Boosting battery state of health estimation based on self-supervised learning
作者机构：Department of EnergyAalborg UniversityAalborg 9220Denmark
出 版 物：《Journal of Energy Chemistry》 (能源化学（英文版）)
年 卷 期：2023年第84卷第9期
页 面：335-346页
核心收录：
基 金：funded by the “SMART BATTERY” project granted by Villum Foundation in 2021 (project number 222860)
主 题：Lithium-ion battery State of health Battery aging Self-supervised learning Prognostics and health management Data-driven estimation
摘 要：State of health(SoH) estimation plays a key role in smart battery health prognostic and ***,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH *** this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH *** from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at *** learning is then used to learn the aging characteristics from the unlabeled data through an *** learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation *** proposed method has been validated under different battery chemistries,formats,operating conditions,and *** estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with *** with other pure supervised machine learning methods demonstrate the superiority of the proposed *** simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.
维普期刊数据库
同方期刊数据库
