Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index.

Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model

Open access

Abstract

Accurate state of charge (SOC) estimation of lithium-ion (Li-ion) batteries is crucial in prolonging cell lifespan and ensuring its safe operation for electric vehicle applications. In this article, we propose the deep learning-based transformer model trained with self-supervised learning (SSL) for end-to-end SOC estimation without the requirements of feature engineering or adaptive filtering. We demonstrate that with the SSL framework, the proposed deep learning transformer model achieves the lowest root-mean-square-error (RMSE) of 0.90% and a mean-absolute-error (MAE) of 0.44% at constant ambient temperature, and RMSE of 1.19% and a MAE of 0.7% at varying ambient temperature. With SSL, the proposed model can be trained with as few as 5 epochs using only 20% of the total training data and still achieves less than 1.9% RMSE on the test data. Finally, we also demonstrate that the learning weights during the SSL training can be transferred to a new Li-ion cell with different chemistry and still achieve on-par performance compared to the models trained from scratch on the new cell.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-021-98915-8

Cites

77 of 77 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 SOC estimation at room temperature. (a) LA92 drive cycle at 25 °C. (b) UDDS drive cycle at 25 °C. (c) US06 drive cycle at 25 °C.
Figure 1 SOC estimation at room temperature. (a) LA92 drive cycle at 25 °C. (b) UDDS drive cycle at 25 °C. (c) US06 drive cycle at 25 °C.CC BY · PubMed Central
Figure 2 SOC estimation at above zero ambient temperatures. (a) LA92 drive cycle at 10 °C. (b) UDDS drive cycle at 10 °C. (c) US06 drive cycle at 10 °C. (d) LA92 drive cycle at 25 °C. (e) UDDS drive cycle at 25 °C. (f) US06 drive cycle at 25 °C. (g) LA92 drive cycle at 40 °C. (h) UDDS drive cycle at 40 °C. (i) US06 drive cycle at 40 °C.
Figure 2 SOC estimation at above zero ambient temperatures. (a) LA92 drive cycle at 10 °C. (b) UDDS drive cycle at 10 °C. (c) US06 drive cycle at 10 °C. (d) LA92 drive cycle at 25 °C. (e) UDDS drive cycle at 25 °C. (f) US06 drive cycle at 25 °C. (g) LA92 drive cycle at 40 °C. (h) UDDS drive cycle at 40 °C. (i) US06 drive cycle at 40 °C.CC BY · PubMed Central
Figure 3 SOC estimation at below zero ambient temperatures. (a) LA92 drive cycle at 0 °C. (b) UDDS drive cycle at 0 °C. (c) US06 drive cycle at 0 °C. (d) LA92 drive cycle at − 10 °C. (e) UDDS drive cycle at − 10 °C. (f) US06 drive cycle at − 10 °C. (g) LA92 drive cycle at − 20 °C. (h) UDDS drive cycle at − 20 °C. (i) US06 drive cycle at − 20 °C.
Figure 3 SOC estimation at below zero ambient temperatures. (a) LA92 drive cycle at 0 °C. (b) UDDS drive cycle at 0 °C. (c) US06 drive cycle at 0 °C. (d) LA92 drive cycle at − 10 °C. (e) UDDS drive cycle at − 10 °C. (f) US06 drive cycle at − 10 °C. (g) LA92 drive cycle at − 20 °C. (h) UDDS drive cycle at − 20 °C. (i) US06 drive cycle at − 20 °C.CC BY · PubMed Central
Figure 4 Estimation plot on the test drive cycles of the Panasonic cell with various training combinations. (a) HWFET cycle at 0 °C. (b) US06 cycle at 0 °C. (c) HWFET cycle at 10 °C. (d) US06 cycle at 10 °C. (e) HWFET cycle at 25 °C. (f) US06 cycle at 25 °C.
Figure 4 Estimation plot on the test drive cycles of the Panasonic cell with various training combinations. (a) HWFET cycle at 0 °C. (b) US06 cycle at 0 °C. (c) HWFET cycle at 10 °C. (d) US06 cycle at 10 °C. (e) HWFET cycle at 25 °C. (f) US06 cycle at 25 °C.CC BY · PubMed Central
Figure 5 Data preprocessing pipeline from raw values to positional encoding. (a) Raw data sample plot from the UDDS drive cycle at − 20 °C ambient temperature. (b) Input-label pairs constructed by sliding a fix width window across the train, validation, and test dataset. (c) Dataset converted into positional encoding to be ingested into Transformer.
Figure 5 Data preprocessing pipeline from raw values to positional encoding. (a) Raw data sample plot from the UDDS drive cycle at − 20 °C ambient temperature. (b) Input-label pairs constructed by sliding a fix width window across the train, validation, and test dataset. (c) Dataset converted into positional encoding to be ingested into Transformer.CC BY · PubMed Central
Figure 6 Framework and architecture of the proposed transformer model.
Figure 6 Framework and architecture of the proposed transformer model.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 77 references

Cited by

See all 196

Metadata

Authors
Hannan, M. A., How, D. N. T., Lipu, M. S. H., Mansor, M., Ker, P. J., Dong, Z. Y., Sahari, K. S. M., Tiong, S. K., Muttaqi, K. M., Mahlia, T. M. I., & Blaabjerg, F.
Affiliations
  • Universiti Tenaga Nasional (MY)
  • National University of Malaysia (MY)
  • UNSW Sydney (AU)
  • University of Wollongong (AU)
  • University of Technology Sydney (AU)
  • Aalborg University (DK)
Corresponding author
  • Hannan, M. A.
  • How, D. N. T.
Venue
Scientific Reports
Published
2021-10-01
Volume
11
Issue
1
Pages
19541-19541
ISSN
2045-2322 (ISSN-L)
OpenAlex
W3203898572
Cited by
196
References
77
Citations by year
2026: 48 · 2025: 48 · 2024: 46 · 2023: 38 · 2022: 15 · 2021: 1
FWCI
8.12
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion, other-oa)
  • Research Online (University of Wollongong) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion)
  • VBN Forskningsportal (Aalborg Universitet) (submittedVersion, cc-by)
  • Greater South Information System
Funders
Ministry of Higher Education, Malaysia (20190101LRGS)
Topics
  • Physical Sciences › Engineering › Automotive Engineering › Battery Modeling and Management
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advancements in Battery Materials
  • Physical Sciences › Engineering › Control and Systems Engineering › Control Systems and Identification
Keywords
state of charge estimation, lithium-ion batteries, self-supervised learning, transformer models, electric vehicles, ambient temperature variation, transfer learning, battery management systems

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model. https://app.cochat.ai/papers/10.1038/s41598-021-98915-8
The paper
Hannan, M. A., How, D. N. T., Lipu, M. S. H., Mansor, M., Ker, P. J., Dong, Z. Y., Sahari, K. S. M., Tiong, S. K., Muttaqi, K. M., Mahlia, T. M. I., & Blaabjerg, F. (2021). Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model. Scientific Reports. https://doi.org/10.1038/s41598-021-98915-8

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.