journal article·2026-03Open access

Accelerated battery state-of-health estimation using conditional autoencoders for intelligent frequency band selection

Hamed Moayyed, Hussein Abdeltawab, Rishivandhiga Jayakumar, Lin Ma

Abstract

Electrochemical Impedance Spectroscopy (EIS) is a widely adopted non-intrusive diagnostic technique in battery management systems (BMS) for evaluating battery state-of-health (SoH) and tracking degradation processes. However, conventional full-spectrum EIS measurements, spanning millihertz to kilohertz, are time-consuming and resource-intensive, limiting their practicality in real-time BMS applications. This work extends diagnostic research to Sodium-ion batteries (SIBs), an emerging technology with limited characterization. Despite their promising advantages in cost, safety, and resource availability, SIBs remain significantly less studied than lithium-ion chemistries. A Conditional Autoencoder, explicitly conditioned on operating mode, temperature, and cycle index, extracts latent features from SIBs’ EIS data, while a Random Forest regressor leverages these features for robust SoH prediction. This optimized framework achieves substantial reductions in required frequency points without sacrificing accuracy. Experimental validation on sodium-ion cells across both charge and discharge modes at and demonstrates clear advantages over full-spectrum baselines in capturing degradation trends with minimal SoH precision reduction. Beyond immediate performance gains, this approach supports the design of next-generation BMS firmware capable of adaptively probing only the most informative frequencies, achieving a 95% reduction in measurement points while preserving near full-spectrum accuracy ( ), enabling intelligent charging, dynamic balancing, and real-time compensation in energy storage systems.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · ECG Monitoring and Analysis · Machine Fault Diagnosis Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (69)

Show source-provided references
1. Towards a smarter battery management system: A critical review on battery state of health monitoring methods10.1016/j.jpowsour.2018.10.019 ↗
2. Review and recent advances in battery health monitoring and prognostics technologies for electric vehicle (EV) safety and mobility10.1016/j.jpowsour.2014.01.085 ↗
3. Prognostics methods for battery health monitoring using a Bayesian framework10.1109/TIM.2008.2005965 ↗
4. State-of-health estimation for lithium-ion batteries based on electrochemical impedance spectroscopy measurements combined with unscented Kalman filter10.1016/j.jpowsour.2024.235450 ↗
5. Early-stage lifetime prediction for lithium-ion batteries: Linear regression-ensemble learning hybrid model based on impedance spectroscopy geometry10.1016/j.jpowsour.2024.235153 ↗
6. State of health (SOH) assessment for LIBs based on characteristic electrochemical impedance10.1016/j.jpowsour.2024.234386 ↗
7. A new diagnostic indicator for lithium-ion batteries via electrochemical impedance spectroscopy: Harnessing the highest frequency peak in distribution of relaxation times10.1016/j.jpowsour.2024.234743 ↗
8. Optimized battery-management system to improve storage lifetime in renewable energy systems10.1016/j.jpowsour.2006.12.024 ↗
9. Sigma-point Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part 2: Simultaneous state and parameter estimation10.1016/j.jpowsour.2006.06.004 ↗
10. Electrochemical impedance spectrum (EIS) variation of lithium-ion batteries due to resting times in the charging processes10.3390/wevj14120321 ↗
11. Determination of the distribution of relaxation times by means of pulse evaluation for offline and online diagnosis of lithium-ion batteries10.3390/batteries7020036 ↗
12. Optimizing experiments for accurate battery circuit parameters estimation: Reduction and adjustment of frequency set used in electrochemical impedance spectroscopy
13. Advanced data-driven techniques in AI for predicting lithium-ion battery remaining useful life: a comprehensive review10.1016/j.gce.2024.09.001 ↗
14. Online state of health estimation of lithium-ion batteries based on improved ampere-count method
15. Online state-of-health estimation of a Li-ion battery using incremental voltage difference and Ampere-hour throughput as indirect health indicators
16. An open circuit voltage-based model for state-of-health estimation of lithium-ion batteries: Model development and validation10.1016/j.jpowsour.2019.227401 ↗
17. On-line optimization of battery open circuit voltage for improved state-of-charge and state-of-health estimation10.1016/j.jpowsour.2015.03.157 ↗
18. Revisiting the dual extended Kalman filter for battery state-of-charge and state-of-health estimation: A use-case life cycle analysis10.1016/j.est.2018.07.006 ↗
19. Comparative study of a structured neural network and an extended Kalman filter for state of health determination of lithium-ion batteries in hybrid electricvehicles10.1016/j.engappai.2012.09.013 ↗
20. Genetically optimized extended Kalman filter for state of health estimation based on Li-ion batteries parameters10.3390/en15093404 ↗
21. A comprehensive equivalent circuit model for lithium-ion batteries, incorporating the effects of state of health, state of charge, and temperature on model parameters10.1016/j.est.2021.103252 ↗
22. Adaptive battery management and parameter estimation through physics-based modeling and experimental verification10.1109/TTE.2016.2558843 ↗
23. Artificial intelligence-driven real-world battery diagnostics10.1016/j.egyai.2024.100419 ↗
24. Estimation of lithium-ion battery health state using enhanced variational autoencoder and bidirectional gated recurrent unit based on electrochemical impedance spectroscopy10.1016/j.jpowsour.2025.237957 ↗
25. State-of-health estimators coupled to a random forest approach for lithium-ion battery aging factor ranking10.1016/j.jpowsour.2020.229154 ↗
26. SOH estimation of lithium-ion batteries based on multi-feature deep fusion and XGBoost10.1016/j.energy.2024.132429 ↗
27. SOH and RUL prediction of lithium-ion batteries based on Gaussian process regression with indirect health indicators10.3390/en13020375 ↗
28. Accurate prediction approach of SOH for lithium-ion batteries based on LSTM method10.3390/batteries9030177 ↗
29. SOH evaluation and RUL estimation of lithium-ion batteries based on MC-CNN-TimesNet model10.1016/j.ress.2025.111125 ↗
30. A simple feature extraction method for estimating the whole life cycle state of health of lithium-ion batteries using transformer-based neural network10.1016/j.jpowsour.2023.233139 ↗
31. Spatio-temporal attention-based hidden physics-informed neural network for remaining useful life prediction10.1016/j.aei.2024.102958 ↗
32. Remaining useful life prediction of lithium-ion batteries based on informer model with multi-feature extraction and Bayesian optimization
33. A generalizable physics-informed neural network for lithium-ion battery SOH estimation utilizing partial charging segments
34. A novel method for state of health estimation of lithium-ion batteries based on improved LSTM and health indicators extraction10.1016/j.energy.2022.123973 ↗
35. State of health estimation of lithium-ion batteries based on multi-health features extraction and improved long short-term memory neural network10.1016/j.energy.2023.128956 ↗
36. A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer model10.1016/j.energy.2022.125501 ↗
37. An encoder-decoder model based on deep learning for state of health estimation of lithium-ion battery10.1016/j.est.2021.103804 ↗
38. Feature-enhanced encoder-decoder model for accurate lithium-ion battery state of health estimation10.1016/j.est.2025.116430 ↗
39. Battery state of health estimation under dynamic operations with physics-driven deep learning10.1016/j.apenergy.2024.123632 ↗
40. Deep learning to estimate lithium-ion battery state of health without additional degradation experiments10.1038/s41467-023-38458-w ↗
41. State of health prognostics for series battery packs: A universal deep learning method10.1016/j.energy.2021.121857 ↗
42. State-of-charge estimation of sodium-ion batteries: A fusion deep learning approach10.1016/j.est.2024.111527 ↗
43. Uncertainty-aware deep learning for reliable health monitoring in safety-critical energy systems10.1016/j.energy.2024.130419 ↗
44. Open access dataset, code library and benchmarking deep learning approaches for state-of-health estimation of lithium-ion batteries10.1016/j.est.2023.109884 ↗
45. Intelligent state of health estimation for lithium-ion battery pack based on big data analysis10.1016/j.est.2020.101836 ↗
46. Flexible battery state of health and state of charge estimation using partial charging data and deep learning10.1016/j.ensm.2022.06.053 ↗
47. Convolutional autoencoder-based SOH estimation of lithium-ion batteries using electrochemical impedance spectroscopy10.1016/j.est.2023.106680 ↗
48. Lithium-ion battery state of health estimation based on multi-source health indicators extraction and sparse Bayesian learning
49. Battery state-of-health estimation based on a metabolic extreme learning machine combining degradation state model and error compensation10.1016/j.energy.2020.119078 ↗
50. A comprehensive study on state-of-charge and state-of-health estimation of sodium-ion batteries10.1016/j.est.2023.108314 ↗
51. Degradation mechanism of sodium-ion batteries and state of health estimation via electrochemical impedance spectroscopy under temperature disturbances
52. Weakly solvating ester electrolyte for high voltage sodium-ion batteries10.1016/j.nanoen.2024.109969 ↗
53. End-to-end deep learning powered battery state of health estimation considering multi-neighboring incomplete charging data10.1016/j.energy.2024.130495 ↗
54. State of charge estimation at different temperatures based on dynamic thermal model for lithium-ion batteries10.1016/j.est.2022.104011 ↗
55. Graphical analysis of electrochemical impedance spectroscopy data in Bode and Nyquist representations10.1016/j.jpowsour.2016.01.073 ↗
56. Yoojin Choi, Mostafa El-Khamy, Jungwon Lee, Variable rate deep image compression with a conditional autoencoder, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 3146–3154.10.1109/ICCV.2019.00324 ↗
57. Random forests
58. Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach10.1016/j.engstruct.2020.110927 ↗
59. A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP)
60. Yang · 2021
61. Equivalent circuit modeling of sodium-ion batteries10.1016/j.est.2021.103233 ↗
62. Emerging chemistry for wide-temperature sodium-ion batteries10.1021/acs.chemrev.3c00728 ↗
63. State-of-health estimation for the lithium-ion battery based on support vector regression10.1016/j.apenergy.2017.08.096 ↗
64. State of health estimation for lithium-ion batteries based on two-stage features extraction and gradient boosting decision tree10.1016/j.energy.2023.129460 ↗
65. State of health estimation of the LiFePO4 power battery based on the forgetting factor recursive Total Least Squares and the temperature correction10.1016/j.energy.2023.128437 ↗
66. Diagnosis of a battery energy storage system based on principal component analysis10.1016/j.renene.2019.08.064 ↗
67. Multi-fault diagnosis for series-connected lithium-ion battery pack with reconstruction-based contribution based on parallel PCA-KPCA10.1016/j.apenergy.2022.119678 ↗
68. Sparse principal component analysis10.1198/106186006X113430 ↗
69. State of health estimation of lithium-ion batteries using Autoencoders and Ensemble Learning10.1016/j.est.2022.105708 ↗