Lithium battery health state estimation method based on genetic convolutional neural network

Abstract

The invention discloses a lithium battery health state estimation method based on a genetic convolutional neural network, and the method specifically comprises the steps of: carrying out charging and discharging of different types of lithium batteries under a constant-current condition till the service life of the battery is ended, finishing recording and forming a constant-current charging voltage curve of the lithium battery; after the battery is charged each time, determining the current capacity of the battery as the true value of a CNN model; characterizing a voltage curve of the recorded voltage curve by using characteristic points, and taking the voltage curve as input data of the CNN model; initializing a network structure and each parameter; grouping the processed training set data, and training each CNN network; and inputting the processed test set data into a group of CNN network structures, and selecting the network structure with the minimum mean square error between the true value and the predicted value as a final prediction model.

Description

technical field [0001] The invention belongs to the technical field of battery management, and relates to a method for estimating the state of health of a lithium battery based on a genetic convolutional neural network. Background technique [0002] Lithium-ion batteries (LIB) have been widely used in electric vehicles, power tools, base station backup power and other fields because of their advantages of high energy density, long life, strong stability and low impact on the environment. In practical applications, a series of irreversible chemical reactions occur inside the battery with each charge and discharge, which leads to the gradual aging of the battery, manifested as capacity decline, power loss, etc. Therefore, it is very necessary to estimate the health status of the battery in advance during its use. It can send an early warning message when the battery life reaches the end, prompting the user or equipment provider to replace the battery in time. [0003] Usually...

AI Technical Summary

Problems solved by technology

SOH can be obtained by direct measurement or indirect calculation of the ratio of the current value of a characteristic parameter to the initial value. Direct measurement requires an instrument to measure the current SOH of the battery after each charge and discharge of the battery. In actual life, we cannot always The battery is disassembled and measured anywhere, so this method is not applicable

Images