A multi-feature combination-based energy storage power station lithium battery capacity estimation method

By conducting aging tests on lithium-ion batteries and extracting current data features, and combining multiple model combinations and linear regression models, the accuracy and generalization problems of lithium-ion battery capacity estimation in energy storage power stations were solved, achieving real-time and accurate capacity estimation.

CN116908727BActive Publication Date: 2026-06-26STATE GRID FUJIAN ELECTRIC POWER CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
STATE GRID FUJIAN ELECTRIC POWER CO LTD
Filing Date
2023-07-14
Publication Date
2026-06-26

Smart Images

  • Figure CN116908727B_ABST
    Figure CN116908727B_ABST
Patent Text Reader

Abstract

The application discloses a kind of energy storage power station lithium battery capacity estimation methods based on multi-feature combination, including the aging test of N same type new lithium ion battery, constructs battery aging test data set;The feature extraction is carried out to the battery aging test data set, constructs feature data set;Build multi-model combination model and linear regression model, and the feature data set is used to train multi-model combination model;The estimation result output by multi-model combination model constitutes new feature data set, and is used to train linear regression model;The maximum available capacity estimation result of new lithium ion battery is estimated using the output result of linear regression model fusion multi-model combination model.This application only extracts features from battery constant voltage charging process, makes full use of the mapping ability between different models for input features and label values, provides effective guarantee for estimation accuracy.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Lithium ion power battery state-of-health estimation method based on machine learning

    CN110346734A

  • Battery aging state estimation method and system based on improved Gaussian process regression

    CN114609538A

  • Capacity estimation method based on voltage integral and LSTM neural network

    CN115561638A