Abstract
An accurate prediction of batteries' future degradation is a key solution to relief the users' anxiety on battery lifespan and electric vehicles' driving range. Technical challenges arise from the highly nonlinear dynamics of battery aging. In this article, a feed-forward migration neural network (NN) is proposed to predict the batteries' aging trajectories. Specifically, a base model that describes the capacity decay over time is first established from the existed battery aging data set. This base model is then transformed by an input-output slope and bias correction (SBC) method structure to capture the degradation of target cell. To enhance the model's nonlinear transfer capability, the SBC model is further integrated into a four-layer NN and easily trained via the gradient correlation algorithm. The proposed migration NN is experimentally verified with four different commercial batteries. The predicted root-mean-square errors (RMSEs) are all lower than 2.5% when using only the first 30% of aging trajectories for NN training. In addition, the illustrative results demonstrate that a small-sized feed-forward NN (down to 1-5-5-1) is sufficient for battery aging trajectory prediction.
Original language | English |
---|---|
Article number | 9028181 |
Pages (from-to) | 363-374 |
Number of pages | 12 |
Journal | IEEE Transactions on Transportation Electrification |
Volume | 6 |
Issue number | 2 |
Early online date | 9 Mar 2020 |
DOIs | |
Publication status | Published - Jun 2020 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2015 IEEE.
Funding
This work was supported in part by the National Natural Science Foundation of China under Project 61433005, in part by the EU funded project under Grant 685716, in part by the Hong Kong Research Grant Council under Grant 16207717, and in part by the Guangdong Scientific and Technological Project under Grant 2017B010120002. (Corresponding authors: Kailong Liu; Furong Gao.) Xiaopeng Tang and Xin Wang are with the Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology, Hong Kong (e-mail: [email protected]; [email protected]). Xiaopeng Tang would like to thank the continuing support from the Guangzhou HKUST Fok Ying Tung Research Institute during the Hong Kong’s unrest and the outbreak of the Covid-19. The institute provides him with not only a safe environment to continue his Ph.D. study, but also a chance to keep contributing to Hong Kong from the perspective of engineering research even in this difficult time.
Keywords
- Aging trajectory prediction
- electric vehicle
- lithium-ion battery management
- model migration
- neural network (NN)