Battery pack SOH and RUL prediction method and system based on inconsistency evaluation

Abstract

The invention relates to a battery pack SOH and RUL prediction method and system based on inconsistency evaluation, and belongs to the technical field of battery management. The method comprises the following steps: selecting a to-be-tested series battery pack, and collecting and arranging technical parameters of the series battery pack; and carrying out a cyclic aging condition of multi-section variable current condition charging and constant current discharging, and establishing a battery pack aging database according to data such as single voltage, battery pack voltage, battery pack currentand the like; judging a local charging stage, and extracting a plurality of characteristic parameters based on a voltage change node; evaluating the inconsistency of the battery pack based on the extracted characteristic parameters, and carrying out the multi-input and double-output data-driven regression model training; evaluating the inconsistency of the battery pack by using the test set data;and predicting the SOH and RUL of the battery pack online by using the regression model obtained by training. On the basis of evaluating the inconsistency of the battery pack, the state and the service life of the battery pack are predicted, and the method adapts to incomplete charging and discharging conditions in actual use.

Description

technical field [0001] The invention belongs to the technical field of battery management, and relates to a battery pack SOH and RUL prediction method and system based on inconsistency evaluation. Background technique [0002] Lithium-ion batteries have the characteristics of long life, low self-discharge rate, and high energy density, making them good energy storage devices. And make it widely used in electrical applications, such as pure electric vehicles, plug-in hybrid vehicles, mobile energy storage equipment, power grids, etc. Due to the limitation of the power and voltage of the battery cells, the electric vehicle power battery pack is usually composed of hundreds or thousands of single cells connected in series and parallel to meet the energy and power requirements of the vehicle. The consistency of the battery pack is usually better when the battery is new, but it will increase with the aging of the battery, such as inconsistent internal resistance, inconsistent ca...

AI Technical Summary

Problems solved by technology

Constant current and constant voltage charging takes a long time, and the actual vehicle is usually an incomplete charging process, so this method also has great implementation difficulties

On the other hand, the existing methods usually focus on the research of the battery cell, but the difference between the battery pack and the cell in actual use is quite large, and the inconsistency is one of the most important influencing factors. At present, the inconsistency analysis has not yet been passed. An Effective Method for Predicting the Aging Condition of Battery Packs

[0005] In response to the above problems, there is no effective solution to extract characteristic parameters based on local charging points in actual vehicles to evaluate the inconsistency of the battery pack, and to predict the battery pack's state of health SOH and remaining life RUL.

Images