电池热失控预测方法、装置、车辆及存储介质
The battery thermal runaway prediction method based on comprehensive scoring and a pre-set forest model solves the problem of insufficient accuracy in existing battery thermal runaway prediction models, and achieves efficient monitoring and accurate prediction of battery overheating risk.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DEEPAL AUTOMOBILE NANJING RESEARCH INSTITUTE CO LTD
- Filing Date
- 2023-06-28
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for predicting battery thermal runaway lack nonlinear fitting of internal battery properties and feature construction of external environmental factors, resulting in insufficient accuracy of prediction models, especially in the inability to establish suitable overheating prediction models under different conditions.
By establishing a comprehensive scoring model and a pre-set forest model, and using the mechanism scoring method to screen vehicles that meet the conditions for thermal runaway prediction, a feature matrix is constructed and the average value of multiple thermal risk probabilities is calculated to generate an overheating prediction model, thereby improving prediction accuracy.
It improves the accuracy of battery thermal runaway prediction, solves the model adaptation problem under different conditions, and enhances the monitoring efficiency of battery overheating risk.
Smart Images
Figure CN117048419B_ABST