All Issue

2025 Vol.38, Issue 5 Preview Page

Research Paper

Deep Learning-Based State-of-Health Estimation Approach for Mobility Batteries

딥러닝 기반 모빌리티 배터리의 건전성 상태 추정 방법

Kyutae Park1
,
Heung Soo Kim2*
박 규태1
,
김 흥수2*
1Graduate Student, Department of Mechanical Engineering, Dongguk University, Seoul, 04620, Korea
2Professor, Department of Mechanical, Robotics and Energy Engineering, Dongguk University, Seoul, 04620, Korea
1동국대학교 기계공학과 석사과정
2동국대학교 기계로봇에너지공학과 교수
*Corresponding Author
31 October 2025. pp. 309-316
PDF XML Citation
Abstract

Accurate real‑time estimation and monitoring of the state of health (SOH) in lithium-ion batteries is critical for mobility applications, as battery failures can result in significant personal injury. This study introduces a method for SOH estimation employing a deep learning-based hybrid neural network that integrates a temporal convolutional network (TCN) and gated recurrent unit (GRU). To facilitate applicability in mobility onboard systems, the proposed model utilizes input data obtained by resampling raw current, voltage, and time signals, which can be directly measured by the battery management system (BMS). The TCN model, trained on both past and current input data, enhances reliability by effectively extracting non-linear features observed during battery degradation, such as local capacity recovery. These extracted features are then processed by the GRU model, which learns temporal patterns and produces precise SOH estimation results. The proposed method was validated using CALCE battery degradation data, achieving consistent and superior performance across all battery cells, with mean absolute error and root mean square error values not exceeding 0.55 and 0.7, respectively.

Keywords
mobility battery
lithium-ion battery
state of health estimation
battery management system
mobility onboard system
deep learning

모빌리티 기기에 주로 사용되는 리튬 이온 배터리는 고장 시 심각한 인명 피해로 이어질 수 있어, 실시간으로 배터리의 건전성 상태(State of Health, SOH)를 정확하게 추정하고 모니터링하는 것이 매우 중요하다. 본 논문에서는 TCN-GRU 하이브리드 딥러닝 신경망 기반 리튬 이온 배터리의 SOH 추정 방법을 제안한다. 제안한 모델은 모빌리티 온보드 시스템에 적용 가능하도록 배터리 관리 시스템(BMS)에서 직접 측정 가능한 전류, 전압, 시간의 원시 데이터를 리샘플링하여 입력으로 사용하였다. 해당 입력 데이터는 과거와 현재의 데이터만을 활용하여 학습하는 TCN 모델을 통해 국소적 용량 회복을 포함한 배터리 열화 과정에서 나타나는 비선형적인 특징을 효과적으로 추출함으로써 모델의 신뢰성을 향상시켰다. 추출된 특징은 GRU 모델에 입력되어 시간적 정보 및 패턴을 학습하며, 정밀한 SOH 추정 결과를 도출하였다. 제안한 방법은 CALCE 배터리 열화 데이터를 기반으로 검증하였으며, 평가 지표인 MAE와 RMSE는 모든 배터리 셀에 대해 각각 최대 0.55 및 0.7의 일관되고 우수한 성능을 보였다.

키워드
모빌리티 배터리
리튬 이온 배터리
건전성 상태
추정
배터리 관리 시스템
모빌리티 온보드 시스템
딥러닝
References
1

Bai, S., Kolter, J.Z., Koltun, V. (2018) An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling, arXiv preprint arXiv:1803.01271.

2

Bockrath, S., Lorentz, V., Pruckner, M. (2023) State of Health Estimation of Lithium-Ion Batteries with a Temporal Convolutional Neural Network using Partial Load Profiles, Appl. Energy, 329, p.120307.

10.1016/j.apenergy.2022.120307
3

Chen, M., Ma, G., Liu, W., Zeng, N., Luo, X. (2023a) An Overview of Data-Driven Battery Health Estimation Technology for Battery Management System, Neurocomput., 532, pp.152~169.

10.1016/j.neucom.2023.02.031
4

Chen, S.Z., Liang, Z., Yuan, H., Yang, L., Xu, F., Fan, Y. (2023b) A Novel State of Health Estimation Method for Lithium-Ion Batteries based on Constant-Voltage Charging Partial Data and Convolutional Neural Network, Energy, 283, p.129103.

10.1016/j.energy.2023.129103
5

Cho, K., Van Merriënboer, B., Bahdanau, D., Bengio, Y. (2014) On the Properties of Neural Machine Translation: Encoder-Decoder Approaches, arXiv preprint arXiv:1409.1259.

10.3115/v1/W14-4012
6

Chung, J., Gulcehre, C., Cho, K., Bengio, Y. (2014) Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, arXiv 2014. arXiv preprint arXiv:1412.3555.

7

Deng, Y., Ying, H., Zhu, H., Wei, K., Chen, J., Zhang, F., Liao, G. (2019) Feature Parameter Extraction and Intelligent Estimation of the State-of-Health of Lithium-Ion Batteries, Energy, 176, pp.91~102.

10.1016/j.energy.2019.03.177
8

Gu, X., Shang, Y., Li, J., Zhu, Y., Tao, X., Geng, H., Zhang,Z., Zhang, C. (2025) Early Warning of Thermal Runaway based on State of Safety for Lithium-Ion Batteries, Commun. Eng., 4(1), p.106.

10.1038/s44172-025-00442-140494989PMC12152129
9

He, W., Williard, N., Osterman, M., Pecht, M. (2011) Prognostics of Lithium-Ion Batteries based on Dempster-Shafer Theory and the Bayesian Monte Carlo Method, J. Power Sources, 196(23), pp.10314~10321.

10.1016/j.jpowsour.2011.08.040
10

Huang, K., Guo, Y.F., Tseng, M.L., Wu, K.J., Li, Z.G. (2018) A Novel Health Factor to Predict the Battery’s State-of-Health Using a Support Vector Machine Approach, Appl. Sci., 8(10), p.1803.

10.3390/app8101803
11

Huang, S., Liu, C., Sun, H., Liao, Q. (2022) State of Health Estimation of Lithium-Ion Batteries based on the Regional Frequency, J. Power Sources, 518, p.230773.

10.1016/j.jpowsour.2021.230773
12

Kim, T., Song, W., Son, D.Y., Ono, L.K., Qi, Y. (2019) Lithium-Ion Batteries: Outlook on Present, Future, and Hybridized Technologies, J. Mater. Chem., A, 7(7), pp.2942~2964.

10.1039/C8TA10513H
13

Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D. (2017) Temporal Convolutional Networks for Action Segmentation and Detection, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, pp.1003~1012.

10.1109/CVPR.2017.113
14

Liu, C., Neale, Z.G., Cao, G. (2016) Understanding Electrochemical Potentials of Cathode Materials in Rechargeable Batteries, Mater. Today, 19(2), pp.109~123.

10.1016/j.mattod.2015.10.009
15

Liu, K., Gao, Y., Zhu, C., Li, K., Fei, M., Peng, C., Zhang, X., Han, Q.L. (2022) Electrochemical Modeling and Parameterization Towards Control-Oriented Management of Lithium-Ion Batteries, Control Eng. Pract., 124, p.105176.

10.1016/j.conengprac.2022.105176
16

Long, J., Shelhamer, E., Darrell, T. (2015) Fully Convolutional Networks for Semantic Segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3431~3440.

10.1109/CVPR.2015.7298965
17

Lu, Z., Li, B., Fu, C., Xu, L., Jiang, B., Li, Z., Wu, J., Jia, S. (2025) A Multi-Scale Cross-Dimension Interaction approach with Adaptive Dilated TCN for RUL Prediction, Sci. Rep., 15(1), p.19229.

10.1038/s41598-025-00572-840451804PMC12127457
18

Nguyen Van, C., Quang, D.T. (2023) Estimation of SoH and Internal Resistances of Lithium Ion Battery based on LSTM Network, Int. J. Electrochem. Sci., 18(6), p.100166.

10.1016/j.ijoes.2023.100166
19

Pi, J., da Silva, S.F., Ozkan, M.F., Gupta, A., Canova, M. (2024) Parameter Identification for Electrochemical Models of Lithium-Ion Batteries Using Bayesian Optimization, IFAC-PapersOnLine, 58(28), pp.180~185.

10.1016/j.ifacol.2024.12.031
20

Tran, M.K., Mathew, M., Janhunen, S., Panchal, S., Raahemifar, K., Fraser, R., Fowler, M. (2021) A Comprehensive Equivalent Circuit Model for Lithium-Ion Batteries, Incorporating the Effects of State of Health, State of Charge, and Temperature on Model Parameters, J. Energy Storage, 43, p.103252.

10.1016/j.est.2021.103252
21

Wei, X., Wang, Z. (2024) TCN-Attention-HAR: Human Activity Recognition based on Attention Mechanism Time Convolutional Network, Sci. Rep., 14(1), p.7414.

10.1038/s41598-024-57912-338548859PMC10978978
Information
  • Publisher :Computational Structural Engineering Institute of Korea
  • Publisher(Ko) :한국전산구조공학회
  • Journal Title :Journal of the Computational Structural Engineering Institute of Korea
  • Journal Title(Ko) :한국전산구조공학회 논문집
  • Volume : 38
  • No :5
  • Pages :309-316
  • Received Date : 2025-06-17
  • Revised Date : 2025-07-07
  • Accepted Date : 2025-07-07
  • DOI :https://doi.org/10.7734/COSEIK.2025.38.5.309
Journal Informaiton Journal of the Computational Structural Engineering Institute of Korea Journal of the Computational Structural Engineering Institute of Korea
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close