Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model

A technology for cycle life and model prediction, applied in the power field, can solve the problems of inability to disassemble lithium batteries, separate testing, and a large number of other problems, avoiding overfitting and underfitting, speeding up training, and large data samples. Effect

Pending Publication Date: 2021-03-12
ALPHA ESS CO LTD
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method for predicting the remaining cycle life of lithium batteries in energy storage systems based on the Xgboost model. Lithium batteries are disassembled and tested individually, so it can only be analyzed and predicted through the operation data of lithium batteries collected during the energy storage process

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
  • Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model
  • Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model
  • Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] refer to figure 1 , a method for predicting the remaining cycle life of a lithium battery in an energy storage system based on the Xgboost model, comprising the following steps:

[0045] S1: Data collection, collecting the actual operation data of the lithium battery during the operation of the energy storage power station, including battery cluster voltage, battery cluster temperature, battery cluster current, battery cluster accumulative charge and discharge times and other available data;

[0046] S2: Data cleaning, organize the collected data, remove invalid, abnormal, and partially missing data, and retain valid data;

[0047] S3: Feature selection, constructing feature data by calculating the original data, analyzing the correlation between feature data, making trade-offs, and selecting appropriate feature data as the input and output of the model;

[0048] S4: Model selection, choose the Xgboost model to predict the remaining cycle life of lithium batteries, usi...

Embodiment 2

[0092] refer to figure 1 , a method for predicting the remaining cycle life of a lithium battery in an energy storage system based on the Xgboost model, comprising the following steps:

[0093] S1: Data collection, collecting the actual operation data of the lithium battery during the operation of the energy storage power station, including battery cluster voltage, battery cluster temperature, battery cluster current, battery cluster accumulative charge and discharge times and other available data;

[0094] S2: Data cleaning, organize the collected data, remove invalid, abnormal, and partially missing data, and retain valid data;

[0095] S3: Feature selection, constructing feature data by calculating the original data, analyzing the correlation between feature data, making trade-offs, and selecting appropriate feature data as the input and output of the model;

[0096] S4: Model selection, choose the Xgboost model to predict the remaining cycle life of lithium batteries, usi...

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 relates to the technical field of electric power, and discloses a method for predicting the residual cycle life of a lithium battery in an energy storage system based on an Xgboost model, and the method comprises the following steps: S1, data collection: collecting the actual operation data of the lithium battery in the operation process of an energy storage power station; S2, data cleaning: sorting the collected data; and S3, feature selection: constructing feature data by calculating original data, and analyzing correlation between the feature data. According to the method, a widely applied life prediction big data model is adopted, the model is mature, the prediction accuracy is high, a parameter adjustment optimization method is adopted, the optimal parameters of the model are determined, the accuracy of the prediction model is improved, and data cleaning and feature extraction are performed on collected original data by adopting a scientific method. The correlation analysis among the characteristics can more visually see the mutual relation among the characteristics and find out important factors influencing the residual cycle life of the lithium battery.

Description

technical field [0001] The invention relates to the field of electric power technology, in particular to a method for predicting the remaining cycle life of a lithium battery in an energy storage system based on an Xgboost model. Background technique [0002] With the increase in the number of electrochemical energy storage power stations, the remote operation and maintenance management of electrochemical power stations has become very important. The life of electrochemical energy storage power stations plays an important role in the operation and maintenance In the life cycle, predicting and pre-processing the failure of batteries has always been a difficult point in remote operation and maintenance. If the battery operation data in the electrochemical energy storage power station collected remotely can be statistically analyzed, a battery life prediction model can be established to advance Predicting its service life and guiding the operation and maintenance of the power s...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01R31/392G01R31/3842G01R31/367
CPCG01R31/367G01R31/3842G01R31/392
Inventor 洪星杨帆
Owner ALPHA ESS CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap