A Data-Driven Approach With Uncertainty Quantification for Predicting Future Capacities and Remaining Useful Life of Lithium-ion Battery

Predicting future capacities and remaining useful life (RUL) with uncertainty quantification is a key but challenging issue in the applications of battery health diagnosis and management. This article applies advanced machine-learning techniques to achieve effective future capacities and RUL predict...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on industrial electronics (1982) Ročník 68; číslo 4; s. 3170 - 3180
Hlavní autoři: Liu, Kailong, Shang, Yunlong, Ouyang, Quan, Widanage, Widanalage Dhammika
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Battery cycles
data-driven approach
Decomposition
Degradation
Diagnosis
Electric vehicles (EVs)
Gaussian process
Ground penetrating radar
Lithium
lithium-ion (Li-ion) batteries
Lithium-ion batteries
Machine learning
Predictions
Predictive models
Rechargeable batteries
Reliability
remaining useful life (RUL)
Uncertainty
uncertainty management
Useful life
ISSN:0278-0046, 1557-9948
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Predicting future capacities and remaining useful life (RUL) with uncertainty quantification is a key but challenging issue in the applications of battery health diagnosis and management. This article applies advanced machine-learning techniques to achieve effective future capacities and RUL prediction for lithium-ion (Li-ion) batteries with reliable uncertainty management. To be specific, after using the empirical mode decomposition (EMD) method, the original battery capacity data is decomposed into some intrinsic mode functions (IMFs) and a residual. Then, the long short-term memory (LSTM) submodel is applied to estimate the residual while the Gaussian process regression (GPR) submodel is utilized to fit the IMFs with the uncertainty level. Consequently, both the long-term dependence of capacity and uncertainty quantification caused by the capacity regenerations can be captured directly and simultaneously. Experimental aging data from different batteries are deployed to evaluate the performance of proposed LSTM+GPR model in comparison with the solo GPR, solo LSTM, GPR+EMD, and LSTM+EMD models. Illustrative results demonstrate the combined LSTM+GPR model outperforms other counterparts and is capable of achieving accurate results for both 1-step and multistep ahead capacity predictions. Even predicting the RUL at the early battery cycle stage, the proposed data-driven approach still presents good adaptability and reliable uncertainty quantification for battery health diagnosis.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0278-0046
1557-9948
DOI:10.1109/TIE.2020.2973876