Projects per year
Abstract
Accurate and reliable degradation and lifetime prediction for lithium-ion batteries is the main challenge for smart prognostic and health management. This article proposes a novel semi-supervised self-learning method for battery lifetime prediction. First, three health indicators (HIs) are extracted from the partial capacity-voltage curve. Second, the capacity estimation model and lifetime prediction model are built using data from three randomly selected batteries in the source domain. Then, the HIs are used to reconstruct the historical capacities to provide pseudo values for self-training of the lifetime model. Finally, the self-trained lifetime model is used to predict future degradation. The uncertainty expression is also included to provide the probabilistic prediction of future capacities. Different application scenarios are considered in the verification. The mean lifetime prediction error is less than 23 cycles with only three known checkpoints for batteries aging under different profiles. Predictions for different battery types show that the errors are less than 50 cycles with relative errors less than 4.1% for long lifespan batteries, and less than 20 cycles with relative errors less than 5.21% for short lifespan batteries. This article guides proper solutions for lifetime prediction when the labeled capacities in the real world are limited.
Original language | English |
---|---|
Journal | IEEE Transactions on Industrial Informatics |
Volume | 19 |
Issue number | 5 |
Pages (from-to) | 6471-6481 |
Number of pages | 11 |
ISSN | 1551-3203 |
DOIs | |
Publication status | Published - 1 May 2023 |
Bibliographical note
Publisher Copyright:IEEE
Keywords
- Aging
- Artificial neural networks
- Batteries
- Data models
- Degradation
- Estimation
- Lithium-ion battery
- Predictive models
- degradation reconstruction
- lifetime prediction
- probabilistic prediction
- semi-supervised learning
- semisupervised learning
- Degradation reconstruction
- lithium-ion battery
Fingerprint
Dive into the research topics of 'Semi-supervised self-learning-based lifetime prediction for batteries'. Together they form a unique fingerprint.-
CROSBAT: SMART BATTERY
Teodorescu, R., Stroe, D., Kulkarni, A., Sui, X., Vilsen, S. B., Che, Y., Zheng, Y., Bharadwaj, P., Weinreich, N. A., Christensen, M. D. & Steffensen, B.
01/09/2021 → 31/08/2027
Project: Research
-
State of Health Estimation and Prediction for Lithium-ion Batteries Based on Transfer Learning
Che, Y., Teodorescu, R. & Sui, X.
01/12/2021 → 31/12/2023
Project: PhD Project
Research output
- 19 Citations
- 1 PhD thesis
-
State of Health Estimation and Prediction for Lithium-ion Batteries Based on Transfer Learning
Che, Y., 2023, Aalborg Universitetsforlag.Research output: PhD thesis
Open AccessFile26 Downloads (Pure)