The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index; 2 of the 9 sources its claims cite were checked for support.
A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries
Open accessAbstract
Accurate state of charge (SOC) estimation is a critical challenge for battery management systems (BMSs), hindered by the nonlinear electrochemistry of lithium-ion batteries, their sensitivity to temperature, and pervasive measurement noise. Crucially, battery aging significantly degrades estimation accuracy, posing a major hurdle for long-term system dependability. We propose the Physics-Informed Transformer (PI-Transformer), a novel framework that integrates high-fidelity electrochemical constraints from the PyBaMM (Version: 25.10.2) model directly into a Transformer architecture. This approach ensures physical consistency while leveraging the Transformer’s self-attention mechanism to model long-term temporal dependencies. The framework is specifically designed to be robust against the effects of battery aging, incorporating an attention-based noise modeling module to enhance resilience against sensor uncertainty and capacity fade. Evaluated on two public datasets under diverse conditions, including variable temperatures, fast-charging protocols, and multiple stages of battery degradation, the PI-Transformer consistently achieves state-of-the-art performance. It demonstrates exceptional robustness and maintains high accuracy under challenging low-temperature and severely aged battery scenarios, highlighting its strong potential for deployment in real-world ESS applications where aging is a primary concern.
Overview
CoChat Summary
TL;DR
The paper proposes PI-Transformer, a Transformer with PyBaMM-derived physics-informed embedding and attention-based noise/aging modeling for SOC estimation in aging lithium-ion batteries. It reports state-of-the-art RMSE and R² across NASA 24 °C/4 °C and Braatz 30 °C fast-charging/aging datasets.
Key findings
- On NASA 24 °C (EXP1), PI-Transformer achieved Validation RMSE 0.0195 and Test RMSE 0.0256, with Validation R² 0.9903 and Test R² 0.9765; the paper states it outperformed the next-best LSTM by 3.5% and 25.2% on validation and test RMSE, respectively.
- On NASA 4 °C (EXP2), it achieved Validation/Test RMSE 0.0226 and R² 0.9783, versus standard Transformer R² 0.9759.
- On Braatz 30 °C fast-charging/aging (EXP3), it achieved Test RMSE 0.0698, a 31.5% reduction versus CNN-Transformer (0.1016), and Test R² 0.9594.
- Ablation: disabling the noise modeling module increased RMSE by 13.3% on NASA 4 °C and 18.4% on Braatz; the Conclusion separately states RMSE increased by over 180% when disabled.
Methods
- PI-Transformer embeds the PyBaMM electrochemical SOC differential equation as a physics-informed embedding, fuses it with data-driven Transformer features, and uses an attention-based noise/aging module; it is trained end-to-end with MSE loss.
- Data: NASA dataset (34 18650-type cells, 2.0 Ah, 24 °C and 4 °C, 7,457,030 samples across 7565 cycles) and Braatz dataset (124 LFP/graphite A123 APR18650M1A cells, 1.1 Ah, 3.3 V, fast-charging at 30 °C). NASA used a chronological 60/20/20 split per cell; Braatz used a stratified random 60/20/20 split by battery ID.
- Compared EKF, LSTM, GRU, Transformer, CNN-Transformer, PI-Transformer, and PI-Transformer without noise; metrics were RMSE, R², and MAE. Training used AdamW, learning rate 0.001 with cosine annealing, batch size 1536, 10 epochs with early stopping, PyTorch 2.0/CUDA 12.1 on an NVIDIA A100; inputs were voltage, current, and temperature, with window length 50, d_model 128, 2 encoder layers, 8 heads, d_ff 512, and dropout 0.2.
Limitations
- Stated: evaluation is limited to Li-ion/LFP chemistries; reliance on accurate temperature measurements may limit practical deployment; computational cost may require optimization for real-time edge inference; and lack of uncertainty quantification limits safety-critical applications.
- Evident: the ablation magnitude is inconsistent—Section 5.2 reports 13.3% and 18.4% RMSE increases when the noise module is disabled, while the Conclusion says “over 180%.”
- Evident: Table 3 reports identical validation and test RMSE/R² for PI-Transformer in EXP2 (0.0226/0.9783), which may indicate a reporting or duplication issue.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 1 Not valid · 6 Not checked · 66 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In practice, Ah-integration with periodic OCV correction remains common due to simplicity [11] but is sensitive to initial SOC errors and sensor drift, leading to cumulative inaccuracies [12].”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 1. Introduction
What the sources say
- Could not verifycites [12] Madani, S.S., Ziebert, C., and Marzband, M. (2023). Thermal Behavior Modeling of Lithium-Ion Batteries: A Comprehensive Review. Symmetry, 15. sourceExperimental — accuracy not yet measured
The passages in Section 4 discuss thermal and electrochemical models, while the equipment-constraints passage concerns uncertainty in thermal analysis. Neither addresses errors in Ah-integration with periodic OCV correction. Searches for Ah-integration, sensor drift, initial SOC errors, and accumulated measurement error found no passage supporting the part attributed to [12]. Page numbers were not available in our copy. (LLM, conf=0.76)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“These capabilities make PyBaMM well-suited for studying degradation mechanisms and state estimation problems; however, direct deployment of full-fidelity models for real-time SOC estimation in battery management systems is hindered by high computational costs and sensitivity to parameter identification errors under dynamic conditions [34].”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 1. Introduction
What the sources say
- Partly supportedcites [34] Hallemans, 2025, Physics-Based Battery Model Parametrisation from Impedance Data, J. Electrochem. Soc. sourceExperimental — accuracy not yet measured
The introductory passage (p. 1) says full DFN models are typically too expensive to simulate in a BMS and that model parameters require sufficiently informative data to be identifiable. It does not establish that parameter-identification errors hinder real-time SOC estimation under dynamic conditions; the drive-cycle validation (section 7.3, p. 14) instead reports reasonable voltage errors for a parametrised reduced-order model. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Evaluated on two public datasets under diverse conditions, including variable temperatures, fast-charging protocols, and multiple stages of battery degradation, the PI-Transformer consistently achieves state-of-the-art performance.”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In summary, the ablation study provides strong empirical evidence that the noise modeling module is a key contributor to the PI-Transformer's superior performance, particularly under aged and noisy conditions.”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 5.2. Ablation Study of the Noise Modeling Module
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The chart clearly illustrates that the performance gap between the models widens as the operating conditions become more challenging.”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 5.2. Ablation Study of the Noise Modeling Module
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
31 more claims
Create a free account to see all 74 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 29
- Probably not a substantial claim. 10
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 2. Problem Formulation for SOC Estimation
“I k is the charging/discharging current (positive for charging, negative for discharging)”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 3.1. Physics-Informed Embedding via PyBaMM
“I(t) is the current (positive for discharge and negative for charge)”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 6. Conclusions and Discussion
“Ablation studies confirm that the adaptive noise modeling module is critical for maintaining performance under noisy and aged conditions, with RMSE increasing by over 180% when disabled.”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 5.2. Ablation Study of the Noise Modeling Module
“when the noise module is disabled, the model's RMSE increases by 13.3% on the NASA 4°C dataset and 18.4% on the Braatz dataset.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > Main contributions:
“the PI-Transformer achieving the lowest error rates and highest R 2 scores across all evaluations.”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 6. Conclusions and Discussion
“| Transformer | 0.0212 | 0.0258 | 0.9810 | 0.0219 | 0.0271 | 0.9759 | | CNN-Transformer | 0.0212 | 0.0273 | 0.9763 | 0.0236 | 0.0301 | 0.9697 | | Transformer-PI (Ours) | 0.0169 | 0.0226 | 0.9783 | 0.0169 | 0.0226 | 0.9783 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 5.1.1. Performance on NASA Dataset at 24 °C (EXP1)
“outperforming the next best model (LSTM) by 3.5% and 25.2%, respectively.”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 6. Conclusions and Discussion
“| LSTM | 0.0154 | 0.0202 | 0.9889 | 0.0266 | 0.0344 | 0.9527 | | GRU | 0.0156 | 0.0201 | 0.9893 | 0.0272 | 0.0335 | 0.9573 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 6. Conclusions and Discussion
“Comprehensive evaluation across three datasets demonstrates superior accuracy, robustness, and generalization”
§ A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries > 4.1. Dataset Description
“This study evaluates the proposed SOC estimation method using two widely recognized public datasets: the NASA dataset and the Braatz dataset [36].”
Citations
Cites
Data-driven prediction of battery cycle life before capacity degradation
Severson, K. A., Attia, P. M., Jin, N., Perkins, N., Jiang, B., Yang, Z., Chen, M. H., Aykol, M., Herring, P. K., Fraggedakis, D., et al. (2019) · Nature Energy · doi:10.1038/s41560-019-0356-8 · Cited by 3,228
Machine learning pipeline for battery state-of-health estimation
Roman, D., Saxena, S., Robu, V., Pecht, M., & Flynn, D. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00312-3 · Cited by 660 · cited 1×
“Such frameworks have also been extended to state of health estimation [19].”
The State of Charge Estimating Methods for Battery: A Review
Chang, W.-Y. (2013) · ISRN Applied Mathematics · doi:10.1155/2013/953792 · Cited by 650
Python battery mathematical modelling (PyBaMM)
Sulzer, V., Marquis, S. G., Timms, R., Robinson, M., & Chapman, S. J. (2021) · Journal of Open Research Software · doi:10.5334/jors.309 · Cited by 477
Lu, J., Xiong, R., Tian, J., Wang, C., & Sun, F. (2023) · Nature Communications · doi:10.1038/s41467-023-38458-w · Cited by 403 · cited 1×
“Their widespread deploy-ment—from consumer electronics to grid-scale storage—has driven rapid market growth, with global EV-related LIB demand reaching 142.8 GWh in 2020 and projected to exceed 91.8 billion USD in the coming years [3].”
InfluentialAn Overview and Comparison of Online Implementable SOC Estimation Methods for Lithium-Ion Battery
Meng, J., Ricco, M., Luo, G., Swierczynski, M., Stroe, D.-I., Stroe, A.-I., & Teodorescu, R. (2018) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2017.2775179 · Cited by 393 · cited 1×
“Ensuring safe and efficient operation therefore requires accurate real-time estimation of internal states—most notably the state of charge (SOC) and state of health (SOH)—which are pivotal for battery management systems (BMSs) [5].”
A Comprehensive Review on the Characteristics and Modeling of Lithium-Ion Battery Aging
Vermeer, W., Chandra Mouli, G. R., & Bauer, P. (2022) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2021.3138357 · Cited by 385 · cited 1×
“Balancing high model fidelity with computational efficiency remains challenging, especially for real-time BMSs [28–30].”
A comprehensive review on estimation strategies used in hybrid and battery electric vehicles
Cuma, M. U., & Koroglu, T. (2015) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2014.10.047 · Cited by 344 · cited 1×
“Balancing high model fidelity with computational efficiency remains challenging, especially for real-time BMSs [28–30].”
Early prediction of battery lifetime via a machine learning based framework
Fei, Z., Yang, F., Tsui, K.-L., Li, L., & Zhang, Z. (2021) · Energy · doi:10.1016/j.energy.2021.120205 · Cited by 302 · cited 1×
“Lithium-ion batteries (LIBs) have become the dominant energy storage technology for electric vehicles and renewable energy integration due to their high energy density, low self-discharge rate, fast response, and long cycle life [1,2].”
A new model for State-of-Charge (SOC) estimation for high-power Li-ion batteries
He, Y., Liu, X., Zhang, C., & Chen, Z. (2013) · Applied Energy · doi:10.1016/j.apenergy.2012.08.031 · Cited by 276
Cited by
Review on improved neural network algorithms for battery state of energy estimation in smart grids
Wang, S., Fu, Y., Zhang, W., Fernández, C., & Blaabjerg, F. (2026) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2026.116797 · Cited by 36
Njathi, Y., Maina, C. W., & Mharakurwa, E. T. (2026) · Batteries · doi:10.3390/batteries12050162
Metadata
- Authors
- Li, X., Wu, G., Chang, F., Xia, W., Sun, S., & Shen, Y.
- Affiliations
- State Grid Nanjing Power Supply Company (China) (CN)
- Chinese Academy of Sciences (CN)
- Corresponding author
- Wu, Guanru
- Venue
- Batteries
- Publisher
- MDPI AG
- Published
- 2025-12-03
- Volume
- 11
- Issue
- 12
- Pages
- 446
- ISSN
- 2313-0105 (ISSN-L)
- OpenAlex
- W4416958527
- Cited by
- 2
- References
- 35
- Citations by year
- 2026: 2
- FWCI
- 0.49
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Batteries (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Science and Technology Project of State Grid Corporation of China (JF2025021)
- Incubation Project of State Grid Jiangsu Electric Power Co., Ltd.
- 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, battery degradation, physics-informed machine learning, transformer models, PyBaMM, battery management systems, energy storage systems, capacity fade, temperature effects, fast charging
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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: A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries. https://app.cochat.ai/papers/10.3390/batteries11120446
- The paper
- Li, X., Wu, G., Chang, F., Xia, W., Sun, S., & Shen, Y. (2025). A Physics-Guided Transformer for Robust State of Charge Estimation in Aging Lithium-Ion Batteries. Batteries. https://doi.org/10.3390/batteries11120446
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.