Search for Author, Title, Keyword
RESEARCH PAPER
Similarity Based Remaining Useful Life Prediction for Lithium-ion Battery under Small Sample Situation Based on Data Augmentation
,
 
,
 
,
 
 
 
 
More details
Hide details
1
School of Electronics and Information Engineering, Beijing jiaotong university, Beijing, 100044, China
 
2
China State Key Laboratory of Rail Traffic control and safety, Beijing jiaotong university, Beijing, 100044, China
 
 
Submission date: 2023-09-18
 
 
Final revision date: 2023-10-30
 
 
Acceptance date: 2023-11-20
 
 
Online publication date: 2023-11-24
 
 
Publication date: 2023-11-24
 
 
Corresponding author
Wei Shangguan   

Beijing jiaotong university, China
 
 
Eksploatacja i Niezawodność – Maintenance and Reliability 2024;26(1):175585
 
HIGHLIGHTS
  • The realistic degradation trajectories are generated based on the single exponential model and Sobol sampling.
  • The Pearson distance is used to assess the similarity between the predicted reference trajectory and the actual trajectory.
  • Based on similarity measures and kernel density estimation, point estimation and uncertainty estimation of RUL are realized.
KEYWORDS
TOPICS
ABSTRACT
Accurately predicting the remaining useful life of lithium-ion batteries is crucial for enhancing battery reliability and reducing maintenance costs. In recent years, similarity-based prediction methods have gained significant attention and practical use. However, these methods rely on sufficient and diverse run-to-failure data. To address this limitation, this paper proposes a data augmentation-based SBP method for accurate RUL prediction of lithium-ion batteries. By employing the single exponential model and Sobol sampling, realistic degradation trajectories can be generated, even with only one complete run-to-failure degradation dataset. The similarity between the generated prediction reference trajectories and real degradation trajectories is evaluated using the Pearson distance, and RUL point estimation is performed through weighted averaging. Furthermore, the uncertainty of the RUL predictions is quantified using kernel density estimation. The effectiveness of the proposed RUL prediction method is validated using the NASA lithium-ion battery dataset.
ACKNOWLEDGEMENTS
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this a rticle. This work was funded by the Beijing Natural Science Foundation (No. L211022) and Fundamental Research Funds for the Central Universities (2023YJS004).
 
CITATIONS (1):
1.
 
eISSN:2956-3860
ISSN:1507-2711
Journals System - logo
Scroll to top