journal article·2026-08Open access

Critical review on integrated convolutional neural network modeling for whole-life-cycle state of health and remaining useful life prediction of lithium-ion batteries adaptive to sharp varying current conditions

Shunli Wang, Yang Wang, Beining Hu, Etse Dablu Bobobee, Koukoyi Ebenezer, Carlos Fernandez

Abstract

This review systematically examines neural network (NN)-based methodologies for predicting the State of Health (SOH) and Remaining Useful Life (RUL) of lithium-ion batteries. It provides a structured analysis and comparison of predominant NN architectures, including Backpropagation Neural Networks (BPNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) with variants such as LSTM and GRU, and Deep Neural Networks (DNNs), focusing on their modeling capabilities, application scenarios, and limitations in capturing nonlinear battery degradation. The discussion highlights that CNNs enable automatic spatial feature extraction from operational data, while RNN-based models are effective in learning temporal dependencies from charge–discharge sequences, and that data-driven approaches exhibit clear advantages over traditional model-based methods under complex and sharply varying operating conditions, despite challenges related to data dependency, computational burden, and generalization capability. Based on the comparative analysis, particular attention is given to CNN-LSTM hybrid models, which integrate convolutional feature abstraction with long-term temporal sequence learning and are well suited to the spatiotemporal characteristics of battery degradation data. Reported studies show that CNN-LSTM-based methods achieve high prediction accuracy and robustness across different datasets and operating scenarios, with representative results including a mean absolute error of 0.99%, a root mean square error of 1.33%, and further reductions to MAE ≤0.924% and RMSE ≤1.170% when combined with attention mechanisms or transfer learning techniques. The identified trends point toward hybrid modeling strategies that combine deep learning architectures with transferable learning capabilities and multi-state estimation frameworks for advanced battery health prognostics.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Advanced Battery Technologies Research · Machine Fault Diagnosis Techniques · Reliability and Maintenance Optimization

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

References (100+)

Show source-provided references
1. Percolative metal Microweb‐Based flexible lithium‐ion battery with fast charging and high energy density10.1002/adma.202407719 ↗
2. Insight into iodine-doped carbon xerogel electrodes on the capacitance and long-term stability of quasi-solid-state supercapacitors10.1016/j.apsusc.2025.164441 ↗
3. Surface engineering of lithium-rich manganese-based cathodes: unlocking high capacity and long cycle life in lithium-ion batteries10.1016/j.cej.2025.168905 ↗
4. Research progress on state-of-health estimating method for lithium-ion batteries
5. Evaluation of cracking damage in electrode materials of a lmo/al-lix lithium-ion battery through analysis of acoustic emission signals10.1016/j.jmrt.2023.04.121 ↗
6. Progress on the fault diagnosis approach for lithium-ion battery systems: advances, challenges, and prospects10.23919/PCMP.2023.000213 ↗
7. Accurate model parameter identification to boost precise aging prediction of lithium‐ion batteries: a review
8. Simultaneous prediction of SOH and RUL for Lithium-ion batteries using transferable knowledge sharing network10.1109/TPEL.2025.3565730 ↗
9. Physics-informed neural network for co-estimation of state of health, remaining useful life, and short-term degradation path in Lithium-ion batteries10.1016/j.apenergy.2025.126427 ↗
10. State of health estimation and remaining useful life prediction of lithium-ion batteries based on optimized echo state network with early data feature
11. Intelligent predictive battery management system with optimized bayesian LSTM network for lithium-ion batteries10.1142/S0218001425590116 ↗
12. Online Co-Estimation of the State-of-Health, state-of-charge and remaining-useful-life of lithium-ion batteries using a discrete capacity loss model10.1109/TTE.2024.3521316 ↗
13. Remaining useful life prediction for lithium-ion battery based on hybrid machine learning with wiener process
14. A lithium-ion battery health state assessment and remaining useful life prediction method based on multi slope features10.1016/j.est.2025.117324 ↗
15. Joint prediction of SOH and RUL of lithium-ion batteries using single-cycle charging data10.1016/j.energy.2025.138351 ↗
16. Battery-Insight-PSO: a machine learning model for accurate prediction of state of health and remaining useful life in lithium-ion batteries
17. A novel hybrid neural network-based SOH and RUL estimation method for lithium-ion batteries10.1016/j.est.2024.113074 ↗
18. A novel sequential estimation framework for battery state of health and remaining useful life based on sparse and limited data10.1016/j.est.2024.113086 ↗
19. Critical summary and perspectives on state-of-health of lithium-ion battery10.1016/j.rser.2023.114077 ↗
20. IVCLNet: a hybrid deep learning framework integrating signal decomposition and attention-enhanced CNN-LSTM for lithium-ion battery SOH prediction and RUL estimation10.3390/en18215677 ↗
21. Health feature parameters-based TCN-GRU-AM for lithium-ion battery SOH and RUL estimation10.1149/1945-7111/ae0984 ↗
22. Hybrid neural networks for lithium-ion batteries state of health estimation and remaining useful life prediction10.1149/1945-7111/ae0feb ↗
23. A bimodal large-small model collaborative network for joint prediction of state of health and remaining useful life of lithium-ion batteries
24. Research advances on thermal runaway mechanism of lithium-ion batteries and safety improvement
25. Deep mining on the formation cycle features for concurrent SOH estimation and RUL prognostication in lithium-ion batteries10.3390/en18082105 ↗
26. Review on health state estimation and life prediction of lithium-ion batteries
27. SOH and RUL estimation for lithium-ion batteries based on partial charging curve features10.3390/en18133248 ↗
28. Intelligent energy storage management trade-off system applied to deep learning predictions10.1016/j.est.2023.106784 ↗
29. A review of expert hybrid and co-estimation techniques for SOH and RUL estimation in battery management system with electric vehicle application10.1016/j.eswa.2023.123123 ↗
30. A review of lithium-ion battery state of health and remaining useful life estimation methods based on bibliometric analysis
31. Early prediction of lithium-ion battery life using a hybrid deep neural network and ensemble learning approach
32. State of health estimation for lithium-ion battery based on multi-stage feature optimization and improved grey wolf optimizer for back propagation neural network10.1007/s11581-025-06947-1 ↗
33. Inherently interpretable physics-informed neural network for battery modeling and prognosis10.1109/TNNLS.2023.3329368 ↗
34. State estimation models of lithium-ion batteries for battery management system: status, challenges, and future trends10.3390/batteries9020131 ↗
35. Applications of artificial neural network based battery management systems: a literature review10.1016/j.rser.2023.114262 ↗
36. Prediction of state-of-health and remaining-useful-life of battery based on hybrid neural network model
37. Robust state of health estimation and remaining useful life prediction for lithium-ion battery with synchronous framework using data-driven integrated model10.1016/j.cie.2025.111575 ↗
38. Estimation of lithium-ion battery electrochemical properties from equivalent circuit model parameters using machine learning10.1016/j.est.2024.113257 ↗
39. Multi-time scale identification of key kinetic processes for lithium-ion batteries considering variable characteristic frequency10.1016/j.jechem.2023.02.022 ↗
40. Health prediction of lithium-ion batteries by combining with empirical mode decomposition and PF-GPR algorithm
41. An AI-Driven particle filter technology for battery system state estimation and RUL prediction10.3390/batteries10120437 ↗
42. Interpretable deep learning with uncertainty quantification for lithium-ion battery SOH estimation10.1016/j.energy.2025.138027 ↗
43. Research status and prospects of state of health estimation methods for lithium-ion batteries
44. Investigation of lithium-ion battery nonlinear degradation by experiments and model-based simulation
45. Lithium-ion battery health state and remaining useful life prediction based on hybrid model MFE-GRU-TCA10.1016/j.est.2024.112442 ↗
46. Application of state of health estimation and remaining useful life prediction for lithium-ion batteries based on AT-CNN-BiLSTM
47. Uncertainty characterization of a CNN method for lithium-ion batteries state of charge estimation using EIS data10.1016/j.measurement.2023.113341 ↗
48. Study of lithium-ion battery internal short circuit diagnosis based on multi-model fusion network model
49. An overview of remaining useful life prediction of battery using deep learning and ensemble learning algorithms on data‐dependent models
50. A visibility graph-based multi-step forecasting method for state-of-health and remaining useful life estimation of lithium-ion battery10.1007/s42835-025-02293-4 ↗
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. Multimodal deep learning with time-frequency health features for battery SOH and RUL prediction10.1016/j.jechem.2025.09.018 ↗
53. Applying neural network to health estimation and lifetime prediction of lithium-ion batteries10.1109/TTE.2024.3457621 ↗
54. Advancements in artificial neural networks for health management of energy storage lithium-ion batteries: a comprehensive review10.1016/j.est.2023.109069 ↗
55. Data driven health and life prognosis management of supercapacitor and lithium-ion battery storage systems: developments, implementation aspects, limitations, and future directions
56. Battery health monitoring and remaining useful life prediction techniques: a review of technologies10.3390/batteries11010031 ↗
57. Artificial intelligence for estimating state of Health and remaining Useful Life of EV batteries: a systematic review10.1016/j.icte.2025.05.013 ↗
58. Advanced data-driven techniques in AI for predicting lithium-ion battery remaining useful life: a comprehensive review10.1016/j.gce.2024.09.001 ↗
59. State-of-the-art artificial intelligence approaches for anomaly detection and remaining useful life prediction: a review10.7717/peerj-cs.3056 ↗
60. Accurate prediction of remaining useful life for lithium-ion battery using deep neural networks with memory features10.3389/fenrg.2023.1059701 ↗
61. A vision transformer-based deep neural network for state of health estimation of lithium-ion batteries10.1016/j.ijepes.2023.109233 ↗
62. Sequential application of denoising autoencoder and long-short recurrent convolutional network for noise-robust remaining-useful-life prediction framework of lithium-ion batteries10.1016/j.cie.2023.109231 ↗
63. Data-driven methods for predicting the state of health, state of charge, and remaining useful life of li-ion batteries: a comprehensive review10.1007/s12541-023-00832-5 ↗
64. Remaining useful life prediction of lithium-ion batteries: a decomposition-based multi-model prediction approach10.1063/5.0268400 ↗
65. Remaining useful life prediction of lithium-ion batteries using monotone decomposition10.1080/00401706.2025.2552297 ↗
66. Hybrid data-driven method with TADBO-SVMD for lithium-ion battery remaining useful life prediction10.1088/1361-6501/addc00 ↗
67. Forecasting cryptocurrency prices using LSTM, GRU, and bi-directional LSTM: a deep learning approach10.3390/fractalfract7020203 ↗
68. Predictive modeling for electric vehicle battery state of health: a comprehensive literature review10.3390/en18020337 ↗
69. Remaining useful life prediction of lithium-ion batteries based on an incremental internal resistance aging model and a gated recurrent unit neural network10.1016/j.energy.2025.137527 ↗
70. A CNN-GRU approach to the accurate prediction of batteries' remaining useful life from charging profiles10.3390/computers12110219 ↗
71. A hybrid neural architecture for enhanced lithium-ion battery SOH estimation and RUL prediction
72. Remaining useful life prediction of lithium-ion battery using ICC-CNN-LSTM methodology10.3390/en16207081 ↗
73. A lithium-ion battery SOH estimation method based on temporal pattern attention mechanism and CNN-LSTM model10.1016/j.compeleceng.2024.109930 ↗
74. Feature-based lithium-ion battery state of health estimation with artificial neural networks10.1016/j.est.2022.104584 ↗
75. Advanced deep learning framework for predicting the remaining useful life of Nissan leaf generation 01 lithium-ion battery modules10.3390/computation13060147 ↗
76. Battery health state prediction based on lightweight neural networks: a review10.1007/s11581-024-05857-y ↗
77. Enhanced remaining useful life prediction of lithium-ion batteries using genetic algorithm-optimized backpropagation neural networks10.1016/j.jpowsour.2025.237619 ↗
78. Remaining useful life estimation of lithium-ion batteries using alpha evolutionary algorithm-optimized deep learning10.3390/batteries11100385 ↗
79. Predicting the operational remaining life of lithium-ion battery with dynamic attention transformer10.1016/j.fub.2025.100075 ↗
80. A comprehensive review on research methods for lithium-ion battery of state of health estimation and end of life prediction: methods, properties, and prospects10.23919/PCMP.2024.000211 ↗
81. Joint prediction of SOH and RUL for lithium batteries considering capacity self recovery and model drift10.1109/JIOT.2025.3550270 ↗
82. A hybrid squeeze excitation gate recurrent unit-autoregressive integrated moving average model for long-term state of health estimation of lithium-ion batteries with adaptive enhancement ability10.1016/j.est.2025.117600 ↗
83. Accurate and efficient SOH estimation for retired batteries10.3390/en16031240 ↗
84. State of health (SOH) assessment for LIBs based on characteristic electrochemical impedance10.1016/j.jpowsour.2024.234386 ↗
85. A novel battery health indicator and PSO-LSSVR for LiFePO4 battery SOH estimation during constant current charging10.1016/j.energy.2023.128782 ↗
86. Prediction of battery SOH and RUL based on cooperative characteristics in voltage-temperature-time dimensions10.1149/1945-7111/acde10 ↗
87. A novel state of health estimation model for lithium-ion batteries incorporating signal processing and optimized machine learning methods10.1007/s11708-024-0969-x ↗
88. Battery pack capacity estimation based on improved cooperative co-evolutionary strategy and LightGBM hybrid models using indirect health features
89. Data-driven lithium-ion batteries capacity estimation based on deep transfer learning using partial segment of charging/discharging data10.1016/j.energy.2023.127033 ↗
90. A data-driven approach for estimating state-of-health of lithium-ion batteries considering internal resistance10.1016/j.energy.2023.127675 ↗
91. Estimating SoC, SoH, or RuL of rechargeable batteries via IoT: a review10.1109/JIOT.2023.3342367 ↗
92. A comprehensive review on lithium-ion battery lifetime prediction and aging mechanism analysis10.3390/batteries11040127 ↗
93. A sequence to sequence prediction model for remaining useful life of lithium-ion batteries with Bayesian optimisation process visualization10.1016/j.est.2024.111346 ↗
94. Review on modeling and soc/soh estimation of batteries for automotive applications10.3390/batteries10010034 ↗
95. Cycle life studies of lithium-ion power batteries for electric vehicles: a review10.1016/j.est.2024.112231 ↗
96. Method of predicting SOH and RUL of lithium-ion battery based on the combination of LSTM and GPR10.3390/su141911865 ↗
97. A higher prediction accuracy–based alpha–beta filter algorithm using the feedforward artificial neural network10.1049/cit2.12148 ↗
98. The SOH estimation and RUL prediction of lithium battery based on BiLSTM
99. GHOSH v1. 0.0: a novel Gauss-Hermite High-Order Sampling Hybrid filter for computationally efficient data assimilation in geosciences
100. A steps-ahead tool wear prediction method based on support vector regression and particle filtering10.1016/j.measurement.2023.113237 ↗