Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sample data set generation method and SOC estimation method of power lithium battery

A sample data set and lithium battery technology, applied in neural learning methods, electricity measurement, electric vehicles, etc., can solve problems such as increasing network training time, and achieve the effect of improving SOC estimation performance, reducing errors, and improving generalization capabilities

Pending Publication Date: 2022-08-02
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the LSTM network, the selection of hyperparameters is usually determined by continuously training the network and combining training experience, which invisibly increases the network training time in the process of trial and error.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sample data set generation method and SOC estimation method of power lithium battery
  • Sample data set generation method and SOC estimation method of power lithium battery
  • Sample data set generation method and SOC estimation method of power lithium battery

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Example 1: as Figure 1-5 As shown, a method for generating a sample data set of a power lithium battery includes:

[0053] Build a lithium battery charging and discharging transient solution model; according to the built lithium battery charging and discharging transient solution model, obtain the lithium battery potential diagram, current density analysis diagram and battery performance analysis diagram at different rates; export the lithium battery potential diagram and current density analysis diagram And the data corresponding to the battery performance analysis chart at different rates; preprocess the exported data to obtain a lithium battery sample data set.

[0054] Further, it is possible to set up the lithium battery charging and discharging transient solution model, including:

[0055] Select the physics field: add a Li-ion battery interface for battery charge-discharge transient research;

[0056] Construction objects: Specify the battery negative electrod...

Embodiment 2

[0075] Example 2: as Figure 6-8 As shown, a method for estimating the SOC of a power lithium battery includes:

[0076] S1. Construct a training set and a test set; divide the lithium battery sample data set obtained by the method for generating a power lithium battery sample data set according to any one of the above into a training set and a test set according to 8:2; or use public lithium battery samples The data set / the lithium battery sample data set collected on site is divided into training set and test set according to 8:2; the lithium battery sample data set includes SOC value, temperature value, discharge rate and voltage data at different discharge rates;

[0077] S2. Determination of LSTM network, the temperature value, discharge rate and voltage data at different discharge rates are determined as the input of the LSTM network, and the SOC value is used as the output of the LSTM network; among them, the LSTM network includes an input layer, a hidden layer, a full ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a sample data set generation method and an SOC estimation method of a power lithium battery. The generation method comprises the steps of building a lithium battery charging and discharging transient solution model; according to the built lithium battery charging and discharging transient solution model, a lithium battery potential chart, a current density analysis chart and a battery different rate performance analysis chart are obtained; exporting data corresponding to the lithium battery potential chart, the current density analysis chart and the battery different rate performance analysis chart; and preprocessing the exported data to obtain a lithium battery sample data set. According to the SOC estimation method, a bat algorithm is introduced, an iterative optimization process is designed, an optimized hyper-parameter combination is obtained, and updated hyper-parameters are input into a network, so that the SOC of the lithium battery is estimated. The method can be suitable for lithium batteries made of different materials, on one hand, the model calculation amount is reduced, on the other hand, the model prediction performance can be improved to a certain degree, the estimation precision of the SOC of the battery is high, and higher adaptability is achieved.

Description

technical field [0001] The invention relates to a method for generating a sample data set of a power lithium battery and a method for estimating SOC, which belong to the state of charge (SOC) prediction category of a battery management system (BMS). Background technique [0002] A good battery management system can improve battery efficiency and prolong battery life. Among them, lithium batteries are considered as one of the most promising energy storage options due to their high energy density, long life, and no pollution. At present, lithium batteries are widely used in industry, daily life and other fields, and estimating SOC with high accuracy can not only estimate the current remaining power of new energy vehicle energy storage batteries, improve balance consistency and output power, and reduce additional redundancy; Provide data basis for accurate assessment of battery health to understand battery aging in real time. Therefore, how to find an effective method to esti...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01R31/367G01R31/387G06N3/04G06N3/08
CPCG01R31/367G01R31/387G06N3/08G06N3/044Y02T10/70
Inventor 杨彪王银双成宬钱斌李琨张长胜金怀平王彬
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com