journal article·2026-11Open access

Physics-informed optical convolution and mixture-of-experts learning for noninvasive lithium-ion battery state-of-health estimation

Sy Ruen Huang, Tai Yuan Zhang, Sin Yan Chen

Abstract

The accurate estimation of battery state of health (SOH) is essential for the reliable operation and management of battery energy storage systems. In practice, SOH estimation is challenging owing to heterogeneous battery populations, nonstationary degradation behavior, and the limited interpretability of many data-driven models. To address this issue, a physics-informed SOH estimation framework is proposed herein. This framework integrates frequency-modulated decomposition, multiscale optical convolution based on Fourier-optical principles, and a soft-gated mixture-of-experts (MoEs) architecture. Post-charge relaxation voltage signals are decomposed into intrinsic oscillatory components and enhanced in the frequency domain to extract degradation-sensitive features across multiple time scales. A dual-branch network jointly models temporal degradation dynamics and operating context information, whereas the soft-gated MoEs enables adaptive expert specialization across different aging stages and battery types. Experimental results demonstrate that the framework achieves robust, stable SOH prediction across the full SOH range, including advanced aging conditions. Interpretability is embedded directly into the model architecture via physically meaningful feature processing and expert-specific responses, providing insights consistent with underlying electrochemical degradation mechanisms. Thus, the proposed framework is well-suited for practical battery health monitoring and condition-aware energy management applications.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Machine Fault Diagnosis Techniques · Silicon Carbide Semiconductor Technologies

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

References (27)

Show source-provided references
1. Capacity fade of Sony 18650 cells cycled at elevated temperatures10.1016/S0378-7753(02)00474-3 ↗
2. Critical review of state of health estimation methods of Li-ion batteries for real applications10.1016/j.rser.2015.11.042 ↗
3. Review of models for predicting the cycling performance of lithium-ion batteries10.1016/j.jpowsour.2005.05.070 ↗
4. A comparative study of equivalent circuit models for Li-ion batteries10.1016/j.jpowsour.2011.10.013 ↗
5. Voltage relaxation-based state-of-health estimation of lithium-ion batteries using convolutional neural networks and transfer learning10.1016/j.est.2023.108579 ↗
6. Synthesize battery degradation modes via a diagnostic and prognostic model10.1016/j.jpowsour.2012.07.016 ↗
7. Online state-of-health estimation for lithium-ion batteries using constant-voltage charging current analysis10.1016/j.apenergy.2018.01.010 ↗
8. Online state-of-health estimation for Li-ion battery using partial charging segment based on support vector machine10.1109/TVT.2019.2927120 ↗
9. Data-driven health estimation of lithium-ion batteries: a review10.1016/j.rser.2019.109254 ↗
10. State of health trajectory prediction based on multi-output Gaussian process regression for lithium-ion battery10.3390/batteries8100134 ↗
11. Gaussian process regression for forecasting battery state of health10.1016/j.jpowsour.2017.05.004 ↗
12. Remaining useful life estimation in prognostics using deep convolution neural networks10.1016/j.ress.2017.11.021 ↗
13. A multi-scale learning approach for remaining useful life prediction of lithium-ion batteries based on variational mode decomposition and Monte Carlo sampling10.1016/j.energy.2023.129086 ↗
14. Lithium-ion battery remaining useful life prediction based on interpretable deep learning and network parameter optimization10.1016/j.apenergy.2024.124713 ↗
15. Frequency-based parameterization of semi-empirical models for state-of-health estimation in lithium-ion batteries10.1149/1945-7111/ae135d ↗
16. Adaptive mixtures of local experts10.1162/neco.1991.3.1.79 ↗
17. AttMoE: attention with mixture of experts for remaining useful life prediction of lithium-ion batteries10.1016/j.est.2024.110780 ↗
18. Bias/variance analyses of mixtures-of-experts architectures10.1162/neco.1997.9.2.369 ↗
19. Holography in artificial neural networks10.1038/343325a0 ↗
20. Critical review of state of health estimation methods of Li-ion batteries for real applications10.1016/j.rser.2015.11.042 ↗
21. State of health estimation of lithium-ion batteries based on feature optimization and data-driven models
22. Flexible method for estimating the state of health of lithium-ion batteries using partial charging segments10.1016/j.energy.2024.131009 ↗
23. All-optical machine learning using diffractive deep neural networks10.1126/science.aat8084 ↗
24. Neuromorphic photonic networks using silicon photonic weight banks10.1038/s41598-017-07754-z ↗
25. Feature mode decomposition: new decomposition theory for rotating machinery fault diagnosis10.1109/TIE.2022.3156156 ↗
26. Differential evolution algorithm with strategy adaptation for global numerical optimization10.1109/TEVC.2008.927706 ↗
27. Shazeer · 2017