Work

Battery health prediction under generalized conditions using a Gaussian process transition model

Year: 2019

Type: article

Abstract: Accurately predicting the future health of batteries is necessary to ensure reliable operation, minimise maintenance costs, and calculate the value of energy storage investments. The complex nature of degradation renders data-driven approaches a promising alternative to mechanistic modelling. Here we show that a Bayesian non-parametric approach, using Gaussian process regression, can predict capacity fade in a variety of usage scenarios, forming a generalised health model. Our results are demonstrated on the open-source NASA Randomised Battery Usage Dataset, with data of 26 cells aged under widely varying operational conditions. Using half of the cells for training, and half for validation, we can accurately predict long term capacity fade, with a best case normalised root mean square error of 4.3%, including accurate estimation of the uncertainty of the prediction.

Source: Journal of Energy Storage

DOI: 10.1016/j.est.2019.03.022

Authors: Robert R. Richardson, Michael A. Osborne, David A. Howey

Institution: University of Oxford

Language: English

Topic: Advanced Battery Technologies Research

Subfield: Automotive Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Affordable and clean energy

Open Access status: hybrid

Estimated APC paid: $1,828