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

A method for on-line discrimination of fuel types based on multi-element flame detector

A technology of fuel type and identification method, applied in instruments, measuring devices, scientific instruments, etc., can solve problems such as large errors, improve combustion efficiency, enhance safety and economy, and avoid unstable flame combustion in the furnace.

Inactive Publication Date: 2011-12-07
BEIHANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method only has a high discrimination rate when the feature distinction between fuels is large. When the features of the fuel are close to each other, that is, when the distinction between the fuel feature values ​​is small, the error of the method larger

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 method for on-line discrimination of fuel types based on multi-element flame detector
  • A method for on-line discrimination of fuel types based on multi-element flame detector
  • A method for on-line discrimination of fuel types based on multi-element flame detector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to enable those skilled in the art to clearly understand the technical solution of the present invention, the specific implementation manners of the present invention are now further described.

[0019] Specific implementation method:

[0020] Such as figure 1 As shown, n (≥ 3) photoelectric sensors are used to obtain a radiation signal of a known fuel combustion flame in the radiation band, and M groups are collected to form a signal sample set {x(m, s)|m=1, 2 , . . . , M; s=1, 2, . . . , n}. Among them, M should be selected so that the signals in the collected sample set {x(m, s)} can cover various conditions of fuel combustion. For example, M=500 may be selected, that is, 500 sets of signals are collected for each fuel. Extract the eigenvalues ​​of the flame in the time domain and frequency domain {c(m, s, t)|m=1, 2,..., M; s=1, 2,..., n; t=1, 2 ,...,T} (such as flicker frequency, mean, root mean square, variance, number of zero crossings, skew rate, kur...

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 discrimination method of fuel types based on a multi-element flame monitor. There are known fuels and new fuels in the combustion, and the characteristic values ​​in the time domain and frequency domain are extracted from the flame radiation signals of the known fuels, and obtained by mathematical transformation. Orthogonalized eigenvalues; based on the orthogonalized eigenvalues, establish a joint probability density model and neural network model of the eigenvalue distribution of known fuels; extract the eigenvalues ​​in the time domain and frequency domain of the combustion flame radiation signal of the fuel to be identified , after mathematical transformation, the orthogonalized eigenvalues ​​are obtained and input into the joint probability density model of various known fuels for judgment. If the fuel to be identified in the combustion is a new fuel, the orthogonality of the flame radiation of the new fuel is saved. To establish the joint probability density model of this new fuel, and update the neural network model; if the fuel to be identified in the combustion is not a new fuel, then the neural network model is used to identify the type of fuel.

Description

【Technical field】 [0001] The invention relates to an online identification method for combustion fuel types, belonging to the technical field of industrial boiler fuel identification. 【Background technique】 [0002] Due to the limitation of economic factors and other factors, industries usually need to burn different types of fuels, and the types of fuels are usually unknown and unpredictable during combustion. The change of fuel type makes the combustion more complicated, directly affects the stability of the combustion flame, makes it very difficult to detect and control the combustion state, and seriously affects the efficiency of combustion. Therefore, the change of fuel type affects the safety and economy of combustion operation. [0003] The neural network technology used in this patent is an artificial neural network, which is composed of a large number of nodes and interconnected with each other, and is a mathematical model for information processing with a connectio...

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): G06K9/62G06N3/02G01N21/00
Inventor 徐立军谭丞李小路
Owner BEIHANG UNIV
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