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

Algorithm based on DFFLS and neural network-ASRUKF for storage battery

A neural network and battery technology, which is applied in the field of algorithms based on DFFRLS and neural network-ASRUKF for batteries, can solve the problems that affect the full utilization of the program, and cannot guarantee the semi-positive definiteness of the state covariance matrix, so as to reduce data saturation and improve The effect of precision, speed and precision

Pending Publication Date: 2021-07-09
HOHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

UKF obtains the statistics of process noise covariance through unscented transformation, but UKF needs to manually specify the initial value of noise covariance, which makes SOC estimation have noise errors, and UKF cannot guarantee the semi-positive definiteness of the state covariance matrix, which affects the full operation of the program. The utilization of the battery management system is of great significance

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
  • Algorithm based on DFFLS and neural network-ASRUKF for storage battery
  • Algorithm based on DFFLS and neural network-ASRUKF for storage battery
  • Algorithm based on DFFLS and neural network-ASRUKF for storage battery

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] An algorithm based on DFFRLS and neural network-ASRUKF for a storage battery, comprising the following steps:

[0042] Step 1, DFFRLS online parameter identification.

[0043] Specific steps are as follows:

[0044] 101), algorithm initialization: set the initial covariance matrix P and parameter vector θ(k) as:

[0045]

[0046] 102), parameter update:

[0047] Among them, θ(k) is the estimated parameter value, and L is the filter gain matrix.

[0048] 103), construct dynamic forgetting factor function:

[0049] In the formula: ε(k+1) is the output variance between the theoretical model and the actual model, λ(k+1) is the dynamic forgetting factor function, and α and γ are positive adjustable parameters.

[0050] 104), gain matrix update:

[0051] L(k+1)=P(k)φ(k+1)[λ(k+1)+φ T (k+1)P(k)φ(k+1)] -1 .

[0052] 105), covariance matrix update:

[0053]

[0054] 106), repeat steps 102)-105), stop running when the program meets the termination condition, and...

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 provides a Algorithm based on DFFLS and neural network-ASRUKF for a storage battery, and relates to the technical field of storage batteries. The algorithm based on the DFFLS and the neural network-ASRUKF for the storage battery comprises the steps of S1, carrying out DFFLS online parameter identification, S2, carrying out SOC estimation by adopting the ASRUKF algorithm, and S3, carrying out SOC joint estimation through the DFFLS and BP-ASRUKF. According to the algorithm based on DFFLS and neural network-ASRUKF for the storage battery, a BP neural network is adopted to replace a polynomial to fit an OCV-SOC curve, the curve fitting precision can be further improved, and therefore the parameter online identification precision is improved, in parameter online identification, the DFFRLS algorithm adopts a dynamically changing forgetting factor, the data saturation phenomenon can be further reduced, compared with an FFRLS algorithm and an RLS algorithm, the algorithm has better rapidity and accuracy, in SOC estimation, the noise covariance matrix is updated in real time, meanwhile, the semi-positive qualitative property of the state covariance matrix is guaranteed, and the influence of noise covariance initial value setting on estimation precision is reduced.

Description

technical field [0001] The invention relates to the technical field of accumulators, in particular to an algorithm based on DFFRLS and neural network-ASRUKF for accumulators. Background technique [0002] In recent years, along with my country's proposed power Internet of Things and energy Internet strategies, renewable energy technology has been greatly developed. As a major commercial application of renewable energy technology, new energy vehicles have gradually become the mainstream travel mode. As the power source of new energy vehicles, the battery is extremely complex and not universal, so it is necessary to establish a suitable battery management system (bat-tery management system, BMS) to obtain the working status of the battery in real time, and its internal status mainly includes State of charge (SOC) and state of health (SO-H). Among them, SOC is one of the core technologies of the battery management system, and accurate SOC estimation can make the storage batter...

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): G06F17/16G06N3/08G01R31/367
CPCG06F17/16G06N3/084G01R31/367
Inventor 顾钟凡陈玉伟李承澳张德春黄海
Owner HOHAI UNIV
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