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

Method for estimating SOC (State of Charge) of single battery in battery pack by considering influence of multiple factors

A single battery and battery pack technology, applied in the direction of measuring electricity, measuring electrical variables, measuring devices, etc., can solve the problems of insufficient experimental data, achieve strong adaptability, good migration and prediction effects, and good application prospects

Active Publication Date: 2022-03-18
HARBIN INST OF TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies in the background technology, the present invention provides a method for estimating the SOC of a single battery in a battery pack that considers the influence of multiple factors. Estimate the adverse effects caused, and propose a migration learning framework that adapts both MPD and CPD to address the problems existing in existing migration learning methods. The method is simple and requires little experimental data

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 estimating SOC (State of Charge) of single battery in battery pack by considering influence of multiple factors
  • Method for estimating SOC (State of Charge) of single battery in battery pack by considering influence of multiple factors
  • Method for estimating SOC (State of Charge) of single battery in battery pack by considering influence of multiple factors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] This embodiment is verified based on the actual battery pack experimental data, wherein the number of single cells in the battery pack is 100, the rated capacity of the battery pack is 96Ah, the charge and discharge cut-off voltages are 420v and 250v respectively, and the rated capacity of the single battery It is 3.2Ah, the battery type is Panasonic NCR18650BD, and the positive and negative electrode materials are Li(NiCoMn)O 2 and graphite, the experiments included capacity test experiments, pulse test experiments and NEDC working conditions under different temperatures (-10°C, 15°C and 45°C) and different aging states (100% SOH (State of Health) and 95% SOH). Condition test experiment.

[0053] A data-driven algorithm based on Long Short Term Memory (LSTM) neural network, MPD based on Geodesic Flow Kernel (GFK) and Maximum Independent Domain Adaptation (MIDA) The fit method is experimentally validated at different temperatures and / or different aging states, and the ...

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 method for estimating SOC (State of Charge) of single batteries in a battery pack considering multi-factor influence, and relates to a battery SOC estimation method. Performing an experiment on a single battery of the same type in the battery pack to obtain source domain data; migrating and transforming the source domain data and the target domain data by using a transfer learning framework, wherein the transfer learning framework comprises feature enhancement, feature compression and MPD adaptation; and carrying out modeling on the transformed source domain data by using a data driving algorithm, and carrying out SOC prediction on the transformed target domain data so as to obtain an SOC estimation value. On the basis of a data-driven algorithm and by adopting a transfer learning method, adverse effects of multiple factors such as temperature and battery aging state on SOC estimation are solved, a transfer learning framework simultaneously adaptive to MPD and CPD is provided for the problems existing in an existing transfer learning method, and the method is simple and needs less experimental data.

Description

technical field [0001] The invention relates to a method for estimating the battery SOC, in particular to a method for estimating the SOC of a single battery in a battery pack considering the influence of multiple factors, and belongs to the technical field of battery research and development. Background technique [0002] The rapid development of electric vehicles has effectively alleviated the energy crisis and environmental degradation, and the power source of electric vehicles is a battery pack composed of a large number of single cells. Among them, the state of charge (State of Charge, Accurate estimation of SOC) is crucial to the safety of electric vehicles, and it can also provide accurate information for designing equilibrium strategies and ensuring the cruising range of electric vehicles. [0003] Due to different production processes and environmental differences, there are inevitably inconsistencies between the single cells in the battery pack. The current method...

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): G01R31/387
CPCG01R31/387Y02T10/70
Inventor 赵林辉秦鹏亮
Owner HARBIN INST OF 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