journal article·2026-07Open access

Critical review of model-based and data-driven methods for accurate battery state of charge estimation in new energy vehicles

Shunli Wang, Siyu Jin, Zhihui Cao, Junjie Xu, Wenqin Wang, Carlos Fernandez

Abstract

In recent years, the rapid growth of the new energy vehicle industry has heightened the importance of lithium-ion battery performance. The State of Charge (SOC), a core parameter reflecting a battery's operational status, is critical for evaluating driving range, safety, and service life. However, accurate and practical SOC estimation remains challenging. This paper systematically reviews mainstream SOC estimation methods, categorizing them into four groups: direct measurement, data-driven, model-based, and fusion methods. A comparative analysis is conducted across six key dimensions: estimation error, algorithm complexity, robustness, response time, adaptability to working conditions, and number of signals required. Findings indicate that fusion methods excel in estimation accuracy and condition adaptability. While model-based and fusion approaches show comparable algorithm complexity—both superior to data-driven methods—the former demonstrates stronger robustness and requires fewer measured signals. Data-driven and fusion methods generally offer faster response times. By outlining the strengths and limitations of existing techniques, this study supports the selection of safe and reliable SOC estimation strategies, thereby helping to mitigate potential hazards from battery overcharging or over-discharging. It also offers a systematic reference for advancing battery management technology in engineering applications.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Advanced Battery Technologies Research · Electric and Hybrid Vehicle Technologies · Electric Vehicles and Infrastructure

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

References (100+)

Show source-provided references
1. Battery multi-time scale fractional-order modeling method for state of charge estimation adaptive to full parameters updating10.1016/j.est.2024.111283 ↗
2. A novel dual gated recurrent unit neural network based on error compensation integrated with Kalman filter for the state of charge estimation of parallel battery modules10.1016/j.jpowsour.2025.236508 ↗
3. State-of-charge estimation of lithium-ion battery based on improved equivalent circuit model considering hysteresis combined with adaptive iterative unscented Kalman filtering10.1016/j.est.2024.114105 ↗
4. An improved model combining machine learning and kalman filtering architecture for state of charge estimation of lithium-ion batteries
5. Beta-Gaussian iterated posterior linearization filter for lithium-ion battery state-of-charge estimation10.1016/j.est.2025.116097 ↗
6. PDFusion: a domain-adaptive incremental learning model based on Physical-Data Fusion for lithium-ion battery state estimation10.1016/j.engappai.2025.110913 ↗
7. State of charge estimation method for lithium-ion batteries based on adaptive central difference particle filter with weight reconstruction10.1016/j.est.2024.114817 ↗
8. Differential current in constant-voltage charging mode: a novel tool for state-of-health and state-of-charge estimation of lithium-ion batteries10.1016/j.energy.2023.129826 ↗
9. State of charge estimation for lithium-ion battery based on dynamic data reconciliation combined with unscented Kalman filtering and long short-term memory network10.1016/j.est.2025.116756 ↗
10. A hybrid data driven framework considering feature extraction for battery state of health estimation and remaining useful life prediction
11. Edge-cloud collaborative method for state of charge estimation of lithium-ion batteries by combining Kalman filter and deep learning10.1016/j.energy.2025.137234 ↗
12. Enhanced state of charge estimation in lithium-ion batteries based on time-frequency-net with time-domain and frequency-domain features10.1016/j.energy.2025.134722 ↗
13. An innovative square root - untraced Kalman filtering strategy with full-parameter online identification for state of power evaluation of lithium-ion batteries10.1016/j.est.2024.114555 ↗
14. Robust SOC estimation for lithium-ion batteries: combination of GRU and FOMIAUKF approach with an improved state transition matrix10.1016/j.energy.2025.136429 ↗
15. Fractional variable-order observer-based method for state-of-charge estimation of lithium-ion batteries10.1016/j.apenergy.2025.125775 ↗
16. Estimation of lithium-ion battery SOC based on GWO-optimized extreme learning machine
17. State of charge estimation for lithium batteries based on model driven fusion with data driven10.1016/j.est.2025.116955 ↗
18. A hybrid model with Gaussian process-based covariance matrix adaptation evolution strategy for state of charge estimation of lithium-ion batteries10.1016/j.est.2025.115948 ↗
19. Target decomposition-led light-weighted offline training strategy-aided data-driven state-of-charge online estimation during constant current charging conditions over battery entire lifespan10.1016/j.energy.2024.132658 ↗
20. SOC estimation of Li-ion batteries based on IHHO-KELM model
21. A framework of joint SOC and SOH estimation for lithium-ion batteries: using BiLSTM as a battery model10.1016/j.jpowsour.2025.236342 ↗
22. SOC estimation of Li-ion battery based on gaussian mixture regression
23. SOC estimation of Li-ion batteries based on Gaussian process regression and UKF
24. Improved particle swarm optimization–long short-term memory model with temperature compensation ability for the accurate state of charge estimation of lithium-ion batteries10.1016/j.est.2024.110871 ↗
25. Enhanced transformer encoder long short-term memory hybrid neural network for multiple temperature state of charge estimation of lithium-ion batteries10.1016/j.jpowsour.2025.236411 ↗
26. Review of battery state estimation methods for electric vehicles - part I: SOC estimation10.1016/j.est.2024.111435 ↗
27. An innovative multitask learning - long short-term memory neural network for the online anti-aging state of charge estimation of lithium-ion batteries adaptive to varying temperature and current conditions10.1016/j.energy.2024.134272 ↗
28. An optimized multi-segment long short-term memory network strategy for power lithium-ion battery state of charge estimation adaptive wide temperatures10.1016/j.energy.2024.132048 ↗
29. An improved log-cosine variation slime mold - simplified gated recurrent neural network for the high-precision state of charge estimation of lithium-ion batteries10.1016/j.est.2024.112412 ↗
30. An improved feedforward-long short-term memory modeling method for the whole-life-cycle state of charge prediction of lithium-ion batteries considering current-voltage-temperature variation10.1016/j.energy.2022.124224 ↗
31. A hybrid deep learning framework integrating bidirectional sliding windows, TCN, and external attention for accurate state-of-charge estimation in lithium-ion batteries10.1016/j.jpowsour.2024.235312 ↗
32. A chaotic firefly - particle filtering method of dynamic migration modeling for the state-of-charge and state-of-health co-estimation of a lithium-ion battery performance10.1016/j.energy.2022.126164 ↗
33. Physics-informed mamba neural network with potential knowledge for state-of-charge estimation of lithium-ion batteries10.1016/j.est.2025.116546 ↗
34. State of charge estimation with representative cells-based hybrid model for lithium-ion battery pack10.1016/j.jpowsour.2025.236911 ↗
35. Trustworthy battery state of charge estimation enabled by multi-task deep learning10.1016/j.energy.2025.136264 ↗
36. State of charge estimation for lithium-ion batteries based on physics-embedded neural network10.1016/j.jpowsour.2025.236785 ↗
37. Lithium-ion batteries state of charge accurate estimation based on fusion deep learning models considering the noises and mechanical properties10.1016/j.est.2025.116899 ↗
38. Data-physics-driven co-estimation of capacity and state of charge for lithium-ion batteries in electric vehicle10.1016/j.est.2024.115188 ↗
39. Dynamic conditions-oriented model-data fused framework enabling state of charge and capacity accurate co-estimation of lithium-ion battery10.1016/j.energy.2025.134668 ↗
40. Improving lightweight state-of-charge estimation of lithium-ion battery using residual network and gated recurrent neural network10.1016/j.est.2025.115934 ↗
41. Mechanical stress-based state-of-charge estimation for lithium-ion batteries via deep learning techniques10.1016/j.energy.2025.136216 ↗
42. State-of-Charge estimation and health prognosis for lithium-ion batteries based on temperature-compensated Bi-LSTM network and integrated attention mechanism10.1109/TIE.2023.3292865 ↗
43. Joint estimation of State of charge and State of energy of lithium-ion batteries based on optimized bidirectional gated recurrent neural network10.1109/TTE.2023.3291501 ↗
44. A state-of-charge and state-of-health joint estimation method of lithium-ion battery based on temperature-dependent extended Kalman filter and deep learning10.1109/TIE.2024.3409912 ↗
45. Lithium-ion battery expansion mechanism and Gaussian process regression based state of charge estimation with expansion characteristics10.1016/j.energy.2024.130541 ↗
46. A fast convergence strategy based on gray wolf optimization algorithm for co-estimation of battery state of charge and capacity10.1016/j.electacta.2023.143525 ↗
47. A novel hybrid deep learning model for accurate state of charge estimation of Li-Ion batteries for electric vehicles under high and low temperature10.1016/j.energy.2024.130584 ↗
48. A novel positional encoded attention-based Long short-term memory network for state of charge estimation of lithium-ion battery10.1016/j.jpowsour.2023.233788 ↗
49. A self-attention-based CNN-Bi-LSTM model for accurate state-of-charge estimation of lithium-ion batteries10.1016/j.est.2024.111524 ↗
50. PSO-GPR model for state estimation of lithium-ion battery using ultrasonic guided waves with multi-feature fusion technique10.1016/j.est.2025.115580 ↗
51. Dual time-scale state-coupled co-estimation of state of charge, state of health and remaining useful life for lithium-ion batteries via Deep Inter and Intra-Cycle Attention Network10.1016/j.est.2023.109797 ↗
52. State of charge estimation for electric vehicles using random forest10.1016/j.geits.2024.100177 ↗
53. State of charge estimation for Li-ion battery during dynamic driving process based on dual-channel deep learning methods and conditional judgement10.1016/j.energy.2024.130948 ↗
54. State of charge estimation for lithium-ion batteries based on data augmentation with generative adversarial network10.1016/j.est.2023.110004 ↗
55. State of charge estimation for lithium-ion battery using Time Series Transformer with De-noise De-stationary Inception Network
56. Enhanced group convolutional hybrid neural network for state of charge estimation of lithium-ion batteries consider temperature uncertainty
57. A Transformer-BiLSTM-MLP model for SOC estimation of lithium-ion batteries
58. A novel M-1 structured Bidirectional Long Short Term Memory-Rauch Tung Striebel Smoothing algorithm for the joint estimation state of charge and multi-constrained sustained peak power of lithium-ion batteries10.1016/j.est.2023.107576 ↗
59. State of charge estimation of lithium-ion batteries based on ultrasonic guided waves by chirped signal excitation10.1016/j.est.2024.110897 ↗
60. C. Wu, Y. Zhao, L. Geng, H. Chen, P. Liu, and X. Zhao, "SOC estimation of lithium-ion batteries based on strong tracking adaptive cubature Kalman filter algorithm," Journal of Chang'an University (Natural Science Edition), vol. 45, no. 2, pp. 165–176, 2025, doi: 10.19721/j.cnki.1671-8879.2025.02.014.
61. A. Tang, S. Liu, H. Zou, Z. Chen, W. Hu, and Y. Li, "SOC estimation based on variational Bayesian unscented Kalman filter," Journal of Southwest University (Natural Science Edition), vol. 46, no. 12, pp. 51–59, 2024, doi: 10.13718/j.cnki.xdzk.2024.12.006.
62. J. Li et al., "State estimation for power battery based on unscented Kalman filter," Dianchi (Battery Bimonthly), vol. 54, no. 3, pp. 341–343, 2024, doi: 10.19535/j.1001-1579.2024.03.010.
63. SOC estimation of lithium-ion batteries based on DN-AUKF
64. Adaptive multistate combined estimation for lithium-ion battery at different temperatures
65. A lumped disturbance compensation scheme for unbiased state-of-charge estimation of lithium-ion batteries10.1109/TPEL.2024.3505924 ↗
66. Improved particle swarm optimization-adaptive dual extended Kalman filtering for accurate battery state of charge and state of energy joint estimation with efficient core factor feedback correction10.1016/j.energy.2025.135686 ↗
67. Joint estimation algorithm of SOC-SOP for lithium-ion battery pack in new energy vehicles
68. Fractional variable resistance-capacitance modeling and state-of-charge estimation of lithium-ion batteries
69. State-of-charge estimation of lithium-ion battery based on a temperature-dependent dual-polarization equivalent circuit model
70. L. Duan, X. Zhang, H. Zhang, H. Song, and X. Ao, "SOC estimation of lithium-ion batterys based on second-order approximation extended Kalman filter," China Mechanical Engineering, vol. 34, no. 15, pp. 1797–1804, 2023, doi: 10.3969/j.issn.1004-132X.2023.15.004.
71. Joint estimation of the state-of-energy and state-of-charge of lithium-ion batteries under a wide temperature range based on the fusion modeling and online parameter prediction10.1016/j.est.2022.105010 ↗
72. Improved volumetric noise-adaptive H-infinity filtering for accurate state of power estimation of lithium-ion batteries with multi-parameter constraint considering low-temperature influence10.1016/j.est.2025.115999 ↗
73. Improved noise bias compensation-equivalent circuit modeling strategy for battery state of charge estimation adaptive to strong electromagnetic interference10.1016/j.est.2023.108974 ↗
74. Battery asynchronous fractional-order thermoelectric coupling modeling and state of charge estimation based on frequency characteristic separation at low temperatures10.1016/j.energy.2024.132730 ↗
75. An improved particle swarm optimization-cubature Kalman particle filtering method for state-of-charge estimation of large-scale energy storage lithium-ion batteries10.1016/j.est.2024.113619 ↗
76. An improved forgetting factor recursive least square and unscented particle filtering algorithm for accurate lithium-ion battery state of charge estimation10.1016/j.est.2022.106478 ↗
77. An error covariance correction-adaptive extended Kalman filter based on piecewise forgetting factor recursive least squares method for the state-of-charge estimation of lithium-ion batteries10.1016/j.est.2023.107629 ↗
78. A novel multi-factor fuzzy membership function - adaptive extended Kalman filter algorithm for the state of charge and energy joint estimation of electric-vehicle lithium-ion batteries10.1016/j.est.2024.111222 ↗
79. A novel fuzzy adaptive cubature Kalman filtering method for the state of charge and state of energy co-estimation of lithium-ion batteries10.1016/j.electacta.2022.140241 ↗
80. A hybrid probabilistic correction model for the state of charge estimation of lithium-ion batteries considering dynamic currents and temperatures10.1016/j.energy.2023.127231 ↗
81. SR-CKF algorithm-based state-of-charge estimation of lithium-ion batteries for energy storage over a wide temperature range10.1016/j.est.2025.116849 ↗
82. A state-of-charge estimation method of the power lithium-ion battery in complex conditions based on adaptive square root extended Kalman filter10.1016/j.energy.2020.119603 ↗
83. Concurrent estimation of lithium-ion battery charge and energy states by fractional-order model and multi-innovation adaptive cubature Kalman filter
84. Robust GenUT-UKF for state of charge estimation of Li-ion battery against data and model uncertainty10.1016/j.est.2025.116360 ↗
85. State of charge estimation of Li-ion batteries based on strong tracking adaptive square root unscented Kalman filter with generalized maximum correntropy criterion10.1016/j.est.2025.115401 ↗
86. State of charge estimation of lithium - ion batteries based on fractional - order model
87. Multi-algorithm fusion SOC estimation basedon gas-liquid dynamics model
88. State of charge estimation of the lithium-ion power battery based on a multi-time-scale improved adaptive unscented kalman filter
89. A modeling and state of charge estimation approach to lithium-ion batteries based on the state-dependent autoregressive model with exogenous inputs10.1016/j.energy.2024.131626 ↗
90. Towards co-estimation of lithium-ion battery state of charge and state of temperature using a thermal-coupled extended single-particle model10.1016/j.energy.2025.136186 ↗
91. W. Song, R. Liu, X. Jin, and W. Guo, “SOC estimation for lithium-ion batteries based on weighted multi-innovation sage–husa adaptive EKF”, Energies, vol. 18, no. 16, 2025.10.3390/en18164364 ↗
92. State-of-charge estimation of lithium-ion batteries in rapid temperature-varying environments based on improved battery model and optimized adaptive cubature Kalman filter
93. X. Guo, L. Li, C. Wang, Y. Wang, and W. Li, "Adaptive fading unscented Kalman filter for lithium battery SoC estimation," Journal of Electronic Measurement and Instrumentation, vol. 38, no. 3, pp. 167–175, 2024.
94. A strong robust state-of-charge estimation method based on the gas-liquid dynamics model10.1016/j.geits.2024.100193 ↗
95. Co-estimation of maximum available capacity and state-of-charge for lithium-ion batteries in multi-operating mode with temperature and degradation state adaptivity10.1016/j.measurement.2023.114019 ↗
96. Dynamic ultrasonic response modeling and accurate state of charge estimation for lithium ion batteries under various load profiles and temperatures10.1016/j.apenergy.2023.122210 ↗
97. Co-estimation of state-of-charge and state-of-temperature for large-format lithium-ion batteries based on a novel electrothermal model10.1016/j.geits.2024.100152 ↗
98. Research on battery state of charge estimation based on variable window adaptive extended Kalman filter10.1016/j.ijoes.2023.100440 ↗
99. Multi-innovation and strong tracking based H∞ filter for state of charge estimation of lithium-ion batteries10.1016/j.est.2024.111039 ↗
100. State-of-charge estimation for lithium-ion batteries based on modified unscented Kalman filter using improved parameter identification10.1016/j.ijoes.2024.100574 ↗