIM as a tool to generate realistic synthetic battery cell data for training data-driven models. A use-case for State-Of-Health (SOH) estimation is presented.

AB - Data-driven methods in the battery intelligence field are highly dependent on data similar to the targeted application. This paper introduces the multi-level simulation framework TRACKSIM as a tool to generate realistic synthetic battery cell data for training data-driven models. A use-case for State-Of-Health (SOH) estimation is presented.

KW - Batteries

KW - Artifical Intelligence

KW - Automotive applications

KW - Simulation

KW - Health assessment

M3 - Article in proceeding

BT - The 26th European Conference on Power Electronics and Applications

ER -

TRACKSIM: A Multi-Level Simulation Framework for Near-Life Battery Data Generation

Abstract

Keywords

Access to Document

Fingerprint

Cite this