Energy storage battery estimation method and system based on deep learning fusion

By calculating the changes in voltage and current, a dynamic internal resistance sequence is obtained, generating trajectory features. These features are then combined with temperature data input into a temporal convolutional network to construct a physical consistency constraint loss function. This solves the estimation accuracy and reliability problems of energy storage batteries under rapid pulse charging and discharging or low-temperature conditions, achieving high-precision real-time estimation.

CN122172036BActive Publication Date: 2026-07-07INNER MONGOLIA UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
INNER MONGOLIA UNIV OF TECH
Filing Date
2026-05-11
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

Existing technologies suffer from decreased accuracy in estimating the remaining capacity and state of health of energy storage batteries under rapid pulse charge-discharge or low-temperature conditions, and the lack of physical consistency constraints leads to insufficient generalization reliability.

Method used

The dynamic internal resistance sequence is obtained by calculating the voltage and current changes, generating trajectory features. These features are then combined with temperature time-series data and input into a time-series convolutional network. A physical consistency constraint loss function is constructed for network training to ensure that the estimation results conform to the ohmic characteristics of the battery.

Benefits of technology

It improves the estimation accuracy under pulse charge-discharge and cryogenic conditions, enhances the generalization reliability of the model under unseen conditions, and meets real-time requirements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122172036B_ABST
    Figure CN122172036B_ABST
Patent Text Reader

Abstract

The application provides a kind of energy storage battery estimation method and system based on deep learning fusion, it is related to energy storage battery management technical field, the application collects voltage, current time series data and calculates the ratio of voltage variation and current variation of adjacent sampling time, obtains dynamic resistance sequence, finally as trajectory feature, trajectory feature and temperature time series data time alignment fusion are input into time convolution network, and output residual capacity and health state;At the same time, based on the open-circuit voltage mapped by the residual capacity estimation value, the predicted voltage value is reconstructed by combining the dynamic resistance sequence and the current time series data, and the deviation between the predicted voltage and the measured voltage is constructed as a physical consistency constraint loss, which is combined with the estimation error loss to form a joint loss function. The parameters of the time convolution network are updated by back propagation, thereby solving the problem of failing to capture the dynamic resistance evolution law and lacking physical consistency constraint, and improving the estimation accuracy and model generalization reliability under complex working conditions.
Need to check novelty before this filing date? Find Prior Art