A method for predicting battery capacity and an electronic device

By establishing a battery capacity prediction model and utilizing process and mechanism characteristic data screening and multi-model fusion, the problem of inaccurate battery capacity prediction in lithium battery production was solved, achieving accurate battery capacity prediction and improved stability.

CN116047309BActive Publication Date: 2026-07-03LENOVO (BEIJING) LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
LENOVO (BEIJING) LTD
Filing Date
2023-02-20
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing technologies make it difficult to accurately predict battery capacity during the lithium battery production process, which affects the battery's energy density, durability, and safety.

Method used

By establishing a battery capacity prediction model, time alignment and preprocessing are performed using process characteristic data and mechanism characteristic data to filter out effective data. By combining multiple prediction strategies and models, the target prediction strategy is determined, and process characteristic data is adjusted to improve prediction accuracy.

Benefits of technology

It improves the accuracy and robustness of battery capacity prediction, and can accurately distinguish battery grades under different production conditions, thereby enhancing battery stability and production control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116047309B_ABST
    Figure CN116047309B_ABST
Patent Text Reader

Abstract

The application provides a battery capacity prediction method, comprising: a first model obtaining process characteristic data of a battery to be predicted, the process characteristic data comprising at least process point data; determining a target prediction strategy based on a fitting result of historical process characteristic data and a candidate prediction strategy, the candidate prediction strategy comprising at least the target prediction strategy, and different candidate prediction strategies being obtained by training different amounts of historical process characteristic data; and determining the battery capacity of the battery to be predicted based on the process characteristic data and the target prediction strategy. Meanwhile, the application also provides an electronic device.
Need to check novelty before this filing date? Find Prior Art