Method and device for early life prediction of large capacity battery cell based on deep learning, and equipment

By constructing a large-capacity lithium-ion battery full life cycle dataset and combining it with a deep learning model constrained by physical information, the problems of accuracy and generalization ability in early life prediction of large-capacity cells were solved, and high-precision, low-cost life end point prediction was achieved.

CN122172015APending Publication Date: 2026-06-09XIAMEN INST OF RARE EARTH MATERIALS +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIAMEN INST OF RARE EARTH MATERIALS
Filing Date
2026-02-03
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies lack high-precision, high-generalization early life prediction schemes for large-capacity lithium-ion cells, especially with insufficient model generalization ability under small sample data conditions, and lack effective methods to combine physical information.

Method used

A dataset of the entire life cycle of a large-capacity lithium-ion battery is constructed, and features such as charging capacity, temperature, incremental capacity, and capacity difference are extracted. A deep learning model with physical information constraints is adopted, and a physical consistency loss term is constructed to optimize the model by using a hybrid model of convolutional neural network and long short-term memory network, combined with the physical information constraints of battery health state degradation dynamics.

Benefits of technology

It significantly improves the early prediction accuracy and model generalization ability of the end-of-life point of large-capacity batteries, reduces testing costs and cycles, and achieves high-reliability prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122172015A_ABST
    Figure CN122172015A_ABST
Patent Text Reader

Abstract

This application provides a method, apparatus, device, and storage medium for predicting the early lifespan of large-capacity battery cells based on deep learning. It constructs a full lifespan dataset of large-capacity lithium-ion batteries under various temperatures and charge / discharge conditions. Utilizing only the first N early cycle data of the battery, four types of features are extracted: charging capacity, temperature, incremental capacity, and capacity difference, constructing a three-dimensional feature tensor. Spatiotemporal features are extracted using a hybrid deep learning model incorporating convolutional neural networks and recurrent neural networks. Physical information constraints from battery degradation dynamics are introduced into the model, establishing a physical consistency loss function that matches the predicted capacity change rate with the actual change rate. Joint optimization yields the lifespan prediction model. This method leverages degradation precursor information and physical prior knowledge from limited early cycle data, significantly improving the early prediction accuracy and model generalization ability for the lifespan termination point of large-capacity batteries, and solving the reliability problem of migrating small-capacity battery models to large-capacity scenarios.
Need to check novelty before this filing date? Find Prior Art