Reconfigurable battery pack SOC estimation method based on rest recovery effect
The invention discloses a reconfigurable battery pack SOC estimation method based on a rest recovery effect, and the method comprises the steps: obtaining current data before a battery unit in a reconfigurable battery pack enters a rest state, SOC data when the battery unit enters the rest state, an...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
26.10.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a reconfigurable battery pack SOC estimation method based on a rest recovery effect, and the method comprises the steps: obtaining current data before a battery unit in a reconfigurable battery pack enters a rest state, SOC data when the battery unit enters the rest state, and voltage data within T seconds after the battery unit enters the rest state, and forming an original data set; performing data preprocessing to obtain a data matrix; building a convolutional neural network model to obtain a network model structure; dividing the data matrix into a training set and a test set, wherein the data of the training set is used for network training; evaluating the model by using the test set, outputting a neural network model if a condition is met, otherwise, returning to the previous step; and for the battery unit entering the rest state in the reconfigurable battery pack, collecting current data before the battery unit enters the rest state and voltage data within T seconds after the bat |
---|---|
Bibliography: | Application Number: CN202110726919 |