A State of Power Based Deep Learning Model for State of Health Estimation of Lithium-Ion Batteries
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, Jisoo | - |
dc.contributor.author | Joe, Inwhee | - |
dc.contributor.author | Hong, Seokjoon | - |
dc.date.accessioned | 2022-07-06T11:35:41Z | - |
dc.date.available | 2022-07-06T11:35:41Z | - |
dc.date.created | 2022-01-05 | - |
dc.date.issued | 2021-11 | - |
dc.identifier.issn | 2367-3370 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/140416 | - |
dc.description.abstract | Recently, research on eco-friendly fuels has been on the rise as various environmental problems have emerged. Many studies are being conducted on lithium-ion batteries among eco-friendly fuels for electric vehicles. Lithium-ion batteries are light and have high energy density, making them important in various fields. However, battery performance may deteriorate or fail due to various reasons. To solve these problems, many research are being conducted on battery care systems. For battery care systems, the values of SoH (State of Health) and SoC (State of Charge) are very important. In this paper, we propose a State of Power (SoP)-based deep learning model for predicting SoH performance of lithium- ion batteries, in that the battery life is determined according to the maximum power level. The proposed method is to calculate SoP values based on measurement from lithium-ion batteries and take them as input when using deep-learning models. Also, the formula for extracting SoP values from lithium-ion battery data is defined and the data extracted by the SoP values are applied to various deep learning models, such as the RNN, LSTM and GRU models. Our experiments are performed on four lithium-ion batteries ‘B0005’, ‘B0006’, ‘B0007’ and ‘B0018’ provided by NASA’s open dataset ‘Battery data set’, and the verification of the experiment is made using root mean squared error (RMSE). The experimental results show that the proposed method in this paper achieves significantly low RMSE values for all deep learning models and all battery data. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Springer Science and Business Media Deutschland GmbH | - |
dc.title | A State of Power Based Deep Learning Model for State of Health Estimation of Lithium-Ion Batteries | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Joe, Inwhee | - |
dc.identifier.doi | 10.1007/978-3-030-90321-3_77 | - |
dc.identifier.scopusid | 2-s2.0-85120683017 | - |
dc.identifier.bibliographicCitation | Lecture Notes in Networks and Systems, v.231, pp.922 - 931 | - |
dc.relation.isPartOf | Lecture Notes in Networks and Systems | - |
dc.citation.title | Lecture Notes in Networks and Systems | - |
dc.citation.volume | 231 | - |
dc.citation.startPage | 922 | - |
dc.citation.endPage | 931 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Battery management systems | - |
dc.subject.keywordAuthor | Lithium-ion batteries | - |
dc.subject.keywordAuthor | Neural networks | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.