Data-driven model enhancement of late-life lithium-ion batteries

Accompanying code to the paper Data-driven model enhancement of late-life lithium-ion batteries: https://doi.org/10.1016/j.fub.2025.100060

Dataset

To get started, you will need to download the dataset used in this research. You can download the dataset from the following link:

https://zenodo.org/doi/10.5281/zenodo.13353324

Once downloaded, please place the dataset in a local directory named data/ within the root of this repository.

Setup

1. Install Julia: To run the code, you will need to have Julia installed on your machine. We recommend using juliaup for easy installation and management of Julia versions: https://julialang.org/downloads/

2. Create the project environment: Navigate to the project directory and start Julia by typing julia in your terminal. Activate the local environment and install all the required packages by running:

   julia> using Pkg
   julia> Pkg.activate(".")
   julia> Pkg.instantiate()

3. Run the code: The Jupyter notebook main.ipynb generates and displays the results as outlined in the paper. There are two alternatives to open and execute a Jupyter notebook in Julia:

• Using Jupyter:
  • Install the IJulia package by running using Pkg; Pkg.add("IJulia") in the Julia REPL (make sure you have the local environment activated).
  • Launch Jupyter with using IJulia; notebook().
  • Open main.ipynb and start executing cells.
• Using Visual Studio Code (VSCode):
  • Install the Julia extension in VSCode.
  • Open main.ipynb in VSCode.
  • Select the Julia kernel from the top right corner and start executing cells (make sure you have selected the local environemnt).

Cite

If you use this work in your research, please cite this paper:

@article{cornejo_data-driven_2025,
	title = {Data-driven model enhancement of late-life lithium-ion batteries},
	volume = {6},
	issn = {2950-2640},
	doi = {10.1016/j.fub.2025.100060},
	journal = {Future Batteries},
	author = {Cornejo, Martín and Jablonski, Sammy and Fischer, Marco and Bahrke, Julius and Jossen, Andreas},
	month = jun,
	year = {2025},
	keywords = {Lithium-ion battery, Battery degradation, Parameter estimation, Gaussian process regression, Equivalent circuit model},
	pages = {100060},
}

License

This project is licensed under the MIT License - see the LICENSE file for details.