Machine learning pipeline for battery state-of-health estimation

Roman, D., Saxena, S., Robu, V., Pecht, M. and Flynn, D. (2021) Machine learning pipeline for battery state-of-health estimation. Nature Machine Intelligence, 3(5), pp. 447-456. (doi: 10.1038/s42256-021-00312-3)

[img] Text
267970.pdf - Accepted Version



Lithium-ion batteries are ubiquitous in applications ranging from portable electronics to electric vehicles. Irrespective of the application, reliable real-time estimation of battery state of health (SOH) by on-board computers is crucial to the safe operation of the battery, ultimately safeguarding asset integrity. In this Article, we design and evaluate a machine learning pipeline for estimation of battery capacity fade—a metric of battery health—on 179 cells cycled under various conditions. The pipeline estimates battery SOH with an associated confidence interval by using two parametric and two non-parametric algorithms. Using segments of charge voltage and current curves, the pipeline engineers 30 features, performs automatic feature selection and calibrates the algorithms. When deployed on cells operated under the fast-charging protocol, the best model achieves a root-mean-squared error of 0.45%. This work provides insights into the design of scalable data-driven models for battery SOH estimation, emphasizing the value of confidence bounds around the prediction. The pipeline methodology combines experimental data with machine learning modelling and could be applied to other critical components that require real-time estimation of SOH.

Item Type:Articles
Additional Information:This work was supported by the Lloyd’s Register Foundation (grant number AtRI_100015), The Engineering and Physical Sciences Research Council (EPSRC), the Center for Doctoral Training in Embedded Intelligence, and Baker Hughes (grant number EP/L014998/1). The work was further supported by the EPSRC through the UK National Centre for Energy Systems Integration (CESI) (grant number EP/P001173/1), and by InnovateUK through the Responsive Flexibility (ReFlex) (project reference 104780).
Glasgow Author(s) Enlighten ID:Flynn, Professor David
Authors: Roman, D., Saxena, S., Robu, V., Pecht, M., and Flynn, D.
College/School:College of Science and Engineering > School of Engineering > Systems Power and Energy
Journal Name:Nature Machine Intelligence
Publisher:Nature Research
ISSN (Online):2522-5839
Published Online:05 April 2021
Copyright Holders:Copyright © 2021, The Author(s), under exclusive licence to Springer Nature Limited
First Published:First published in Nature Machine Intelligence 3(3): 447-456
Publisher Policy:Reproduced in accordance with the publisher copyright policy

University Staff: Request a correction | Enlighten Editors: Update this record