文献类型：期刊文献

英文题名：Enhancing degradation trend prediction of lithium-ion battery capacity in complex aging scenarios: A Bayesian-optimized hybrid architecture combining local and global feature learning

作者：Yin, Changdong[1];Fei, Binyu[1];Yao, Jun[1,2];Wu, Yiwen[3];Xu, Zhou[1];Chen, Jianjun[4];Wan, Luanfei[1];Ge, Xin[1];Liu, Qiang[1];Ye, Dongdong[5]

机构：[1]Wuhu Inst Technol, Sch Elect & Automat, Wuhu 241006, Peoples R China;[2]Anhui Normal Univ, Sch Phys & Elect Informat, Wuhu 241000, Peoples R China;[3]Wuhu Inst Technol, Inst Intelligent Mfg, Wuhu 241006, Peoples R China;[4]East China Univ Sci & Technol, Sch Mech & Power Engn, Key Lab Safety Sci Pressurized Syst, Minist Educ, Shanghai 200237, Peoples R China;[5]Anhui Polytech Univ, Sch Artificial Intelligence, Wuhu 241000, Peoples R China

年份：2026

卷号：38

期号：2

外文期刊名：JOURNAL OF KING SAUD UNIVERSITY COMPUTER AND INFORMATION SCIENCES

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001701792400001)】；

基金：This work was supported by the National Natural Science Foundation of China (52205547), Key projects of Natural Science Research of Universities in Anhui Province (2023AH052384, 2023AH052380, 2023AH052399), Natural Science Key Research Project of Wuhu Institute of Technology (wzyzrzd202502, wzyzrzd202503, wzyzrzd202504), Provincial Quality Engineering Projects of Higher Education Institutions in Anhui Province (No. 2024jyxm0912), Excellent Young Talents Fund of Higher Education Institutions of Anhui Province (2024AH030006), Undergraduate Teaching Quality Improvement Program Project of Anhui Polytechnic University (2024szyzk51), Science and Technology Plan Project of Wuhu City (No. 2023yf131, No. 2025kj048), Scientific Research Start-up Fund for Introduced Talents of Wuhu Institute of Technology (wzyrc202201).

语种：英文

外文关键词：Lithium-ion battery; Capacity estimation; Degradation trend; Bayesian optimization; Transformer-CNN; Module contribution

摘要：Accurate prediction of lithium-ion battery capacity degradation under complex aging conditions is essential for reliable health monitoring in energy storage systems. Existing prediction methods exhibit limited capability in resolving the multi-scale measurement challenge for simultaneously capturing long-term degradation trends and short-term capacity fluctuations. This study develops a Bayesian-optimized Transformer-CNN hybrid architecture (BOTC) that innovatively integrates multi-head self-attention mechanisms for global trend measurement and adaptive 1D convolutional kernels for local anomaly quantification, incorporated with Gaussian process surrogate modeling for Bayesian hyperparameter optimization and dual sliding-window sampling strategy. Furthermore, systematic ablation experiments integrated with Shapley value theory establish a quantifiable contribution model for each module in the hybrid architecture. Rigorous experimental validation on datasets of two distinct chemical systems was performed to prove the validity of the method. Results demonstrate that the proposed feature fusion architecture achieves significant improvements in both accuracy and robustness compared to advanced baseline models. Contribution quantification analysis reveals complementary mechanisms among Transformer, CNN, and Bayesian optimization in long-term trend modeling, local fluctuation detection, and model robustness enhancement. The proposed framework provides a high-precision and interpretable solution for battery health management, while its modular design enables task-specific customization, offering broad engineering applicability in real-world energy storage systems.