Improved singular filtering-Gaussian process regression-long short-term memory model for whole-life-cycle remaining capacity estimation of lithium-ion batteries adaptive to fast aging and multi-current variations

Shunli Wang, Fan Wu, Paul Takyi-Aninakwa, Carlos Fernandez, Daniel-Ioan Stroe and Qi Huang

Energy, 2023, vol. 284, issue C

Abstract: For the development of low-temperature power systems in aviation, the transport synergistic carrier optimization of lithium-ions and electrons is conducted to improve the low-temperature adaptability of lithium-ion batteries. In this paper, an improved robust multi-time scale singular filtering-Gaussian process regression-long short-term memory (SF-GPR-LSTM) modeling method is proposed for the remaining capacity estimation. The optimized multi-task training strategy is constructed for the rapid battery performance evaluation, realizing the refined mathematical dynamic characterization for the mapping relationship of the physical carrier transports to obtain the simultaneous improvement of multi-dimensional physical features and a spiral-up iterative optimization scheme. The adaptability of the model is verified using datasets from the whole-life-cycle test conducted on two batteries, and evaluated by root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R-squared metrics. Even when only using 55% of the datasets to estimate the remaining capacity, the estimation has good effects, with RMSE of 2.3484%, MAE of 0.82526%, MAPE of 0.90716%, and R-squared value of 92.457%. The proposed SF-GPR-LSTM model enables the carrier transport synergistic optimization effectively, laying a theoretical foundation for the whole-life-cycle battery remaining capacity estimation at extremely low temperatures.

Keywords: Lithium-ion battery; Singular filtering-Gaussian process regression-long short-term memory network; Whole-life-cycle remaining capacity estimation; Fast-fading aging; Collaborative carrier transport (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223020716
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:284:y:2023:i:c:s0360544223020716

DOI: 10.1016/j.energy.2023.128677

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().