Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

On-line battery soh estimation method based on fractional order neural network and dual volume Kalman

A neural network and neural network model technology, applied in the field of battery health management, can solve the problems of slow training speed and inability to converge, and achieve the effects of fast convergence speed, effective function approximation ability, and high prediction accuracy

Active Publication Date: 2019-06-14
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the neural network model also has certain problems. Its training speed is slow, and there will be situations where it cannot converge. However, the neural network with fractional order improvement can not only improve its convergence speed, but also improve the prediction accuracy of the model.

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
  • On-line battery soh estimation method based on fractional order neural network and dual volume Kalman
  • On-line battery soh estimation method based on fractional order neural network and dual volume Kalman
  • On-line battery soh estimation method based on fractional order neural network and dual volume Kalman

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The invention will be described in further detail below in conjunction with the accompanying drawings.

[0051] The schematic diagram of online estimation of battery dynamic system is as follows: figure 1 Shown, concrete operation of the present invention comprises the following steps:

[0052] In step 1, the visible state of the dynamic system is measured by sensors.

[0053] In step 2, the historical data of the same type of battery is used as the initial training data set, and the neural network algorithm improved by the fractional order theory is used to train the model, and an equivalent model representing the nonlinear relationship of the battery system is obtained.

[0054] The flowchart of the fractional order neural network algorithm in step 2 is as follows figure 2 As shown, the specific process is as follows:

[0055] Step 2.1, the topology of the fractional order neural network is a three-layer network structure (1 input layer, 1 hidden layer and 1 outpu...

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 an online battery SOH (state of health) estimation method based on a fractional order neural network and a double-volume Kalman, belonging to the field of battery health management. The specific steps are: (1) collect the visible state quantity of the battery through the sensor; (2) train the fractional neural network model offline; (3) add the real-time data collected in step (1) to the initial training data set to make the model more accurate (4) Establish a discrete state space model to represent the mapping function between the hidden state and the visible state of the battery; (5) Use the dual volumetric Kalman filter (DCKF) algorithm to perform online fractional order neural network model update, while online estimation of the hidden state is performed. The invention can update the storage battery model on-line, adapt the model to the constantly changing dynamic environment, and improve the efficiency and accuracy of battery health management.

Description

technical field [0001] The invention discloses an online battery SOH (state of health) estimation method based on a fractional order neural network and a double-volume Kalman, belonging to the field of battery health management. Background technique [0002] With the continuous development of the national economy, the modernization requirements in the fields of energy, electric power, transportation, communication, and environmental protection are constantly increasing. The battery system as a backup energy source is being widely used. For all power supply systems that are not allowed to cut off, the battery pack is an indispensable backup power system. Moreover, the battery system is more and more widely used in various industries. . Whether the battery is running normally or not directly affects the normal, reliable and safe operation of various equipment in the application field. Therefore, accurately estimating the state of health of the battery is of great significanc...

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): G01R31/367G01R31/388G01R31/392G01R31/396G06N3/04G06N3/08
CPCG06N3/08G01R31/367G01R31/392G06N3/048
Inventor 陈则王林娅朱晓栋崔江王友仁
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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
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