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

A battery soh prediction method based on unsupervised transfer learning

A transfer learning and prediction method technology, applied in the field of battery SOH prediction based on unsupervised transfer learning, can solve the problems of new battery performance prediction, data-driven model reliability, and difficulty in ensuring the same data distribution of training data, etc. Achieve the effect of applicability guarantee

Active Publication Date: 2021-07-13
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF20 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Researchers have proposed a variety of data-driven SOH estimation methods. However, current research mainly focuses on the modeling process of specific power battery health states under experimental conditions. How to predict the performance of new batteries without historical SOH data is still a problem. unresolved issues
Due to different battery types and usage environments, it is difficult to ensure that the training data and the predicted object have the same data distribution. When the training data and the actual predicted battery data distribution are different, the reliability of the general data-driven model will be difficult to guarantee.

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
  • A battery soh prediction method based on unsupervised transfer learning
  • A battery soh prediction method based on unsupervised transfer learning
  • A battery soh prediction method based on unsupervised transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0057] ANN (Artificial Neural Network): artificial neural network;

[0058] newff: the function of training feedforward and backpropagation network in matlab

[0059] GPR (Gaussian Process Regression) Gaussian process regression;

[0060] fitgpr: the function of training the GPR model in the GPML toolbox of matlab

[0061] KNN (K-Nearest Neighbor) K nearest neighbor node algorithm;

[0062] fitcknn: the function of training KNN in matlab

[0063] TCA (Transfer Component Analysis) migration component analysis;

[0064] JDA (Joint Domain Adaptation) joint domain matching;

[0065] DDA (Dual Domain Adaption) double domain matching, our new domain matching algorithm;

[0066] figure 1 It is a flow chart of the battery SOH prediction method based on unsupervised transfer learning in the present invention.

[0067] In this example, if figur...

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 battery SOH prediction method based on unsupervised transfer learning. By extracting the features of two batteries, a domain matching algorithm is used to adjust the two feature spaces, so that the conditional distribution and marginal distribution of the two feature spaces match , and by adjusting the sample weights, the weights of two spatially related samples become larger, and the weights of unrelated samples become smaller; in this way, one battery data can be used for training through domain matching, and ordinary machine learning algorithms can be used to predict another battery. SOH has the advantages of high applicability, high prediction accuracy, and simple implementation.

Description

technical field [0001] The invention belongs to the technical field of battery state of health assessment, and more specifically, relates to a battery SOH prediction method based on unsupervised transfer learning. Background technique [0002] The state of health of batteries is closely related to the range, safety and reliability of electric vehicles. Due to the complex mechanism of battery degradation and numerous influencing factors, accurate and reliable estimation of the battery's state of health (SOH) is a difficult issue in battery management technology. [0003] The data-driven method represented by machine learning is flexible, does not require modeling, and has good nonlinear mapping capabilities. It is currently a research hotspot in this field. Researchers have proposed a variety of data-driven SOH estimation methods. However, current research mainly focuses on the modeling process of specific power battery health states under experimental conditions. How to pre...

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 Patents(China)
IPC IPC(8): G01R31/367G01R31/392
CPCG01R31/367G01R31/392
Inventor 盛瀚民刘鑫邵晋梁陈凯周圆
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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