PDF

Learning battery model parameter dynamics from

Antti Aitio, Dominik Jöst

2021Englishbatteriesenergy storageelectrochemistrybattery healthstate of healthGaussian processGaussian processesmachine learning

Abstract

Language:

Estimating state of health is a critical function of a battery management system but remains challenging due to the variability of operating conditions and usage requirements of real applications. This paper proposes a hybrid approach combining data- and model-driven techniques for battery health estimation. We demonstrate a Bayesian data-driven method, Gaussian process regression, to estimate model parameters as functions of states, operating conditions, and lifetime. Computational efficiency is ensured through a recursive approach yielding a unified joint state-parameter estimator that learns parameter dynamics from data and is robust to gaps and varying operating conditions. Results show the efficacy of the method on both simulated and measured data, including accurate estimates and forecasts of battery capacity and internal resistance, which opens up new opportunities to understand battery ageing in real applications.

Download

Cite This Work

@article{d691db2d-50db-4044-a6e1-365516c0e73f,
  title={Learning battery model parameter dynamics from},
  author={Antti Aitio and Dominik Jöst},
  year={2021},
  language={English}
}
TY  - JOUR
TI  - Learning battery model parameter dynamics from
AU  - Antti Aitio
AU  - Dominik Jöst
PY  - 2021
LA  - English
ER  -

Similar Items

COURS ACCUMULATTEURS BATTERIES 4

Yaya Dagal D

This document presents an educational module on electrochemical energy storage systems—primary cells, accumulators, and batteries—with specific emphas

2021enPDF

Team finds major storage capacity in water-based batteries

Raven Wuebker

This article reports recent advances in the development of metal-free, water-based batteries as a safer and more sustainable alternative to convention

2023enPDF

Polymer-air battery research investigates advanced energy storage solutions

Raven Wuebker

This article reports recent advances in the development of polymer–air batteries as safer, more sustainable alternatives to conventional metal–air and

2023enPDF

New material allows for better hydrogen-based batteries and fuel cells

Riken

This article reports the development of a room-temperature hydride ion (H⁻)-conducting solid electrolyte, representing a significant advance toward pr

2023enPDF

RUBIN TP

2025enPDF

Understanding the mechanism for the low-temperature reduction of Fe2O3 to Fe in alkaline electrolytes

Raj Shekhar, Semanti Mukhopadhyay

Conversion reactions for iron oxide to iron metal enable zero-emissions iron for steelmaking and low-cost batteries for long duration energy storage.

2024enPDF