CN109269951B - Image-based flotation tailing ash content, concentration and coarse particle content detection method - Google Patents
Image-based flotation tailing ash content, concentration and coarse particle content detection method Download PDFInfo
- Publication number
- CN109269951B CN109269951B CN201811038931.5A CN201811038931A CN109269951B CN 109269951 B CN109269951 B CN 109269951B CN 201811038931 A CN201811038931 A CN 201811038931A CN 109269951 B CN109269951 B CN 109269951B
- Authority
- CN
- China
- Prior art keywords
- image
- concentration
- flotation
- content
- coarse 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.)
- Active
Links
- 238000005188 flotation Methods 0.000 title claims abstract description 69
- 239000011362 coarse particle Substances 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 39
- 239000002245 particle Substances 0.000 claims description 44
- 239000003245 coal Substances 0.000 claims description 30
- 238000005259 measurement Methods 0.000 claims description 15
- 239000003250 coal slurry Substances 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 239000003550 marker Substances 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 239000005304 optical glass Substances 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000005273 aeration Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 238000005457 optimization 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
-
- 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—Investigating concentration of particle suspensions by optical means
Landscapes
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the technical field of flotation tailing mine, and provides a method for detecting ash content, concentration and coarse particle content of flotation tailing based on images, which respectively extracts images aiming at flotation tailings with different ash content, concentration and coarse particle content and establishes a feature library based on image features; constructing an ash content, concentration and coarse particle content prediction model of the flotation tailings according to the feature library; and extracting the flotation tailing image to be detected, and determining the ash content, the concentration and the coarse particle content of the flotation tailings according to the prediction model. The invention has the beneficial effects that: the problem of large subjective factors of manual observation is avoided; the detection time is short, the frequency is high, and the production requirement is met; high efficiency, reduced workman working strength, can realize that the workshop subtracts the personnel, reduce the production cost of labor.
Description
Technical Field
The invention relates to the technical field of flotation tailing mine, in particular to a method for detecting ash content, concentration and coarse particle content of flotation tailing based on images.
Background
Along with the continuous improvement of the automation overall level of the industrial process, the automatic control and the intelligent control of the coal slime flotation process are more and more emphasized by people. One of the key links of the intelligent control of the flotation process is to realize the online detection of the product quality, including flotation of clean coal and tail coal. However, the lack of related detection technologies and sensors severely limits the development of intelligent flotation. The quality detection research of flotation products always focuses on flotation of clean coal, and flotation of tail coal is neglected. The flotation tailing quality is used as important feedback information and plays a crucial role in realizing closed-loop optimization control of the flotation process.
In the actual production process of coal slime flotation, field operators mainly rely on naked eyes to visually observe the color of tailings to judge ash content, judge whether flotation tailings have the problem of coarse flotation through hand grasping feeling, and adjust variables such as reagent dosage, foam layer thickness, aeration quantity and the like on the basis, so that the quality of flotation products is guaranteed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for detecting the ash content, the concentration and the coarse particle content of flotation tailings based on images, which utilizes a machine vision method to detect the ash content, the concentration and the coarse particle content of the flotation tailings.
The technical scheme of the invention is as follows:
an image-based flotation tailing ash content, concentration and coarse particle content detection method comprises the following steps:
respectively extracting images aiming at flotation tailings with different ash contents, concentrations and coarse particle contents, and establishing a feature library based on image features;
constructing an ash content, concentration and coarse particle content prediction model of the flotation tailings according to the feature library;
and extracting the flotation tailing image to be detected, and determining the ash content, the concentration and the coarse particle content of the flotation tailing according to the prediction model.
Further, an image analyzed by ash content detection is shot by an image acquisition system consisting of a fixed-focus lens, a color CCD industrial camera and an annular LED light source, and a direct illumination mode is adopted; the image analyzed by concentration detection and coarse particle content detection is shot by an image acquisition system consisting of a double-telecentric lens, a black-and-white CCD industrial camera and a parallel light source, and a backlight transmission illumination mode is adopted.
Further, the ash detection comprises the following steps:
step 1, collecting flotation tailing samples and color images with different concentrations and different ash contents, and classifying according to the ash content testing result;
step 2, preprocessing the image and removing noise in the image;
step 3, R, G, B, Y, U, V, H, S, I component characteristics of the image in RGB, YUV and HSI color space domains are extracted;
step 4, establishing a regression model of the ash content of the tailings with the same concentration, performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, and selecting a color difference variable C formed by linear combination of R, G, B three components according to the model fitting effectrgbThe method is used as a model independent variable to establish a soft measurement model of the ash content of the coal slurry with the same concentration, and the model form is as follows:
wherein y is the model ash output, a1、b1、c1、k1、k2Is a coefficient;
and 5, introducing a concentration correction function as follows:
wherein M issRepresenting the concentration of the tailing coal slurry, and j is an unknown coefficient;
step 6, constructing a soft measurement model form of the ash content of the flotation tail coal as follows:
Ash=a1ln{(k1R+k2G-B)/[1+exp(j*Ms)]+b1}+c1
wherein Ash represents the Ash content of the tail coal.
And 7, analyzing the flotation tailing image to be detected by using the soft measurement model, and detecting the ash content of the tailing.
Further, the concentration detection comprises the following steps:
step 1, collecting flotation tailing samples with different concentrations and black-and-white images, and classifying according to the result of the concentration test;
step 2, preprocessing the image and removing noise in the image;
step 3, extracting the gray characteristic of the image;
step 4, establishing a prediction model of the coal slurry concentration, selecting an image gray mean value to establish a soft measurement model of the coal slurry concentration, and performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, wherein the model form is as follows:
wherein M isSFor flotation tailing concentration, Gray is image Gray average value, a2、b2Are coefficients.
And 5, analyzing the flotation tailing image to be detected by using the soft measurement model, and detecting the concentration of the tailings.
Further, the concentration detection comprises the following steps:
step 1, collecting flotation tailing samples with different concentrations and black-and-white images, and classifying according to the result of the concentration test;
step 2, calibrating a camera by adopting an optical glass checkerboard, determining checkerboard angular points by utilizing a Harris angular point algorithm, then calculating the number of pixels between every two vertically and horizontally adjacent vertexes in a visual field range, namely the Euclidean distance between the adjacent vertexes, and then calculating the real size represented by each pixel point;
step 3, preprocessing the image and removing noise in the image;
step 4, carrying out binarization processing on the preprocessed image, and then eliminating a large amount of agglomerated non-target particles while smoothing the edges of the target particles through morphological processing; in order to avoid the influence of incomplete particle images on the analysis result of the field of view boundary, the particles connected with the image boundary need to be eliminated;
step 5, a watershed algorithm is controlled to segment the adhered particles in the image based on the distance variable and the marker; first, a distance transformation is to be carried out, by means of mathematical morphologyExtracting local maximum value points in the image after distance transformation by using the extended maximum transformation H-maximum technology, and combining the local maximum value points by using a morphological dilation method to obtain internal mark points and an internal mark image fgmEliminating over-segmentation, obtaining external marker and external marker image f by one time of watershed operationbm(ii) a Then based on the obtained internal and external marks, modifying the original gradient image by using a forced minimum technology, and then performing secondary watershed operation to finally complete segmentation;
step 6, carrying out edge detection on the segmented particle image, and then extracting the quantity distribution and geometric parameters of the target coal particles;
step 7, establishing a flotation tailing coarse particle content prediction model, respectively shooting a plurality of pictures, counting the particle size and the coarse particle number, calculating the average value of the coarse particle number, performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, and finally establishing the flotation tailing coarse particle content prediction model, wherein the form is as follows:
y=a3x+b3
y represents the coarse particle content of the flotation tailings; x represents the number of coarse particles measured by image method, a3、b3Are coefficients.
And 8, analyzing the flotation tailing image to be detected by using the soft measurement model, and detecting the coarse particle content of the tailing.
Further, in step 6, the geometric parameters of the target coal particles include: particle area, particle perimeter, equivalent circle diameter, particle shape index, and ovality parameters.
Further, in step 7, the coal particle size characterization based on the image method adopts an equivalent circle diameter, namely a particle projection area equivalent diameter.
Further, the particle size of the coarse particles of the flotation tail coal is larger than 250 um.
The invention has the beneficial effects that: the problem of large subjective factors of manual observation is avoided; the detection time is short, the frequency is high, and the production requirement is met; high efficiency, reduced workman working strength, can realize that the workshop subtracts the personnel, reduce the production cost of labor.
Detailed Description
Hereinafter, specific embodiments of the present invention will be described in detail. It should be noted that technical features or combinations of technical features described in the following embodiments should not be considered as being isolated, and they may be combined with each other to achieve better technical effects.
The experimental sample of the embodiment of the invention is from a Liuwan coal preparation plant, and the process of a coal preparation second workshop of the Liuwan coal preparation plant comprises the following steps: raw coal of 50-1mm size fraction is sorted by a dense medium cyclone, the raw coal below 1mm is classified by a classification concentration cyclone, the classification granularity is 0.25mm, wherein the overflow of 1-0.25mm size fraction is sorted by a TBS coarse coal slime sorting machine, and the coal slime of 0.25-0mm size fraction enters 4 XJM-S-20 flotation systems. The research object of the embodiment is tail coal of coal slime flotation.
The embodiment of the invention provides a detection method for analyzing ash content, concentration and coarse particle content based on a flotation tailing image. In the invention, an image analyzed by ash content detection is shot by an image acquisition system consisting of a fixed-focus lens, a color CCD industrial camera and an annular LED light source, and a direct illumination mode is adopted; the image analyzed by concentration detection and coarse particle content detection is shot by an image acquisition system consisting of a double telecentric lens, a black-and-white CCD industrial camera and a parallel light source, and a backlight transmission illumination mode is adopted. The method comprises the steps of firstly, constructing a feature library based on image features by using a traditional detection means of the ash content, the concentration and the coarse particle content of the tailings, and constructing a prediction model of the ash content, the concentration and the coarse particle content of the tailings.
The embodiment of the invention adopts the technical scheme that:
firstly, ash content detection:
1. collecting flotation tailing samples with different concentrations and ash contents and color images by professionals, and classifying according to the result of ash content testing;
2. the image is preprocessed, noise in the image is removed, image quality is improved, and useful information is highlighted.
3. Extracting R, G, B, Y, U, V, H, S, I component characteristics of the image in RGB, YUV and HSI color space domains;
4. establishing a regression model of the ash content of the tailings with the same concentration, screening the existing color characteristic parameters and a series of self-established characteristic parameters, performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, and selecting a color difference variable Crgb formed by R, G, B three-component linear combination as a model independent variable to establish a soft measurement model of the ash content of the coal slurry with the same concentration according to the model fitting effect, wherein the model form is as follows:
wherein y is the ash output result of the regression model of the tailings ash with the same concentration.
The fitting parameters and evaluation indices are shown in table 1.
TABLE 1 Soft-measurement model fitting parameters and evaluation indexes for ash content of tailings
In the table r2For determining the coefficients, the method is mainly used for evaluating the fitting effect and the quality, r2The closer to 1, the better the fitting effect of the regression equation is explained; r is2Closer to 0 indicates a poorer fit. RMSE is the root mean square error, MRE is the average relative error, MaxRE is the maximum relative error.
5. Introducing a concentration correction function
Is concentration pair CrgbCorrection function of value, MsRepresenting the tail coal slurry concentration. The soft measurement model form of the ash content of the flotation tail coal is constructed as follows:
Ash=31.171ln{(0.266R+0.87G-B)/[1+exp(-0.186Ms)]+1.592}-34.026
wherein Ash represents the Ash content of the tail coal.
Secondly, concentration detection:
1. collecting flotation tailing samples with different concentrations and black and white images by professionals, and classifying according to the result of the concentration of the assay;
2. the image is preprocessed, noise in the image is removed, image quality is improved, and useful information is highlighted.
3. Extracting gray features of the image;
4. establishing a coal slurry concentration prediction model, screening the existing gray characteristic parameters, performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, and selecting an image gray mean value to establish a coal slurry concentration soft measurement model according to the model fitting effect, wherein the model form is as follows:
wherein MS is the concentration of the flotation tailings.
The fitting parameters and evaluation indices are shown in table 2.
TABLE 2 concentration prediction model fitting parameters and evaluation indices
Thirdly, detecting the content of coarse particles:
1. collecting flotation tailing samples with different coarse particle contents and black and white images by professionals, and classifying according to coarse particle content testing results;
2. the method comprises the steps of adopting an optical glass checkerboard calibration camera, determining checkerboard angular points by using a Harris angular point algorithm, then calculating the number of pixels between two vertically and horizontally adjacent vertexes in a field range, namely the Euclidean distance between the adjacent vertexes, and then calculating the real size represented by each pixel point.
3. The image is preprocessed, noise in the image is removed, image quality is improved, and useful information is highlighted.
4. And carrying out binarization processing on the preprocessed image, and then eliminating a large amount of agglomerated non-target particles while smoothing the edges of the target particles through morphological processing. In order to avoid that the incomplete grain image at the boundary of the field of view affects the analysis result, the grains connected with the image boundary need to be eliminated.
5. And (4) applying a watershed algorithm controlled based on the distance variable and the marker to segment the conglutinated particles in the image. Firstly, distance transformation is required to be carried out, local maximum value points in an image after the distance transformation are extracted by means of an extended maximum transformation (H-maximum) technology in mathematical morphology, local maximum value points are combined by adopting a morphological middle expansion method to obtain internal mark points and an internal mark image fgm, over-segmentation is eliminated, an external mark symbol and an external mark image fbm are obtained through watershed operation for one time, then the original gradient image is modified by utilizing a forced minimum technology based on the obtained internal mark and the external mark, and then the secondary watershed operation is carried out, so that an ideal segmentation effect is finally obtained.
6. And (3) carrying out edge detection on the segmented particle image, and then extracting the quantity distribution and geometric parameters (particle area, particle perimeter, equivalent circle diameter, particle shape index, ellipticity parameter and the like) of the target coal particles.
7. Establishing a flotation tailing coarse particle content prediction model, respectively shooting five pictures, and counting the particle size and the number of coarse particles (the particle size is larger than 250um) by using the method described above, wherein the coal particle size characterization based on an image method adopts an equivalent circle diameter, namely a particle projection area equivalent diameter, and calculates the average value of the number of the coarse particles, the average value of the number of the coarse particles detected by the image method and the content of the coarse particles present an obvious linear relation, and a least square method is used for performing function fitting to obtain a formula coefficient and a fitting result, so that the finally established flotation tailing coarse particle content prediction model is in the form of the following formula
y=0.2342x+2.0655
y represents the coarse particle content of the flotation tailings; x represents the number of coarse particles measured by image method.
The results of the measurements of the coal slurry image particles with different coarse particle contents are shown in table 3.
TABLE 3 coal slurry image particle detection results with different coarse particle contents
While several embodiments of the present invention have been presented herein, it will be appreciated by those skilled in the art that changes may be made to the embodiments herein without departing from the spirit of the invention. The above-described embodiments are merely exemplary and should not be taken as limiting the scope of the invention.
Claims (5)
1. The method for detecting the ash content, the concentration and the coarse particle content of the flotation tailings based on the image is characterized by comprising the following steps: hardware structure aspect: the multi-parameter detection system based on the image is shot by an image acquisition system consisting of a fixed-focus lens, a color CCD industrial camera and an annular LED light source, and the ash content detection is realized by adopting a direct illumination mode; the device consists of a double telecentric lens, a black-and-white CCD industrial camera and a parallel light source, and realizes concentration detection and coarse particle content detection by adopting a backlight transmission illumination mode; in the aspect of algorithm: respectively extracting images aiming at flotation tailings with different ash contents, concentrations and coarse particle contents, and establishing an image-based feature library; constructing an ash content, concentration and coarse particle content prediction model of the flotation tailings according to the feature library; extracting an image of the flotation tailings to be detected, and determining the ash content, the concentration and the coarse particle content of the flotation tailings according to the prediction model;
the ash content detection comprises the following steps:
step 1, collecting flotation tailing samples and color images with different concentrations and different ash contents, and classifying according to the ash content testing result;
step 2, preprocessing the image and removing noise in the image;
step 3, R, G, B, Y, U, V, H, S, I component characteristics of the image in RGB, YUV and HSI color space domains are extracted;
step 4, establishing a regression model of the ash content of the tailings with the same concentration, performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, and selecting a color difference variable C formed by linear combination of R, G, B three components according to the model fitting effectrgbThe method is used for establishing a soft measurement model of the ash content of the coal slurry with the same concentration as a model independent variable, and the model form is as follows:
wherein y is the model ash output, a1、b1、c1、k1、k2Is a coefficient;
and 5, introducing a concentration correction function as follows:
wherein M issRepresenting the concentration of the tailing coal slurry, and j is a coefficient;
step 6, constructing a soft measurement model form of the ash content of the flotation tail coal as follows:
Ash=a1ln{(k1R+k2G-B)/[1+exp(j*Ms)]+b1}+c1
wherein Ash represents the Ash content of the tail coal;
and 7, analyzing the flotation tailing image to be detected by using the soft measurement model in the step 6, and detecting the ash content of the tailings.
2. The method of claim 1, wherein the concentration detection comprises the steps of:
step 1, collecting flotation tailing samples with different concentrations and black-and-white images, and classifying according to the result of the concentration test;
step 2, preprocessing the image and removing noise in the image;
step 3, extracting the gray characteristic of the image;
step 4, establishing a prediction model of the coal slurry concentration, selecting an image gray mean value to establish a soft measurement model of the coal slurry concentration, and performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, wherein the model form is as follows:
wherein M isSFor flotation tailing concentration, Gray is image Gray average value, a2、b2Is a coefficient;
and 5, analyzing the flotation tailing image to be detected by using the model in the step 4, and detecting the concentration of the tailing.
3. The method of claim 1, wherein the coarse content detection comprises the steps of:
step 1, collecting flotation tailing samples with different coarse particle contents and black-and-white images, and classifying according to coarse particle content testing results;
step 2, adopting an optical glass checkerboard calibration camera, determining checkerboard angular points by using a Harris angular point algorithm, then calculating the number of pixels between all two vertically and horizontally adjacent vertexes in a visual field range, namely the Euclidean distance between the adjacent vertexes, and then calculating the real size represented by each pixel point;
step 3, preprocessing the image and removing noise in the image;
step 4, carrying out binarization processing on the preprocessed image, and then eliminating a large amount of agglomerated non-target particles while smoothing the edges of the target particles through morphological processing; in order to avoid the influence of incomplete particle images on the analysis result of the field of view boundary, the particles connected with the image boundary need to be eliminated;
step 5, a watershed algorithm is controlled to segment the adhered particles in the image based on the distance variable and the marker; first, a distance transformation is to be carried out, using mathematical modalitiesExtracting local maximum points in the image after distance transformation by using an extended maximum transformation H-maximum technology in science, and combining the local maximum points by using a morphological expansion method to obtain internal mark points and an internal mark image fgmEliminating over-segmentation, obtaining external marker and external marker image f by one time of watershed operationbm(ii) a Then, based on the obtained internal and external marks, modifying the original gradient image by using a forced minimum technology, and then performing secondary watershed operation to finally complete segmentation;
step 6, carrying out edge detection on the segmented particle image, and then extracting the quantity distribution and geometric parameters of the target coal particles;
step 7, establishing a flotation tailing coarse particle content prediction model, respectively shooting a plurality of pictures, counting the particle size and the coarse particle number, calculating the average value of the coarse particle number, wherein the average value of the coarse particle number detected by an image method and the coarse particle content present an obvious linear relation, performing function fitting by using a least square method to obtain a formula coefficient and a fitting result, and finally establishing the flotation tailing coarse particle content prediction model, wherein the form is as follows:
y=a3x+b3
y represents the coarse particle content of the flotation tailings; x represents the number of coarse particles measured by image method, a3、b3Is a coefficient;
and 8, analyzing the image of the flotation tailings to be detected by using the model in the step 7, and detecting the content of coarse particles in the tailings.
4. The method of claim 3, wherein in step 6, the geometric parameters of the target coal particles comprise: particle area, particle perimeter, equivalent circle diameter, particle shape index, and ovality parameters.
5. The method of claim 3, wherein in step 7, the coal particle size characterization based on the image method adopts equivalent circle diameter, namely equivalent diameter of particle projection area, and coarse particles refer to particles with equivalent circle diameter larger than 250 um.
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 CN109269951A (en) | 2019-01-25 |
CN109269951B true 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) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110070537B (en) * | 2019-04-25 | 2021-10-15 | 清华大学 | Intelligent identification method and device for granularity and sphericity of static image particles |
CN110766699B (en) * | 2019-07-22 | 2022-03-15 | 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 |
CN110399888B (en) * | 2019-07-25 | 2021-08-27 | 西南民族大学 | Weiqi judging 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 |
CN110766709B (en) * | 2019-10-30 | 2021-03-30 | 成都理工大学 | Landslide particle accumulation characteristic identification method based on image identification |
CN112798467B (en) * | 2020-12-15 | 2023-01-31 | 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 |
CN113191452B (en) * | 2021-05-21 | 2022-03-01 | 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 |
CN113970510B (en) * | 2021-10-20 | 2024-04-30 | 天地(唐山)矿业科技有限公司 | Flotation tailing granularity online detection device and method based on artificial bionic |
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 |
CN114713381B (en) * | 2022-03-23 | 2023-07-07 | 中国矿业大学 | Flotation intelligent dosing system and dosing method based on flotation tail coal mine slurry detection |
CN114897835B (en) * | 2022-05-16 | 2023-04-28 | 中国矿业大学 | Image-based real-time detection system for ash content of coal products |
CN115452824A (en) * | 2022-08-30 | 2022-12-09 | 中国矿业大学 | Method for predicting ash content of coal flotation tailings on dynamic overflow surface through multiple models |
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 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1065496A3 (en) * | 1999-06-29 | 2003-11-05 | Tripath Imaging, Inc. | Method and apparatus for deriving separate images from multiple chromogens in a biological specimen |
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 |
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 |
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 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002057143A (en) * | 2000-08-07 | 2002-02-22 | Hitachi Ltd | Floating foreign matter detector |
CN104567711B (en) * | 2015-01-23 | 2017-06-06 | 中国特种设备检测研究院 | A kind of side expansion measuring system and method based on projection and Digital Image Processing |
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 |
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 (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1065496A3 (en) * | 1999-06-29 | 2003-11-05 | Tripath Imaging, Inc. | Method and apparatus for deriving separate images from multiple chromogens in a biological specimen |
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 |
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 |
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 |
Non-Patent Citations (3)
Title |
---|
Switching and optimizing control for coal flotation process based on a hybrid model;Zhiyong Dong et al.;《PLOS ONE》;20171017;第1-20页 * |
基于图像灰度特征的浮选尾矿灰分软测量研究;高博;《中国优秀硕士学位论文全文数据库工程科技I辑》;20170215(第02期);第3.1-3.7、5.1-5.4节 * |
管道内稀疏颗粒相图像法多参数测量;周骛等;《工程热物理学报》;20150331;第36卷(第3期);第3-4节以及图7 * |
Also Published As
Publication number | Publication date |
---|---|
CN109269951A (en) | 2019-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109269951B (en) | Image-based flotation tailing ash content, concentration and coarse particle content detection method | |
Dehrouyeh et al. | Grading and quality inspection of defected eggs using machine vision | |
CN109872300B (en) | Visual saliency detection method for appearance defects of friction plate | |
Omid et al. | An expert egg grading system based on machine vision and artificial intelligence techniques | |
Elbehiery et al. | Surface defects detection for ceramic tiles using image processing and morphological techniques | |
CN104914111B (en) | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method | |
Liming et al. | Automated strawberry grading system based on image processing | |
Zhang et al. | Multi-information online detection of coal quality based on machine vision | |
CN107607554A (en) | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks | |
CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
CN110705655A (en) | Tobacco leaf classification method based on coupling of spectrum and machine vision | |
CN110403232A (en) | A kind of cigarette quality detection method based on second level algorithm | |
CN103954634A (en) | Online quality detection system for printed matter | |
CN109598715A (en) | Material size online test method based on machine vision | |
CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
CN111242896A (en) | Color printing label defect detection and quality rating method | |
CN106548480A (en) | A kind of agricultural product volume rapid measurement device and measuring method based on machine vision | |
CN110554052A (en) | artificial board surface defect detection method and system | |
CN104952754B (en) | Silicon chip method for separating after plated film based on machine vision | |
CN109115775B (en) | Betel nut grade detection method based on machine vision | |
CN110687121A (en) | Intelligent online detection and automatic grading method and system for ceramic tiles | |
CN108020554A (en) | A kind of steel strip surface defect recognition detection method | |
CN115345876A (en) | Bolt thread defect detection method based on ultrasonic image | |
CN110009609B (en) | Method for rapidly detecting yellow rice | |
CN101477025A (en) | Fast evaluation method for collection exhibition materials based on image processing |
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 |
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 |
|
TR01 | Transfer of patent right |