Dynamic Long Short-Term Memory Neural-Network- Based Indirect Remaining-Useful-Life Prognosis for Satellite Lithium-Ion Battery
Source abstract
Abstract
On-line remaining-useful-life (RUL) prognosis is still a problem for satellite Lithium-ion (Li-ion) batteries. Meanwhile, capacity, widely used as a health indicator of a battery (HI), is inconvenient or even impossible to measure. Aiming at practical and precise prediction of the RUL of satellite Li-ion batteries, a dynamic long short-term memory (DLSTM) neural-network-based indirect RUL prognosis is proposed in this paper. Firstly, an indirect HI based on the Spearman correlation analysis method is extracted from the battery discharge voltages, and the relationship between the indirect HI indices and battery capacity is established using a polynomial fitting method. Then, by integrating the Adam method, L2 regularization method, and incremental learning, a DLSTM method is proposed and applied for Li-ion battery RUL prognosis. Finally, verification of the results on NASA #5 battery data sets demonstrates that the proposed method has better dynamic performance and higher accuracy than the three other popular methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Quanzhou Institute of Equipment Manufacturing Haixi Institutes, Chinese Academy of Science, Quanzhou 362200, China
College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Funding
Equipment Pre-research National Defense Science Technology Key Laboratory Foundation · Postgraduate Research & Practice Innovation Program of Jiangsu Province · Nature Science Foundation of China · Key Laboratory of Spacecraft Fault Diagnosis and Maintenance on Orbit
References (36)
Show source-provided references
1. Data-driven hybrid remaining useful life estimation approach for spacecraft lithium-ion battery10.1016/j.microrel.2017.06.045 ↗
2. Ageing mechanisms in lithium-ion batteries10.1016/j.jpowsour.2005.01.006 ↗
3. State of the art and taxonomy of prognostics approaches, trends of prognostics applications and open issues towards maturity at different technology readiness levels10.1016/j.ymssp.2017.01.050 ↗
4. A novel multistage support vector machine based approach for Li-ion battery remaining useful life estimation10.1016/j.apenergy.2015.08.119 ↗
5. Reduced kernel recursive least squares algorithm for aero-engine degradation prediction10.1016/j.ymssp.2017.03.046 ↗
6. Wang, X., Jiang, B., Lu, N., and Cocquempot, V. (2018, January 29–31). Accurate prediction of RUL under uncertainty conditions: Application to the traction system of a high-speed train. Proceedings of the 10th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, IFAC Safe Process 2018, Warsaw, Poland.
7. Comparison of different approaches for lifetime prediction of electrochemical systems—Using lead-acid batteries as example10.1016/j.jpowsour.2007.08.057 ↗
8. On-board state-of-health monitoring of lithium-ion batteries using linear parameter-varying models10.1016/j.jpowsour.2012.11.102 ↗
9. An integrated unscented kalman filter and relevance vector regression approach for lithium-ion battery remaining useful life and short-term capacity prediction10.1016/j.ress.2015.07.013 ↗
10. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs10.1016/j.jpowsour.2004.02.031 ↗
11. Remaining useful life prediction and state of health diagnosis for Lithium-Ion batteries using particle filter and support vector regression10.1109/TIE.2017.2782224 ↗
12. A mutated particle filter technique for system state estimation and battery life prediction10.1109/TIM.2014.2303534 ↗
13. Remaining useful life prediction of lithium-ion battery with unscented particle filter technique10.1016/j.microrel.2012.12.004 ↗
14. Particle learning framework for estimating the remaining useful life of Lithium-Ion batteries10.1109/TIM.2016.2622838 ↗
15. Interacting multiple model particle filter for prognostics of lithium-ion batteries10.1016/j.microrel.2017.02.003 ↗
16. An improved autoregressive model by particle swarm optimization for prognostics of lithium-ion batteries10.1016/j.microrel.2013.01.006 ↗
17. Liu, J., Saxena, A., Goebel, K., Saha, B., and Wang, W. (2010, January 13–16). An adaptive recurrent neural network for remaining useful life prediction of Lithium-ion batteries. Proceedings of the Annual Conference of the Prognostics and Health Management Society 2010 (PHM 2010), Portland, OR, USA.10.36001/phmconf.2010.v2i1.1896 ↗
18. Aging prediction and state of charge estimation of a LiFePO4 battery using input time-delayed neural networks10.1016/j.epsr.2017.01.032 ↗
19. State of charge estimation of lithium-ion batteries using optimized Levenberg-Marquardt wavelet neural network10.1016/j.energy.2018.04.085 ↗
20. Lithium-ion battery remaining useful life estimation with an optimized relevance vector machine algorithm with incremental learning10.1016/j.measurement.2014.11.031 ↗
21. A novel health indicator for on-line lithium-ion batteries remaining useful life prediction10.1016/j.jpowsour.2016.04.119 ↗
22. A naive Bayes model for robust remaining useful life prediction of lithium-ion battery10.1016/j.apenergy.2013.12.020 ↗
23. Residual lifetime prediction for lithium-ion battery based on functional principal component analysis and Bayesian approach10.1016/j.energy.2015.07.022 ↗
24. A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve10.1016/j.jpowsour.2018.03.015 ↗
25. Saha, B., and Goebel, K. (2018, March 05). Battery Data Set, NASA Ames Prognostics Data Repository, Available online: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/.
26. A review on the key issues for lithium-ion battery management in electric vehicles10.1016/j.jpowsour.2012.10.060 ↗
27. An analytical model for predicting the remaining battery capacity of Lithium-Ion batteries10.1109/TVLSI.2006.876094 ↗
28. Prognostics in battery health management10.1109/MIM.2008.4579269 ↗
29. A fast estimation algorithm for lithium-ion battery state of health10.1016/j.jpowsour.2018.06.036 ↗
30. Satellite Lithium-Ion battery remaining cycle life prediction with novel indirect health indicator extraction10.3390/en6083654 ↗
31. Detecting trends using spearman’s rank correlation coefficient10.1080/713848278 ↗
32. SOM-based partial labeling of imbalanced data stream10.1016/j.neucom.2016.11.088 ↗
33. Gers, F.A., Schmidhuber, J., and Cummins, F. (1999, January 7–10). Learning to forget: Continual prediction with LSTM. Proceedings of the 9th International Conference on Artificial Neural Networks, (ICANN’99), Edinburgh, UK.10.1049/cp:19991218 ↗
34. A direct adaptive method for faster backpropagation learning: The RPROP algorithm
35. Kingma, D., and Ba, J.L. (arXiv, 2014). Adam: A method for stochastic optimization, arXiv.
36. On the stability of inverse problems