一种电池剩余寿命预测方法、系统、设备及介质
By employing dynamic sequence modeling and variational continuous learning, a variable-length time series is constructed and model parameters are optimized, which solves the problems of insufficient accuracy and real-time performance in battery life prediction and achieves efficient and stable prediction of remaining battery life.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG ELECTRIC POWER SCI RES INST ENERGY TECH CO LTD
- Filing Date
- 2025-09-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to balance accuracy and real-time performance in battery life prediction, especially when dealing with nonlinear degradation processes and streaming data scenarios. Traditional methods suffer from issues such as information truncation, high computational complexity, and large storage overhead.
We employ a method based on dynamic sequence modeling and variational continuous learning. By collecting battery monitoring data in real time, we construct a variable-length time series. We then extract aging features by combining convolutional layers and global pooling layers, and optimize model parameters using variational inference to achieve rapid convergence and real-time updates.
It improves the accuracy and real-time performance of battery remaining life prediction, reduces computational complexity, and ensures the model's adaptability and the stability of prediction results under new data scenarios.
Smart Images
Figure CN121186642B_ABST