CN106778816A - Combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis - Google Patents
Combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis Download PDFInfo
- Publication number
- CN106778816A CN106778816A CN201611047414.5A CN201611047414A CN106778816A CN 106778816 A CN106778816 A CN 106778816A CN 201611047414 A CN201611047414 A CN 201611047414A CN 106778816 A CN106778816 A CN 106778816A
- Authority
- CN
- China
- Prior art keywords
- mixed coefficint
- burning
- combustion stability
- combustion
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Control Of Combustion (AREA)
Abstract
The invention belongs to combustion flame image processing technique field, more particularly to a kind of combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis, the method is first to combustion flame image zooming-out feature, calculate burning mixed coefficint, burning mixed coefficint fluctuation parameters, black imperial length and black imperial length fluctuations parameter, with the mixed coefficint that burns, burning mixed coefficint fluctuation parameters, black imperial length and black imperial length fluctuations parameter are characterized index, by selecting the corresponding membership function of characteristic index, calculate fuzzy set to be checked and stablize fuzzy set, approach degree between unstable fuzzy set, combustion stability is differentiated according to Similarity Principle, thus the combustion stability method of discrimination based on fuzzy diagnosis is set up.The present invention has taken into full account influence of the burning mixed coefficint to combustion stability, the ability with identification flame combustion stability well, can correctly distinguish combustion stability and instable situation, and accuracy rate is higher.
Description
Technical field
The invention belongs to combustion flame image processing technique field, and in particular to one kind is based on burning mixed coefficint and obscures
The combustion stability method of discrimination of identification.
Background technology
Coal is one of main energy sources of China, and the consumption of wherein coal-burning boiler accounts for sizable ratio.Station boiler
Combustion stability is directly connected to the reliability and security of boiler operatiopn, combustion instability or firing optimization is bad not only can
Cause steam parameter to fluctuate, boiler thermal output declines, and may cause stove chamber fire-extinguishing, or even trigger furnace explosion,
Cause huge economic loss.Therefore real-time detection is carried out to boiler combustion flame, sets up combustion stability method of discrimination, improved
Efficiency of combustion, reduces Air-pollution From Combustion, with important engineer applied meaning.
The research method for boiler combustion stability is mainly bright by measuring flame characteristic signal such as flame at this stage
Degree, flame intensity and flame spectrum etc., and then the feature that the Mathematical treatments such as spectrum analysis obtain reflection combustion position is carried out to it
Information.Flame image monitoring system is widely used recently as China's major part station boiler, for furnace flame detection is provided
Fired state visual information, researchers are by being processed flame image and extracted individual features amount, with reference to nerve net
The methods such as network, SVMs, rough set theory and fuzzy diagnosis complete the differentiation of boiler combustion stability state.
It is worth noting that, the mixed effect of hot-fluid is to combustion position in stove also important, combustion in coal dust and stove
It is the characteristic parameter for characterizing coal dust and hot-fluid mixed effect in stove to burn hybrid parameter, if coal dust and hot-fluid mixed effect in stove
Preferably, then combustion position is preferable in stove, flameholding；If mixed effect is poor, the coal dust firing time can be increased, reduce coal dust
Efficiency of combustion, causes combustion instability, therefore burning mixed coefficint studies significant for boiler combustion stability.
From the foregoing, it will be observed that the combustion stability method of discrimination based on flame image is ripe not enough at this stage, it is not accounted for
Influence of the burning mixed coefficint to boiler combustion stability, causes combustion stability to differentiate that result precision is relatively low.
The content of the invention
Regarding to the issue above, the present invention proposes a kind of combustion stability based on burning mixed coefficint and fuzzy diagnosis and sentences
Other method, the method is comprised the following steps：
Step one, region is characterized with flame combustion area, extracts corresponding grey parameter G and grayscale position distributed constant D, meter
Calculate burning mixed coefficint H and burning mixed coefficint fluctuation △ H；
Step 2, rim detection is carried out to burning image, calculates black imperial length DI and Hei Long length fluctuations parameter △ DI；
Step 3, is joined with the mixed coefficint H that burns, burning mixed coefficint fluctuation △ H, black imperial length DI and Hei Long length fluctuations
Number △ DI are characterized index, set up the combustion stability method of discrimination based on fuzzy diagnosis.
Preferably, in step one, the computational methods of burning mixed coefficint H are as follows：Region is characterized with flame combustion area, it is right
It carries out piecemeal treatment, extracts the grayscale distribution information in each segmented areas, including grey parameter G and grayscale position distributed constant
D, the grey parameter G are by building the characteristic vector of pixel grayscale statistical information and best features vector in each segmented areas
Euclidean distance and weight acquisition, the grayscale position distributed constant D be by the half-tone information of all subregion, with image
Region to black imperial edge distance as its positional information, buildWherein N is subregion number,For
Subregion gray-level features,It is jth subregion the i-th gray level set pixel number, piIt is i-th point in weight vectors P
Amount, n is number of greyscale levels, siIt is the i-th subregion central point to the distance of segmentation straight line；
Burning mixed coefficint is determined according to the grey parameter G and grayscale position distributed constant D
Wherein α is weight coefficient, and span is (0,1),It is Normalized Grey Level parameter,It is Normalized Grey Level position distribution parameter, wherein t is subregion pixel.
Preferably, burning mixed coefficint fluctuation parameters △ H computational methods are as follows：Take two frame continuous time flame video images
Mixed coefficint difference Δ Hi=| Hi-Hi-1| to describe moment burning mixed coefficint fluctuation situation, boiler combustion is reacted with this steady
It is fixed, wherein Δ HiIt is the burning mixed coefficint fluctuation parameters at i moment, HiIt is the burning mixed coefficint at i moment, Hi-1It is the i-1 moment
Burning mixed coefficint.
Preferably, in step 2, the computational methods of black imperial length DI are as follows：According to black imperial length effective coverage and coal dust gas
The stream direction of motion determines n bars straight line to be detected, and every straight line shade of gray maximum point is found by first-order difference algorithm, obtains n
Black imperial edge coordinate is organized, each marginal point is to the distance on flame image borderIt is put down
Average is the black imperial length of flame imageWherein (xi0,yi0) it is the i-th straight line initial pixel point coordinates, (xij,
yij) it is i-th straight line shade of gray maximum pixel point coordinates.
Preferably, black imperial length fluctuations parameter △ DI computational methods are as follows：Take two frame continuous time flame video images
Black imperial length difference Δ DIi=| DIi-DIi-1| to describe the moment black imperial length fluctuations situation, wherein Δ DIiIt is the black dragon at i moment
Length fluctuations parameter, DIiIt is the black imperial length at i moment, DIi-1It is the black imperial length at i-1 moment.
Preferably, in step 3, the combustion stability method of discrimination bag based on burning mixed coefficint and fuzzy diagnosis is set up
Include following steps：
(1) membership function for choosing the burning mixed coefficint H and black imperial length parameter DI is respectively type bigger than normal
Ridge shape distribution function, osculant second-degree parabola distribution function, choose burning mixed coefficint fluctuation parameters △ H and described black
The membership function of imperial length fluctuations parameter △ DI is the secondary parabolic type distribution of type less than normal；
(2) the characteristic index degree of membership of stabilization combustion flame video image is chosen as stability criterion fuzzy set U1, choose
The characteristic index degree of membership of rough burning flame video image is used as unstable standard fuzzy set U2；
(3) Flame Image Characteristics parameter to be determined is extracted, characteristic index degree of membership is calculated, combustion stability differentiation side is built
The factor fuzzy set A of methodi, A is calculated respectivelyiWith stability criterion fuzzy set U1With unstable standard fuzzy set U2Euclid
Approach degree, combustion stability is differentiated using Similarity Principle.
The present invention constructs the combustion stability based on burning mixed coefficint and fuzzy diagnosis and sentences according to coal dust firing image
Other method, realizes the differentiation to boiler combustion stability, and the method has taken into full account burning mixed coefficint to combustion stability
Influence, with well identification flame combustion stability ability, can correctly distinguish combustion stability with it is instable
Situation, accuracy rate is higher.
Brief description of the drawings
Fig. 1 is combustion stability method of discrimination flow chart proposed by the present invention
Fig. 2 is the burning image of the embodiment of the present invention
Fig. 3 is the black imperial length effective coverage schematic diagram of burning image of the embodiment of the present invention
Specific embodiment
Below in conjunction with the accompanying drawings, embodiment is elaborated.
In boiler combustion process, burning mixed coefficint directly affects boiler combustion situation, and the present invention is by the side shown in Fig. 1
Method differentiates to combustion stability, specifically includes following steps：
Step one：Region is characterized with flame combustion area, corresponding grey parameter G and grayscale position distributed constant D, meter is extracted
Burning mixed coefficint H and burning mixed coefficint fluctuation △ H are calculated, it is as follows in detail：
Burning image is gathered by flame image sensor, the embodiment of the present invention uses the combustion that size is 320*240
Image is burnt, referring to Fig. 2.Region is characterized with flame combustion area, piecemeal treatment is carried out to characteristic area, it is t to be divided into N number of size
Every sub-regions are carried out Gray Classification treatment by the adjacent void-free subregion of × t successively, extract the ash in each segmented areas
Degree distributed intelligence, including grey parameter G and grayscale position distributed constant D, so that by coal dust pixel in stove on locus
Gradation of image distribution situation is incorporated into the measurement of coal dust and hot-fluid mixed effect-burning mixed coefficint in stove.
Grey parameter G is the characteristic vector and best features by building pixel grayscale statistical information in each segmented areas
The Euclidean distance of vector simultaneously weights acquisition.Correspond in n grades of gray level image, when mixed effect is worst, pixel in characteristic area
Point is distributed in relatively low gray level set；When mixed effect is optimal, pixel is concentrated on compared with high grade grey level set in region.Together
When due to the less gray level set pixel of gray value it is more, mixed effect is poorer；The larger gray level set picture of gray value
Vegetarian refreshments is more, and mixed effect is better, therefore the influence that different grey-scale set is evaluated mixed effect is measured by weighting.
Each gray level set pixel number is belonged to according to all subregion, obtains belonging to each gray level collection in characteristic area
The pixel number of conjunction.By building a n dimensional feature vector A=(a1,…,ai,…,an), wherein aiIt is the i-th gray scale set
The ratio of pixel number and the total pixel number in region, ideally, coal dust with hot-fluid mixed effect in stove preferably when, burning effect
Fruit is optimal, burning image characteristic area brightness highest, so with Ab=(0 ..., 0 ..., 0,1) as n dimension best features vectors.
While withAs weight vectors, grey parameter is calculatedWherein, pi,ai,abi
Vector P, A, A are represented respectivelybIn i-th component, N be subregion number.
Grayscale position distributed constant D is by the half-tone information of all subregion, with image sub-zones to black imperial edge
Distance builds grayscale position distributed constant as its positional informationWherein N is subregion number,For
Subregion gray-level features,It is jth subregion the i-th gray level set pixel number, piIt is i-th point in weight component P
Amount, n is number of greyscale levels, siIt is the i-th subregion central point to the distance of segmentation straight line.
Mixed coefficint is determined according to grey parameter G and grayscale position distributed constant DWherein α is
Weight coefficient, span is (0,1),It is Normalized Grey Level parameter,For
Normalized Grey Level position distribution parameter, wherein t is subregion pixel.
When the condition such as breeze airflow speed or in-furnace temperature changes, then coal dust also will hair with hot-fluid mixed effect in stove
Changing, the mixed coefficint that now burns will occur larger fluctuation.Take the burning mixed stocker of two frame continuous time flame video images
Number difference Δ Hi=| Hi-Hi-1| come describe the moment burning mixed coefficint fluctuation situation, with this react boiler combustion stabilization whether,
Wherein Δ HiFor the burning mixed coefficint at i moment fluctuates.
Step 2, rim detection is carried out to burning image, calculates black imperial length DI and Hei Long length fluctuations parameter △ DI, in detail
It is thin as follows：
During black imperial linear measure longimetry, what is worked is the central region of mixed airflow, the effective district of its feature extraction
Domain is as shown in Figure 3.When breeze airflow never combustion zone enters initial combustion area, flame image is grey along the pixel of airflow direction
Degree will be significantly increased, and from initial combustion area to unburned area, gray scale is quickly reduced, and the gray scale ladder on two directions is calculated respectively
Degree, it may be determined that black imperial length edge pixel.Rim detection is carried out to flame image using first-order difference algorithm.By finding
Maximum forward difference, i.e., shade of gray maximum point in prescribed direction in image determines black imperial edge.
N bars straight line to be detected is determined according to black imperial length effective coverage and the breeze airflow direction of motion, and by a jump
Divide algorithm to find every straight line shade of gray maximum point, obtain the black imperial edge coordinate of n groups.Each marginal point is to flame image border
Distance beIts average value is the black imperial length of flame imageWherein
(xi0,yi0) it is the i-th straight line initial pixel point coordinates, (xij,yij) it is i-th straight line shade of gray maximum pixel point coordinates.
When causing breeze airflow or flame spread speed to change because external condition changes, black dragon front and rear will move
Dynamic, black imperial length changes, it will cause coal powder ignition unstable, in addition flame blow-off phenomenon, therefore black imperial length with
Time change situation can reactive combustion stability state, take the black imperial length difference Δ DI of two frame continuous time flame video imagesi
=| DIi-DIi-1| to describe the moment black imperial length fluctuations situation, wherein Δ DIiIt is the black imperial length fluctuations at i moment.
Step 3, sets up the combustion stability based on burning mixed coefficint and fuzzy diagnosis and differentiates：
Numerical value should be close to 1 in optimum combustion regime for burning mixed coefficint H, and the more remote combustion efficiency of distance 1 is poorer.Combustion
When burning mixed coefficint near 0 or 1, its nominal growth is little on combustion efficiency influence, otherwise then influences larger, therefore chooses inclined
Large-scale ridge shape distribution is used as best combustion mixed coefficint membership function mui1, it is burning mixed coefficint H, x ∈ [0,1] to take x, then
When burning mixed coefficint fluctuation Δ H fluctuations are larger, combustion efficiency is changed greatly, and combustion instability increases, therefore
Using the secondary parabolic type distribution of type less than normal as best combustion mixed coefficint fluctuation membership function u2.X is taken for mixed coefficint fluctuates
50 × Δ H, x ∈ [0,50], then
Black imperial length DI length in optimum combustion regime is in moderate state, and black imperial length is closer to image middle part, combustion
Burning effect is better, and combustion efficiency lifting when being drawn close to centre is slower, conversely, combustion efficiency is poorer, but when being drawn close to centre
Combustion efficiency lifting is faster.Therefore the distribution of osculant second-degree parabola is taken as optimal black imperial length membership function u3, takeDImaxIt is maximum black imperial length, x ∈ [0,1], then
Black imperial length fluctuations Δ DI level off to 0 when combustion efficiency it is optimal, as black imperial length fluctuations increase, combustion efficiency becomes
Difference, the speed that combustion efficiency is deteriorated accelerates, and thus selects type second-degree parabola distribution less than normal to be subordinate to as optimal black imperial length fluctuations
Membership fuction u4.TakeX ∈ [0,5], then
When combustion case is optimal in the ideal situation, coal dust should be combustion in optimum state with hot-fluid mixed effect in stove
It is 1 to burn mixed coefficint H, and black imperial length DI should be in flame image centre position, and H and Hei Long are long for burning mixed coefficint fluctuation Δ
DI is minimum for degree fluctuation Δ, i.e., undulating value is 0.Now each characteristic index degree of membership u1=1, u2=1, u3=1, u4=1, selection is steady
Calibrate quasi- fuzzy set U1=(1,1,1,1).Conversely, when combustion position is worst in the ideal situation, burning mixed coefficint H numerical value compared with
Small, black imperial length DI should be long or too short, and DI is very big for burning mixed coefficint fluctuation Δ H and Hei Long length fluctuations Δ, therefore
Select unstable standard fuzzy set U2=(0,0,0,0).
Burning mixed coefficint H, burning mixed coefficint fluctuation Δ H, black imperial length DI are extracted based on combustion flame image respectively
And black dragon fluctuation Δ DI, it is calculated to optimum combustion regime degree of membership, obtain fuzzy set X to be detectedi.According to Similarity Principle,
Fuzzy set X to be detected is calculated respectivelyiWith stability criterion fuzzy set U1, unstable standard fuzzy set U2Euclid's approach degreeWherein n is the burner number of gathered flame video image, this reality
Apply n=4 in example；I=1,2 ..., m, m are resulting fuzzy set number to be detected, m=60 in the present embodiment；J=1,2.
Combustion stability is differentiated according to Similarity Principle.If N (Xi,U1)>N(Xi,U2), illustrate fuzzy set XiWith stability criterion
Fuzzy set U1Closer to then corresponding flame image boiler combustion balanced condition；Conversely, boiler combustion situation is unstable.
This embodiment is only the present invention preferably specific embodiment, but protection scope of the present invention is not limited thereto,
Any one skilled in the art the invention discloses technical scope in, the change or replacement that can be readily occurred in,
Should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
It is defined.
Claims (6)
1. it is a kind of based on burning mixed coefficint and fuzzy diagnosis combustion stability method of discrimination, it is characterised in that methods described
By extracting the Flame Image Characteristics that flame image sensor is gathered, burning mixed coefficint, burning mixed coefficint fluctuation ginseng are calculated
Several, black imperial length, black imperial length fluctuations parameter, set up based on fuzzy diagnosis combustion stability method of discrimination, specifically include with
Lower step：
Step one, region is characterized with flame combustion area, extracts grey parameter and grayscale position distributed constant, calculates burning mixing
Coefficient and burning mixed coefficint fluctuation parameters；
Step 2, rim detection is carried out to burning image, calculates black imperial length and Hei Long length fluctuations parameters；
Step 3, with the mixed coefficint that burns, burning mixed coefficint fluctuation parameters, black imperial length and Hei Long length fluctuations parameter as special
Index is levied, the combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis is set up.
2. combustion stability method of discrimination according to claim 1, it is characterised in that in the step one, the burning
The computational methods of mixed coefficint are as follows：Region is characterized with flame combustion area, piecemeal treatment is carried out to it, extract each segmented areas
Interior grayscale distribution information, including grey parameter and grayscale position distributed constant, the grey parameter is by building each piecemeal area
The Euclidean distance of the characteristic vector of pixel grayscale statistical information and best features vector and acquisition is weighted in domain, the gray level bit
Put distributed constant be by the half-tone information of all subregion, using image on all subregion to the distance at black imperial edge as its position
Information, buildsWherein D is grayscale position distributed constant, and N is subregion number,It is subregion gray scale
Level feature,It is jth subregion the i-th gray level set pixel number, piIt is i-th component in weight vectors P, n is gray scale
Series, siIt is the i-th subregion central point to the distance of segmentation straight line；
Burning mixed coefficint is determined according to the grey parameter and the grayscale position distributed constant
Wherein α is weight coefficient, and span is (0,1),It is Normalized Grey Level parameter,It is Normalized Grey Level position distribution parameter, wherein t is subregion pixel.
3. combustion stability method of discrimination according to claim 2, it is characterised in that the burning mixed coefficint fluctuation ginseng
Number calculating method is as follows：Take the burning mixed coefficint difference Δ H of two frame continuous time flame imagesi=| Hi-Hi-1| to describe when this
The burning mixed coefficint fluctuation situation at quarter, boiler combustion stability, wherein Δ H are reacted with thisiIt is the burning mixed coefficint at i moment
Fluctuation parameters, HiIt is the burning mixed coefficint at i moment, Hi-1It is the burning mixed coefficint at i-1 moment.
4. combustion stability method of discrimination according to claim 1, it is characterised in that in the step 2, the black dragon
The computational methods of length are as follows：N bars straight line to be detected is determined according to black imperial length effective coverage and the breeze airflow direction of motion, is led to
Cross first-order difference algorithm and find every straight line shade of gray maximum point, obtain the black imperial edge coordinate of n groups, each marginal point to flame
The distance of image boundary isIts average value is the black imperial length of flame imageWherein (xi0,yi0) it is the i-th straight line initial pixel point coordinates, (xij,yij) it is i-th straight line shade of gray maximum
Pixel point coordinates.
5. combustion stability method of discrimination according to claim 4, it is characterised in that the black imperial length fluctuations parameter meter
Calculation method is as follows：Take the black imperial length difference Δ DI of two frame continuous time flame imagesi=| DIi-DIi-1| to describe the moment black dragon
Length fluctuations situation, wherein Δ DIiIt is the black imperial length fluctuations parameter at i moment, DIiIt is the black imperial length at i moment, DIi-1It is i-1
The black imperial length at moment.
6. combustion stability method of discrimination according to claim 1, it is characterised in that in the step 3, the foundation
Combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis is comprised the following steps：
(1) membership function for setting the burning mixed coefficint and the black imperial length parameter is respectively type ridge bigger than normal shape distribution
Function, osculant second-degree parabola distribution function, set burning mixed coefficint fluctuation parameters and the black imperial length fluctuations
The membership function of parameter is the secondary parabolic type distribution of type less than normal；
(2) the characteristic index degree of membership of stabilization combustion flame image is chosen as stability criterion fuzzy set, chooses rough burning
The characteristic index degree of membership of flame image is used as unstable standard fuzzy set；
(3) Flame Image Characteristics parameter to be determined is extracted, characteristic index degree of membership is calculated, combustion stability method of discrimination is built
Factor fuzzy set, calculates the factor fuzzy set several with the Europe of stability criterion fuzzy set and unstable standard fuzzy set respectively
In approach degree, using Similarity Principle differentiate combustion stability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611047414.5A CN106778816B (en) | 2016-11-23 | 2016-11-23 | Combustion stability judging method based on combustion mixing coefficient and fuzzy recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611047414.5A CN106778816B (en) | 2016-11-23 | 2016-11-23 | Combustion stability judging method based on combustion mixing coefficient and fuzzy recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106778816A true CN106778816A (en) | 2017-05-31 |
| CN106778816B CN106778816B (en) | 2020-06-05 |
Family
ID=58974514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611047414.5A Expired - Fee Related CN106778816B (en) | 2016-11-23 | 2016-11-23 | Combustion stability judging method based on combustion mixing coefficient and fuzzy recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778816B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445845A (en) * | 2018-02-12 | 2018-08-24 | 国网山东省电力公司电力科学研究院 | A kind of Intelligent boiler combustion stability suitable for large-scale power station judges system and method |
| CN109214332A (en) * | 2018-08-31 | 2019-01-15 | 华北电力大学 | A kind of combustion stability method of discrimination based on furnace flame image fractal characteristic |
| CN113674280A (en) * | 2021-10-25 | 2021-11-19 | 启东万惠机械制造有限公司 | Method for measuring temperature of hearth of power station boiler |
| CN114754353A (en) * | 2022-04-13 | 2022-07-15 | 山西大学 | Circulating fluidized bed boiler combustion optimization method fusing neighborhood rough set machine learning |
| CN118155736A (en) * | 2024-01-29 | 2024-06-07 | 中国人民解放军陆军装甲兵学院 | Propellant combustion product analysis method based on image feature processing technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2390675A (en) * | 2002-07-10 | 2004-01-14 | Univ Greenwich | Flame characteristic monitor using digitising image camera |
| CN103077394A (en) * | 2012-12-31 | 2013-05-01 | 天津大学 | Method for automatically monitoring flame combustion stability |
| CN105183935A (en) * | 2015-07-20 | 2015-12-23 | 昆明理工大学 | Evaluation method for flame burning condition and stability |
| CN105912872A (en) * | 2016-04-27 | 2016-08-31 | 华北电力大学 | Measurement method of coal dust and in-furnace heat flow mixing effect on the basis of combustion image |
-
2016
- 2016-11-23 CN CN201611047414.5A patent/CN106778816B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2390675A (en) * | 2002-07-10 | 2004-01-14 | Univ Greenwich | Flame characteristic monitor using digitising image camera |
| CN103077394A (en) * | 2012-12-31 | 2013-05-01 | 天津大学 | Method for automatically monitoring flame combustion stability |
| CN105183935A (en) * | 2015-07-20 | 2015-12-23 | 昆明理工大学 | Evaluation method for flame burning condition and stability |
| CN105912872A (en) * | 2016-04-27 | 2016-08-31 | 华北电力大学 | Measurement method of coal dust and in-furnace heat flow mixing effect on the basis of combustion image |
Non-Patent Citations (4)
| Title |
|---|
| HUA CHEN 等: "Recognition of the Temperature Condition of a Rotary Kiln Using Dynamic Features of a Series of Blurry Flame Images", 《IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS》 * |
| 刘禾 等: "基于火焰序列图像的煤粉燃烧稳定性判别", 《动力工程》 * |
| 刘禾: "基于火焰图像和模糊神经网络的锅炉燃烧稳定性判别", 《仪器仪表学报》 * |
| 黄耀松 等: "火焰燃烧的特征量提取及稳定性识别", 《现代电力》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445845A (en) * | 2018-02-12 | 2018-08-24 | 国网山东省电力公司电力科学研究院 | A kind of Intelligent boiler combustion stability suitable for large-scale power station judges system and method |
| CN108445845B (en) * | 2018-02-12 | 2020-02-14 | 国网山东省电力公司电力科学研究院 | Intelligent boiler combustion stability judgment system and method suitable for large power station |
| CN109214332A (en) * | 2018-08-31 | 2019-01-15 | 华北电力大学 | A kind of combustion stability method of discrimination based on furnace flame image fractal characteristic |
| CN113674280A (en) * | 2021-10-25 | 2021-11-19 | 启东万惠机械制造有限公司 | Method for measuring temperature of hearth of power station boiler |
| CN114754353A (en) * | 2022-04-13 | 2022-07-15 | 山西大学 | Circulating fluidized bed boiler combustion optimization method fusing neighborhood rough set machine learning |
| CN118155736A (en) * | 2024-01-29 | 2024-06-07 | 中国人民解放军陆军装甲兵学院 | Propellant combustion product analysis method based on image feature processing technology |
| CN118155736B (en) * | 2024-01-29 | 2024-08-23 | 中国人民解放军陆军装甲兵学院 | Propellant combustion product analysis method based on image feature processing technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106778816B (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778816A (en) | Combustion stability method of discrimination based on burning mixed coefficint and fuzzy diagnosis | |
| CN103886344B (en) | A kind of Image Fire Flame recognition methods | |
| CN106846305B (en) | A kind of boiler combustion stability monitoring method based on the more characteristics of image of flame | |
| CN202101268U (en) | Boiler furnace temperature field distribution control system | |
| CN102538000B (en) | Combustion flame diagnostic method | |
| CN107326137B (en) | Blast funnace hot blast stove burns stove process operating parameters multistage matching optimization method at times | |
| CN107730548A (en) | It is a kind of based on average gray and area towards heating furnace flame real-time detection method | |
| Huang et al. | Optimization of combustion based on introducing radiant energy signal in pulverized coal-fired boiler | |
| CN104534507B (en) | A kind of boiler combustion optimization control method | |
| Wang et al. | Pattern recognition for measuring the flame stability of gas-fired combustion based on the image processing technology | |
| CN108954375A (en) | Saving coals from boiler control method | |
| CN107191914A (en) | Boiler on-line tuning system and method based on as-fired coal information and fire defector | |
| JPH06220789A (en) | Method and apparatus for monitoring and controlling black liquor recovery oven | |
| CN110245850A (en) | A kind of sintering process operating mode's switch method and system considering timing | |
| CN103256620A (en) | Multi-information-fusion intelligent flame detecting device and detecting method thereof | |
| CN110400018B (en) | Operation control method, system and device for coal-fired power plant pulverizing system | |
| CN104633765A (en) | Energy-conservation control system and method | |
| CN111158239A (en) | Association rule algorithm and neural network-based pulverizing system performance optimization method | |
| CN101423348A (en) | Integrated recognition method for sintering conditions of cement rotary kiln | |
| Sujatha et al. | Soft sensor for flame temperature measurement and IoT based monitoring in power plants | |
| CN104008385A (en) | Coal-fired power plant furnace chamber flame judging method based on double images | |
| CN112040174A (en) | Underground coal flow visual detection method | |
| CN105912872B (en) | Hot-fluid mixed effect measure in a kind of coal dust and stove based on burning image | |
| CN110686272B (en) | On-line soft measurement method for coal amount entering furnace based on combustor video signal | |
| CN112733900B (en) | Boiler combustion state stability judging method based on deep migration learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200605 Termination date: 20201123 |