State-of-Health Estimation of Lithium-Ion Batteries with Attention-Based Deep Learning
- Authors
- Cui, Shengmin; Shin, Jisoo; Woo, Hyehyun; Hong, Seokjoon; Joe, Inwhee
- Issue Date
- Dec-2020
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Keywords
- Attention; Gated recurrent unit; Lithium-ion battery; State of health
- Citation
- Advances in Intelligent Systems and Computing, v.1295, pp.322 - 331
- Indexed
- SCOPUS
- Journal Title
- Advances in Intelligent Systems and Computing
- Volume
- 1295
- Start Page
- 322
- End Page
- 331
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/144198
- DOI
- 10.1007/978-3-030-63319-6_28
- ISSN
- 2194-5357
- Abstract
- Lithium-ion batteries are most commonly used in electric vehicles (EVs). The battery management system (BMS) assists in utilizing the energy stored in the battery more effectively through various functions. State of health (SOH) estimation is an essential function in a BMS. The accurate estimation of SOH can be used to calculate the remaining lifetime and ensure the reliability of batteries. In this paper, we propose a data-driven deep learning method that combines Gate Recurrent Unit (GRU) and attention mechanism for SOH estimation of lithium-ion batteries. Real-life datasets of batteries from NASA are used for evaluating our proposed model. The experimental results show that the proposed deep learning model has higher accuracy than conventional data-driven models. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.