一种不完备充放电数据下的锂离子电池健康状态评估方法

本发明提供一种不完备充放电数据下的锂离子电池健康状态评估方法，包括如下步骤：步骤1、进行电池特征提取与重构；步骤2、采用高斯过程模拟输入特征与电池SOH之间的映射关系；步骤3、构建基于变分推理的序列化高斯过程回归模型。本发明适用于实际电池工况，针对实际应用中锂离子电池的充放电数据是部分且随机的问题，基于等电压区间时间差构建了一种基于随机充放电过程的共性特征。本发明可以实现基于任意电池充放电区间数据的电池SOH评估。 The invention provides a lithium ion battery health state evaluation method under incomple...

Full description

Saved in:
Bibliographic Details
Format Patent
LanguageChinese
Published 29.08.2023
Subjects
MEASURING
MEASURING ELECTRIC VARIABLES
MEASURING MAGNETIC VARIABLES
PHYSICS
TESTING
Online AccessGet full text

Cover

More Information
Summary:本发明提供一种不完备充放电数据下的锂离子电池健康状态评估方法，包括如下步骤：步骤1、进行电池特征提取与重构；步骤2、采用高斯过程模拟输入特征与电池SOH之间的映射关系；步骤3、构建基于变分推理的序列化高斯过程回归模型。本发明适用于实际电池工况，针对实际应用中锂离子电池的充放电数据是部分且随机的问题，基于等电压区间时间差构建了一种基于随机充放电过程的共性特征。本发明可以实现基于任意电池充放电区间数据的电池SOH评估。 The invention provides a lithium ion battery health state evaluation method under incomplete charging and discharging data. The method comprises the following steps: step 1, carrying out battery feature extraction and reconstruction; 2, simulating a mapping relation between the input characteristics and the SOH of the battery by adopting a Gaussian process; and step 3, constructing a serialized Gaussian process regression model based on variational reasoning. The method is suitable for actual battery working conditions, and a common feature based on a random charging and discharging process is constructed based on equal voltage interval time difference aiming at the problem that charging and discharging data of a lithium ion battery in actual application is partial and random. According to the invention
Bibliography:Application Number: CN202210815701