JERAJournal of Electronic Research and Application2208-35022208-3510Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jera.v9i6.13167ArticleHealth Status Prediction Of Lithium Batteries Based On Deep Learninghttps://artdesignp.com/journal/JERA/9/6/10.26689/jera.v9i6.13167ZhangHai-Rui,ZhaoYueling,XueYan-Bo2025962025-12-16Aiming at the shortcomings of traditional State of Health (SOH) prediction methods in nonlinear modeling and temporal dependence handling, this paper proposes a hybrid CNN-GRU model integrated with the Dung Beetle Optimization (DBO) algorithm (denoted as DBO-CNN-GRU) for lithium battery SOH prediction. Indirect health factors strongly correlated with SOH are extracted from the NASA public dataset, and their effectiveness is verified using Pearson and Spearman correlation coefficients. A CNN-GRU model is designed: the convolutional neural network (CNN) is used to capture local features, and the gated recurrent unit (GRU) is combined to model the temporal dependence of capacity degradation. Furthermore, the DBO algorithm is introduced to optimize the model’s hyperparameters, enhancing the global search capability. Experiments show that the DBO-CNN-GRU model achieves significantly better test performance on the NASA dataset than the single CNN, GRU, and LSTM models.

Zhu Z, 2023, Research on SOH Estimation and RUL Prediction Methods of Electric Vehicle Lithium-Ion Batteries Based on Deep Learning, thesis, Qingdao University of Science and Technology.

Lu H, 2019, Theoretical Study on Polymer Electrode Materials for Lithium-Ion Batteries, thesis, Beijing University of Technology.

Geng M, Fan M, Wei B, 2025, SOH Estimation of Energy Storage Batteries Based on Fragmented Data. Global Energy Interconnection, 8(1): 57–66.

Zhang C, Chen Y, Liu M, et al., 2025, A State of Health Estimation Method for Lithium-Ion Batteries using ICA-T Features and CNN-LA-BiLSTM. Energy Storage Science and Technology, 14(3): 1–17.

Yuan J, Liu D, 2025, Research on Rapid Sorting Model for Health Status of Retired Power Lithium-Ion Batteries Based on GA-BP Neural Network. Technology Innovation and Application, 15(3): 29–32.

Wang Q, Sheng Q, Liu W, 2025, Research on the Improvement and Application of State Estimation Algorithm for Lithium Iron Phosphate Batteries in Low-Temperature Environments. Journal of Physics: Conference Series, 2941(1): 12023–12029.

Patrizi G, Canzanella F, Ciani L, 2024, Towards a State of Health Definition of Lithium Batteries through Electrochemical Impedance Spectroscopy. Electronics, 13(8): 22–35.

Braun A, Behmann R, Chabrol D, 2024, Single-Cell Operando SOC and SOH Diagnosis in a 24V Lithium Iron Phosphate Battery with a Voltage-Controlled Model. Journal of Energy Storage, 2024: 10986–10997.

Runze W, Junfu L, Xinyu W, 2024, Deep Learning Model for State of Health Estimation of Lithium Batteries based on Relaxation Voltage. Journal of Energy Storage, 2024: 10189–10199.

Wu X, 2024, Joint Estimation of State of Charge and State of Health of Lithium-Ion Batteries Based on Filters, thesis, Guangxi University.

Du L, Li Z, Li Z, et al., 2025, DBO-CNN-BiLSTM-AM Short Term Photovoltaic Power Generation Prediction based on Feature Optimization. Renewable Energy Resources,43(11): 1–11.