Method and system for ore granularity identification based on broken product particle size distribution characteristics

Abstract

The application discloses a kind of ore granularity identification method and system based on broken product particle size distribution characteristics, the method includes: collecting the image of broken product to be detected, and the total mass of broken product is counted;The broken product image is identified, and the broken ore particle in which granularity is greater than boundary granularity is identified;The particle size of the broken ore particle identified and the corresponding size of the screen above cumulative yield of granularity greater than boundary granularity are counted;Linear regression analysis is carried out on the above statistical data, and the granularity characteristic equation and curve of the broken ore particle with granularity greater than boundary granularity are obtained, and the granularity characteristic curve of all broken products is obtained accordingly;Integrate the above data, and calculate the relevant data required in subsequent production process.The present application can obtain the important data required in subsequent production, such as particle size distribution, screen above cumulative yield, each particle level yield and P80 value of broken product without screening, and real-time detection of data can also be realized.

Description

Technical Field

[0001] This invention relates to the field of mineral processing technology, and in particular to a method and system for identifying ore particle size based on the particle size distribution characteristics of crushed products. Background Technology

[0002] The first step in the mineral processing industry is ore crushing and grinding, which is essentially a process of reducing the particle size of the ore. Accurate ore particle size identification is crucial for predicting and optimizing energy consumption in ore crushing and grinding. While traditional screening methods can provide precise particle distribution curves on conveyor belts, they process massive amounts of ore and are too time-consuming, lacking the real-time detection capabilities required for intelligent industrial development.

[0003] With the development of image recognition technology, artificial intelligence-based methods for ore particle size identification have emerged. This method predicts the overall ore particle size distribution curve by identifying the particle size distribution on the surface of ore piles on conveyor belts. However, due to limitations in the development of image recognition algorithms, this method is powerless to identify fine-grained mineral particles and often identifies fine-grained ore particle groups as whole ore blocks, resulting in significant errors. Summary of the Invention

[0004] This invention provides a method and system for identifying ore particle size based on the particle size distribution characteristics of crushed products, in order to solve the technical problem that existing ore particle size identification technologies are powerless to identify fine-grained mineral particles and often identify fine-grained ore particle groups as whole ore blocks, thereby causing huge errors.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] On one hand, the present invention provides a method for identifying ore particle size based on the particle size distribution characteristics of crushed products, the method comprising:

[0007] Images of the broken products to be inspected are acquired, and the total mass of the broken products to be inspected is calculated.

[0008] The image of the crushed product to be tested is identified to identify crushed ore particles with a particle size larger than the boundary particle size, and the image information of crushed ore particles with a particle size larger than the boundary particle size is obtained.

[0009] Based on the image recognition results, the particle size of the crushed ore particles with a particle size greater than the boundary particle size and the cumulative oversize yield of the corresponding particle size are calculated and statistically analyzed.

[0010] Linear regression analysis was performed on the particle size and cumulative over-screen yield of crushed ore particles larger than the boundary particle size to obtain the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size. Based on the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size, the particle size characteristic equation and particle size characteristic curve of crushed ore particles smaller than the boundary particle size were fitted to obtain the particle size characteristic curve of all crushed products, thereby obtaining the particle size and cumulative over-screen yield of all crushed products.

[0011] Based on the particle size and cumulative yield on the screen of all crushed products, and combined with the total mass of all crushed products, the relevant data required for subsequent production processes are calculated; wherein, the relevant data includes: the mass, yield and P80 value of each particle size of the crushed products, and the total mass of the crushed products.

[0012] Furthermore, the broken product to be tested is located on the conveyor belt;

[0013] The acquisition of images of the broken product to be inspected includes:

[0014] An industrial high-definition camera is used to photograph the broken product to be inspected, thereby obtaining an image of the broken product. The industrial high-definition camera is a plurality of cameras, which are placed above the conveyor belt at a preset distance apart. The shooting direction of each industrial high-definition camera intersects the broken product on the conveyor belt at a preset angle. During each shooting, multiple cameras simultaneously photograph the broken product on the conveyor belt.

[0015] Furthermore, the image of the crushed product to be tested is identified to identify crushed ore particles with a particle size larger than the boundary particle size, thus obtaining image information of crushed ore particles with a particle size larger than the boundary particle size, including:

[0016] Images of broken products captured by multiple industrial high-definition cameras are fused together. The parts with the same content in the multiple images are merged, and the parts with different content are stitched together to obtain the fused image.

[0017] A preset recognition algorithm is used to identify the fused image, thereby identifying broken ore particles with a particle size larger than the boundary particle size. The identified broken ore particles with a particle size larger than the boundary particle size are then subjected to image segmentation and noise reduction processing to obtain image information of the broken ore particles with a particle size larger than the boundary particle size. The image information includes the size, shape, outline, and particle boundary information of each identified ore particle.

[0018] Further, the step of calculating and statistically analyzing the particle size of the identified crushed ore particles larger than the boundary particle size and the cumulative over-the-screen yield of the corresponding particle size based on the image recognition results includes:

[0019] Based on the image recognition results, the image is binarized to obtain the area of ​​the two-dimensional irregular shape of each identified broken ore particle with a particle size larger than the boundary particle size. Based on the area of ​​the two-dimensional irregular shape of the ore particle, the diameter of each ore particle is calculated using the equivalent circle diameter method, as shown in the following formula:

[0020]

[0021] Where d is the equivalent circle diameter; S is the area of ​​a single particle's two-dimensional irregular shape; π is taken as 3.14;

[0022] After completing the particle size calculation, each particle is numbered and arranged in descending order of particle size. The cumulative yield on the sieve for the corresponding particle size is then calculated. The formula for calculating the cumulative yield on the sieve is as follows:

[0023]

[0024] Where R is the cumulative yield over the sieve; m i represents the mass of the i-th ore particle; k represents the number of crushed ore particles larger than the boundary particle size in the image of the crushed product to be detected; n represents the total number of ore particles in the image of the crushed product to be detected; S i ρ represents the area of ​​the two-dimensional irregular shape of the i-th ore in the image of the crushed product to be detected; ρ represents the density of the ore particles; S0 represents the total area of ​​the two-dimensional irregular shape of all the identified crushed products after binarization.

[0025] Furthermore, the particle size characteristic curve is the Rossin-Rammel particle size characteristic curve, with the horizontal axis being lg(x) and the vertical axis being... The equation of the curve is expressed as follows:

[0026]

[0027] Where x represents the particle size of the crushed product; R represents the cumulative yield over the screen; e represents the natural constant, with a value of 2.71828; b represents a parameter related to the fineness of the product; n represents a parameter related to the material properties; when x and R are known, the values ​​of n and b can be obtained from the intersection of the particle size characteristic curve on the horizontal and vertical axes.

[0028] The particle size characteristic equation is the Rossin-Rammel particle size characteristic equation, and its calculation formula is as follows:

[0029] Furthermore, the formulas for calculating the yield of each particle size fraction of the crushed product are as follows:

[0030]

[0031] Among them, x1 and x2 are the particle sizes of the crushed products, where x1 < x2; γ is the yield of the -x2 + x1 particle size fraction; b represents a parameter related to the fineness of the product; n represents a parameter related to the material properties; R1 represents the cumulative oversize yield of the particle size x1; R2 represents the cumulative oversize yield of the particle size x2.

[0032] Furthermore, the formula for calculating the mass of each particle size fraction of the crushed product is:

[0033] m = M·γ

[0034] Among them, m is the mass of a certain particle size fraction; M is the total mass of all crushed products; γ is the yield of a certain particle size fraction.

[0035] Furthermore, the formula for calculating the P80 value is as follows:

[0036]

[0037] Among them, P80 is the particle size of the crushed product corresponding to a cumulative oversize yield of 80%; b represents a parameter related to the fineness of the product; n represents a parameter related to the material properties.

[0038] Furthermore, the value range of the boundary particle size is 5 mm to 10 mm.

[0039] On the other hand, the present invention also provides an ore particle size identification system based on the particle size distribution characteristics of crushed products. The ore particle size identification system based on the particle size distribution characteristics of crushed products includes:

[0040] A data acquisition module for:

[0041] Collecting images of the crushed products to be detected and counting the total mass of the crushed products to be detected;

[0042] A data processing module for:

[0043] Identifying the images of the crushed products to be detected, identifying the crushed ore particles with a particle size greater than the boundary particle size, and obtaining the image information of the crushed ore particles with a particle size greater than the boundary particle size;

[0044] Based on the image recognition results, calculating and counting the particle sizes of the identified crushed ore particles with a particle size greater than the boundary particle size and the cumulative oversize yield of the corresponding particle sizes;

[0045] Linear regression analysis was performed on the particle size and cumulative over-screen yield of crushed ore particles larger than the boundary particle size to obtain the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size. Based on the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size, the particle size characteristic equation and particle size characteristic curve of crushed ore particles smaller than the boundary particle size were fitted to obtain the particle size characteristic curve of all crushed products, thereby obtaining the particle size and cumulative over-screen yield of all crushed products.

[0046] Based on the particle size and cumulative yield on the screen of all crushed products, and combined with the total mass of all crushed products, the relevant data required for subsequent production processes are calculated; wherein, the relevant data includes: the mass, yield and P80 value of each particle size of the crushed products, and the total mass of the crushed products;

[0047] The data output module is used for:

[0048] The data processing module outputs the relevant data required for subsequent production processes.

[0049] In another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-described method.

[0050] In another aspect, the present invention also provides a computer-readable storage medium storing at least one instruction that is loaded and executed by a processor to implement the above-described method.

[0051] The beneficial effects of the technical solution provided by this invention include at least the following:

[0052] This invention utilizes an industrial high-definition camera to acquire image information of the crushed product. It then uses a machine vision recognition method to fit and calculate the actual particle size distribution and cumulative yield on the screen of the crushed product. Finally, combined with the quality of the crushed product, it can output the data required for subsequent production. This invention enables real-time monitoring of the particle size distribution information of the crushed product and provides important reference information and guidance for subsequent production. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1This is a schematic diagram of the execution flow of the ore particle size identification method based on the particle size distribution characteristics of crushed products provided in an embodiment of the present invention;

[0055] Figure 2 This is a structural block diagram of an ore particle size identification system based on the particle size distribution characteristics of crushed products provided in an embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0057] First Embodiment

[0058] To address the problems encountered in current methods of obtaining information such as particle size distribution, yield of each particle size class, and P80 value of crushed products through screening, including complex operation, data acquisition delays, inability to monitor crushing process data in real time, and the inability of existing ore particle size identification technologies to identify fine-grained mineral particles (often misidentifying fine-grained ore particles as whole ore blocks, resulting in significant errors), this embodiment employs a machine vision recognition system. Utilizing the particle size distribution characteristics of crushed products, the effective information acquisition steps are divided into six parts: image acquisition, image stitching, image recognition, particle size detection, distribution fitting, and data integration. This provides an ore particle size identification method based on the particle size distribution characteristics of crushed products. The aim is to use a machine vision recognition system and the particle size distribution characteristics method to calculate, statistically analyze, and output relevant data of crushed products, including particle size distribution, cumulative yield on the screen, and P80 value. This achieves real-time monitoring and statistical analysis of the crushing effect, providing guidance for real-time monitoring of particle size detection and distribution, and offering real-time and effective suggestions for subsequent production.

[0059] The method in this embodiment can be implemented by an electronic device, which can be a terminal or a server. The execution flow of the method is as follows: Figure 1 As shown, it includes the following steps:

[0060] S1, acquire images of the broken products to be inspected, and calculate the total mass of the broken products to be inspected;

[0061] It should be noted that this embodiment detects broken products located on a conveyor belt. To achieve this, two industrial high-definition cameras simultaneously capture images of the broken products from different positions, obtaining multiple images of the broken products. The two industrial high-definition cameras are placed a certain distance apart above the conveyor belt, with their shooting directions intersecting the broken products on the belt at a certain angle. Each time an image is captured, both cameras simultaneously photograph the broken products on the belt, thus obtaining two original high-definition images of the broken products after each shot. Furthermore, in this embodiment, a single shot is taken on a unit of broken products along a 1-meter-long conveyor belt at a conveyor speed of 1 m / s. The industrial high-definition cameras are set to capture an image every 1 second to ensure that all broken products passing through the machine vision recognition system on the belt are detected. The entire system operates continuously to achieve real-time detection of broken product information.

[0062] The quality of the crushed products is obtained by weighing with a belt scale for subsequent data statistics and calculations.

[0063] S2, identify the image of the crushed product to be detected, identify the crushed ore particles with a particle size larger than the boundary particle size, and obtain the image information of the crushed ore particles with a particle size larger than the boundary particle size.

[0064] Specifically, in this embodiment, the processing procedure of S2 described above is as follows:

[0065] S21 employs AI algorithms to fuse multiple images of broken products simultaneously captured by two industrial high-definition cameras. This ensures that the captured images cover the entire broken product, capturing every detail. Specifically, it merges identical portions of two images, stitches together dissimilar portions, and enhances details in blurred areas to guarantee a clear image and minimize interference with subsequent operations.

[0066] S22, a preset recognition algorithm is used to recognize the stitched image, identify the broken ore particles whose particle size is larger than the boundary particle size, and perform image segmentation and noise reduction processing on the identified broken ore particles whose particle size is larger than the boundary particle size to enhance the boundary of the identified ore particles and reduce the interference of fine-grained products on the system, thereby obtaining image information of broken ore particles whose particle size is larger than the boundary particle size; wherein, the image information includes: the size, shape, outline and particle boundary information of each identified ore particle.

[0067] It should be noted that the boundary particle size refers to the lower limit of the precise recognition particle size of the machine vision recognition system. The value of the boundary particle size is generally affected by a variety of factors such as the system working environment, the shape and texture of the ore being tested, the dust on the surface of the ore, the resolution of the camera, and the parameters of the system. It is generally 5-10mm. The boundary particle size used in this method is 5mm, which means that the particle size of the ore to be identified and detected should be greater than 5mm.

[0068] S3, based on the image recognition results, calculate and statistically analyze the particle size of the crushed ore particles with a particle size greater than the boundary particle size and the cumulative over-the-screen yield of the corresponding particle size;

[0069] It should be noted that, generally, the particle size of irregularly shaped particles is considered to be represented by the equivalent circular diameter. Therefore, in this embodiment, when detecting and statistically analyzing the particle size of the identified particles, the diameter of a single particle is calculated using the equivalent circular diameter method. This yields the diameters of particles larger than the boundary particle size in all crushed products, and each particle is then numbered and sorted. The specific processing procedure is as follows:

[0070] S31. The image is binarized to obtain the area of ​​the two-dimensional irregular shape of each identified broken ore particle with a particle size larger than the boundary particle size. Based on the area of ​​the two-dimensional irregular shape of the ore particle, the diameter of each ore particle is calculated using the equivalent circle diameter method, as shown in the following formula:

[0071]

[0072] Where d is the equivalent circle diameter; S is the area of ​​a single particle's two-dimensional irregular shape; π is taken as 3.14;

[0073] S32, After completing the particle size calculation, number each particle and arrange them in descending order of particle size. Calculate the cumulative yield data on the sieve for the corresponding particle size. The formula for calculating the cumulative yield on the sieve is as follows:

[0074]

[0075] Where R is the cumulative yield over the sieve; m i represents the mass of the i-th ore particle; k represents the number of crushed ore particles larger than the boundary particle size in the image of the crushed product to be detected; n represents the total number of ore particles in the image of the crushed product to be detected; S i ρ represents the area of ​​the two-dimensional irregular shape of the i-th ore in the image of the crushed product to be detected; ρ represents the density of the ore particles; S0 represents the total area of ​​the two-dimensional irregular shape of all the identified crushed products after binarization.

[0076] S4. Perform linear regression analysis on the particle size and cumulative yield of crushed ore particles larger than the boundary particle size to obtain the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size. Based on the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size, fit the particle size characteristic equation and particle size characteristic curve of crushed ore particles smaller than the boundary particle size to obtain the particle size characteristic curve of all crushed products, and thus obtain the particle size and cumulative yield of all crushed products.

[0077] It's worth noting that numerous studies have shown that the particle size distribution of sub-particle groups after ore crushing follows a statistical distribution. Researchers in the field of mineral processing technology have found that by plotting the logarithm of ore particle size on the x-axis and the cumulative distribution rate of the ore particle group on the y-axis, a straight line segment can be obtained. In 1934, Rosin and Rammler, using statistical methods to organize the particle size distribution of products from crushers and mills, derived the Rosin-Rammler distribution characteristic function applicable to ore crushing and grinding products, which is still in use today. Furthermore, AI-based image recognition technology is accurate and reliable in predicting coarse-grained ores, but often exhibits significant deviations in predicting fine-grained ores.

[0078] Therefore, this embodiment, based on the inherent particle size distribution characteristics of ore crushing and grinding products, namely the Rossin-Lammler characteristic distribution, accurately obtains the particle distribution of coarse-grained ore using AI-based image recognition technology. Based on the characteristic that "the particle size distribution of all products from the crushing operation conforms to the Rossin-Lammler particle size equation," it fits the overall product distribution curve of the ore particle group, thereby calculating the particle distribution of fine-grained ore, obtaining the particle size and cumulative oversize yield data of all crushed products, further deriving the yield of each particle size class, and integrating the weight information recorded by the weighing system to obtain the relevant data required for subsequent production processes. This achieves accurate identification of ore crushing and grinding products.

[0079] Based on the above, the particle size characteristic curve in S4 is the Rossin-Rammel particle size characteristic curve, with the horizontal axis being lg(x) and the vertical axis being... The equation of the curve is expressed as follows:

[0080]

[0081] Where x represents the particle size of the crushed product in mm; R represents the cumulative yield over the screen in %; e represents the natural constant with a value of 2.71828; b represents a parameter related to the fineness of the product; n represents a parameter related to the properties of the material; the values ​​of n and b can be obtained from the intersection of the particle size characteristic curve on the horizontal and vertical axes.

[0082] The particle size characteristic equation is the Rosin-Rammler particle size characteristic equation, and its calculation formula is: R = 100e -bxn .

[0083] The particle size distribution characteristics of particles with a size less than 5 mm also conform to the Rosin-Rammler particle size characteristic equation and curve of the overall crushed product. Therefore, based on the Rosin-Rammler particle size characteristic equation and curve of particles larger than 5 mm, the particle size distribution and cumulative oversize yield information of each particle size fraction of the crushed product below 5 mm can be fitted.

[0084] S5. Based on the particle size and cumulative oversize yield of all crushed products, combined with the total mass of all crushed products, the relevant data required for the subsequent production process are calculated;

[0085] Among them, in this embodiment, the relevant data required for the subsequent production process calculated include: the mass, yield, and P80 value of each particle size fraction of the crushed product, as well as the total mass of the crushed product.

[0086] The yield of each particle size fraction is calculated based on the cumulative oversize yield data, and the calculation formula is as follows:

[0087]

[0088] Among them, x1 and x2 are the particle sizes of the crushed product, x1 < x2, with the unit of mm; γ is the yield of the -x2 + x1 particle size fraction, %, b represents a parameter related to the fineness of the product; n represents a parameter related to the properties of the material; R1 represents the cumulative oversize yield of particle size x1, %, and R2 represents the cumulative oversize yield of particle size x2, %.

[0089] The calculation formula for the mass of each particle size fraction of the crushed product is:

[0090] m = M·γ

[0091] Among them, m is the mass of a certain particle size fraction, with the unit of g; M is the mass of all crushed products, with the unit of g; γ is the yield of a certain particle size fraction, %.

[0092] Furthermore, the calculation formula for the P80 value is as follows:

[0093]

[0094] Among them, P80 is the particle size of the crushed product corresponding to a cumulative oversize yield of 80%, with the unit of mm; b represents a parameter related to the fineness of the product; n represents a parameter related to the properties of the material.

[0095] Based on the above, it should be noted that the particle size analysis process of crushed products is divided into three important parts: image acquisition and recognition, ore particle size calculation and data statistics, and linear regression analysis and fitting. The final accuracy of the particle size analysis of crushed products depends on the accuracy of these three steps. Therefore, this embodiment adopts a modular architecture method to address the three parts of image acquisition and recognition, ore particle size calculation and data statistics, and linear regression analysis and fitting. Through image acquisition, image stitching, image recognition, particle size statistics, distribution fitting, and data integration, the production data required for subsequent production is finally obtained. Thus, a method for ore particle size identification based on the particle size distribution characteristics of crushed products using machine vision is established.

[0096] This method utilizes industrial high-definition cameras to acquire image information of crushed products. It then uses machine vision recognition methods to fit and calculate information such as the particle size distribution and cumulative yield on the screen of the actual crushed products. Finally, combined with the quality of the crushed products, it can output the data required for subsequent production. This method enables real-time monitoring of the particle size distribution information of crushed products and provides important reference information and corresponding guidance for subsequent production.

[0097] To further illustrate the implementation process of this method, we will now apply it to a real-world scenario.

[0098] The experimental object in this embodiment is a section of crushed product from a copper mine beneficiation plant. The maximum particle size is no more than 18mm. The width of the conveyor belt for the section of crushed product is 1m, and the conveying speed is 1m / s. Using this method, the ore on the belt is tested once every 1s. Each test is based on the crushed product of a 1m long belt. The crushed product on the belt is evenly distributed. The weight of the ore tested in a single test is about 600kg.

[0099] The conveyor belt and ore particle size machine vision recognition system are activated. Two industrial high-definition cameras simultaneously photograph the ore on the belt. AI algorithms are used to stitch the two images together to obtain a complete and clear image. Computer algorithms then perform noise reduction and binarization on the processed image to identify two-dimensional images of ore particles larger than 5mm, and perform particle boundary enhancement processing. Computer algorithms are used to obtain the area of ​​the two-dimensional irregular image of the identified particles and calculate the equivalent circle diameter. This is used as the particle size of the ore; the particles for which the particle size calculation has been completed are numbered and sorted from largest to smallest, and then the formula is used... The cumulative oversize yield of the identified crushed product is calculated. In this embodiment, the first scan and identification identified a total of 256 ore particles larger than 5 mm. Further, after calculating the particle size and cumulative oversize yield data of the identified ore, this method performs linear regression analysis based on the above data to obtain the particle size characteristic curve of the ore larger than 5 mm. Then, based on this, the particle size characteristic curve of the ore smaller than 5 mm is fitted, finally obtaining the particle size characteristic curve of all crushed products. The curve expression is as follows: From this equation, we know that b = 1.9767 and n = 1.9213. Therefore, the particle size characteristic equation for all crushed products is: This yields information such as the particle size characteristic equations and particle size characteristic curves for all crushed products. During the initial identification and calculation process in this embodiment, the quantum system uses a belt scale to obtain the mass data of the crushed products in this experiment, which is 592.65 kg. By integrating the particle size characteristic equations and particle size characteristic curves of all crushed products with the mass data of the crushed products, the algorithm calculates the data required for subsequent production. The calculation results for the relevant data are as follows:

[0100] "+0.5-1mm particle size yield":

[0101]

[0102] "+0.5-1mm particle size":

[0103] m=M·γ=592.65×45.49%=269.60kg;

[0104] “P80 value”:

[0105]

[0106] The obtained data is then transmitted to the next production process.

[0107] The entire process is completed within 1 second. Immediately after completion, the next batch of crushed products is identified, calculated, and statistically analyzed. The above process is repeated to achieve real-time monitoring of the crushed products on the conveyor belt.

[0108] Second Embodiment

[0109] This embodiment provides an ore particle size identification system based on the particle size distribution characteristics of crushed products. The ore particle size identification system based on the particle size distribution characteristics of crushed products is as follows: Figure 2 As shown, it includes the following modules:

[0110] The data acquisition module is used for:

[0111] Images of the broken products to be inspected are acquired, and the total mass of the broken products to be inspected is calculated.

[0112] The data processing module is used for:

[0113] The image of the crushed product to be tested is identified to identify crushed ore particles with a particle size larger than the boundary particle size, and the image information of crushed ore particles with a particle size larger than the boundary particle size is obtained.

[0114] Based on the image recognition results, the particle size of the crushed ore particles with a particle size greater than the boundary particle size and the cumulative oversize yield of the corresponding particle size are calculated and statistically analyzed.

[0115] Linear regression analysis was performed on the particle size and cumulative over-screen yield of crushed ore particles larger than the boundary particle size to obtain the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size. Based on the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size, the particle size characteristic equation and particle size characteristic curve of crushed ore particles smaller than the boundary particle size were fitted to obtain the particle size characteristic curve of all crushed products, thereby obtaining the particle size and cumulative over-screen yield of all crushed products.

[0116] Based on the particle size and cumulative yield on the screen of all crushed products, and combined with the total mass of all crushed products, the relevant data required for subsequent production processes are calculated; wherein, the relevant data includes: the mass, yield and P80 value of each particle size of the crushed products, and the total mass of the crushed products;

[0117] The data output module is used for:

[0118] The data processing module outputs the relevant data required for subsequent production processes.

[0119] The ore particle size identification system based on the particle size distribution characteristics of crushed products in this embodiment corresponds to the ore particle size identification method based on the particle size distribution characteristics of crushed products in the first embodiment described above. The functions implemented by each module in the ore particle size identification system based on the particle size distribution characteristics of crushed products in this embodiment correspond one-to-one with the process steps in the ore particle size identification method based on the particle size distribution characteristics of crushed products in the first embodiment described above; therefore, they will not be repeated here.

[0120] Third Embodiment

[0121] This embodiment provides an electronic device, which includes a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment.

[0122] The electronic device can vary considerably depending on its configuration or performance, and may include one or more processors (central processing units, CPUs) and one or more memories, wherein the memories store at least one instruction that is loaded by the processor and executed in accordance with the above method.

[0123] Fourth embodiment

[0124] This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0125] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0126] 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 block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0128] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0129] Finally, it should be noted that the above description represents a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make various improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A method for identifying ore particle size based on the particle size distribution characteristics of crushed products, characterized in that, include: Images of the broken products to be inspected are acquired, and the total mass of the broken products to be inspected is calculated. The image of the crushed product to be tested is identified to identify crushed ore particles with a particle size larger than the boundary particle size, and the image information of crushed ore particles with a particle size larger than the boundary particle size is obtained. Based on the image recognition results, the particle size of the crushed ore particles with a particle size greater than the boundary particle size and the cumulative oversize yield of the corresponding particle size are calculated and statistically analyzed. Linear regression analysis was performed on the particle size and cumulative over-screen yield of crushed ore particles larger than the boundary particle size to obtain the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size. Based on the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size, the particle size characteristic equation and particle size characteristic curve of crushed ore particles smaller than the boundary particle size were fitted to obtain the particle size characteristic curve of all crushed products, thereby obtaining the particle size and cumulative over-screen yield of all crushed products. Based on the particle size and cumulative yield on the screen of all crushed products, and combined with the total mass of all crushed products, the relevant data required for subsequent production processes are calculated; wherein, the relevant data includes: the mass, yield and P80 value of each particle size of the crushed products, and the total mass of the crushed products; The calculation and statistical analysis of the particle size of the identified crushed ore particles larger than the boundary particle size, based on image recognition results, and the cumulative over-sieve yield of the corresponding particle size, includes: Based on the image recognition results, the image is binarized to obtain the area of ​​the two-dimensional irregular shape of each identified broken ore particle with a particle size larger than the boundary particle size. Based on the area of ​​the two-dimensional irregular shape of the ore particle, the diameter of each ore particle is calculated using the equivalent circle diameter method, as shown in the following formula: ； in, The equivalent circle diameter; The area of ​​a single particle's two-dimensional irregular shape; Take 3.14; After completing the particle size calculation, each particle is numbered and arranged in descending order of particle size. The cumulative yield on the sieve for the corresponding particle size is then calculated. The formula for calculating the cumulative yield on the sieve is as follows: ； in, Cumulative yield over the sieve; Indicates the first i The mass of each ore particle; k This indicates the number of crushed ore particles in the image of the crushed product to be inspected that have a particle size larger than the boundary particle size; n This indicates the total number of ore particles in the image of the crushed product to be inspected; The image representing the broken product to be inspected. i The area of ​​a two-dimensional irregular shape of an ore; S0 represents the density of the ore particles; S0 represents the total area of ​​the two-dimensional irregular shape of all identified crushed products after binarization. The particle size characteristic curve is the Rossin-Lammler particle size characteristic curve, and the horizontal axis of the curve is... The vertical axis is The equation of the curve is expressed as follows: ； in, Indicates the particle size of the crushed product; Indicates the cumulative yield over the sieve; This represents the natural constant, with a value of 2.71828. Parameters related to product fineness; Indicates parameters related to material properties; in and When known, and The value can be obtained from the intersection of the particle size characteristic curve on the horizontal and vertical axes; The particle size characteristic equation is the Rossin-Rammel particle size characteristic equation, and its calculation formula is as follows: .

2. The ore particle size identification method based on the particle size distribution characteristics of crushed products as described in claim 1, characterized in that, The broken product to be tested is located on the conveyor belt; The acquisition of images of the broken product to be inspected includes: An industrial high-definition camera is used to photograph the broken product to be inspected, thereby obtaining an image of the broken product. The industrial high-definition camera is a plurality of cameras, which are placed above the conveyor belt at a preset distance apart. The shooting direction of each industrial high-definition camera intersects the broken product on the conveyor belt at a preset angle. During each shooting, multiple cameras simultaneously photograph the broken product on the conveyor belt.

3. The ore particle size identification method based on the particle size distribution characteristics of crushed products as described in claim 2, characterized in that, The image of the crushed product to be inspected is identified to identify crushed ore particles with a particle size larger than the boundary particle size, thus obtaining image information of the crushed ore particles with a particle size larger than the boundary particle size, including: Images of broken products captured by multiple industrial high-definition cameras are fused together. The parts with the same content in the multiple images are merged, and the parts with different content are stitched together to obtain the fused image. A preset recognition algorithm is used to identify the fused image, thereby identifying broken ore particles with a particle size larger than the boundary particle size. The identified broken ore particles with a particle size larger than the boundary particle size are then subjected to image segmentation and noise reduction processing to obtain image information of the broken ore particles with a particle size larger than the boundary particle size. The image information includes the size, shape, outline, and particle boundary information of each identified ore particle.

4. The ore particle size identification method based on the particle size distribution characteristics of crushed products as described in claim 1, characterized in that, The formulas for calculating the yield of each particle size of the crushed product are as follows: ； in, , For the particle size of the crushed product, < ; For a certain particle size yield; Parameters related to product fineness; Parameters related to the properties of materials; Indicates granularity as Cumulative yield on the sieve; Indicates granularity as The cumulative yield on the sieve.

5. The ore particle size identification method based on the particle size distribution characteristics of crushed products as described in claim 1, characterized in that, The formula for calculating the mass of each particle size of the crushed product is as follows: ； in, The mass of a certain particle size; M For the quality of all crushed products; γ The yield for a certain particle size.

6. The ore particle size identification method based on the particle size distribution characteristics of crushed products as described in claim 1, characterized in that, The formula for calculating the P80 value is as follows: ； in, This refers to the particle size of the crushed product when the cumulative yield over the screen is 80%. b Parameters related to product fineness; n These represent parameters related to the properties of the material.

7. The ore particle size identification method based on the particle size distribution characteristics of crushed products as described in any one of claims 1 to 6, characterized in that, The boundary particle size ranges from 5 mm to 10 mm.

8. A particle size identification system for ore based on the particle size distribution characteristics of crushed products, characterized in that, include: The data acquisition module is used for: Images of the broken products to be inspected are acquired, and the total mass of the broken products to be inspected is calculated. The data processing module is used for: The image of the crushed product to be tested is identified to identify crushed ore particles with a particle size larger than the boundary particle size, and the image information of crushed ore particles with a particle size larger than the boundary particle size is obtained. Based on the image recognition results, the particle size of the crushed ore particles with a particle size greater than the boundary particle size and the cumulative oversize yield of the corresponding particle size are calculated and statistically analyzed. Linear regression analysis was performed on the particle size and cumulative over-screen yield of crushed ore particles larger than the boundary particle size to obtain the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size. Based on the particle size characteristic equation and particle size characteristic curve of crushed ore particles larger than the boundary particle size, the particle size characteristic equation and particle size characteristic curve of crushed ore particles smaller than the boundary particle size were fitted to obtain the particle size characteristic curve of all crushed products, thereby obtaining the particle size and cumulative over-screen yield of all crushed products. Based on the particle size and cumulative yield on the screen of all crushed products, and combined with the total mass of all crushed products, the relevant data required for subsequent production processes are calculated; wherein, the relevant data includes: the mass, yield and P80 value of each particle size of the crushed products, and the total mass of the crushed products; The data output module is used for: Output the relevant data required for the subsequent production process calculated by the data processing module; Based on image recognition results, the particle size of the identified crushed ore particles larger than the boundary particle size and the cumulative oversize yield of the corresponding particle size are calculated and statistically analyzed, including: Based on the image recognition results, the image is binarized to obtain the area of ​​the two-dimensional irregular shape of each identified broken ore particle with a particle size larger than the boundary particle size. Based on the area of ​​the two-dimensional irregular shape of the ore particle, the diameter of each ore particle is calculated using the equivalent circle diameter method, as shown in the following formula: ； in, The equivalent circle diameter; The area of ​​a single particle's two-dimensional irregular shape; Take 3.14; After completing the particle size calculation, each particle is numbered and arranged in descending order of particle size. The cumulative yield on the sieve for the corresponding particle size is then calculated. The formula for calculating the cumulative yield on the sieve is as follows: ； in, Cumulative yield over the sieve; Indicates the first i The mass of each ore particle; k This indicates the number of crushed ore particles in the image of the crushed product to be inspected that have a particle size larger than the boundary particle size; n This indicates the total number of ore particles in the image of the crushed product to be inspected; The image representing the broken product to be inspected. i The area of ​​a two-dimensional irregular shape of an ore; S0 represents the density of the ore particles; S0 represents the total area of ​​the two-dimensional irregular shape of all identified crushed products after binarization. The particle size characteristic curve is the Rossin-Lammler particle size characteristic curve, and the horizontal axis of the curve is... The vertical axis is The equation of the curve is expressed as follows: ； in, Indicates the particle size of the crushed product; Indicates the cumulative yield over the sieve; This represents the natural constant, with a value of 2.71828. Parameters related to product fineness; Indicates parameters related to material properties; in and When known, and The value can be obtained from the intersection of the particle size characteristic curve on the horizontal and vertical axes; The particle size characteristic equation is the Rossin-Rammel particle size characteristic equation, and its calculation formula is as follows: .

Images