journal article·2026-06-28Open access

Adaptive Generalization in Lithium-Ion Battery RUL Prediction via Synergistic Attention–Residual Networks

Chao Chen, Lifeng Deng, Hao Li, Jing Zhou

Batteries· Volume 12· Issue 7

Abstract

Accurate prediction of remaining useful life (RUL) for lithium-ion batteries remains a critical yet complex challenge due to highly non-linear degradation dynamics and profound data heterogeneity across varying operational profiles. While convolutional neural networks (CNNs) have shown promise in battery health management, traditional architectures struggle with gradient vanishing in deep feature spaces and lack the adaptive capacity to filter early-cycle noise under diverse degradation conditions. To improve robust RUL estimation across heterogeneous benchmark datasets, this paper proposes a deep learning framework that integrates residual connections with dual-attention mechanisms (ResCNN). Specifically, the residual structures effectively mitigate gradient degradation during the extraction of abstract degradation patterns. Concurrently, a synergistic Squeeze-and-Excitation (SE) and Multi-Head Attention module adaptively calibrates channel-wise feature importance and captures long-range temporal dependencies inherent in complex capacity fade processes. The proposed framework is evaluated under a wide spectrum of degradation conditions and distinct cathode systems (LFP and LCO) using both dataset-specific train/validation/test protocols and strict source-to-target cross-dataset transfer tests. Experimental results demonstrate that ResCNN achieves consistently lower prediction errors than baseline models across the evaluated datasets and maintains positive explanatory power on unseen target datasets without target-domain training. Ablation studies further validate the synergistic contribution of each architectural component toward capturing intrinsic battery aging phenomena.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Advanced Battery Materials and Technologies

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

Affiliations

College of Computer Science and Engineering, Sichuan University of Science and Engineering, Yibin 644005, China

Intelligent Perception and Control Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Yibin 644005, China

Funding

Sichuan Science and Technology Innovation Talent Project · Scientific Research and Innovation Team Program of Sichuan University of Technology

References (62)

Show source-provided references
1. Zhang, W., Pranav, R., Wang, R., Lee, C., Zeng, J., Cho, M., and Shim, J. (2024). Lithium-Ion Battery Life Prediction Using Deep Transfer Learning. Batteries, 10.10.3390/batteries10120434 ↗
2. Wang, Z., Shangguan, W., Peng, C., and Cai, B. (2024). Similarity based remaining useful life prediction for lithium-ion battery under small sample situation based on data augmentation. Eksploat. Niezawodność, 26.10.17531/ein/175585 ↗
3. Chen, C., Wei, J., and Li, Z. (2023). Remaining useful life prediction for lithium-ion batteries based on a hybrid deep learning model. Processes, 11.10.3390/pr11082333 ↗
4. Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder10.55981/j.mev.2024.905 ↗
5. Remaining useful life distribution prediction framework for lithium-ion battery fused prior knowledge and monitoring data10.1088/1361-6501/ace925 ↗
6. Schaeffer, J., Galuppini, G., Rhyu, J., Asinger, P.A., Droop, R., Findeisen, R., and Braatz, R.D. (2024). Cycle life prediction for lithium-ion batteries: Machine learning and more. Proceedings of the 2024 American Control Conference (ACC), IEEE.10.23919/ACC60939.2024.10644790 ↗
7. Madani, S.S., Ziebert, C., Vahdatkhah, P., and Sadrnezhaad, S.K. (2024). Recent progress of deep learning methods for health monitoring of lithium-ion batteries. Batteries, 10.10.3390/batteries10060204 ↗
8. Remaining useful life prediction of lithium-ion batteries with limited degradation history using random forest10.1109/TTE.2023.3323976 ↗
9. Optimizing battery RUL prediction of lithium-ion batteries based on Harris hawk optimization approach using random forest and LightGBM10.1109/ACCESS.2023.3304699 ↗
10. Umayal, R., Darapaneni, N., Aditya, V., and Paduri, A.R. (2023). Machine learning based remaining useful life prediction of lithium-ion batteries in electric vehicle battery management system. Proceedings of the 2023 International Conference on Communication, Security and Artificial Intelligence (ICCSAI), IEEE.10.1109/ICCSAI59793.2023.10421014 ↗
11. Remaining useful life prediction of lithium-ion battery with optimal input sequence selection and error compensation10.1016/j.neucom.2020.07.081 ↗
12. Jia, J., Liang, J., Shi, Y., Wen, J., Pang, X., and Zeng, J. (2020). SOH and RUL prediction of lithium-ion batteries based on Gaussian process regression with indirect health indicators. Energies, 13.10.3390/en13020375 ↗
13. Lithium-ion battery SOH prediction based on multi-dimensional features and multi-model feature selector10.1016/j.energy.2025.136844 ↗
14. Li, H., Chen, C., Wei, J., Chen, Z., Lei, G., and Wu, L. (2024). State of health (soh) estimation of lithium-ion batteries based on abc-bigru. Electronics, 13.10.3390/electronics13091675 ↗
15. Zhang, S., Li, Y., Zhao, D., Cui, Z., and Zhang, Q. (2023). Remaining Useful Life Prediction of a Lithium-Ion Battery Based on AE and Modified Transformer. Proceedings of the 2023 China Automation Congress (CAC), IEEE.10.1109/CAC59555.2023.10450600 ↗
16. Enhancing the Sustainability of Underground Battery Storage: A Robust SOC Estimation Model Against Thermal Variations for Green Energy Systems10.62762/JGEE.2025.689319 ↗
17. A linear-complexity deep learning framework for efficient battery State of Health estimation in resource-constrained systems10.1016/j.engappai.2026.115420 ↗
18. Improving Lithium-Ion Battery Reliability Through Neural Network Remaining Useful Life Prediction10.11591/ijai.v14.i1.pp83-91 ↗
19. Gravitational search algorithm based LSTM deep neural network for battery capacity and remaining useful life prediction with uncertainty10.1109/TIA.2024.3429452 ↗
20. Zhang, Z., Liu, P., Ge, W., and Lai, Y. (2023). Remaining useful life prediction of lithium-ion battery based on new health factor in long short-term memory network. Proceedings of the 2023 7th International Conference on Deep Learning Technologies, ACM.10.1145/3613330.3613333 ↗
21. Remaining useful life prediction of lithium-ion battery based on AConvST-LSTM-Net-TL10.1088/1402-4896/adaa35 ↗
22. Neural Representation-Based Wiener Process with Meta-Learning for Battery RUL Prediction Under Time-Varying Degradation Rate
23. Zhao, J., Zhu, Y., Zhang, B., Liu, M., Wang, J., Liu, C., and Hao, X. (2023). Review of state estimation and remaining useful life prediction methods for lithium–ion batteries. Sustainability, 15.10.3390/su15065014 ↗
24. State-of-health and remaining-useful-life estimations of lithium-ion battery based on temporal convolutional network-long short-term memory10.1016/j.est.2023.109498 ↗
25. Battery health prognosis using improved temporal convolutional network modeling10.1016/j.est.2022.104480 ↗
26. A deep attention-assisted and memory-augmented temporal convolutional network based model for rapid lithium-ion battery remaining useful life predictions with limited data10.1016/j.est.2023.106903 ↗
27. A Remaining Useful Life Prediction Method for Lithium-ion Battery Based on Temporal Transformer Network10.1016/j.procs.2022.12.383 ↗
28. Zhang, W., Jia, J., Pang, X., Wen, J., Shi, Y., and Zeng, J. (2024). An Improved Transformer Model for Remaining Useful Life Prediction of Lithium-Ion Batteries under Random Charging and Discharging. Electronics, 13.10.3390/electronics13081423 ↗
29. Predictive Battery Health Management with Transfer Learning and Online Model Correction10.1109/TVT.2021.3055811 ↗
30. State-of-Health Estimation for Lithium-Ion Batteries Using Domain Adversarial Transfer Learning10.1109/TPEL.2021.3117788 ↗
31. Tran, K., Huynh, B., Le, T., Pham, L., Nguyen, V.R., Tran Anh, D., and Trinh, H.C. (2025). HybridoNet-Adapt: A domain-adapted framework for accurate lithium-ion battery RUL prediction. PLoS ONE, 20.10.1371/journal.pone.0335066 ↗
32. A Physics-Constrained Bayesian Neural Network for Battery Remaining Useful Life Prediction10.1016/j.apm.2023.05.038 ↗
33. A framework for Li-ion battery prognosis based on hybrid Bayesian physics-informed neural networks10.1038/s41598-023-33018-0 ↗
34. Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis10.1038/s41467-024-48779-z ↗
35. Capacity fade modelling of lithium-ion battery under cyclic loading conditions10.1016/j.jpowsour.2016.08.054 ↗
36. Model based identification of aging parameters in lithium ion batteries10.1016/j.jpowsour.2013.01.041 ↗
37. A model for degradation of electrochemical devices based on linear non-equilibrium thermodynamics and its application to lithium ion batteries10.1016/j.jpowsour.2011.03.005 ↗
38. Zhuang, Z., Li, Y., and Yang, T. (2024). Remaining Useful Life Prediction of Lithium-Ion Battery Based on AUKF and CNN-BiLSTM. Proceedings of the 2024 IEEE 13th Data Driven Control and Learning Systems Conference (DDCLS), IEEE.10.1109/DDCLS61622.2024.10606840 ↗
39. Lv, K., Ma, Z., Bao, C., and Liu, G. (2024). Indirect prediction of lithium-ion battery RUL based on CEEMDAN and CNN-BiGRU. Energies, 17.10.3390/en17071704 ↗
40. Deep learning-based remaining useful life prediction of lithium-ion battery considering two-phase aging process10.1149/1945-7111/ad9cc9 ↗
41. Remaining useful life prediction of lithium-ion batteries based on health indicator and Gaussian process regression model10.1109/ACCESS.2019.2905740 ↗
42. Multi-kernel relevance vector machine with parameter optimization for cycling aging prediction of lithium-ion batteries10.1109/JESTPE.2021.3133697 ↗
43. Remaining useful life prediction of lithium-ion batteries based on deep learning and soft sensing10.3390/act10090234 ↗
44. Wu, L., Guo, W., Tang, Y., Sun, Y., and Qin, T. (2024). Remaining useful life prediction of lithium-ion batteries based on neural network and adaptive unscented kalman filter. Electronics, 13.10.3390/electronics13132619 ↗
45. Remaining useful life prediction method of lithium-ion battery Based on KPCA-IVMD-SE-DNN10.1088/1742-6596/2741/1/012073 ↗
46. Liu, J., Cheng, K., Jin, H., and Wu, Z. (2022). An image captioning algorithm based on combination attention mechanism. Electronics, 11.10.3390/electronics11091397 ↗
47. Wang, D., Xiang, S., Zhou, Y., Mu, J., Zhou, H., and Irampaye, R. (2022). Multiple-attention mechanism network for semantic segmentation. Sensors, 22.10.3390/s22124477 ↗
48. Liu, J., Yang, J., Liu, K., and Xu, L. (2022). Ocean current prediction using the weighted pure attention mechanism. J. Mar. Sci. Eng., 10.10.3390/jmse10050592 ↗
49. Zhao, L., Song, S., Wang, P., Wang, C., Wang, J., and Guo, M. (2024). A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries. Front. Comput. Sci., 18.10.1007/s11704-023-3277-4 ↗
50. Remaining useful life prediction for lithium-ion batteries with a hybrid model based on TCN-GRU-DNN and dual attention mechanism10.1109/TTE.2023.3247614 ↗
51. Remaining useful life prediction of lithium-ion batteries: A temporal and differential guided dual attention neural network10.1109/TEC.2023.3321045 ↗
52. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
53. Closed-loop optimization of fast-charging protocols for batteries with machine learning10.1038/s41586-020-1994-5 ↗
54. Zhang, H., Gui, X., Zheng, S., Lu, Z., Li, Y., and Bian, J. (2024, January 7–11). BatteryML: An Open-source Platform for Machine Learning on Battery Degradation. Proceedings of the the Twelfth International Conference on Learning Representations, Vienna, Austria.10.1038/s42256-024-00972-x ↗
55. Real-time personalized health status prediction of lithium-ion batteries using deep transfer learning10.1039/D2EE01676A ↗
56. Yuan, Y., Ma, G., and Xu, S. (2022). The Dataset for: Real-Time Personalized Health Status Prediction of Lithium-Ion Batteries Using Deep Transfer Learning. Mendeley Data, Version 2.
57. Prognostics of lithium-ion batteries based on Dempster–Shafer theory and the Bayesian Monte Carlo method10.1016/j.jpowsour.2011.08.040 ↗
58. An ensemble model for predicting the remaining useful performance of lithium-ion batteries10.1016/j.microrel.2012.12.003 ↗
59. AttMoE: Attention with mixture of experts for remaining useful life prediction of lithium-ion batteries10.1016/j.est.2024.110780 ↗
60. Prediction of Remaining Useful Life of Lithium-ion Battery Using Convolutional Neural Network-Bidirectional Long Short-Term Memory with Attention Mechanism10.1088/2631-8695/ae2064 ↗
61. PatchFormer: A novel patch-based transformer for accurate remaining useful life prediction of lithium-ion batteries10.1016/j.jpowsour.2025.236187 ↗
62. Zhao, T., Zhang, Y., Wang, M., Feng, W., Cao, S., and Wang, G. (2025). Remaining useful life prediction of lithium-ion batteries based on hybrid LSTM-Transformer model. Front. Electron., 6.10.3389/felec.2025.1654344 ↗