CN117611961A - Ore granularity identification method and system based on particle size distribution characteristics of crushed products - Google Patents

Ore granularity identification method and system based on particle size distribution characteristics of crushed products Download PDF

Info

Publication number
CN117611961A
CN117611961A CN202311491067.5A CN202311491067A CN117611961A CN 117611961 A CN117611961 A CN 117611961A CN 202311491067 A CN202311491067 A CN 202311491067A CN 117611961 A CN117611961 A CN 117611961A
Authority
CN
China
Prior art keywords
particle size
crushed
ore
boundary
granularity
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
Application number
CN202311491067.5A
Other languages
Chinese (zh)
Inventor
刘政宇
杨志广
孙春宝
寇珏
曲福明
王晓莉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology Beijing USTB
Original Assignee
University of Science and Technology Beijing USTB
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Science and Technology Beijing USTB filed Critical University of Science and Technology Beijing USTB
Priority to CN202311491067.5A priority Critical patent/CN117611961A/en
Publication of CN117611961A publication Critical patent/CN117611961A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Multimedia (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Sorting Of Articles (AREA)

Abstract

The invention discloses an ore granularity identification method and system based on crushed product granularity distribution characteristics, wherein the method comprises the following steps: collecting an image of a crushed product to be detected, and counting the total mass of the crushed product; identifying crushed product images, and identifying crushed ore particles with the granularity larger than the boundary granularity; counting the particle size of the identified crushed ore particles having a particle size greater than the boundary particle size and the cumulative yield on screen of the corresponding particle size; performing linear regression analysis on the statistical data to obtain a particle size characteristic equation and a curve of crushed ore particles with the particle size larger than the boundary particle size, and accordingly obtaining particle size characteristic curves of all crushed products; and integrating the data, and calculating to obtain related data required by the subsequent production process. By adopting the scheme of the invention, the crushed products can obtain important data required by subsequent production such as particle size distribution, accumulated yield on a sieve, yield of each particle size, P80 value and the like of the crushed products without sieving, and real-time detection of the data can be realized.

Description

Ore granularity identification method and system based on particle size distribution characteristics of crushed products
Technical Field
The invention relates to the technical field of mineral processing, in particular to an ore granularity identification method and system based on particle size distribution characteristics of crushed products.
Background
The first step in the mineral processing industry is ore crushing and grinding, which is the particle size reduction process of the ore. The accurate ore granularity identification has important significance for ore grinding energy consumption prediction and optimization. In the past, though an accurate ore particle distribution curve on a conveying belt can be obtained by adopting a screening method, the amount of ore processed by the screening method is huge and takes too long, and the method does not have the immediate detectability required by the development of industrial intelligence.
With the development of image recognition technology, an artificial intelligence-based ore particle size recognition method is raised, and the method predicts the overall ore particle size distribution curve by recognizing the particle size distribution of the ore pile surface on a belt. However, this approach is limited by the limitations of image recognition algorithm development, which is incapable of recognizing fine-fraction mineral particles and tends to recognize the fine-fraction mineral particle population as a monolithic ore, resulting in a large error.
Disclosure of Invention
The invention provides an ore granularity identification method and system based on the granularity distribution characteristics of crushed products, which aim to solve the technical problems that the existing ore granularity identification technology cannot identify fine-fraction mineral particles and often identifies fine-fraction ore particle groups as whole ores, thereby causing huge errors.
In order to solve the technical problems, the invention provides the following technical scheme:
in one aspect, the invention provides an ore particle size identification method based on the particle size distribution characteristics of crushed products, which comprises the following steps:
collecting an image of a broken product to be detected, and counting the total mass of the broken product to be detected;
identifying an image of a crushed product to be detected, and identifying crushed ore particles with the granularity larger than the boundary granularity to obtain image information of the crushed ore particles with the granularity larger than the boundary granularity;
calculating and counting the particle size of the identified crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the screen of the corresponding particle size based on the image identification result;
performing linear regression analysis on the particle size of the crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve to obtain a particle size characteristic equation and a particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, fitting the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size smaller than the boundary particle size based on the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, and obtaining the particle size characteristic curve of all crushed products so as to obtain the particle size and the cumulative yield on the sieve of all crushed products;
calculating relevant data required by the subsequent production process based on the granularity of all the crushed products and the accumulated yield on the screen by combining the total mass of all the crushed products; wherein the related data includes: the mass, yield and P80 value of each fraction of the crushed product and the total mass of the crushed product.
Further, the broken product to be detected is positioned on the belt;
the acquisition of an image of the crushed product to be detected comprises:
shooting a broken product to be detected by using an industrial high-definition camera to obtain an image of the broken product to be detected; the industrial high-definition cameras are arranged above the belt at intervals of preset distances, shooting directions of the industrial high-definition cameras intersect broken products on the belt at preset angles, and when shooting is carried out each time, the multiple cameras shoot broken products on the belt at the same time.
Further, identifying the image of the crushed product to be detected, identifying crushed ore particles with the granularity larger than the boundary granularity, and obtaining image information of the crushed ore particles with the granularity larger than the boundary granularity, wherein the image information comprises the following steps:
fusing the images of the broken products shot by the plurality of industrial high-definition cameras, merging the same parts of the content in the plurality of images, and splicing the different parts of the content to obtain a fused image;
identifying the fused images by adopting a preset identification algorithm, identifying broken ore particles with the granularity larger than the boundary granularity, and carrying out image segmentation and noise reduction on the identified broken ore particles with the granularity larger than the boundary granularity to obtain image information of the broken ore particles with the granularity larger than the boundary granularity; wherein the image information includes: the size, shape, contour, and grain boundary information of each identified ore grain.
Further, the calculating and counting the particle size of the identified crushed ore particles having a particle size larger than the boundary particle size and the cumulative yield on screen of the corresponding particle size based on the image identification result includes:
based on an image recognition result, performing binarization processing on the image to obtain two-dimensional irregular pattern areas of each recognized broken ore particle with the granularity larger than the boundary granularity, and calculating the diameter of each ore particle by adopting an equivalent circle diameter method based on the two-dimensional irregular pattern areas of the ore particles, wherein the formula is as follows:
wherein d is the equivalent circle diameter; s is the two-dimensional irregular pattern area of a single particle; pi is 3.14;
after the particle size calculation is completed, numbering the calculated particles one by one, and arranging the particles according to the order of the particle sizes from large to small, and calculating cumulative yield data on a sieve corresponding to the particle sizes, wherein the cumulative yield calculation formula on the sieve is as follows:
wherein R is cumulative yield on screen; m is m i Representing the mass of the ith ore particle; k represents the number of broken ore particles with the granularity larger than the boundary granularity in the image of the broken product to be detected; n represents the total number of ore particles in the image of the crushed product to be detected; s is S i Representing a two-dimensional irregular pattern area of an ith ore in an image of the crushed product to be detected; ρ represents the density of the ore particles; s is S 0 And representing the total area of the two-dimensional irregular graph after binarization treatment of all the identified broken products.
Further, the particle size characteristic curve is a rogowski-lamb particle size characteristic curve, the abscissa of the curve is lg (x), and the ordinate isThe curve equation is expressed as follows:
wherein x represents the particle size of the crushed product; r represents cumulative yield on screen; e represents a natural constant, and the value is 2.71828; b represents a parameter related to fineness of the product; n represents a parameter related to a property of the material; when x and R are known, the values of n and b can be obtained according to the intersection point of the granularity characteristic curve on the horizontal and vertical axes;
the particle size characteristic equation is a rogin-lamb particle size characteristic equation, and the calculation formula is as follows:
further, the yield of each fraction of the crushed product is calculated as follows:
wherein x is 1 、x 2 To crush the particle size of the product, x 1 <x 2 The method comprises the steps of carrying out a first treatment on the surface of the Gamma is-x 2 +x 1 Yield of the fraction; b represents a parameter related to fineness of the product; n represents a parameter related to a property of the material; r is R 1 Indicating a particle size of x 1 Is a cumulative yield on screen; r is R 2 Indicating a particle size of x 2 Is a cumulative yield on screen.
Further, the calculation formula of the mass of each particle fraction of the crushed product is as follows:
m＝M·γ
wherein m is the mass of a certain size fraction; m is the mass of all crushed products; gamma is the yield of a certain fraction.
Further, the calculation formula of the P80 value is as follows:
wherein P80 is the corresponding crushed product particle size at 80% cumulative yield on screen; b represents a parameter related to fineness of the product; n represents a parameter related to the properties of the material.
Further, the value range of the boundary granularity is 5 mm-10 mm.
In another aspect, the present invention also provides an ore particle size identification system based on the particle size distribution characteristics of the crushed products, the ore particle size identification system based on the particle size distribution characteristics of the crushed products comprising:
the data acquisition module is used for:
collecting an image of a broken product to be detected, and counting the total mass of the broken product to be detected;
a data processing module for:
identifying an image of a crushed product to be detected, and identifying crushed ore particles with the granularity larger than the boundary granularity to obtain image information of the crushed ore particles with the granularity larger than the boundary granularity;
calculating and counting the particle size of the identified crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the screen of the corresponding particle size based on the image identification result;
performing linear regression analysis on the particle size of the crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve to obtain a particle size characteristic equation and a particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, fitting the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size smaller than the boundary particle size based on the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, and obtaining the particle size characteristic curve of all crushed products so as to obtain the particle size and the cumulative yield on the sieve of all crushed products;
calculating relevant data required by the subsequent production process based on the granularity of all the crushed products and the accumulated yield on the screen by combining the total mass of all the crushed products; wherein the related data includes: the mass, yield and P80 value of each particle fraction of the crushed product and the total mass of the crushed product;
the data output module is used for:
and outputting the related data required by the subsequent production process calculated by the data processing module.
In yet another aspect, the present invention also provides an electronic device including a processor and a memory; wherein the memory stores at least one instruction that is loaded and executed by the processor to implement the above-described method.
In yet another aspect, the present invention also provides a computer readable storage medium having at least one instruction stored therein, the instruction being loaded and executed by a processor to implement the above method.
The technical scheme provided by the invention has the beneficial effects that at least:
according to the scheme, the image information of the crushed products is obtained by utilizing an industrial high-definition camera, the information such as the particle size distribution of the actual crushed products, the accumulated yield on a screen and the like is fitted and calculated by an ore particle size machine vision recognition method, and finally, the data required by subsequent production can be output by combining the quality of the crushed products; the invention can realize real-time monitoring of the particle size distribution information of the crushed products and provide important reference information and corresponding guidance for subsequent production.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an embodiment of an ore particle size identification method based on the particle size distribution characteristics of crushed products;
fig. 2 is a block diagram of an ore particle size identification system based on crushed product particle size distribution characteristics according to an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings.
First embodiment
Aiming at the problems that the prior art mainly obtains the information such as the particle size distribution, the yield of each particle size and the P80 value of a crushed product through a screening method, has complex operation process, delayed data acquisition and incapability of monitoring the data information of the crushing process in real time, and the prior art of identifying the particle size of the ore does not have the ability to identify the fine-size mineral particles, and often identifies the fine-size ore particles as a whole ore, and causes huge errors, the embodiment adopts a machine vision identification system, utilizes the particle size distribution characteristic method of the crushed product to divide the effective information obtaining step of the crushed product into six parts such as image acquisition, image splicing, image identification, particle size detection, distribution fitting and data integration.
The method of the present embodiment may be implemented by an electronic device, which may be a terminal or a server. The execution flow of the method is shown in fig. 1, and comprises the following steps:
s1, collecting an image of a broken product to be detected, and counting the total mass of the broken product to be detected;
it should be noted that, in this embodiment, broken products located on a belt are detected, and in this embodiment, two industrial high-definition cameras are used to shoot broken products to be detected from different positions at the same time, so as to obtain multiple images of the broken products to be detected; the two industrial high-definition cameras are placed above the belt at a certain distance, the shooting directions of the two industrial high-definition cameras intersect broken products on the belt at a certain angle, and when shooting each time, the two cameras shoot the broken products on the belt at the same time, so that original high-definition images of the two broken products are obtained after shooting each time. Further, in the embodiment, the single shooting is performed by taking broken products of a belt with the length of 1 meter as a unit, the conveying speed of the belt is 1m/s, and the industrial high-definition camera is set to shoot every 1s, so that all broken products on the belt passing through a machine vision recognition system are ensured to be detected; the whole system continuously works to realize the real-time detection effect on the broken product information.
The quality of the crushed products is obtained by weighing by a belt scale and is used for the statistics and calculation of the follow-up related data.
S2, identifying an image of a crushed product to be detected, and identifying crushed ore particles with the granularity larger than the boundary granularity to obtain image information of the crushed ore particles with the granularity larger than the boundary granularity;
specifically, in the present embodiment, the processing procedure of S2 described above is as follows:
s21, fusing a plurality of broken product images shot by two industrial high-definition cameras at the same time by adopting an AI algorithm so as to ensure that the shot photo content covers all broken products as much as possible and ensure that each detail is recorded. The method comprises the following steps: combining the same content parts in the two images, splicing different content parts, strengthening details of the fuzzy content parts, and ensuring that the photographed photo content is clear so as to reduce interference on subsequent operations;
s22, recognizing spliced images by adopting a preset recognition algorithm, recognizing broken ore particles with the granularity larger than the boundary granularity, performing image segmentation and noise reduction on the recognized broken ore particles with the granularity larger than the boundary granularity, strengthening the boundary of the recognized ore particles, reducing the interference of a fine-particle-grade product on a system, and obtaining image information of the broken ore particles with the granularity larger than the boundary granularity; wherein the image information includes: the size, shape, contour, and grain boundary information of each identified ore grain.
The boundary grain size refers to the lower limit of the accurate identification grain size of the machine vision identification system, the value of the boundary grain size is generally influenced by various factors such as the working environment of the system, the shape and texture of the ore to be detected, the dust on the surface of the ore, the resolution of a camera, the parameters of the system and the like, and is generally 5-10mm, and the boundary grain size obtained by the method is 5mm, namely the granularity of the ore required to be identified and detected is larger than 5mm.
S3, calculating and counting the particle size of the identified broken ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve with the corresponding particle size based on the image identification result;
in this embodiment, when the particle diameter of the identified particle is detected and counted, the diameter of the single particle is calculated by the equivalent circle diameter method, so as to obtain the diameter of the particle with the particle diameter larger than the boundary particle diameter in all the crushed products, and the number ordering treatment is performed on each particle. The specific treatment process is as follows:
s31, performing binarization processing on the image to obtain two-dimensional irregular pattern areas of each identified broken ore particle with the granularity larger than the boundary granularity, and calculating the diameter of each ore particle by adopting an equivalent circle diameter method based on the two-dimensional irregular pattern areas of the ore particles, wherein the formula is as follows:
wherein d is the equivalent circle diameter; s is the two-dimensional irregular pattern area of a single particle; pi is 3.14;
s32, numbering the calculated particles one by one after the particle size calculation is completed, and arranging the particles according to the order of the particle sizes from large to small, and calculating cumulative yield data on a sieve corresponding to the particle sizes, wherein the cumulative yield calculation formula on the sieve is as follows:
wherein R is cumulative yield on screen; m is m i Representing the mass of the ith ore particle; k represents the number of broken ore particles with the granularity larger than the boundary granularity in the image of the broken product to be detected; n represents the total number of ore particles in the image of the crushed product to be detected; s is S i Representing a two-dimensional irregular pattern area of an ith ore in an image of the crushed product to be detected; ρ represents the density of the ore particles; s is S 0 And representing the total area of the two-dimensional irregular graph after binarization treatment of all the identified broken products.
S4, carrying out linear regression analysis on the particle size of the crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve to obtain a particle size characteristic equation and a particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, fitting the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size smaller than the boundary particle size based on the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, and obtaining the particle size characteristic curve of all the crushed products so as to obtain the particle size and the cumulative yield on the sieve of all the crushed products;
it should be noted that, a lot of researches indicate that the particle size distribution of the sub-particle group after ore crushing is in accordance with the statistical distribution. Researchers in the technical field of mineral processing find that a straight line segment can be obtained by taking the logarithm of the particle size of the mineral particles as an abscissa and the accumulated distribution rate of the mineral particle groups as an ordinate. In 1934, the statistical approach to the classification of the particle size distribution of the products of crushers and mills by the use of the Rammler and the Rosin (Rosin) gave rise to the characteristic raxin-Rammler distribution function for crushed ore products, which has been used until now. Furthermore, AI-based image recognition techniques are accurate and reliable for the prediction of coarse fraction ore, but tend to deviate greatly in the prediction of fine fraction ore particles.
Therefore, the embodiment accurately obtains the particle distribution situation of coarse-particle ore based on the inherent particle size distribution gene characteristic of the ore crushing and grinding product, namely, the characteristic of the rogin-lamb characteristic distribution, and fits the product distribution curve of the whole ore particle group according to the characteristic that the particle size distribution of all products of crushing operation accords with a rogin-lamb particle size equation, so as to calculate the particle distribution of fine-particle ore, obtain the particle size of all crushed products and cumulative yield data on a screen, further obtain the yield of each particle product, and obtain the related data required by the subsequent production process by integrating weight information recorded by a weighing subsystem. Realizing the accurate identification of the ore grinding products.
Based on the above, the particle size characteristic curve in S4 is a Sioocta-lamb particle size characteristic curve, the abscissa of the curve is lg (x), and the ordinate isThe curve equation is expressed as follows:
wherein x represents the particle size of the crushed product in mm; r represents cumulative yield on screen,%; e represents a natural constant, and the value is 2.71828; b represents a parameter related to fineness of the product; n represents a parameter related to a property of the material; the values of n and b can be obtained according to the intersection point of the granularity characteristic curve on the horizontal and vertical axes;
the particle size characteristic equation is a rogin-lamb particle size characteristic equation, and the calculation formula is as follows: r=100deg.C -bxn 。
The particle size distribution characteristics of the particles with the particle size smaller than 5mm also accord with the Rodin-Roman particle size characteristic equation and curve of the whole crushed product, so that the particle size distribution and the cumulative yield information on the sieve of each particle size of the crushed product with the particle size smaller than 5mm can be fitted according to the Rodin-Roman particle size characteristic equation and curve of the particles with the particle size larger than 5mm.
S5, calculating relevant data required by a subsequent production process based on the granularity and the cumulative yield on the screen of all the crushed products and combining the total mass of all the crushed products;
in this embodiment, the calculated related data required for the subsequent production process includes: the mass, yield and P80 value of each fraction of the crushed product and the total mass of the crushed product.
The yield of each fraction was calculated from the cumulative yield data on the sieve as follows:
wherein x is 1 、x 2 To crush the particle size of the product, x 1 <x 2 Unit mm; gamma is-x 2 +x 1 Yield in fraction,%; b represents a parameter related to fineness of the product; n represents a parameter related to a property of the material; r is R 1 Indicating a particle size of x 1 Cumulative yield on screen,%; r is R 2 Indicating a particle size of x 2 Cumulative yield on screen,%.
The calculation formula of the mass of each particle fraction of the crushed product is as follows:
m＝M·γ
wherein m is the mass of a certain size fraction, and the unit is g; m is the mass of all crushed products, and the unit g; gamma is the yield of a certain fraction,%.
Further, the calculation formula of the P80 value is as follows:
wherein P80 is the corresponding crushed product granularity in mm when the cumulative yield on the screen is 80%; b represents a parameter related to fineness of the product; n represents a parameter related to the properties of the material.
Based on the above, it should be noted that the process of analyzing the particle size of the crushed product is divided into three important parts, namely, image acquisition and identification, ore particle size calculation and data statistics, linear regression analysis and fitting, and the final accuracy of the particle size analysis of the crushed product depends on the accuracy of the three steps.
The method utilizes an industrial high-definition camera to acquire image information of a crushed product, fits and calculates information such as particle size distribution, accumulated yield on a screen and the like of the actual crushed product through an ore particle size machine vision recognition method, and finally can output data required by subsequent production by combining the quality of the crushed product; by the method, the real-time monitoring of the particle size distribution information of the crushed products can be realized, and important reference information and corresponding guidance are provided for subsequent production.
In the following, to further illustrate the implementation of the method, it is applied to a practical scenario.
The experimental object of the embodiment is a section of broken product of a copper ore dressing plant, the maximum granularity of the broken product is not more than 18mm, the width of a section of broken product conveying belt is 1m, the conveying speed is 1m/s, the method is adopted to detect the ore on the belt every 1s, each detection takes broken products of a belt with the length of 1m as a unit, the broken products on the belt are uniformly distributed, and the weight of the ore detected in a single time is about 600 kg.
Starting a conveyor belt and an ore granularity machine vision recognition system, simultaneously photographing ores on the conveyor belt by two industrial high-definition cameras, splicing the two photos by an AI algorithm aiming at the obtained photos to obtain a processed complete and clear photo, carrying out noise reduction and binarization processing on the processed photo by a computer algorithm, recognizing a two-dimensional image of ore particles with granularity more than 5mm, and carrying out particle boundary strengthening processing on the two-dimensional image; acquiring the area of the two-dimensional irregular image of the identified particles by using a computer algorithm, and calculating the equivalent circle diameterAnd takes the particle size of the ore particles as the particle size; numbering the particles with the calculated particle size, sorting the particles according to the particle size from large to small, and using the formula +.>Calculating the cumulative yield on screen of the identified portion of crushed product; the first scan and identification of this example was performed with a total of 256 ore particles greater than 5mm. Further, after calculating to obtain the particle size of the identified ore and cumulative yield data on the sieve, the method performs linear regression analysis according to the data to obtain a particle size characteristic curve of part of ore with the particle size of more than 5mm, then fits the particle size characteristic curve of part of ore with the particle size of less than 5mm according to the particle size characteristic curve, and finally obtains the particle size characteristic curve of all crushed products, wherein the curve expression is as follows: />From this formula, b=1.9767, n= 1.9213, so the particle size characteristic equation of the whole crushed product is: />Thus obtaining the information such as the particle size characteristic equation, the particle size characteristic curve graph and the like of all the crushed products; in the first recognition and calculation process of the embodiment, the weighing subsystem is obtained by using the belt scaleThe quality data of the crushed products in the experiment is 592.65kg, the information such as the particle size characteristic equation, the particle size characteristic curve graph and the like of all the crushed products is integrated with the quality data of the crushed products, the data required by subsequent production is calculated by utilizing an algorithm, and the calculation result of the related data is as follows:
"+0.5-1mm fraction yield":
"+0.5-1mm fraction mass":
m＝M·γ＝592.65×45.49％＝269.60kg；
"P80 value":
the obtained data are transferred to the next production process.
The whole working process is completed within 1s, after the completion, the vertical horse starts to identify, calculate and count the next batch of broken products, and the work is repeated, so that the broken products on the belt are monitored in real time.
Second embodiment
The embodiment provides an ore particle size identification system based on the particle size distribution characteristics of crushed products, which is shown in fig. 2, and comprises the following modules:
the data acquisition module is used for:
collecting an image of a broken product to be detected, and counting the total mass of the broken product to be detected;
a data processing module for:
identifying an image of a crushed product to be detected, and identifying crushed ore particles with the granularity larger than the boundary granularity to obtain image information of the crushed ore particles with the granularity larger than the boundary granularity;
calculating and counting the particle size of the identified crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the screen of the corresponding particle size based on the image identification result;
performing linear regression analysis on the particle size of the crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve to obtain a particle size characteristic equation and a particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, fitting the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size smaller than the boundary particle size based on the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, and obtaining the particle size characteristic curve of all crushed products so as to obtain the particle size and the cumulative yield on the sieve of all crushed products;
calculating relevant data required by the subsequent production process based on the granularity of all the crushed products and the accumulated yield on the screen by combining the total mass of all the crushed products; wherein the related data includes: the mass, yield and P80 value of each particle fraction of the crushed product and the total mass of the crushed product;
the data output module is used for:
and outputting the related data required by the subsequent production process calculated by the data processing module.
The ore particle size identification system based on the particle size distribution characteristics of the crushed product of the present embodiment corresponds to the ore particle size identification method based on the particle size distribution characteristics of the crushed product of the first embodiment described above; the functions realized by the functional modules in the ore particle size identification system based on the particle size distribution characteristics of the crushed products in the embodiment are in one-to-one correspondence with the flow steps in the ore particle size identification method based on the particle size distribution characteristics of the crushed products in the first embodiment; therefore, the description is omitted here.
Third embodiment
The embodiment provides an electronic device, which comprises a processor and a memory; wherein the memory stores at least one instruction that is loaded and executed by the processor to implement the method of the first embodiment.
The electronic device may vary considerably in configuration or performance and may include one or more processors (central processing units, CPU) and one or more memories having at least one instruction stored therein that is loaded by the processors and performs the methods described above.
Fourth embodiment
The present embodiment provides a computer-readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the method of the first embodiment described above. The computer readable storage medium may be, among other things, ROM, random access memory, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. The instructions stored therein may be loaded by a processor in the terminal and perform the methods described above.
Furthermore, it should be noted that the present invention can be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
It is finally pointed out that the above description of the preferred embodiments of the invention, it being understood that although preferred embodiments of the invention have been described, it will be obvious to those skilled in the art that, once the basic inventive concepts of the invention are known, several modifications and adaptations can be made without departing from the principles of the invention, and these modifications and adaptations are intended to be within the scope of the invention. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Claims (10)

1. An ore particle size identification method based on particle size distribution characteristics of crushed products is characterized by comprising the following steps:
collecting an image of a broken product to be detected, and counting the total mass of the broken product to be detected;
identifying an image of a crushed product to be detected, and identifying crushed ore particles with the granularity larger than the boundary granularity to obtain image information of the crushed ore particles with the granularity larger than the boundary granularity;
calculating and counting the particle size of the identified crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the screen of the corresponding particle size based on the image identification result;
performing linear regression analysis on the particle size of the crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve to obtain a particle size characteristic equation and a particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, fitting the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size smaller than the boundary particle size based on the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, and obtaining the particle size characteristic curve of all crushed products so as to obtain the particle size and the cumulative yield on the sieve of all crushed products;
calculating relevant data required by the subsequent production process based on the granularity of all the crushed products and the accumulated yield on the screen by combining the total mass of all the crushed products; wherein the related data includes: the mass, yield and P80 value of each fraction of the crushed product and the total mass of the crushed product.
2. The method for identifying ore particle size based on particle size distribution characteristics of crushed products according to claim 1, wherein the crushed products to be detected are located on a belt;
the acquisition of an image of the crushed product to be detected comprises:
shooting a broken product to be detected by using an industrial high-definition camera to obtain an image of the broken product to be detected; the industrial high-definition cameras are arranged above the belt at intervals of preset distances, shooting directions of the industrial high-definition cameras intersect broken products on the belt at preset angles, and when shooting is carried out each time, the multiple cameras shoot broken products on the belt at the same time.
3. The method for identifying ore particle size based on the particle size distribution characteristics of crushed products according to claim 2, wherein the image of the crushed product to be detected is identified, wherein the crushed ore particles having a particle size larger than the boundary particle size are identified, and image information of the crushed ore particles having a particle size larger than the boundary particle size is obtained, comprising:
fusing the images of the broken products shot by the plurality of industrial high-definition cameras, merging the same parts of the content in the plurality of images, and splicing the different parts of the content to obtain a fused image;
identifying the fused images by adopting a preset identification algorithm, identifying broken ore particles with the granularity larger than the boundary granularity, and carrying out image segmentation and noise reduction on the identified broken ore particles with the granularity larger than the boundary granularity to obtain image information of the broken ore particles with the granularity larger than the boundary granularity; wherein the image information includes: the size, shape, contour, and grain boundary information of each identified ore grain.
4. The method for identifying ore particle size based on characteristics of particle size distribution of crushed products according to claim 1, wherein the calculating and counting the identified particle sizes of crushed ore particles having a particle size larger than a boundary particle size and the cumulative yield on screen of the corresponding particle sizes based on the image identification result comprises:
based on an image recognition result, performing binarization processing on the image to obtain two-dimensional irregular pattern areas of each recognized broken ore particle with the granularity larger than the boundary granularity, and calculating the diameter of each ore particle by adopting an equivalent circle diameter method based on the two-dimensional irregular pattern areas of the ore particles, wherein the formula is as follows:
wherein d is the equivalent circle diameter; s is the two-dimensional irregular pattern area of a single particle; pi is 3.14;
after the particle size calculation is completed, numbering the calculated particles one by one, and arranging the particles according to the order of the particle sizes from large to small, and calculating cumulative yield data on a sieve corresponding to the particle sizes, wherein the cumulative yield calculation formula on the sieve is as follows:
wherein R is cumulative yield on screen; m is m i Representing the mass of the ith ore particle; k represents the number of broken ore particles with the granularity larger than the boundary granularity in the image of the broken product to be detected; n represents the total number of ore particles in the image of the crushed product to be detected; s is S i Representing a two-dimensional irregular pattern area of an ith ore in an image of the crushed product to be detected; ρ represents the density of the ore particles; s is S 0 And representing the total area of the two-dimensional irregular graph after binarization treatment of all the identified broken products.
5. The method for identifying the particle size of ore based on the particle size distribution characteristics of crushed products according to claim 1, wherein the particle size characteristic curve is a rogin-lamb particle size characteristic curve, the abscissa of the curve is lg (x), and the ordinate isThe curve equation is expressed as follows:
wherein x represents the particle size of the crushed product; r represents cumulative yield on screen; e represents a natural constant, and the value is 2.71828; b represents a parameter related to fineness of the product; n represents a parameter related to a property of the material; when x and R are known, the values of n and b can be obtained according to the intersection point of the granularity characteristic curve on the horizontal and vertical axes;
the particle size characteristic equation is a rogin-lamb particle size characteristic equation, and the calculation formula is as follows:
6. the method for identifying the ore particle size based on the particle size distribution characteristics of the crushed product according to claim 1, wherein the yield of each particle size of the crushed product is calculated as follows:
wherein x is 1 、x 2 To crush the particle size of the product, x 1 <x 2 The method comprises the steps of carrying out a first treatment on the surface of the Gamma is-x 2 +x 1 Yield of the fraction; b represents a parameter related to fineness of the product; n represents a parameter related to a property of the material; r is R 1 Indicating a particle size of x 1 Is a cumulative yield on screen; r is R 2 Indicating a particle size of x 2 Is a cumulative yield on screen.
7. The method for identifying the ore particle size based on the particle size distribution characteristics of the crushed product according to claim 1, wherein the calculation formula of the mass of each particle size of the crushed product is as follows:
m＝M·γ
wherein m is the mass of a certain size fraction; m is the mass of all crushed products; gamma is the yield of a certain fraction.
8. The method for identifying ore particle size based on the particle size distribution characteristics of crushed products according to claim 1, wherein the calculation formula of the P80 value is as follows:
wherein P80 is the corresponding crushed product particle size at 80% cumulative yield on screen; b represents a parameter related to fineness of the product; n represents a parameter related to the properties of the material.
9. The method for identifying the particle size of ore based on the particle size distribution characteristics of crushed products according to any one of claims 1 to 8, wherein the boundary particle size has a value ranging from 5mm to 10mm.
10. An ore particle size identification system based on crushed product particle size distribution characteristics, comprising:
the data acquisition module is used for:
collecting an image of a broken product to be detected, and counting the total mass of the broken product to be detected;
a data processing module for:
identifying an image of a crushed product to be detected, and identifying crushed ore particles with the granularity larger than the boundary granularity to obtain image information of the crushed ore particles with the granularity larger than the boundary granularity;
calculating and counting the particle size of the identified crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the screen of the corresponding particle size based on the image identification result;
performing linear regression analysis on the particle size of the crushed ore particles with the particle size larger than the boundary particle size and the cumulative yield on the sieve to obtain a particle size characteristic equation and a particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, fitting the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size smaller than the boundary particle size based on the particle size characteristic equation and the particle size characteristic curve of the crushed ore particles with the particle size larger than the boundary particle size, and obtaining the particle size characteristic curve of all crushed products so as to obtain the particle size and the cumulative yield on the sieve of all crushed products;
calculating relevant data required by the subsequent production process based on the granularity of all the crushed products and the accumulated yield on the screen by combining the total mass of all the crushed products; wherein the related data includes: the mass, yield and P80 value of each particle fraction of the crushed product and the total mass of the crushed product;
the data output module is used for:
and outputting the related data required by the subsequent production process calculated by the data processing module.
CN202311491067.5A 2023-11-09 2023-11-09 Ore granularity identification method and system based on particle size distribution characteristics of crushed products Pending CN117611961A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311491067.5A CN117611961A (en) 2023-11-09 2023-11-09 Ore granularity identification method and system based on particle size distribution characteristics of crushed products

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311491067.5A CN117611961A (en) 2023-11-09 2023-11-09 Ore granularity identification method and system based on particle size distribution characteristics of crushed products

Publications (1)

Publication Number Publication Date
CN117611961A true CN117611961A (en) 2024-02-27

Family

ID=89957028

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311491067.5A Pending CN117611961A (en) 2023-11-09 2023-11-09 Ore granularity identification method and system based on particle size distribution characteristics of crushed products

Country Status (1)

Country Link
CN (1) CN117611961A (en)

Similar Documents

Publication Publication Date Title
Kistner et al. Monitoring of mineral processing systems by using textural image analysis
CN111275044A (en) Weak supervision target detection method based on sample selection and self-adaptive hard case mining
CN111242108B (en) Belt transfer point coal blockage identification method based on target detection
Igathinathane et al. Comparison of particle size distribution of celestite mineral by machine vision ΣVolume approach and mechanical sieving
CN104198497A (en) Surface defect detection method based on visual saliency map and support vector machine
CN111715540B (en) Apparatus and method for sorting coal and gangue
Zhao et al. Recognition of flooding and sinking conditions in flotation process using soft measurement of froth surface level and QTA
CN112330653A (en) Online ore granularity detection method based on image recognition technology
Kandlbauer et al. Sensor-based particle size determination of shredded mixed commercial waste based on two-dimensional images
CN113688751A (en) Method and device for analyzing alum blossom characteristics by using image recognition technology
Chen et al. Soybean seed counting and broken seed recognition based on image sequence of falling seeds
CN111507980B (en) Correction method for detecting particle size distribution of ore crushed and ground product by dynamic image method
CN117611961A (en) Ore granularity identification method and system based on particle size distribution characteristics of crushed products
CN112255148B (en) Ore granularity detection system and detection method
Fu et al. Quantitative ore texture analysis with convolutional neural networks
AU2021105929A4 (en) A Multi-Parameter Prediction Model For Coal Sample Hardiness
JP6892019B2 (en) Powder ratio measurement method and equipment
CN114821165A (en) Track detection image acquisition and analysis method
CN113409297A (en) Aggregate volume calculation method, particle form grading data generation method, system and equipment
CN112598618A (en) Mill ore feeding amount prediction method based on image recognition technology
CN113628155A (en) Green ball particle size detection method and system of disc pelletizer
CN113344276B (en) Method for predicting ore particle shape, quality and density index probability distribution
CN112058701B (en) Coal and coal gangue sorting system and method based on polarization imaging
Budzan et al. Grain size determination and classification using adaptive image segmentation with grain shape information for milling quality evaluation
CN116129365B (en) Method and system for detecting particle materials on conveying equipment

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