A Data-Driven Battery Degradation Estimation Method for Low-Earth-Orbit (LEO) Satellites
Source abstract
Abstract
Battery degradation is a critical challenge in the operation and longevity of low-Earth-orbit (LEO) satellites because of its direct impact on mission reliability and power system performance. This study proposes a data-driven approach to accurately estimating the degradation of satellite batteries by integrating a transformer network model for voltage prediction and unscented Kalman filter (UKF) techniques for online state estimation. By utilizing on-orbit telemetry data and machine-learning-based modeling, the proposed method provides processing-time improvements by addressing the limitations of traditional methods imposed by their reliance on predefined conditions and user expertise. The proposed framework is validated using real satellite telemetry data from KOMPSAT-5, demonstrating its ability to predict battery degradation trends over time and under varying operational conditions. This approach minimizes manual data processing requirements and enables the consistent and precise monitoring of battery health.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Fault Detection and Control Systems · Advancements in Battery Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of KOMPSAT-7 Program, Korea Aerospace Research Institute, Daejeon 34133, Republic of Korea
School of Electronic Engineering, Gyeongsang National University, Jinju 34158, Republic of Korea
Funding
Gyeongsang National University
References (25)
Show source-provided references
1. Optimal Battery Planning for Microgrid Applications Considering Battery Swapping and Evolution of the SOH During Lifecycle Aging10.1109/JSYST.2023.3285147 ↗
2. Development and On-Orbit Operation of Lithium-Ion Pouch Battery for Small Scientific Satellite “REIMEI”10.1016/j.jpowsour.2011.06.051 ↗
3. Battery Management System With State-of-Charge and Opportunistic State-of-Health for a Miniaturized Satellite10.1109/TAES.2019.2958161 ↗
4. Advancing Lithium-Ion Battery Health Prognostics With Deep Learning: A Review and Case Study
5. Saleem, U., Li, W., Liu, W., Ahmad, I., Aslam, M.M., and Lateef, H.U. (2023, January 29–30). Investigation of Deep Learning Based Techniques for Prognostic and Health Management of Lithium-Ion Battery. Proceedings of the 2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Bucharest, Romania.10.1109/ECAI58194.2023.10194122 ↗
6. Ersöz, B., Oyucu, S., Aksöz, A., Sağıroğlu, Ş., and Biçer, E. (2024). Interpreting CNN-RNN Hybrid Model-Based Ensemble Learning with Explainable Artificial Intelligence to Predict the Performance of Li-Ion Batteries in Drone Flights. Appl. Sci., 14.10.3390/app142310816 ↗
7. Convolutional Transformer-Based Multiview Information Perception Framework for Lithium-Ion Battery State-of-Health Estimation10.1109/TIM.2023.3300451 ↗
8. Ahmed, A.M., Salama, A., Ibrahim, H.A., Sayed, M.A.E., and Yacout, S. (2019, January 2–9). Prediction of Battery Remaining Useful Life on Board Satellites Using Logical Analysis of Data. Proceedings of the 2019 IEEE Aerospace Conference, Big Sky, MT, USA.10.1109/AERO.2019.8741717 ↗
9. Shangguan, D., Chen, L., and Ding, J. (2020). A Digital Twin-Based Approach for the Fault Diagnosis and Health Monitoring of a Complex Satellite System. Symmetry, 12.10.3390/sym12081307 ↗
10. Gayrard, J.-D. (2021, January 27–30). Inclined MEO constellation to provide cost effective global high speed trunking services. Proceedings of the 38th International Communications Satellite Systems Conference (ICSSC 2021), Hybrid Conference, Arlington, VA, USA.10.1049/icp.2022.0551 ↗
11. A Method for Interval Prediction of Satellite Battery State of Health Based on Sample Entropy10.1109/ACCESS.2019.2939593 ↗
12. Wang, X., Gao, Y., Lu, D., Li, Y., Du, K., and Liu, W. (2024). Lithium Battery SoC Estimation Based on Improved Iterated Extended Kalman Filter. Appl. Sci., 14.10.3390/app14135868 ↗
13. Small Satellites an Overview and Assessment10.1016/j.actaastro.2020.01.034 ↗
14. Guirguis, J., and Ahmed, R. (2024). Transformer-Based Deep Learning Models for State of Charge and State of Health Estimation of Li-Ion Batteries: A Survey Study. Energies, 17.10.3390/en17143502 ↗
15. Wang, R., Ma, L., He, G., Johnson, B.A., Yan, Z., Chang, M., and Liang, Y. (2024). Transformers for Remote Sensing: A Systematic Review and Analysis. Sensors, 24.10.3390/s24113495 ↗
16. Bayesian Deep Neural Network to Compensate for Current Transformer Saturation10.1109/ACCESS.2021.3127542 ↗
17. Notani, S., and Bhattacharya, S. (2011, January 17–22). Flexible electrical power system controller design and battery integration for 1U to 12U CubeSats. Proceedings of the 2011 IEEE Energy Conversion Congress and Exposition, Phoenix, AZ, USA.10.1109/ECCE.2011.6064262 ↗
18. Ahwiadi, M., and Wang, W. (2025). Battery Health Monitoring and Remaining Useful Life Prediction Techniques: A Review of Technologies. Batteries, 11.10.3390/batteries11010031 ↗
19. Liang, Y., and Zhao, S. (2024). Early Prediction of Remaining Useful Life for Lithium-Ion Batteries with the State Space Model. Energies, 17.10.3390/en17246326 ↗
20. Jiang, J., Qu, B., Liu, S., Yan, H., Zhang, Z., and Chang, C. (2024). Fault Diagnosis of Lithium-Ion Batteries Based on the Historical Trajectory of Remaining Discharge Capacity. Appl. Sci., 14.10.3390/app142310895 ↗
21. Huang, Q., Li, J., Xu, Q., He, C., Yang, C., Cai, L., Xu, Q., Xiang, L., Zou, X., and Li, X. (2024). State of Charge Estimation in Batteries for Electric Vehicle Based on Levenberg–Marquardt Algorithm and Kalman Filter. World Electr. Veh. J., 15.10.3390/wevj15090391 ↗
22. Bouchareb, H., Saqli, K., M’sirdi, N.K., and Oudghiri Bentaie, M. (2024). Lithium-Ion Battery Health Management and State of Charge (SOC) Estimation Using Adaptive Modelling Techniques. Energies, 17.10.3390/en17225746 ↗
23. A Bayesian Optimized Deep Learning Approach for Accurate State of Charge Estimation of Lithium Ion Batteries Used for Electric Vehicle Application10.1109/ACCESS.2024.3380188 ↗
24. Prediction of COVID-19 Data Using Improved ARIMA-LSTM Hybrid Forecast Models10.1109/ACCESS.2023.3291999 ↗
25. Bi-LSTM-Based Two-Stream Network for Machine Remaining Useful Life Prediction10.1109/TIM.2022.3167778 ↗