一种基于电化学模型与机器学习的锂离子电池多状态联合估计方法
By combining electrochemical models with machine learning methods, highly sensitive parameters are screened and parameter evolution models are constructed. LSTM and XGBoost are used for joint estimation of multiple states of lithium-ion batteries, which solves the problems of lack of a unified framework and insufficient generalization ability in the existing technology for state estimation, and achieves efficient and accurate state estimation and cross-scenario adaptation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HARBIN INST OF TECH
- Filing Date
- 2025-06-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing lithium-ion battery state estimation methods lack a unified physical and data fusion framework for multi-state joint estimation, and have weak generalization ability, making it difficult to adapt to the state estimation needs under different operating conditions and battery systems.
A hybrid approach combining electrochemical models and machine learning is adopted. Highly sensitive parameters are screened through parameter sensitivity analysis, a parameter evolution model is constructed, and SOH estimation and voltage correction are performed by combining improved LSTM and XGBoost models to achieve multi-state joint estimation.
It improves parameter identification efficiency and model stability, enhances the accuracy of state estimation and cross-scenario adaptability, and is suitable for next-generation intelligent BMS systems.
Smart Images
Figure CN120595176B_ABST