@inproceedings{BruckerBesslerGasper2021,
  author    = {Brucker, Jennifer and Bessler, Wolfgang G. and Gasper, Rainer},
  title     = {Grey-box modelling of lithium-ion batteries using neural ordinary differential equations},
  booktitle = {Proceedings of the 10th DACH+ Conference on Energy Informatics},
  volume    = {4},
  number    = {Suppl 3.},
  editor    = {Weidlich, Anke and Neumann, Dirk and Gust, Gunther and Staudt, Philipp and Sch{\"a}fer, Mirko},
  issn      = {2520-8942},
  doi       = {10.1186/s42162-021-00170-8},
  url       = {https://energyinformatics.springeropen.com/articles/10.1186/s42162-021-00170-8},
  institution = {INES - Institut f{\"u}r nachhaltige Energiesysteme},
  pages     = {15},
  year      = {2021},
  abstract  = {Grey-box modelling combines physical and data-driven models to benefit from their respective advantages. Neural ordinary differential equations (NODEs) offer new possibilities for grey-box modelling, as differential equations given by physical laws and neural networks can be combined in a single modelling framework. This simplifies the simulation and optimization and allows to consider irregularly-sampled data during training and evaluation of the model. We demonstrate this approach using two levels of model complexity; first, a simple parallel resistor-capacitor circuit; and second, an equivalent circuit model of a lithium-ion battery cell, where the change of the voltage drop over the resistor-capacitor circuit including its dependence on current and State-of-Charge is implemented as NODE. After training, both models show good agreement with analytical solutions respectively with experimental data.},
  language  = {en}
}