journal article·2026-05Open access

Incorporating dynamic mode decomposition and domain adversarial training for cross-domain state of health estimation of lithium-ion batteries

Qinan Lu, Weiliang Peng, Hongyu Chen, Renzong Hu, Guangzhong Dong, Wei Min Huang, Qiying Han, Haihua Guo, Bin Yuan, Yujiang Lou

Abstract

State of Health (SOH) is a critical indicator for evaluating the degradation level of lithium-ion batteries, yet it cannot be measured directly and must be estimated from operational data. Although notable progress has been achieved in SOH estimation, most existing methods rely on extensive aging experiments to obtain labeled data for target batteries, which require substantial experimental effort and limit practical applicability. This limitation is further aggravated under cross-domain conditions and in offline application scenarios. In this work, we propose a deep-learning-based framework for cross-domain SOH estimation with minimal reliance on labeled target battery data. The framework extracts SOH-related feature sequences from constant current charging curves and employs dynamic mode decomposition to characterize degradation dynamics. Domain adversarial training is further introduced to learn domain-invariant representations using only a small portion of target domain data. The proposed method is validated on battery datasets covering multiple domains, demonstrating reliable SOH estimation performance under significant domain discrepancy. This work highlights the potential of data-driven transfer learning approaches to reduce the need for degradation experiments and to support efficient SOH estimation in both online and offline application scenarios.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Machine Fault Diagnosis Techniques · Advancements in Battery Materials

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

References (49)

Show source-provided references
1. A review of multi-state joint estimation for lithium-ion battery: research status and suggestions10.1016/j.est.2023.109071 ↗
2. Technoeconomic model of second-life batteries for utility-scale solar considering calendar and cycle aging10.1016/j.apenergy.2020.115127 ↗
3. Automotive Li-Ion batteries: current status and future perspectives10.1007/s41918-018-0022-z ↗
4. Machine learning-based state of health prediction for battery systems in real-world electric vehicles10.1016/j.est.2023.107426 ↗
5. Toward a BMS2 design framework: adaptive data-driven state-of-health estimation for second-life batteries with BIBO stability guarantees10.1109/TTE.2025.3530498 ↗
6. Life Cycle Assessment of repurposed electric vehicle batteries: an adapted method based on modelling energy flows10.1016/j.est.2018.07.008 ↗
7. Economic analysis of second use electric vehicle batteries for residential energy storage and load-levelling10.1016/j.enpol.2014.04.016 ↗
8. Review on degradation mechanism and health state estimation methods of lithium-ion batteries
9. Multiscale investigation of discharge rate dependence of capacity fade for lithium-ion battery10.1016/j.jpowsour.2022.231516 ↗
10. Realistic lifetime prediction approach for Li-ion batteries10.1016/j.apenergy.2015.10.115 ↗
11. Degradation model of high-nickel positive electrodes: effects of loss of active material and cyclable lithium on capacity fade10.1016/j.jpowsour.2022.232461 ↗
12. Machine learning for predicting battery capacity for electric vehicles10.1016/j.etran.2022.100214 ↗
13. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries10.1016/j.apenergy.2019.114296 ↗
14. A State of health estimation method for lithium-ion batteries based on improved particle filter considering capacity regeneration10.3390/en14165000 ↗
15. Artificial Neural Networks, Gradient Boosting and Support Vector Machines for electric vehicle battery state estimation: a review10.1016/j.est.2022.105384 ↗
16. State-of-health estimation for lithium-ion batteries with hierarchical feature construction and auto-configurable Gaussian process regression10.1016/j.energy.2022.125503 ↗
17. A deep learning method for online capacity estimation of lithium-ion batteries10.1016/j.est.2019.100817 ↗
18. SOH estimation of LMO/NMC-based electric vehicle lithium-ion batteries using the incremental capacity analysis technique
19. Synchronous estimation of state of health and remaining useful lifetime for lithium-ion battery using the incremental capacity and artificial neural networks10.1016/j.est.2019.100951 ↗
20. Flexible method for estimating the state of health of lithium-ion batteries using partial charging segments10.1016/j.energy.2024.131009 ↗
21. Online capacity estimation of lithium-ion batteries with deep long short-term memory networks10.1016/j.jpowsour.2020.228863 ↗
22. Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation10.1038/s41467-022-29837-w ↗
23. Battery capacity estimation using 10-second relaxation voltage and a convolutional neural network10.1016/j.apenergy.2022.120308 ↗
24. Estimation of lithium-ion battery State of health-based multi-feature analysis and convolutional neural network–long short-term memory10.3390/su17094014 ↗
25. State of health estimation of lithium-ion battery based on CNN–WNN–WLSTM10.1007/s40747-023-01300-3 ↗
26. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis10.1038/s41467-024-48779-z ↗
27. A multi-scale framework for unsupervised anomaly detection in lithium-ion battery packs10.1016/j.est.2026.120341 ↗
28. Battery cross-operation-condition lifetime prediction via interpretable feature engineering assisted adaptive machine learning10.1021/acsenergylett.3c01012 ↗
29. Wang · 2024
30. Deep learning to estimate lithium-ion battery state of health without additional degradation experiments10.1038/s41467-023-38458-w ↗
31. Deep convolutional neural network based closed-loop SOC estimation for lithium-ion batteries in hierarchical scenarios
32. Fine-tuning enables state of health estimation for lithium-ion batteries via a time series foundation model10.1016/j.energy.2024.134177 ↗
33. Efficient hybrid deep learning model for battery state of health estimation using transfer learning10.3390/en18061491 ↗
34. End-to-end capacity estimation of lithium-ion batteries with an enhanced long short-term memory network considering domain adaptation10.1016/j.jpowsour.2021.230823 ↗
35. Multisource domain adaption for health degradation monitoring of lithium-ion batteries10.1109/TTE.2021.3085430 ↗
36. Battery health prognostic with sensor-free differential temperature voltammetry reconstruction and capacity estimation based on multi-domain adaptation10.1016/j.etran.2023.100245 ↗
37. Xing · 2025
38. Yang · 2024
39. Adaptive multi-domain capacity estimation for battery energy storage system based on multi-scale random sequence feature fusion10.1016/j.energy.2025.134997 ↗
40. A cross-material lithium-ion battery state of health estimation method based on three-stage domain adaptation10.1016/j.energy.2025.139376 ↗
41. Lu
42. Cycle life testing and modeling of graphite/LiCoO2 cells under different state of charge ranges10.1016/j.jpowsour.2016.07.057 ↗
43. An ensemble model for predicting the remaining useful performance of lithium-ion batteries10.1016/j.microrel.2012.12.003 ↗
44. Howey · 2017
45. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
46. Dynamic mode decomposition of numerical and experimental data10.1017/S0022112010001217 ↗
47. On dynamic mode decomposition: theory and applications10.3934/jcd.2014.1.391 ↗
48. Wang
49. Nie