CN108956400A - A kind of Measure Method of Pulverized Coal and device based on image recognition - Google Patents
A kind of Measure Method of Pulverized Coal and device based on image recognition Download PDFInfo
- Publication number
- CN108956400A CN108956400A CN201810809081.8A CN201810809081A CN108956400A CN 108956400 A CN108956400 A CN 108956400A CN 201810809081 A CN201810809081 A CN 201810809081A CN 108956400 A CN108956400 A CN 108956400A
- Authority
- CN
- China
- Prior art keywords
- image
- pulverized coal
- target
- powder density
- coal particle
- 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.)
- Pending
Links
- 239000003245 coal Substances 0.000 title claims abstract description 360
- 238000000034 method Methods 0.000 title claims abstract description 59
- 239000002245 particle Substances 0.000 claims abstract description 201
- 239000000843 powder Substances 0.000 claims abstract description 141
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000006243 chemical reaction Methods 0.000 claims abstract description 27
- 238000001914 filtration Methods 0.000 claims abstract description 25
- 238000003709 image segmentation Methods 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 20
- 239000002817 coal dust Substances 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 14
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 239000000446 fuel Substances 0.000 description 5
- 230000002902 bimodal effect Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011049 filling Methods 0.000 description 1
- 239000003500 flue dust Substances 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003447 ipsilateral effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G01N15/075—
Abstract
The embodiment of the invention provides a kind of Measure Method of Pulverized Coal and relevant device based on image recognition, for measuring the coal powder density in primary air inlet.This method comprises: obtaining the first pulverized coal particle image in Target pipe;Image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image;The second pulverized coal particle image is split by image segmentation, to obtain first object region, the first object region is the region of pulverized coal particle in the second pulverized coal particle image;Binary conversion treatment is carried out to the first object region and obtains the second target area;Shape filtering processing is carried out to second target area, to obtain third target area;Determine the gross area of pulverized coal particle in the third target area;Target coal powder density is determined according to the image area of the gross area of pulverized coal particle in the third target area and the second pulverized coal particle image.
Description
Technical field
The present invention relates to field of thermal power, in particular to a kind of Measure Method of Pulverized Coal and dress based on image recognition
It sets.
Background technique
Coal powder density in the unit primary air inlet of thermal power plant is the stable important ginseng with economical operation of boiler of power plant
Number.Reasonable and equilibrium coal powder density is of great significance for the normal operation of Power Plant.
Studies have shown that it is inclined to will lead to power plant boiler unstable combustion, eccentricity of fire, the center circle of contact when coal powder density unevenness
It moves, the problems such as flow of flue gas is uneven, unburned carbon in flue dust is high, and then boiler efficiency is caused to decline, it is serious or even can cause quick-fried
It runs affairs former, boiler is caused not transport normally.Therefore, the coal powder density accurately in measurement primary air inlet stablizes high efficiency boiler
Operation has great importance.
Summary of the invention
The embodiment of the invention provides a kind of Measure Method of Pulverized Coal based on image recognition and based on image recognition
Coal concentration measuring device, for measuring the coal powder density in primary air inlet.
First aspect of the embodiment of the present invention provides a kind of Measure Method of Pulverized Coal based on image recognition, specific to wrap
It includes:
The first pulverized coal particle image in Target pipe is obtained, the Target pipe is the pipeline of coal powder density to be measured;
Image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image;
The second pulverized coal particle image is split by image segmentation, to obtain first object region, described
One target area is the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment is carried out to the first object region and obtains the second target area;
Shape filtering processing is carried out to second target area, to obtain third target area;
Determine the gross area of pulverized coal particle in the third target area;
According to the gross area of pulverized coal particle in the third target area and the image of the second pulverized coal particle image
Area determines that target coal powder density, the target coal powder density are the coal powder density in the Target pipe.
Optionally, the gross area and second pulverized coal particle according to pulverized coal particle in the third target area
The image area of image determines that target coal powder density includes:
The target coal powder density is calculated by following formula:
Wherein, the N is the target coal powder density, the A0For the image area of the second pulverized coal particle image,
The A is the gross area of pulverized coal particle in the third target area, and the k is preset conversion coefficient, the A=∑i∑jf
(i, j), (i, j) ∈ R, the R are the third target area.
Optionally, the gross area and second pulverized coal particle according to pulverized coal particle in the third target area
After the image area of image determines target coal powder density, the method also includes:
The first coal powder density is obtained, first coal powder density is to carry out reality to the coal powder density in the Target pipe
Measure obtained coal powder density;
First coal powder density and the target coal powder density are analyzed, to be corrected to the k.
Optionally, described that image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image
Include:
Histogram equalization processing is carried out to the first pulverized coal particle image, with first coal dust that obtains that treated
Particle image;
To treated, the first pulverized coal particle image carries out the disposal of gentle filter, to obtain second pulverized coal particle
Image.
Optionally, the gross area and second pulverized coal particle according to pulverized coal particle in the third target area
After the image area of image determines target coal powder density, the method also includes:
The target coal powder density is exported.
The embodiment of the present application second aspect provides a kind of coal concentration measuring device based on image recognition, comprising:
First acquisition unit, for obtaining the first pulverized coal particle image in Target pipe, the Target pipe is to be measured
Measure the pipeline of coal powder density;
Image enhancing unit, for carrying out image enhancement to the first pulverized coal particle image, to obtain the second coal dust
Grain image;
Image segmentation unit, for being split by image segmentation to the second pulverized coal particle image, to obtain
One target area, the first object region are the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment unit obtains the second target area for carrying out binary conversion treatment to the first object region;
Shape filtering processing unit, for carrying out shape filtering processing to second target area, to obtain third mesh
Mark region;
First determination unit, for determining the gross area of pulverized coal particle in the third target area;
Second determination unit, for the gross area and second coal according to pulverized coal particle in the third target area
The image area of powder particles image determines that target coal powder density, the target coal powder density are that the coal dust in the Target pipe is dense
Degree.
Optionally, second determination unit is specifically used for:
The target coal powder density is calculated by following formula:
Wherein, the N is the target coal powder density, the A0For the image area of the second pulverized coal particle image,
The A is the gross area of pulverized coal particle in the third target area, and the k is preset conversion coefficient, the A=∑i∑jf
(i, j), (i, j) ∈ R, the R are the third target area.
Optionally, described device further include:
Second acquisition unit, for obtaining the first coal powder density, first coal powder density is in the Target pipe
Coal powder density carry out the obtained coal powder density of actual measurement;
Unit is corrected, for analyzing first coal powder density and the target coal powder density, to the k
It is corrected.
The third aspect of the embodiment of the present invention provides a kind of processor, and the processor is for running computer program, institute
It executes when stating computer program operation such as the step of above-mentioned various aspects the method.
Fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, is stored thereon with computer journey
Sequence, it is characterised in that: the computer program is when being executed by processor the step of above-mentioned various aspects the method.
As can be seen from the above technical solutions, the first pulverized coal particle image for obtaining Target pipe first, to the first coal dust
Particle image carries out image enhancement, obtains the second pulverized coal particle image, is split to the second pulverized coal particle image, obtains first
Target area, the first object region are the region of pulverized coal particle in the second pulverized coal particle image, are carried out to first object region
Binary conversion treatment and shape filtering processing, obtain third target area, determine pulverized coal particle in third target area later
The gross area determines mesh according to the area of the gross area of pulverized coal particle in third target area and the second pulverized coal particle image later
Mark coal powder density.Due to carrying out image enhancement, image segmentation, binary conversion treatment and form to the pulverized coal particle image got
After filtering processing, coal powder density is determined, so that the coal powder density that measurement obtains is more accurate, later according to coal powder density pair
Boiler combustion optimizes, and auxiliary thermal power generation system realizes more efficient fuel control, so as to improve boiler operatiopn
Stability and economy.
Detailed description of the invention
Fig. 1 is the flow diagram of the Measure Method of Pulverized Coal provided in an embodiment of the present invention based on image recognition;
Fig. 2 is that one embodiment of the coal concentration measuring device provided in an embodiment of the present invention based on image recognition is illustrated
Figure;
Fig. 3 is that the hardware configuration of the coal concentration measuring device provided in an embodiment of the present invention based on image recognition is illustrated
Figure;
Fig. 4 is the embodiment schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention;
Fig. 5 is a kind of embodiment schematic diagram of computer readable storage medium provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the invention provides a kind of Measure Method of Pulverized Coal and relevant device based on image recognition, for surveying
Measure the coal powder density in primary air inlet.
Description and claims of this specification and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein
Or the sequence other than the content of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that
Cover it is non-exclusive include, for example, containing the process, method, system, product or equipment of a series of steps or units need not limit
In step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, produce
The other step or units of product or equipment inherently.
The embodiment of the present application proposes a kind of Measure Method of Pulverized Coal and device based on image recognition, for measuring one
Coal powder density in secondary wind powder pipe.Image Acquisition window is opened up on primary wind and powder pipeline, shoots air hose using microscopic camera
Interior coal dust image obtains pulverized coal flow image information in a non-contact manner;It is surveyed by image enhancement, image segmentation, target area
Amount and etc. measurement primary wind pipe in coal dust distributed density;The coal powder density information that measurement obtains passes through data interface module
Incoming boiler combustion optimization adjust automatically circuit, auxiliary dcs (Distributed Control System,
DCS) system realizes more efficient fuel control, so as to improve boiler operatiopn stability and economy etc..
The coal powder density based on image recognition is surveyed from the angle of the coal concentration measuring device based on image recognition below
Amount method is illustrated, and being somebody's turn to do the coal concentration measuring device based on image recognition can be server, or in server
Functional unit, do not limit specifically.
Referring to Fig. 1, Fig. 1 is one of the Measure Method of Pulverized Coal provided in an embodiment of the present invention based on image recognition
Embodiment schematic diagram, comprising:
101, the first pulverized coal particle image in Target pipe is obtained.
The first coal dust in the present embodiment, in the available Target pipe of coal concentration measuring device based on image recognition
Particle image, wherein Target pipe is the pipeline of coal powder density to be measured.Specifically, selecting one section in primary wind and powder pipeline
Long straight pipeline opens up Image Acquisition window as Target pipe in the middle part of Target pipe, wherein selects the purpose of long straight pipeline
It is to try to that the pulverized coal flow in Image Acquisition window is avoided turbulent phenomenon occur, influences accuracy of measurement.In Image Acquisition window
Be arranged side by side a pair of of light source and video camera, and opposite side and same side light source can be selected in the arrangement of light source, and type selecting is monochromatic scattering side
The light intensity of formula, such pulverized coal particle reflection is uniform and is not in mirror-reflection phenomenon.According to the fineness of pulverized coal particle and
Coal dust flow velocity selects suitable high speed microscope camera, it is desirable that the coal dust image shot is without virtualization, trailing phenomenon, image resolution
Rate is high, and pulverized coal particle quantity is not less than 100 in every frame image.
It should be noted that camera shooting collecting part is required to the high temperature and abrasion environment of tolerance primary wind and powder pipeline.Energy
Enough guarantee within an overhaul life, do not need to safeguard and replaces.In addition the camera shooting collecting part can self-cleaning and maintenance, protect
Demonstrate,prove the service life under dusty.And because, without light, device increases two monochromatic scattering light sources in primary air inlet, point
Not being installed on camera shooting, collecting part is ipsilateral and opposite side, the sequence for enabling the irradiation of two side light sources is selected by controller, so that coal
Powder particles can obtain qualitative picture by the method for reflection.The flow velocity about 20m/S or so of First air in primary air inlet, to keep away
Exempt from captured image to occur blurring and trailing phenomenon, the camera in device selects high speed camera, guarantees image's authenticity.It examines
The diameter for considering captured pulverized coal particle is only micron order, therefore device selects high resolution microscope head bust shot coal dust figure
Picture.
102, image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image.
In the present embodiment, had the following characteristics that by the coal dust image that high speed camera is shot due to the pulverized coal flow in air hose
Three-dimensional distribution cylindrical, according to the distance difference apart from light source, in image existing prospect pulverized coal particle relatively become clear it is reflective,
Have powerful connections the darker reflective of pulverized coal particle, includes more complicated background information in general image, causes image grayscale contrast
It is low.The background with jamming pattern is filtered out by the method for image enhancement, the brightness and contrast of increase foreground graphic as far as possible is
Obtain the important prerequisite of high quality pulverized coal particle image.Therefore, the test device of coal powder density can be with the first pulverized coal particle image
Image enhancement is carried out, to obtain the second pulverized coal particle image, specifically, carrying out histogram equalization to the first pulverized coal particle image
Processing, with the first pulverized coal particle image that obtains that treated;To treated, the first pulverized coal particle image is carried out at smothing filtering
Reason, to obtain the second pulverized coal particle image.Histogram equalization processing can be carried out to the first pulverized coal particle image first, due to
The characteristics of pulverized coal particle image is that picture contrast is low, and intensity profile is more concentrated, and image detail is unobvious.Therefore, to its into
The primary work of row image enhancement is to increase contrast, the detailed information such as grain edges in prominent image.Histogram is image ash
The function of grade is spent, for expressing the statistical information of image grayscale distribution situation, it describes gray level and gray-level pixels number
Between corresponding relationship.Image enhancement is carried out to the first pulverized coal particle using histogram equalization, can effectively widen pulverized coal particle
The intensity profile of image enhances image detail.The central idea of histogram equalization processing is the intensity histogram original image
Figure becomes being uniformly distributed in whole tonal ranges from some gray scale interval for comparing concentration.Histogram equalization is exactly to figure
As carrying out Nonlinear extension, image pixel value is redistributed, keeps the pixel quantity in certain tonal range roughly the same.Histogram
Equalization is exactly that the histogram distribution to the first pulverized coal particle image is changed to be uniformly distributed histogram distribution.
Due to the influence that pulverized coal particle is imaged in background, by existing in the first pulverized coal particle image of histogram equalization
A large amount of background noise information.It needs to filter out this kind of noise using the method for smothing filtering.Smoothing filter is a low pass
Filter, the most commonly used is median filters.The principle of median filtering be with the intermediate value of each point gray value in a neighborhood of pixels come
Instead of the gray value of the pixel, connect so that differing bigger pixel with surrounding pixel gray value and being replaced with surrounding pixel
Close value, to eliminate isolated noise.Assuming that f (i, j) is that position is the gray value of the pixel of (i, j) in image, then filtered through intermediate value
Output valve F (i, j) after wave are as follows:
F (i, j)=Med { f (x, y) }, (x, y) belongs to M;
Wherein, M indicates the Neighbourhood set centered on (i, j), and Med expression takes median to the data in Neighbourhood set.
103, the second pulverized coal particle image is split by image segmentation, to obtain first object region.
In the present embodiment, image segmentation is the principle based on pixel number similitude and space proximity, and image is divided
For several significant regions, and extract the process of target area.First pulverized coal particle image obtains second through image enhancement
After pulverized coal particle image, the contrast of target image and background image is improved, and noise information also obtains centainly
The filtering of degree is laid a good foundation for the dividing processing of image.The characteristics of pulverized coal particle image is prospect particle with bright anti-
Light, and background is more dim, therefore can choose the bimodal thresholding method of gray scale and come out the image segmentation of particle in prospect, with
Just subsequent feature extraction.The algorithm idea of bimodal thresholding method assumes that the gray level of image object and background has significance difference
Different, the grey level histogram of image is in bimodal shape, two of them wave crest respectively correspond the target (i.e. first object region) of image with
Background, and trough is corresponding with the edge of image, then takes segmentation threshold of the minimum trough gray value as Two-peak method between bimodal
Value.Thus, it is possible to be split by image segmentation to the second pulverized coal particle image, to obtain first object region, wherein the
One target area is the region of pulverized coal particle in the second pulverized coal particle image, in addition, background area is also obtained after being split
Domain,
104, binary conversion treatment is carried out to first object region and obtains the second target area.
In the present embodiment, the coal concentration measuring device based on image recognition handle to first object region
To the second target area, wherein the second pulverized coal particle image can form first object region and background area after image segmentation,
For the comparison for further enhancing first object region and background area, binary conversion treatment need to be carried out to image.By background area
Gray value is set to complete white, the gray value in first object region is set to completely black, the binaryzation of image can be realized.
105, shape filtering processing is carried out to the second target area, to obtain third target area.
In the present embodiment, the image after binarization segmentation by illumination and segmentation threshold due to being influenced, easily by the first mesh
A part of object pixel is identified as background or hole noise in mark region, or background is accidentally known and is.Namely the coal based on image recognition
Powder apparatus for measuring concentration can carry out shape filtering processing to the second target area, to obtain third target area.
Need to illustrate when, the major calculations of shape filtering have burn into expansion, opening operation and four kinds of closed operation.Corrode table
Show and the inside of image is filtered, as a result, the periphery of image is removed, while retaining the interior section of image, expands
The outside of image is filtered in expression, as a result, a circle has been expanded in the periphery of image, while retaining the inside of image
Part.On the basis of expanding and corroding two basic operations, it is combined into opening operation and closed operation, wherein opening operation is first corruption
It is expanded after erosion, function can be used for the fritter spot noise in image background, reject the bumps on image border, keep boundary flat
It is sliding;Closed operation is first to expand post-etching, and function is for filling the minuscule hole in image, with first object after removal segmentation
The hole noise formed in region, while connecting adjacent object, its smooth boundary.In the present embodiment, shaped using open and close operator group
State filter, cannot be only used for eliminating hole noise and spot noise after binaryzation in image, and smooth first object region
Image border, be convenient for subsequent parameter measurement.
106, the gross area of pulverized coal particle in third target area is determined.
In the present embodiment, the coal concentration measuring device based on image recognition can calculate third target by following formula
The gross area of pulverized coal particle in region:
A=∑i∑jF (i, j) (i, j) ∈ R;
Wherein, A is the gross area of pulverized coal particle in third target area, and R is third target area.
107, according to the image area of the gross area of pulverized coal particle in third target area and the second pulverized coal particle image
Determine target coal powder density.
In the present embodiment, coal powder density refers to the quality of pulverized coal particle in unit volume.In pulverized coal flow flat image, coal dust
Concentration can be characterized as in image the area in pulverized coal particle region and again the ratio between with total image area.This ratio and actual coal
Powder concentration there are a proportionate relationship, the proportionate relationship can be it is pre-set, specifically, can be calculated by following formula
Target coal powder density, wherein target coal powder density is the coal powder density in Target pipe:
Wherein, N is target coal powder density, A0For the image area of the second pulverized coal particle image, A is in third target area
The gross area of pulverized coal particle, k are preset conversion coefficient.
It should be noted that can be carried out to the coal powder density in Target pipe real after obtaining target coal powder density
Border measurement, obtains the first coal powder density;
First coal powder density and target coal powder density are analyzed, to be corrected to k.
Specifically, according to system detection to coal powder density data compared and analyzed with measured data, to preset
Conversion coefficient is modified, to improve the precision of preset conversion coefficient.
Also need to illustrate when, after obtaining target coal powder density, target coal powder density can be exported.Specifically
, based on image recognition coal concentration measuring device determining target coal powder density can be uploaded to Power Plant DCS System or
Other man-machine interfaces, so that auxiliary thermal power generation system realizes more efficient fuel control, so as to improve boiler operatiopn
Stability and economy.
In conclusion the first pulverized coal particle image of Target pipe is obtained first, to the first pulverized coal particle in the present embodiment
Image carries out image enhancement, obtains the second pulverized coal particle image, is split to the second pulverized coal particle image, obtains first object
Region, the first object region are the region of pulverized coal particle in the second pulverized coal particle image, carry out two-value to first object region
Change processing and shape filtering processing, obtains third target area, determine total face of pulverized coal particle in third target area later
Product, determines target coal according to the area of the gross area of pulverized coal particle in third target area and the second pulverized coal particle image later
Powder concentration.Due to carrying out image enhancement, image segmentation, binary conversion treatment and shape filtering to the pulverized coal particle image got
After processing, coal powder density is determined, so that the coal powder density that measurement obtains is more accurate, later according to coal powder density to boiler
Burning optimizes, and auxiliary thermal power generation system realizes more efficient fuel control, stablizes so as to improve boiler operatiopn
Property and economy.
The embodiment of the present invention is illustrated from the angle of the Measure Method of Pulverized Coal based on image recognition above, below
The embodiment of the present invention is illustrated from the angle of the coal concentration measuring device based on image recognition.
Referring to Fig. 2, the embodiment of the coal concentration measuring device in the embodiment of the present invention based on image recognition includes:
First acquisition unit 201, for obtaining the first pulverized coal particle image in Target pipe, the Target pipe be to
Measure the pipeline of coal powder density;
Image enhancing unit 202, for carrying out image enhancement to the first pulverized coal particle image, to obtain the second coal dust
Particle image;
Image segmentation unit 203, for being split by image segmentation to the second pulverized coal particle image, to obtain
First object region, the first object region are the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment unit 204 obtains the second target area for carrying out binary conversion treatment to the first object region
Domain;
Shape filtering processing unit 205, for carrying out shape filtering processing to second target area, to obtain third
Target area;
First determination unit 206, for determining the gross area of pulverized coal particle in the third target area;
Second determination unit 207, for according to the gross area of pulverized coal particle in the third target area and described
The image area of two pulverized coal particle images determines that target coal powder density, the target coal powder density are the coal in the Target pipe
Powder concentration.
Optionally, second determination unit 207 is specifically used for:
The target coal powder density is calculated by following formula:
Wherein, the N is the target coal powder density, the A0For the image area of the second pulverized coal particle image,
The A is the gross area of pulverized coal particle in the third target area, and the k is preset conversion coefficient, the A=∑i∑jf
(i, j), (i, j) ∈ R, the R are the third target area.
Optionally, described device further include:
Second acquisition unit 208, for obtaining the first coal powder density, first coal powder density is to the Target pipe
Interior coal powder density carries out the coal powder density that actual measurement obtains;
Unit 209 is corrected, for analyzing first coal powder density and the target coal powder density, to institute
K is stated to be corrected.
Interactive mode between each unit of the coal concentration measuring device based on image recognition in the present embodiment is as before
The description in embodiment illustrated in fig. 1 is stated, specific details are not described herein again.
In conclusion the first pulverized coal particle image of Target pipe is obtained first, to the first pulverized coal particle in the present embodiment
Image carries out image enhancement, obtains the second pulverized coal particle image, is split to the second pulverized coal particle image, obtains first object
Region, the first object region are the region of pulverized coal particle in the second pulverized coal particle image, carry out two-value to first object region
Change processing and shape filtering processing, obtains third target area, determine total face of pulverized coal particle in third target area later
Product, determines target coal according to the area of the gross area of pulverized coal particle in third target area and the second pulverized coal particle image later
Powder concentration.Due to carrying out image enhancement, image segmentation, binary conversion treatment and shape filtering to the pulverized coal particle image got
After processing, coal powder density is determined, so that the coal powder density that measurement obtains is more accurate, later according to coal powder density to boiler
Burning optimizes, and auxiliary thermal power generation system realizes more efficient fuel control, stablizes so as to improve boiler operatiopn
Property and economy.
The coal powder density based on image recognition in the embodiment of the present invention is surveyed from the angle of modular functionality entity above
Amount device is described, below from the angle of hardware handles to the coal powder density based on image recognition in the embodiment of the present invention
Measuring device is described.
Referring to Fig. 3, coal concentration measuring device 300 1 implementations based on image recognition in the embodiment of the present invention
Example, comprising:
(wherein the quantity of processor 303 can be with for input unit 301, output unit 302, processor 303 and memory 304
One or more, in Fig. 3 by taking a processor 303 as an example).In some embodiments of the invention, input unit 301, output
Unit 302, processor 303 and memory 304 can be connected by bus or other means, wherein to be connected by bus in Fig. 3
For.
Wherein, the operational order stored by calling memory 304, processor 303, for executing following steps:
The first pulverized coal particle image in Target pipe is obtained, the Target pipe is the pipeline of coal powder density to be measured;
Image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image;
The second pulverized coal particle image is split by image segmentation, to obtain first object region, described
One target area is the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment is carried out to the first object region and obtains the second target area;
Shape filtering processing is carried out to second target area, to obtain third target area;
Determine the gross area of pulverized coal particle in the third target area;
According to the gross area of pulverized coal particle in the third target area and the image of the second pulverized coal particle image
Area determines that target coal powder density, the target coal powder density are the coal powder density in the Target pipe.
Optionally, the gross area and second pulverized coal particle according to pulverized coal particle in the third target area
The image area of image determines that target coal powder density includes:
The target coal powder density is calculated by following formula:
Wherein, the N is the target coal powder density, the A0For the image area of the second pulverized coal particle image,
The A is the gross area of pulverized coal particle in the third target area, and the k is preset conversion coefficient, the A=∑i∑jf
(i, j), (i, j) ∈ R, the R are the third target area.
Optionally, the gross area and second pulverized coal particle according to pulverized coal particle in the third target area
After the image area of image determines target coal powder density, the first coal powder density is obtained, first coal powder density is to described
Coal powder density in Target pipe carries out the coal powder density that actual measurement obtains;
First coal powder density and the target coal powder density are analyzed, to be corrected to the k.
Optionally, described that image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image
Include:
Histogram equalization processing is carried out to the first pulverized coal particle image, with first coal dust that obtains that treated
Particle image;
To treated, the first pulverized coal particle image carries out the disposal of gentle filter, to obtain second pulverized coal particle
Image.
Optionally, the gross area and second pulverized coal particle according to pulverized coal particle in the third target area
After the image area of image determines target coal powder density, the target coal powder density is exported.
Referring to Fig. 4, Fig. 4 is the embodiment schematic diagram of electronic equipment provided in an embodiment of the present invention.
As shown in figure 4, the embodiment of the invention provides a kind of electronic equipment 400, including memory 410, processor 420 and
It is stored in the computer program 411 that can be run on memory 410 and on processor 420, processor 420 executes computer program
It is performed the steps of when 411
The first pulverized coal particle image in Target pipe is obtained, the Target pipe is the pipeline of coal powder density to be measured;
Image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image;
The second pulverized coal particle image is split by image segmentation, to obtain first object region, described
One target area is the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment is carried out to the first object region and obtains the second target area;
Shape filtering processing is carried out to second target area, to obtain third target area;
Determine the gross area of pulverized coal particle in the third target area;
According to the gross area of pulverized coal particle in the third target area and the image of the second pulverized coal particle image
Area determines that target coal powder density, the target coal powder density are the coal powder density in the Target pipe.
In the specific implementation process, when processor 420 executes computer program 411, the corresponding embodiment of Fig. 1 may be implemented
Middle any embodiment.
Since the electronic equipment that the present embodiment is introduced is that the coal dust based on image recognition is dense in the implementation embodiment of the present invention
Equipment used by measurement method is spent, so based on method described in the embodiment of the present invention, those skilled in the art
The specific embodiment and its various change form that the electronic equipment of the present embodiment can be understood, so herein for the electronics
How equipment realizes that the method in the embodiment of the present invention is no longer discussed in detail, as long as those skilled in the art implement the present invention
Equipment used by method in embodiment belongs to the range of the invention to be protected.
Referring to Fig. 5, Fig. 5 is a kind of embodiment signal of computer readable storage medium provided in an embodiment of the present invention
Figure.
As shown in figure 5, present embodiments providing a kind of computer readable storage medium 500, it is stored thereon with computer journey
Sequence 511, the computer program 511 realize following steps when being executed by processor:
The first pulverized coal particle image in Target pipe is obtained, the Target pipe is the pipeline of coal powder density to be measured;
Image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image;
The second pulverized coal particle image is split by image segmentation, to obtain first object region, described
One target area is the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment is carried out to the first object region and obtains the second target area;
Shape filtering processing is carried out to second target area, to obtain third target area;
Determine the gross area of pulverized coal particle in the third target area;
According to the gross area of pulverized coal particle in the third target area and the image of the second pulverized coal particle image
Area determines that target coal powder density, the target coal powder density are the coal powder density in the Target pipe.
In the specific implementation process, Fig. 1 corresponding embodiment may be implemented when which is executed by processor
Middle any embodiment.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to the method for the embodiment of the present invention, equipment (system) and computer program product flow chart and/
Or block diagram describes.It should be understood that each process that can be realized by computer program instructions in flowchart and/or the block diagram and/
Or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer program instructions
To general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate one
A machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that the embodiment of the present invention can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the present invention
Form.It is deposited moreover, the present invention can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only the embodiment of the present invention, are not intended to restrict the invention.To those skilled in the art,
The invention may be variously modified and varied.It is all within the spirit and principles of the present invention made by any modification, equivalent replacement,
Improve etc., it should be included within scope of the presently claimed invention.
Claims (10)
1. a kind of Measure Method of Pulverized Coal based on image recognition characterized by comprising
The first pulverized coal particle image in Target pipe is obtained, the Target pipe is the pipeline of coal powder density to be measured;
Image enhancement is carried out to the first pulverized coal particle image, to obtain the second pulverized coal particle image;
The second pulverized coal particle image is split by image segmentation, to obtain first object region, first mesh
Mark the region that region is pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment is carried out to the first object region and obtains the second target area;
Shape filtering processing is carried out to second target area, to obtain third target area;
Determine the gross area of pulverized coal particle in the third target area;
According to the image area of the gross area of pulverized coal particle in the third target area and the second pulverized coal particle image
Determine that target coal powder density, the target coal powder density are the coal powder density in the Target pipe.
2. the method according to claim 1, wherein described according to pulverized coal particle in the third target area
The image area of the gross area and the second pulverized coal particle image determines that target coal powder density includes:
The target coal powder density is calculated by following formula:
Wherein, the N is the target coal powder density, the A0For the image area of the second pulverized coal particle image, the A
For the gross area of pulverized coal particle in the third target area, the k is preset conversion coefficient, the A=∑i∑jF (i,
J), (i, j) ∈ R, the R are the third target area.
3. according to the method described in claim 2, it is characterized in that, described according to pulverized coal particle in the third target area
After the image area of the gross area and the second pulverized coal particle image determines target coal powder density, the method also includes:
The first coal powder density is obtained, first coal powder density is to carry out actual measurement to the coal powder density in the Target pipe
Obtained coal powder density;
First coal powder density and the target coal powder density are analyzed, to be corrected to the k.
4. the method according to claim 1, wherein described carry out image increasing to the first pulverized coal particle image
By force, include: to obtain the second pulverized coal particle image
Histogram equalization processing is carried out to the first pulverized coal particle image, with first pulverized coal particle that obtains that treated
Image;
To treated, the first pulverized coal particle image carries out the disposal of gentle filter, to obtain the second pulverized coal particle figure
Picture.
5. method according to claim 1 to 4, which is characterized in that described according to the third target area
It is described after the image area of the gross area of interior pulverized coal particle and the second pulverized coal particle image determines target coal powder density
Method further include:
The target coal powder density is exported.
6. a kind of coal concentration measuring device based on image recognition characterized by comprising
First acquisition unit, for obtaining the first pulverized coal particle image in Target pipe, the Target pipe is coal to be measured
The pipeline of powder concentration;
Image enhancing unit, for carrying out image enhancement to the first pulverized coal particle image, to obtain the second pulverized coal particle figure
Picture;
Image segmentation unit, for being split by image segmentation to the second pulverized coal particle image, to obtain the first mesh
Region is marked, the first object region is the region of pulverized coal particle in the second pulverized coal particle image;
Binary conversion treatment unit obtains the second target area for carrying out binary conversion treatment to the first object region;
Shape filtering processing unit, for carrying out shape filtering processing to second target area, to obtain third target area
Domain;
First determination unit, for determining the gross area of pulverized coal particle in the third target area;
Second determination unit, for the gross area and second coal dust according to pulverized coal particle in the third target area
The image area of grain image determines that target coal powder density, the target coal powder density are the coal powder density in the Target pipe.
7. device according to claim 6, which is characterized in that second determination unit is specifically used for:
The target coal powder density is calculated by following formula:
Wherein, the N is the target coal powder density, the A0For the image area of the second pulverized coal particle image, the A
For the gross area of pulverized coal particle in the third target area, the k is preset conversion coefficient, the A=∑i∑jF (i,
J), (i, j) ∈ R, the R are the third target area.
8. device according to claim 8, which is characterized in that described device further include:
Second acquisition unit, for obtaining the first coal powder density, first coal powder density is to the coal in the Target pipe
Powder concentration carries out the coal powder density that actual measurement obtains;
Unit is corrected, for analyzing first coal powder density and the target coal powder density, to carry out to the k
Correction.
9. a kind of processor, which is characterized in that the processor is for running computer program, when the computer program is run
It executes such as the step of any one of claim 1 to 5 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program
It is realized when being executed by processor such as the step of any one of claim 1 to 5 the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810809081.8A CN108956400A (en) | 2018-07-20 | 2018-07-20 | A kind of Measure Method of Pulverized Coal and device based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810809081.8A CN108956400A (en) | 2018-07-20 | 2018-07-20 | A kind of Measure Method of Pulverized Coal and device based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108956400A true CN108956400A (en) | 2018-12-07 |
Family
ID=64464079
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810809081.8A Pending CN108956400A (en) | 2018-07-20 | 2018-07-20 | A kind of Measure Method of Pulverized Coal and device based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108956400A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113160225A (en) * | 2021-05-20 | 2021-07-23 | 神华准格尔能源有限责任公司 | Strip mine dust concentration identification method, storage medium and electronic equipment |
CN114046748A (en) * | 2021-09-27 | 2022-02-15 | 广州超音速自动化科技股份有限公司 | Particle detection method, device and system for lithium battery diaphragm |
US11475552B2 (en) * | 2019-12-03 | 2022-10-18 | Purdue Research Foundation | Method and apparatus for sensing suspended dust concentration |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101153850A (en) * | 2006-09-30 | 2008-04-02 | 长安大学 | Method and system for detecting asphalt mixture |
CN101393108A (en) * | 2008-10-10 | 2009-03-25 | 南京航空航天大学 | Oil liquid abrasive grain on-line monitoring method and system |
CN101799393A (en) * | 2010-01-28 | 2010-08-11 | 天津大学 | Automatic quantitative evaluation method of microstructure character of particulate matters discharged by diesel engine |
CN103278431A (en) * | 2013-04-22 | 2013-09-04 | 西安交通大学 | On-line monitoring and analyzing method of lubrication oil wear particles based on video acquisition |
WO2014161585A1 (en) * | 2013-04-05 | 2014-10-09 | Bastidas García Óscar | Particle counting system adaptable to an optical instrument |
CN107844683A (en) * | 2017-10-17 | 2018-03-27 | 华东医药(杭州)基因科技有限公司 | A kind of computational methods of digital pcr concentration of liquid drops |
-
2018
- 2018-07-20 CN CN201810809081.8A patent/CN108956400A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101153850A (en) * | 2006-09-30 | 2008-04-02 | 长安大学 | Method and system for detecting asphalt mixture |
CN101393108A (en) * | 2008-10-10 | 2009-03-25 | 南京航空航天大学 | Oil liquid abrasive grain on-line monitoring method and system |
CN101799393A (en) * | 2010-01-28 | 2010-08-11 | 天津大学 | Automatic quantitative evaluation method of microstructure character of particulate matters discharged by diesel engine |
WO2014161585A1 (en) * | 2013-04-05 | 2014-10-09 | Bastidas García Óscar | Particle counting system adaptable to an optical instrument |
CN103278431A (en) * | 2013-04-22 | 2013-09-04 | 西安交通大学 | On-line monitoring and analyzing method of lubrication oil wear particles based on video acquisition |
CN107844683A (en) * | 2017-10-17 | 2018-03-27 | 华东医药(杭州)基因科技有限公司 | A kind of computational methods of digital pcr concentration of liquid drops |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11475552B2 (en) * | 2019-12-03 | 2022-10-18 | Purdue Research Foundation | Method and apparatus for sensing suspended dust concentration |
CN113160225A (en) * | 2021-05-20 | 2021-07-23 | 神华准格尔能源有限责任公司 | Strip mine dust concentration identification method, storage medium and electronic equipment |
CN114046748A (en) * | 2021-09-27 | 2022-02-15 | 广州超音速自动化科技股份有限公司 | Particle detection method, device and system for lithium battery diaphragm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108956400A (en) | A kind of Measure Method of Pulverized Coal and device based on image recognition | |
US9846929B2 (en) | Fast density estimation method for defect inspection application | |
CN111105405B (en) | New energy lithium battery surface defect detection method based on adaptive deep learning | |
CN108009529B (en) | Forest fire smoke video target detection method based on characteristic root and hydrodynamics | |
CN111982910B (en) | Weak supervision machine vision detection method and system based on artificial defect simulation | |
JP6448065B2 (en) | Image processing system, image processing method, and image processing program | |
CN111476758B (en) | Defect detection method and device for AMOLED display screen, computer equipment and storage medium | |
CN107918953B (en) | Three-dimensional space-based laser scanning power line point cloud extraction method and device | |
CN110544261A (en) | Blast furnace tuyere coal injection state detection method based on image processing | |
CN111065915B (en) | Apparatus for optimizing external inspection of target object and method thereof | |
KR20080096263A (en) | System for processing digit image, and method thereof | |
CN108492291A (en) | A kind of photovoltaic silicon chip Defect Detection system and method based on CNN segmentations | |
CN115100168A (en) | System and method for detecting sub-surface defects under wafer back sealing film | |
Liberzon et al. | XPIV–Multi-plane stereoscopic particle image velocimetry | |
CN108615039A (en) | Cartridge case defect automatic testing method based on computer vision | |
Sun et al. | Deep learning-assisted automated sewage pipe defect detection for urban water environment management | |
Wang et al. | Research of ore particle size detection based on image processing | |
CN115597494B (en) | Precision detection method and system for prefabricated part preformed hole based on point cloud | |
Leng et al. | On analysis of circle moments and texture features for cartridge images recognition | |
Asano | Texture analysis using morphological pattern spectrum and optimization of structuring elements | |
CN109035324A (en) | A kind of coal dust flow-speed measurement method and device based on image recognition | |
Liancheng et al. | Ore granularity detection and analysis system based on image processing | |
Wang et al. | Deep learning based distortion restoration and defect segmentation from linear scanning camera images | |
CN110321886A (en) | A kind of character area recognition methods and device | |
CN111932515B (en) | Short circuit detection method and system for product residual defects and defect classification system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181207 |