CN109269951A - Floating tail-coal ash content, concentration, coarse granule detection method of content based on image - Google Patents
Floating tail-coal ash content, concentration, coarse granule detection method of content based on image Download PDFInfo
- Publication number
- CN109269951A CN109269951A CN201811038931.5A CN201811038931A CN109269951A CN 109269951 A CN109269951 A CN 109269951A CN 201811038931 A CN201811038931 A CN 201811038931A CN 109269951 A CN109269951 A CN 109269951A
- Authority
- CN
- China
- Prior art keywords
- image
- concentration
- coarse granule
- content
- coal
- 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
- 239000008187 granular material Substances 0.000 title claims abstract description 56
- 238000007667 floating Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 239000010883 coal ash Substances 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 46
- 239000002956 ash Substances 0.000 claims abstract description 43
- 239000003245 coal Substances 0.000 claims abstract description 39
- 238000005188 flotation Methods 0.000 claims abstract description 37
- 239000000284 extract Substances 0.000 claims abstract description 8
- 239000002245 particle Substances 0.000 claims description 35
- 239000000126 substance Substances 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 239000012530 fluid Substances 0.000 claims description 8
- 239000003550 marker Substances 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 239000003250 coal slurry Substances 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 239000005304 optical glass Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000005273 aeration Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000012800 visualization 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 present invention relates to floating tail-coal mine technical fields, provide a kind of floating tail-coal ash content based on image, concentration, coarse granule detection method of content, this method extracts image for different ash contents, the flotation tailing of concentration, coarse granule content respectively, establishes the feature database based on characteristics of image;Ash content, concentration, coarse granule content prediction model according to feature database building flotation tailing;Flotation tailing image to be detected is extracted, according to the prediction model, determines ash content, the concentration, coarse granule content of flotation tailing.The invention has the benefit that the problem for avoiding the subjective factor of artificial observation big;Detection time is short, and frequency is high, meets production needs;It is high-efficient, worker's working strength is reduced, it can be achieved that the workshop personnel reduction, reduces productive manpower cost.
Description
Technical field
The present invention relates to floating tail-coal mine technical field, in particular to a kind of floating tail-coal ash content based on image, concentration,
Coarse granule detection method of content.
Background technique
With the continuous promotion of industrial process automation integral level, the automatic control and intelligent control of coal slime flotation process
Also it is increasingly valued by people.The key link of floatation process intelligent control first is that realize product quality online inspection
It surveys, including floatation clean coal and tail coal.However the missing of correlation detection technology and sensor seriously limits flotation intelligence hair
Exhibition.The quality testing research of floating product focuses mostly in terms of floatation clean coal all the time, and has ignored floating tail-coal.Flotation
Tail coal quality is of crucial importance realization floatation process closed optimized control as important feedback information.
In coal slime flotation actual production process, site operation personnel relies primarily on gross visualization tail coal color judgement ash
Point, while feeling is grabbed by hand and judges that flotation tailing with the presence or absence of " running thick " problem, carries out dosing, bubble on this basis
The adjustment of the variables such as foam layer thickness, aeration quantity, to guarantee floating product quality.
Summary of the invention
The object of the invention is to overcome the deficiencies of the prior art and provide a kind of floating tail-coal ash content based on image,
Concentration, coarse granule detection method of content, are realized using the method for machine vision to floating tail-coal ash content, concentration and coarse granule
The detection of content.
Technical scheme is as follows:
A kind of floating tail-coal ash content based on image, concentration, coarse granule detection method of content, this method comprises:
For different ash contents, the flotation tailing of concentration, coarse granule content, image is extracted respectively, is established special based on image
The feature database of sign;
Ash content, concentration, coarse granule content prediction model according to feature database building flotation tailing;
Flotation tailing image to be detected is extracted, according to the prediction model, determines ash content, the concentration, thick of flotation tailing
Grain content.
Further, ash content detects analyzed image by tight shot, colored CCD industrial camera and annular LED light source
The image capturing system of composition is shot, and takes direct illumination mode;The image that Concentration Testing and coarse granule content detection are analyzed
The image capturing system shooting being made of doubly telecentric camera lens, black-white CCD industrial camera and source of parallel light, takes backlight transmission to shine
Bright mode.
Further, ash content detection includes the following steps:
Step 1, the flotation tailing sample and color image for acquiring various concentration, different ash contents, and according to chemical examination ash content knot
Fruit is classified;
Step 2 pre-processes image, removes the noise in image;
Step 3 extracts R, G, B, Y, U, V, H, S, I component feature of the image under RGB, YUV, HSI color space domain;
Step 4 establishes same concentrations tailings ash content regression model, carries out the public affairs that Function Fitting obtains using least square method
Formula coefficient and fitting result select the color difference variable C from R, G, B three-component linear combination according to models fitting effectrgb
The foundation of same concentrations coal slurry ash content soft-sensing model is carried out as model independent variable, model form is as follows:
Wherein y is that model ash content exports as a result, a1、b1、c1、k1、k2For coefficient;
Step 5 introduces concentration correction function, as follows:
Wherein MsTail coal coal-water fluid concentration is represented, j is unknowm coefficient;
Step 6, building floating tail-coal ash content soft-sensing model form are as follows:
Ash=a1ln{(k1R+k2G-B)/[1+exp(j*Ms)]+b1}+c1
Wherein Ash indicates tail coal ash content.
Step 7 analyzes flotation tailing image to be detected using above-mentioned soft-sensing model, detects tailings ash content.
Further, Concentration Testing includes the following steps:
Step 1, the flotation tailing sample and black white image for acquiring various concentration, and divided according to chemical examination concentration results
Class;
Step 2 pre-processes image, removes the noise in image;
Step 3, the gray feature for extracting image;
Step 4, the prediction model for establishing coal-water fluid concentration select image grayscale mean value to carry out coal-water fluid concentration soft-sensing model
Foundation, carry out Function Fitting obtained equation coefficients and fitting result using least square method, model form is as follows:
Wherein MSFor flotation tailing concentration, Gray is image grayscale mean value, a2、b2For coefficient.
Step 5 analyzes flotation tailing image to be detected using above-mentioned soft-sensing model, detects tailings concentration.
Further, Concentration Testing includes the following steps:
Step 1, the flotation tailing sample and black white image for acquiring various concentration, and divided according to chemical examination concentration results
Class;
Step 2, using optical glass gridiron pattern calibration for cameras, determine X-comers using Harris angle point algorithm, so
Calculate the number of pixels between all vertical and horizontal adjacent two vertex within sweep of the eye afterwards, i.e., the Euclidean between adjacent vertex away from
From then calculating full-size(d) representated by each pixel;
Step 3 pre-processes image, removes the noise in image;
Step 4 carries out binary conversion treatment to pretreated image, then by Morphological scale-space to target
Grain edge eliminates the non-targeted particle of a large amount of agglomerates while carrying out smooth;For the imperfect particle figure for avoiding visual field border
As impact analysis as a result, the particle being connected with image boundary need to be weeded out;
Step 5, using based on apart from variable and marker character control watershed algorithm the adhesion particle in image is divided
It cuts;Range conversion should be carried out first, adjusted the distance after transformation by the extension maximum transformation H-maxima technology in mathematical morphology
Image in Local modulus maxima extract, Local modulus maxima is merged using expanding method in morphology, is obtained
To inner marker point and inner marker image fgm, over-segmentation is eliminated, a secondary ridge operation obtains external label symbol and external mark
Remember image fbm;It is then based on the interior external labeling got, using forcing minimum technology to modify former gradient image, is connect down
It carries out two secondary ridge operations, is finally completed segmentation;
Step 6, to after segmentation particle image carry out edge detection, then extract target coal particle distributed number and
Geometric parameter;
Step 7 establishes floating tail-coal coarse granule content prediction model, shoots several pictures respectively, to grain graininess and
Coarse granule number is counted, and coarse granule number average value is calculated, the coarse granule number average value that image method detects and thick
Apparent linear relationship is presented in granule content, carries out the equation coefficients and fitting knot that Function Fitting obtains using least square method
Fruit, the floating tail-coal coarse granule content prediction model finally established, form such as following formula:
Y=a3x+b3
Y indicates floating tail-coal coarse granule content;X indicates the coarse granule number that image method measures, a3、b3For coefficient.
Step 8 analyzes flotation tailing image to be detected using above-mentioned soft-sensing model, detects tailing coarse granule content.
Further, in step 6, the geometric parameter of target coal particle includes: that particle area, particle circumference, equivalent circular are straight
Diameter, grain shape index and ovality parameter.
Further, in step 7, the coal grain particle size Lambda characterization based on image method is thrown using equivalent diameter, i.e. particle
Shadow area equivalent diameter.
Further, the coarse grained granularity of floating tail-coal is greater than 250um.
The invention has the benefit that the problem for avoiding the subjective factor of artificial observation big;Detection time is short, and frequency is high,
Meet production needs;It is high-efficient, worker's working strength is reduced, it can be achieved that the workshop personnel reduction, reduces productive manpower cost.
Specific embodiment
The specific embodiment of the invention is discussed in detail below.It should be noted that technology described in following embodiments is special
The combination of sign or technical characteristic is not construed as isolated, they can be combined with each other to reach better skill
Art effect.
Experiment sample of the embodiment of the present invention comes from Liu Wan coal preparation plant, two plant process of Liu Wan coal preparation plant coal separation are as follows: 50-1mm
Grade raw coal is sorted using dense medium cyclone, and 1mm is classified below by way of multi-stage PCE cyclone, partition size
0.25mm, wherein overflow 1-0.25mm grade is sorted using TBS separation of coarse slime machine, the coal slime of 0.25-0mm grade into
Enter 4 XJM-S-20 floatation systems.The present embodiment research object is the tail coal of coal slime flotation.
The embodiment of the invention provides a kind of detections based on flotation tailing image analysis ash content, concentration, coarse granule content
Method.In the present invention, ash content detects analyzed image by tight shot, colored CCD industrial camera and annular LED light source group
At image capturing system shooting, take direct illumination mode;The image that Concentration Testing and coarse granule content detection are analyzed by
The image capturing system shooting of doubly telecentric camera lens, black-white CCD industrial camera and source of parallel light composition, takes backlight transmission to illuminate
Mode.The method of the present invention is based on characteristics of image first with traditional tailings ash content, concentration, the building of coarse granule content detection means
Feature database, and construct tailings ash content, concentration, coarse granule content prediction model.
Technical solution used in the embodiment of the present invention are as follows:
One, ash content detects:
1, the flotation tailing sample and color image of various concentration difference ash content are acquired by professional, and according to chemical examination
Ash content result is classified;
2, image is pre-processed, removes the noise in image, improve picture quality, prominent useful information.
3, R, G, B, Y, U, V, H, S, I component feature of the image under RGB, YUV, HSI color space domain are extracted;
4, it establishes same concentrations tailings ash content regression model, screens existing Color characteristics parameters at present and self-built
Series of features parameter carries out the equation coefficients and fitting result that Function Fitting obtains using least square method, quasi- according to model
Effect is closed, has selected the color difference variable Crgb from R, G, B three-component linear combination to carry out as model independent variable identical
The foundation of concentration coal slurry ash content soft-sensing model, model form are as follows:
Wherein y is that same concentrations tailings ash content regression model ash content exports result.
Fitting parameter and evaluation index are as shown in table 1.
1 tail coal ash content soft-sensing model fitting parameter of table and evaluation index
R in table2For the coefficient of determination, it is mainly used to evaluate fitting effect and quality, r2Closer to 1, illustrate that regression equation is quasi-
The effect of conjunction is better;r2Closer to 0, illustrate that fitting effect is poorer.RMSE is root-mean-square error, MRE is averagely opposite misses
Difference, MaxRE are maximum relative error.
5, concentration correction function is introduced
It is concentration to CrgbThe correction function of value, MsRepresent tail coal coal-water fluid concentration.Construct floating tail-coal ash content soft-sensing model
Form is as follows:
Ash=31.171ln { (0.266R+0.87G-B)/[1+exp (- 0.186Ms)]+1.592}-34.026
Wherein Ash indicates tail coal ash content.
Two, Concentration Testing:
1, the flotation tailing sample and black white image of various concentration are acquired by professional, and according to chemical examination concentration results
Classify;
2, image is pre-processed, removes the noise in image, improve picture quality, prominent useful information.
3, the gray feature of image is extracted;
4, establish the prediction model of coal-water fluid concentration, screen existing gray feature parameter at present, using least square method into
Line function is fitted to obtain equation coefficients and fitting result, and according to models fitting effect, selection has image grayscale mean value to carry out coal
The foundation of concentration soft-sensing model is starched, model form is as follows:
Wherein MS is flotation tailing concentration.
Fitting parameter and evaluation index are shown in Table 2.
2 concentration prediction model fitting parameter of table and evaluation index
Three, coarse granule content detection:
1, the flotation tailing sample and black white image of different coarse granule contents are acquired by professional, and thick according to chemical examination
Granule content result is classified;
2, using optical glass gridiron pattern calibration for cameras, X-comers is determined using Harris angle point algorithm, are then counted
The number of pixels between all vertical and horizontal adjacent two vertex within sweep of the eye, i.e. Euclidean distance between adjacent vertex are calculated, after
And calculate full-size(d) representated by each pixel.
3, image is pre-processed, removes the noise in image, improve picture quality, prominent useful information.
4, binary conversion treatment is carried out to pretreated image, then by Morphological scale-space to target particles side
Edge eliminates the non-targeted particle of a large amount of agglomerates while carrying out smooth.For the imperfect particle image shadow for avoiding visual field border
Analysis is rung as a result, the particle being connected with image boundary need to be weeded out.
5, using based on apart from variable and marker character control watershed algorithm the adhesion particle in image is split.It is first
Range conversion should be first carried out, is adjusted the distance by extension maximum transformation (H-maxima) technology in mathematical morphology transformed
Local modulus maxima in image extracts, and is merged, is obtained to Local modulus maxima using expanding method in morphology
Inner marker point and inner marker image fgm, eliminate over-segmentation, and a secondary ridge operation obtains external label symbol and external mark
Remember image fbm, be then based on the interior external labeling got, using forcing minimum technology to modify former gradient image, connects down
It carries out two secondary ridge operations, finally obtains ideal segmentation effect.
6, edge detection, the distributed number of the target coal particle then extracted and several are carried out to the particle image after segmentation
What parameter (particle area, particle circumference, equivalent diameter, grain shape index and ovality parameter etc.).
7, floating tail-coal coarse granule content prediction model is established, five pictures is shot respectively, utilizes method as described above
Grain graininess and coarse granule (granularity is greater than 250um) number are counted, coal grain particle size Lambda characterization of this patent based on image method
Using equivalent diameter, i.e. grain projected area equivalent diameter, coarse granule number average value, image method detection are calculated
Apparent linear relationship is presented in coarse granule number average value and coarse granule content out, and it is quasi- to carry out function using least square method
Conjunction obtains equation coefficients and fitting result, the floating tail-coal coarse granule content prediction model finally established, form such as following formula
Y=0.2342x+2.0655
Y indicates floating tail-coal coarse granule content;X indicates the coarse granule number that image method measures.
The testing result of different coarse granule content coal slurry imaged particles is shown in Table 3.
The different coarse granule content coal slurry imaged particles testing results of table 3
Although having been presented for several embodiments of the present invention herein, it will be appreciated by those of skill in the art that
Without departing from the spirit of the invention, the embodiments herein can be changed.Above-described embodiment is only exemplary,
It should not be using the embodiments herein as the restriction of interest field of the present invention.
Claims (7)
1. floating tail-coal ash content, concentration, coarse granule detection method of content based on image, which is characterized in that this method comprises:
For different ash contents, the flotation tailing of concentration, coarse granule content, image is extracted respectively, is established based on characteristics of image
Feature database;
Ash content, concentration, coarse granule content prediction model according to feature database building flotation tailing;
Flotation tailing image to be detected is extracted, according to the prediction model, determines that ash content, concentration, the coarse granule of flotation tailing contain
Amount.
2. the method as described in claim 1, which is characterized in that ash content detects analyzed image by tight shot, colored CCD
The image capturing system shooting of industrial camera and annular LED light source composition, takes direct illumination mode;Concentration Testing and coarse granule
The image capturing system that the image that content detection is analyzed is made of doubly telecentric camera lens, black-white CCD industrial camera and source of parallel light
Shooting, takes backlight transmission lighting method.
3. the method as described in claim 1, which is characterized in that ash content detection includes the following steps:
Step 1, acquisition various concentration, different ash content flotation tailing sample and color image, and according to chemical examination ash content result into
Row classification;
Step 2 pre-processes image, removes the noise in image;
Step 3 extracts R, G, B, Y, U, V, H, S, I component feature of the image under RGB, YUV, HSI color space domain;
Step 4 establishes same concentrations tailings ash content regression model, carries out the formula system that Function Fitting obtains using least square method
Several and fitting result selects the color difference variable C from R, G, B three-component linear combination according to models fitting effectrgbAs
Model independent variable carries out the foundation of same concentrations coal slurry ash content soft-sensing model, and model form is as follows:
Wherein y is that model ash content exports as a result, a1、b1、c1、k1、k2For coefficient;
Step 5 introduces concentration correction function, as follows:
Wherein MsTail coal coal-water fluid concentration is represented, j is coefficient;
Step 6, building floating tail-coal ash content soft-sensing model form are as follows:
Ash=a1ln{(k1R+k2G-B)/[1+exp(j*Ms)]+b1}+c1
Wherein Ash indicates tail coal ash content.
Step 7 analyzes flotation tailing image to be detected using the soft-sensing model in step 6, detects tailings ash content.
4. the method as described in claim 1, which is characterized in that Concentration Testing includes the following steps:
Step 1, the flotation tailing sample and black white image for acquiring various concentration, and classified according to chemical examination concentration results;
Step 2 pre-processes image, removes the noise in image;
Step 3, the gray feature for extracting image;
Step 4, the prediction model for establishing coal-water fluid concentration select image grayscale mean value to carry out building for coal-water fluid concentration soft-sensing model
It is vertical, the equation coefficients and fitting result that Function Fitting obtains are carried out using least square method, model form is as follows:
Wherein MSFor flotation tailing concentration, Gray is image grayscale mean value, a2、b2For coefficient.
Step 5 utilizes the model analysis flotation tailing image to be detected in step 4, detection tailings concentration.
5. the method as described in claim 1, which is characterized in that coarse granule content detection includes the following steps:
The flotation tailing sample and black white image of step 1, the different coarse granule contents of acquisition, and according to chemical examination coarse granule content results
Classify;
Step 2, using optical glass gridiron pattern calibration for cameras, determine X-comers using Harris angle point algorithm, then count
The number of pixels between all vertical and horizontal adjacent two vertex within sweep of the eye, i.e. Euclidean distance between adjacent vertex are calculated, after
And calculate full-size(d) representated by each pixel;
Step 3 pre-processes image, removes the noise in image;
Step 4 carries out binary conversion treatment to pretreated image, then by Morphological scale-space to target particles side
Edge eliminates the non-targeted particle of a large amount of agglomerates while carrying out smooth;To avoid the imperfect particle image of visual field border from influencing
Analysis is as a result, the particle being connected with image boundary need to be weeded out;
Step 5, using based on apart from variable and marker character control watershed algorithm the adhesion particle in image is split;It is first
Range conversion should be first carried out, is adjusted the distance transformed image by the extension maximum transformation H-maxima technology in mathematical morphology
In Local modulus maxima extract, Local modulus maxima is merged using expanding method in morphology, obtains inside
Mark point and inner marker image fgm, over-segmentation is eliminated, a secondary ridge operation obtains external label symbol and external label image
fbm;It is then based on the interior external labeling got, using forcing minimum technology to modify former gradient image, followed by two
Secondary ridge operation is finally completed segmentation;
Step 6 carries out edge detection to the particle image after segmentation, then extracts the distributed number and geometry of target coal particle
Parameter;
Step 7 establishes floating tail-coal coarse granule content prediction model, several pictures is shot respectively, to grain graininess and thick
Grain number mesh is counted, and coarse granule number average value, the coarse granule number average value and coarse granule that image method detects are calculated
Apparent linear relationship is presented in content, carries out the equation coefficients and fitting result that Function Fitting obtains using least square method, most
The floating tail-coal coarse granule content prediction model established eventually, form such as following formula:
Y=a3x+b3
Y indicates floating tail-coal coarse granule content;X indicates the coarse granule number that image method measures, a3、b3For coefficient.
Step 8 utilizes the model analysis flotation tailing image to be detected in step 7, detection tailing coarse granule content.
6. method as claimed in claim 5, which is characterized in that in step 6, the geometric parameter of target coal particle includes: particle
Area, particle circumference, equivalent diameter, grain shape index and ovality parameter.
7. method as claimed in claim 5, which is characterized in that in step 7, what the coal grain particle size Lambda characterization based on image method used
It is equivalent diameter, i.e., grain projected area equivalent diameter, coarse granule refer to that equivalent diameter is greater than the particle of 250um.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811038931.5A CN109269951B (en) | 2018-09-06 | 2018-09-06 | Image-based flotation tailing ash content, concentration and coarse particle content detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811038931.5A CN109269951B (en) | 2018-09-06 | 2018-09-06 | Image-based flotation tailing ash content, concentration and coarse particle content detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109269951A true CN109269951A (en) | 2019-01-25 |
CN109269951B CN109269951B (en) | 2021-12-03 |
Family
ID=65188462
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811038931.5A Active CN109269951B (en) | 2018-09-06 | 2018-09-06 | Image-based flotation tailing ash content, concentration and coarse particle content detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109269951B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110070537A (en) * | 2019-04-25 | 2019-07-30 | 清华大学 | The granularity of still image particle and the intelligent identification Method of sphericity and device |
CN110362710A (en) * | 2019-08-25 | 2019-10-22 | 贵州大学 | Pulp density test macro and method based on image recognition technology |
CN110399888A (en) * | 2019-07-25 | 2019-11-01 | 西南民族大学 | A kind of go judgment system based on MLP neural network and computer vision |
CN110647887A (en) * | 2019-07-23 | 2020-01-03 | 太原理工大学 | Method for extracting internal marker in coal slime flotation foam image segmentation |
CN110766709A (en) * | 2019-10-30 | 2020-02-07 | 成都理工大学 | Landslide particle accumulation characteristic identification method based on image identification |
CN110766699A (en) * | 2019-07-22 | 2020-02-07 | 中南大学 | Texture feature measurement method based on Euclidean distance judgment |
CN112798467A (en) * | 2020-12-15 | 2021-05-14 | 中煤科工集团唐山研究院有限公司 | Intelligent online ash detection device and detection method based on high-speed microscopic vision |
CN113191452A (en) * | 2021-05-21 | 2021-07-30 | 中国矿业大学(北京) | Coal ash content online detection system based on deep learning and detection method thereof |
CN113658212A (en) * | 2021-08-13 | 2021-11-16 | 青岛科技大学 | Image prediction method |
CN114791480A (en) * | 2022-03-14 | 2022-07-26 | 国能智深控制技术有限公司 | Soft measurement method and device for dense medium ash content of coal preparation plant |
CN114897835A (en) * | 2022-05-16 | 2022-08-12 | 中国矿业大学 | Coal product ash content real-time detection system based on image |
CN115494096A (en) * | 2022-10-24 | 2022-12-20 | 青岛理工大学 | Metallurgical solid waste identification method and system based on X-ray diffraction spectrum |
CN115861235A (en) * | 2022-12-05 | 2023-03-28 | 中国矿业大学 | Flotation tailing ash content prediction method based on multi-feature data fusion |
WO2023179344A1 (en) * | 2022-03-23 | 2023-09-28 | 中国矿业大学 | Intelligent flotation agent addition system based on flotation coal tailing slurry detection, and agent addition method |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1065496A2 (en) * | 1999-06-29 | 2001-01-03 | Tripath Imaging, Inc. | Method and apparatus for deriving separate images from multiple chromogens in a biological specimen |
US20020016068A1 (en) * | 2000-08-07 | 2002-02-07 | Hiroyuki Nakano | Method and its apparatus for detecting floating particles in a plasma processing chamber and an apparatus for processing a semiconductor device |
CN102297822A (en) * | 2010-06-22 | 2011-12-28 | 中国矿业大学 | Method for predicting ash content of coal particles by utilizing image analysis |
CN103267762A (en) * | 2013-05-09 | 2013-08-28 | 中国矿业大学 | Coal slurry ash online detection system based on image method, and method |
CN103424406A (en) * | 2013-09-03 | 2013-12-04 | 上海理工大学 | Image method measuring device and method for gas-liquid two-phase flow in pipelines |
CN104316443A (en) * | 2014-09-30 | 2015-01-28 | 杭州电子科技大学 | PM2.5 concentration monitoring method based on CCD back scattering |
CN104567711A (en) * | 2015-01-23 | 2015-04-29 | 中国特种设备检测研究院 | Side expansion value measuring system and method based on projection and digital image processing |
CN105872373A (en) * | 2016-03-31 | 2016-08-17 | 北京奇虎科技有限公司 | Automatic defogging photographing method, device and equipment |
CN205664783U (en) * | 2016-06-03 | 2016-10-26 | 绵阳市维博电子有限责任公司 | Vision measuring device based on two telecentric mirror heads |
CN107451590A (en) * | 2017-07-19 | 2017-12-08 | 哈尔滨工程大学 | Gas detection identification and concentration method for expressing based on EO-1 hyperion infrared image |
CN107860691A (en) * | 2017-10-17 | 2018-03-30 | 中国矿业大学(北京) | A kind of laser mine coal dust method of telemetering based on machine vision technique |
CN207263130U (en) * | 2017-10-10 | 2018-04-20 | 东莞市嘉仪自动化设备科技有限公司 | A kind of one-touch 3D profile measurements equipment |
-
2018
- 2018-09-06 CN CN201811038931.5A patent/CN109269951B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1065496A2 (en) * | 1999-06-29 | 2001-01-03 | Tripath Imaging, Inc. | Method and apparatus for deriving separate images from multiple chromogens in a biological specimen |
US20020016068A1 (en) * | 2000-08-07 | 2002-02-07 | Hiroyuki Nakano | Method and its apparatus for detecting floating particles in a plasma processing chamber and an apparatus for processing a semiconductor device |
CN102297822A (en) * | 2010-06-22 | 2011-12-28 | 中国矿业大学 | Method for predicting ash content of coal particles by utilizing image analysis |
CN103267762A (en) * | 2013-05-09 | 2013-08-28 | 中国矿业大学 | Coal slurry ash online detection system based on image method, and method |
CN103424406A (en) * | 2013-09-03 | 2013-12-04 | 上海理工大学 | Image method measuring device and method for gas-liquid two-phase flow in pipelines |
CN104316443A (en) * | 2014-09-30 | 2015-01-28 | 杭州电子科技大学 | PM2.5 concentration monitoring method based on CCD back scattering |
CN104567711A (en) * | 2015-01-23 | 2015-04-29 | 中国特种设备检测研究院 | Side expansion value measuring system and method based on projection and digital image processing |
CN105872373A (en) * | 2016-03-31 | 2016-08-17 | 北京奇虎科技有限公司 | Automatic defogging photographing method, device and equipment |
CN205664783U (en) * | 2016-06-03 | 2016-10-26 | 绵阳市维博电子有限责任公司 | Vision measuring device based on two telecentric mirror heads |
CN107451590A (en) * | 2017-07-19 | 2017-12-08 | 哈尔滨工程大学 | Gas detection identification and concentration method for expressing based on EO-1 hyperion infrared image |
CN207263130U (en) * | 2017-10-10 | 2018-04-20 | 东莞市嘉仪自动化设备科技有限公司 | A kind of one-touch 3D profile measurements equipment |
CN107860691A (en) * | 2017-10-17 | 2018-03-30 | 中国矿业大学(北京) | A kind of laser mine coal dust method of telemetering based on machine vision technique |
Non-Patent Citations (4)
Title |
---|
ZHIYONG DONG ET AL.: "Switching and optimizing control for coal flotation process based on a hybrid model", 《PLOS ONE》 * |
周骛等: "管道内稀疏颗粒相图像法多参数测量", 《工程热物理学报》 * |
杨林等: "动态图像颗粒粒度粒形测量装置", 《山东理工大学学报(自然科学版)》 * |
高博: "基于图像灰度特征的浮选尾矿灰分软测量研究", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110070537A (en) * | 2019-04-25 | 2019-07-30 | 清华大学 | The granularity of still image particle and the intelligent identification Method of sphericity and device |
CN110766699B (en) * | 2019-07-22 | 2022-03-15 | 中南大学 | Texture feature measurement method based on Euclidean distance judgment |
CN110766699A (en) * | 2019-07-22 | 2020-02-07 | 中南大学 | Texture feature measurement method based on Euclidean distance judgment |
CN110647887A (en) * | 2019-07-23 | 2020-01-03 | 太原理工大学 | Method for extracting internal marker in coal slime flotation foam image segmentation |
CN110399888A (en) * | 2019-07-25 | 2019-11-01 | 西南民族大学 | A kind of go judgment system based on MLP neural network and computer vision |
CN110362710A (en) * | 2019-08-25 | 2019-10-22 | 贵州大学 | Pulp density test macro and method based on image recognition technology |
CN110766709A (en) * | 2019-10-30 | 2020-02-07 | 成都理工大学 | Landslide particle accumulation characteristic identification method based on image identification |
CN112798467A (en) * | 2020-12-15 | 2021-05-14 | 中煤科工集团唐山研究院有限公司 | Intelligent online ash detection device and detection method based on high-speed microscopic vision |
CN113191452A (en) * | 2021-05-21 | 2021-07-30 | 中国矿业大学(北京) | Coal ash content online detection system based on deep learning and detection method thereof |
CN113658212A (en) * | 2021-08-13 | 2021-11-16 | 青岛科技大学 | Image prediction method |
CN114791480A (en) * | 2022-03-14 | 2022-07-26 | 国能智深控制技术有限公司 | Soft measurement method and device for dense medium ash content of coal preparation plant |
WO2023179344A1 (en) * | 2022-03-23 | 2023-09-28 | 中国矿业大学 | Intelligent flotation agent addition system based on flotation coal tailing slurry detection, and agent addition method |
WO2023179111A1 (en) * | 2022-03-23 | 2023-09-28 | 中国矿业大学 | Intelligent flotation chemicals loading system and method based on flotation tailing ore pulp detection |
CN114897835A (en) * | 2022-05-16 | 2022-08-12 | 中国矿业大学 | Coal product ash content real-time detection system based on image |
CN115494096A (en) * | 2022-10-24 | 2022-12-20 | 青岛理工大学 | Metallurgical solid waste identification method and system based on X-ray diffraction spectrum |
CN115861235A (en) * | 2022-12-05 | 2023-03-28 | 中国矿业大学 | Flotation tailing ash content prediction method based on multi-feature data fusion |
Also Published As
Publication number | Publication date |
---|---|
CN109269951B (en) | 2021-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109269951A (en) | Floating tail-coal ash content, concentration, coarse granule detection method of content based on image | |
CN106841209B (en) | One kind being based on big data self study chemical fiber wire ingot intelligence appearance detection system and method | |
CN104715239B (en) | A kind of vehicle color identification method based on defogging processing and weight piecemeal | |
CN110276386A (en) | A kind of apple grading method and system based on machine vision | |
CN101403703B (en) | Real-time detection method for foreign fiber in lint | |
CN106934386B (en) | A kind of natural scene character detecting method and system based on from heuristic strategies | |
CN106651872A (en) | Prewitt operator-based pavement crack recognition method and system | |
CN101877074A (en) | Tubercle bacillus target recognizing and counting algorithm based on diverse characteristics | |
CN106140648B (en) | A kind of chicken genetic ability for carcass weight automatic grading system and stage division based on machine vision | |
CN108181316B (en) | Bamboo strip defect detection method based on machine vision | |
CN103971126A (en) | Method and device for identifying traffic signs | |
CN109191459A (en) | The automatic identification and ranking method of continuous casting billet macrostructure center segregation defect | |
CN114897898B (en) | Board quality classification method based on image processing | |
CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
CN110403232A (en) | A kind of cigarette quality detection method based on second level algorithm | |
CN113109348B (en) | Paddle image transfer printing defect identification method based on machine vision | |
CN105973904B (en) | A kind of edible oil method for detecting impurities based on image background probability graph | |
CN108765402A (en) | Non-woven fabrics defects detection and sorting technique | |
CN107341790A (en) | A kind of image processing method of environment cleanliness detection | |
CN110687121A (en) | Intelligent online detection and automatic grading method and system for ceramic tiles | |
CN101097205A (en) | Method for automatically detecting aeolotropism in charred coal organization | |
CN109089992A (en) | A kind of classification method and system of the Estimation of The Fish Freshness based on machine vision | |
CN102855641A (en) | Fruit level classification system based on external quality | |
CN105893960A (en) | Road traffic sign detecting method based on phase symmetry | |
CN109859231A (en) | A kind of leaf area index extraction threshold segmentation method based on optical imagery |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230116 Address after: 030000 Plant 2, No. 51, Zhengyang Street, Taiyuan Tanghuai Park, Shanxi Comprehensive Reform Demonstration Zone, Taiyuan City, Shanxi Province Patentee after: SHANXI ZHIZHUO ELECTRICAL Co.,Ltd. Address before: 030032 plant 2, No. 51, Zhengyang Street, Tanghuai Park, Taiyuan comprehensive reform demonstration zone, Taiyuan, Shanxi Province Patentee before: SHANXI ZHIZHUO ELECTRICAL Co.,Ltd. Patentee before: Taiyuan University of Technology |