A life-prediction method for lithium-ion batteries based on a fusion model and an attention mechanism

Xian-bao Wang; Fei-teng Wu; Ming-hai Yao

doi:10.1007/s11801-020-9214-y

Optoelectronics Letters ›› 2020, Vol. 16 ›› Issue (6) : 410-417. DOI: 10.1007/s11801-020-9214-y

Article

A life-prediction method for lithium-ion batteries based on a fusion model and an attention mechanism

Author information +

History +

Abstract

The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To overcome these problems, this paper proposes a deep-learning model combining an autoencoder network and a long short-term memory network. First, this model applies the characteristics of the autoencoder to reduce the dimensionality of the high-dimensional features extracted from the battery data set and realize the fusion of complex time-domain features, which overcomes the problems of redundant model information and low computational efficiency. This model then uses a long short-term memory network that is sensitive to time-series data to solve the long-path dependence problem in the prediction of battery life. Lastly, the attention mechanism is used to give greater weight to features that have a greater impact on the target value, which enhances the learning effect of the model on the long input sequence. To verify the efficacy of the proposed model, this paper uses NASA’s lithium-ion battery cycle life data set.

Cite this article

EndNote

Ris (Procite)

Bibtex

Download citation ▾

Xian-bao Wang, Fei-teng Wu, Ming-hai Yao. A life-prediction method for lithium-ion batteries based on a fusion model and an attention mechanism. Optoelectronics Letters, 2020, 16(6): 410‒417 https://doi.org/10.1007/s11801-020-9214-y

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	ZhangJ, LeeJ. Journal of Power Sources, 2011, 196: 6007 CrossRef Google scholar

[2]	HeW, WilliardN, OstermanM, PechtM. Journal of Power Sources, 2011, 196: 10314 CrossRef Google scholar

[3]	HuX, ZouC, ZhangC, LiY. IEEE Power Energy Magazine, 2017, 15: 20 CrossRef Google scholar

[4]	DatongL, JianbaoZ, LimengG. Journal of Instrumentation, 2015, 36: 1

[5]	XuX, ChenN. Reliability Engineering & System Safety, 2017, 159: 47 CrossRef Google scholar

[6]	HuX, CaoD, EgardtB. IEEE/ASME Transactions on Mechatronics, 2018, 23: 161

[7]	PatilM A, TagadeP, HariharanK S, KolakeS M, SongT, YeoT, DooS. Applied Energy, 2015, 159: 285 CrossRef Google scholar

[8]	WangD, MiaoQ, PechtM. Journal of Power Sources, 2013, 239: 253 CrossRef Google scholar

[9]	LIU JIE and SAXENA, An Adaptive Recurrent Nm-ion Batteries, Annual Conference of the Prognostics and Health Management Society, 1 (2010).

[10]	Rezvani Mohammad, AbuAil Mohamed, Lee Seungchul and Jay Lee, A Comparative Analysis of Techniques for Electric Vehicle Battery Prognostics and Health Management (PHM), Sae Technical Paper, 2011-01-2247.

[11]	WuJ, ZhangC, ChenZ. Applied Energy, 2016, 173: 134 CrossRef Google scholar

[12]	LeiREN, YaqiangS, JinC, LinZ. Journal of Manufacturing Systems, 2018, 48: 71 CrossRef Google scholar

[13]	YutingW, YuanM, ShaopengD, LiL, YingqiL. Neurocomputing, 2018, 275: 167 CrossRef Google scholar

[14]	ZouH, HastieT, TibshiraniR. Journal of Computational and Graphical Statistics, 2006, 15: 265 CrossRef Google scholar

[15]	Md Shamim Reza and Jinwen Ma, ICA and PCA Integrated Feature Extraction for Classification, IEEE 13th International Conference on Signal Processing (ICSP), Chengdu, China, 453 (2016).