|Electrochemical Finite Element Modelling to Assist Development of Machine-Learning Tools for Battery Ageing Modelling|
|SweGRIDS research area||Materials for Power Grid and Storage|
|SweGRIDS project code||MTL9|
|Researcher||Litao Yin (webpage)|
|Project period||2021-08-01 to 2021-12-31|
|Project supervisor||Daniel Brandell (webpage)|
back to project index
Two trends in Li-ion research are currently developing at a rapid speed: (1) using finite element methods (FEM) to estimate lifetime, ageing mechanisms, etc., and (2) using machine-learning (ML)/artificial intelligence (AI) tools for analyzing large data sets of battery test data, and thereby creating models for battery ageing depending on use conditions. This project regards the combination of these two approaches, to assist training and validating the AI, and rendering the ML models better transparent in terms of physical description. Thereby, they can be used for improved battery design. Battery FEM models will thus be employed in this project to generate a much larger matrix of simulated battery ageing data, which the ML model will be validated against. Moreover, the FEM data sets generated will aid in determining which ageing mechanism that is dominating under what battery operating condition, and why.
Summary of work
Prof. Kristina Edström, Uppsala University
Dr. Cathy Yao Chen, ABB
Dr. Shiva Sander-Tavallaey, ABB
Publications by this researcher
See alternatively the researcher's full DiVA list of publications, with options for sorting.
Publications in journals and conferences usually will not show until a while after they are published.
Analyzing and mitigating battery ageing by self-heating through a coupled thermal-electrochemical model of cylindrical Li-ion cells
Litao Yin, Are Björneklett, Elisabeth Söderlund, Daniel Brandell.
2021, Journal of Energy Storage, vol. 39
Publication list last updated from DiVA on 2021-11-23 03:01.
Page started: 2021-08-01
Last generated: 2021-11-23