Abstract
Data-driven nonparametric Li-ion battery ageing model aiming at learning from real operation data - Part B: Cycling operation
Highlights
Lithium-ion (Li-ion) battery technology has gained a significant market share as the principal energy storage solution for many industrial applications, mainly due to its high energy efficiency and high specific energy and power [1,2]
This study extends the secondary contributions presented in the first paper of the series to the cycle ageing use-case: i) The quantification of the minimal number of laboratory tests required for the design of an accurate cycle ageing model for a broad operating window. ii) The validation of the proposed ageing model with an extensive experimental ageing dataset, involving 122 cells tested during more than three years at static conditions, and 2 additional cells tested at dynamic operating conditions. iii) The sensitivity analysis of the capacity loss with respect to the different stress-factors, from the point of view of the developed model
The second metric was defined as the root-meansquare error (RMSE) of the predicted capacity curve:
Summary
Lithium-ion (Li-ion) battery technology has gained a significant market share as the principal energy storage solution for many industrial applications, mainly due to its high energy efficiency and high specific energy and power [1,2]. These gaps strongly limit the accuracy and applicability of the models within the context of real deployment In this sense, investigation in data-driven Li-ion ageing models should be more focussed on the implementation or discovery of features presenting strong predictive capabilities (as suggested in [6]), as well as the deeper validation of the developed models under broad operating conditions. The present study aims to extend existing research by integrating the following main contributions: i) The development of a generic data-driven cycle ageing model, able to perform accurate capacity loss predictions for a broad range of cycling conditions, and usable for a large diversity of Li-ion battery applications. Both sections aim to illustrate the ability of the GP model to learn from new data observation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.