Novel crushing and grinding energy discrimination method based on mineral fracture morphology characteristics

Abstract

A novel crushing and grinding energy distinguishing method based on mineral fracture morphology characteristics comprises the steps that firstly, magnetic iron ore particles of the same size fraction crushed by different crushing energies are scanned through an electron microscope, the relation between the intergranular fracture proportion and the crushing energy is analyzed, and when the crushing energy reaches a certain value, the intergranular fracture proportion is decreased, and the transgranular fracture proportion is increased; further scanning magnetic iron ore particles with different particle size levels after crushing with the same crushing energy through an electron microscope, analyzing the relationship between the intergranular fracture ratio of the different particle size levels and the crushing energy, and then calculating and establishing the function relationship between the intergranular fracture ratio of the different particle size levels and the crushing energy after single-particle magnetic iron ore is crushed; meanwhile, the function relation between the intergranular fracture proportion of different particle fractions and the crushing energy after particle swarm magnetite is crushed is calculated and established, the correlation R2 of the function is larger than 0.95, and therefore the novel crushing and grinding energy distinguishing method based on the mineral fracture morphology characteristics is provided. And quantifiable basic conditions are provided for further research on crushing of magnetite ore and other minerals.

Description

Technical Field

[0001] The present invention relates to the technical field of particle morphology analysis after ore crushing, and particularly to a new method for discriminating grinding energy based on the fracture morphology characteristics of minerals. Background Art

[0002] The crushing process of ore is a prerequisite for sorting and smelting. As a raw material for steel smelting, the surface morphology of magnetite ore particles after being crushed by a crushing device has both intergranular fractures and transgranular fractures. The crushing energy applied by the crushing device to magnetite ore is the cause of ore crushing and also the cause of the formation of the surface morphology. What is the specific relationship between the crushing energy and the surface morphology of magnetite ore particles after crushing? There is no in-depth research in the prior art. More specifically, the relationship between the proportion of intergranular fractures after crushing and the crushing energy has not been mentioned in the literature. The inventor believes that it is necessary to establish a judgment method for the relationship between the two to guide the research on magnetite ore crushing. Summary of the Invention

[0003] The purpose of the present invention is to solve the above problems and provide a new method for discriminating grinding energy based on the fracture morphology characteristics of minerals.

[0004] The technical solution of the present invention is: a new method for discriminating grinding energy based on the fracture morphology characteristics of minerals, comprising the following steps:

[0005] a. Use a drop hammer testing machine to crush a magnetite ore sample multiple times to determine that the critical energy for magnetite ore fracture is 100.00 J. Obtain the fracture surface morphology of the magnetite ore at this time through electron microscopy scanning to obtain the morphology of the fracture surface; the determination of the critical energy for ore fracture provides a basis for adjusting different crushing energies later. After electron microscopy scanning and observation, it is determined that the main fracture type of the magnetite ore at this time is intergranular fracture.

[0006] b. Adjust the drop hammer testing machine and use different crushing energies to crush single-particle magnetite ore. The crushing energy gradually increases or decreases. Obtain the fracture surface morphologies of magnetite corresponding to each crushing energy through electron microscopy scanning, arrange and compare them in sequence, and determine the crushing energy level at which the fracture surface type changes from a larger proportion of intergranular fractures to a larger proportion of transgranular fractures; by adjusting the crushing energy, observe the change in the proportion of intergranular fractures and explore the preliminary relationship between the proportion of intergranular fractures and the crushing energy.

[0007] c. Select the particles after crushing single-particle magnetite ore at the same crushing energy, classify the crushed magnetite ore particles by screening, obtain the fracture surface pictures of magnetite ore particles at each different particle size level through electron microscopy scanning, and count the proportion of intergranular fractures among them; after screening, observe the proportion of intergranular fractures in particles at different particle size levels through electron microscopy. As the particle size decreases, the proportion of intergranular fractures gradually decreases.

[0008] d. Repeat step c multiple times. For the fracture surfaces of magnetite ores with different particle sizes under different crushing energies in step b, count the proportion of intergranular fractures. Explore the relationship between different crushing energies and the proportion of intergranular fractures in particles of different size grades. Establishing a quantitative correspondence is conducive to establishing its functional relationship.

[0009] e. Summarize the data in step d, plot points in a coordinate system, and then fit a curve according to the plotted points to establish a functional relationship between the proportion of intergranular fractures in particles of different particle size grades after crushing of single-particle magnetite ore and the crushing energy.

[0010] f. According to the processes in steps b - d above, crush the bulk magnetite ore at different crushing energies, classify the particles after crushing at each crushing energy, obtain the fracture surface pictures of each particle size grade through electron microscopy scanning, and count the proportion of intergranular fractures among them. For the bulk magnetite ore, the same method of crushing and electron microscopy observation as that of the above single-particle magnetite ore is used. Continuously adjust the energy level and repeat multiple times to obtain the data of the proportion of intergranular fractures after crushing of the bulk.

[0011] g. Summarize the data in step f and establish a functional relationship between the proportion of intergranular fractures in particles of different particle size grades after crushing of the bulk magnetite ore and the crushing energy. After establishing this function, it can be used to guide the adjustment of the crushing energy during ore crushing.

[0012] Preferably, the selected crushing energies in step b are 226.01 J, 376.69 J, 527.36 J, 640.37 J, 753.38 J, and 866.38 J in sequence. It is determined that within the range of 226.01 J - 640.37 J of the crushing energy in step b, the proportion of intergranular fractures is relatively large in the particle fracture types of magnetite ore. When the crushing energy reaches 753.38 J, intergranular - transgranular coupled fractures occur. When the crushing energy reaches 866.38 J, the proportion of transgranular fractures is relatively large in the particle fracture types of magnetite ore.

[0013] Preferably, the particle size classification for electron microscopy observation of the particles after crushing of single-particle magnetite ore in step c is: -1.180 + 0.900, -0.900 + 0.600, -0.600 + 0.300, -0.300 + 0.150, -0.150 + 0.074, -0.074 + 0.038, -0.038 + 0.019, with the unit of mm. The functional relationship between the proportion of intergranular fractures in different particle size grades and the crushing energy in step e is as follows

[0014] -1.180 + 0.900 y = 227.353 - 28.2791nx R 2 = 0.96;

[0015] -0.900 + 0.600y = 198.995 - 25.304lnx R 2 = 0.96;

[0016] -0.600 + 0.300y = 109.849 - 13.597lnx R 2 = 0.95;

[0017] -0.300 + 0.150y = 48.031 - 5.975lnx R 2 = 0.95;

[0018] -0.150 + 0.074y = 27.055 - 3.185lnx R 2 = 0.98;

[0019] -0.074 + 0.038y = 21.584 - 2.873lnx R 2 = 0.95;

[0020] -0.038 + 0.019y = 9.662 - 1.209lnx R 2 = 0.94;

[0021] In each of the above formulas, y is the intergranular fracture ratio, x is the crushing energy, and R 2 is the function correlation. Preferably, in step g, the crushing energies of the granular magnetite ore are 332.59 J, 432.36 J, 532.14 J, 631.25 J, and 731.69 J in sequence; the particle size grading for electron microscope observation after crushing is: -1.180 + 0.900, -0.900 + 0.600, -0.600 + 0.300, -0.300 + 0.150, -0.150 + 0.074, -0.074 + 0.038, -0.038 + 0.019, with the unit of mm; the functional relationships between the intergranular fracture ratios and the crushing energies for different particle size levels are as follows

[0022] -1.180 + 0.900y = 289.187 - 37.679lnx R 2 = 0.98;

[0023] -0.900 + 0.600y = 244.894 - 31.551lnx R 2 = 0.98;

[0024] -0.600 + 0.300y = 198.682 - 27.897lnx R 2 = 0.99;

[0025] -0.300 + 0.150y = 64.844 - 8844lnx_R 2 = 0.96;

[0026] -0.150 + 0.074y = 36.708 - 4.984lnx_R 2 = 0.98;

[0027] -0.074 + 0.038y = 33.116 - 4.660lnx_R 2 = 0.96;

[0028] -0.038 + 0.019y = 14.923 - 2.096lnx_R 2 = 0.95;

[0029] In each of the above formulas, y is the intergranular fracture ratio, x is the crushing energy, and R 2 is the function correlation. Preferably, in step b, particles with a median particle size range of -10.000 + 5.000 mm after being crushed with different crushing energies are selected for electron microscopy scanning. Selecting the median range corresponding to the particle size of the particles after being crushed with different crushing energies is more representative and comparable, and the comparison results are also reasonable.

[0030] Preferably, in steps c and f, a magnetite fracture morphology classification and recognition software is used. This software is established through deep learning and obtains an available model through learning and training with manually calibrated pictures. Through this model, picture recognition can be quickly achieved, improving the picture recognition efficiency and the progress speed of steps c and f. The establishment and application steps of this software are as follows;

[0031] 61. Crush magnetite ore through a crushing device, collect the crushed magnetite ore particles and evenly divide them into N groups. After each group is spread out, electron microscopy scanning is carried out, and the N scanned pictures after scanning are imported into a computer, where N ≥ 1000;

[0032] 62. Manually calibrate the surface morphology of the particles in each area of each scanned picture. Different particle morphologies are respectively calibrated as one of the two fracture types, intergranular fracture or transgranular fracture, and the number of intergranular fracture particles and transgranular fracture particles in this picture are summarized and calculated. Repeat this step to obtain N calibrated pictures.

[0033] 63. Establish a fully convolutional neural network model based on the SSD algorithm in the computer for learning and training the calibrated pictures completed in step 62.

[0034] 64. Import most of the calibrated pictures completed in step 62 into the fully convolutional neural network model based on the SSD algorithm on the computer for deep learning training. After deep learning training, a picture recognition model is formed. Use the remaining calibrated pictures to test the picture recognition model. If the test accuracy meets the requirements, stop the deep learning training and retain the trained model. If the test accuracy does not meet the requirements, continue with deep learning training and testing until the test accuracy meets the requirements, and retain the trained picture recognition model.

[0035] 65. Establish a connection between the software in the computer and the picture recognition model obtained in step 64 above.

[0036] 66. Collect the ore particles that have completed the crushing work in step c or f and require particle morphology recognition. After spreading them out flat, take pictures by electron microscope scanning to form pictures to be recognized.

[0037] 67. Import the pictures to be recognized into the above software through the software, and then use the picture recognition model to perform picture recognition, output the number of transgranular fractures and the number of intergranular fractures of the ore particles in the picture, calculate the intergranular fracture ratio, and output the recognized and calculated data through the software for use in step e or g.

[0038] Preferably, the manual calibration in step 62 is carried out based on the sample of the surface morphology picture of the ore particles with intergranular fracture. In the sample of this picture, the fracture surface shows a sugar cube-like pattern and the edges of the fracture surface interface are clear.

[0039] Preferably, the manual calibration in step 62 is carried out based on the sample of the surface morphology picture of the ore particles with transgranular fracture. In the sample of this picture, the fracture surface shows a step pattern, or a river pattern, or a tearing pattern, or a secondary crack pattern.

[0040] Preferably, 70% of the calibrated pictures are used for deep learning training in step 64, and the remaining 30% of the calibrated pictures are used to test the trained model.

[0041] Preferably, the required test accuracy in step 64 is not less than 94%.

[0042] The beneficial effects of the present invention are as follows: The present invention proposes a new method for discriminating grinding energy based on the fracture morphology characteristics of minerals. First, magnetite ore particles of the same particle size after being crushed with different crushing energies are scanned by an electron microscope to analyze the relationship between the proportion of intergranular fractures and the crushing energy. When the crushing energy reaches a certain value, the proportion of intergranular fractures decreases and the proportion of transgranular fractures increases. Further, magnetite ore particles of different particle size levels after being crushed with the same crushing energy are scanned by an electron microscope to analyze the relationship between the proportion of intergranular fractures of different particle size levels and the crushing energy. Then, the functional relationship between the proportion of intergranular fractures of different particle size levels and the crushing energy after a single particle of magnetite ore is crushed is calculated and established. At the same time, the functional relationship between the proportion of intergranular fractures of different particle size levels and the crushing energy after a particle group of magnetite ore is crushed is calculated and established. The correlation R of this function 2 > 0.95, thus proposing a new method for discriminating grinding energy based on the fracture morphology characteristics of minerals, providing quantifiable basic conditions for further research on the crushing of magnetite ore and other minerals.

[0043] In this judgment method, in order to quickly identify and judge how many intergranular fractures there are and what proportion they account for in the magnetite ore particles after crushing, an identification system and software based on the deep learning method are established, so as to quickly identify and count the surface morphology of the magnetite ore particles after crushing, quickly obtain the number and proportion of intergranular fractures, and provide a faster prerequisite method and tool for the establishment of the above function. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is the surface morphology of magnetite ore at critical fracture in step a of the judgment method of the present invention;

[0045] Figure 2 is the fracture morphology of magnetite ore under different crushing energies in step b of the judgment method of the present invention, where

[0046] (a) is the fracture morphology of magnetite ore when the crushing energy is 226.01 J;

[0047] (b) is the fracture morphology of magnetite ore when the crushing energy is 376.69 J;

[0048] (c) is the fracture morphology of magnetite ore when the crushing energy is 527.36 J;

[0049] (d) is the fracture morphology of magnetite ore when the crushing energy is 640.37 J;

[0050] (e) is the fracture morphology of magnetite ore when the crushing energy is 753.38 J;

[0051] (f) is the fracture morphology of magnetite ore when the crushing energy is 866.38 J;

[0052] Figure 3These are the fracture morphologies of magnetite ores with different particle size grades under the same crushing energy in step c of the judgment method of the present invention, where

[0053] (a) is the fracture morphology of magnetite ore with a particle size grade of -2.000 + 1.180 mm;

[0054] (b) is the fracture morphology of magnetite ore with a particle size grade of -1.180 + 0.900 mm;

[0055] (c) is the fracture morphology of magnetite ore with a particle size grade of -0.900 + 0.600 mm;

[0056] (d) is the fracture morphology of magnetite ore with a particle size grade of -0.600 + 0.300 mm;

[0057] (e) is the fracture morphology of magnetite ore with a particle size grade of -0.300 + 0.150 mm;

[0058] (f) is the fracture morphology of magnetite ore with a particle size grade of -0.150 + 0.074 mm;

[0059] (g) is the fracture morphology of magnetite ore with a particle size grade of -0.074 + 0.038 mm;

[0060] (h) is the fracture morphology of magnetite ore with a particle size grade of -0.038 + 0.019 mm;

[0061] Figure 4 This is the relationship diagram between the intergranular fracture ratio and the crushing energy of single-particle magnetite ore after crushing at different particle size grades, which is drawn by summarizing the data in step e of the judgment method of the present invention;

[0062] Figure 5 This is the relationship diagram between the intergranular fracture ratio and the crushing energy of particle group magnetite ore after crushing at different particle size grades, which is drawn by summarizing the data in step g of the judgment method of the present invention. Detailed implementation manners

[0063] Example 1: Refer to Figures 1-4 , a new method for discriminating grinding energy based on the fracture morphology characteristics of minerals, includes the following steps:

[0064] a. Use a drop hammer testing machine to crush the magnetite ore sample multiple times to determine that the critical energy for the fracture of magnetite ore is 100.00 J. Obtain the fracture surface morphology of the magnetite ore at this time through electron microscope scanning, and obtain the morphology of the fracture surface; the determination of the critical energy for ore fracture provides a basis for adjusting different crushing energies later, and the crushing energy is not lower than this critical energy. After electron microscope scanning and observation, it is determined that the main fracture type of the magnetite ore at this time is intergranular fracture.

[0065] b. Adjust the heavy hammer test machine, use different crushing energies to crush single-particle magnetite ore, the crushing energy gradually increases or decreases, obtain the fracture morphology of the magnetite corresponding to each crushing energy through electron microscope scanning, arrange and compare them in sequence, and determine the crushing energy level at which the fracture type changes from a larger proportion of intergranular fracture to a larger proportion of transgranular fracture; by adjusting the crushing energy, observe the change in the proportion of intergranular fracture, and explore the qualitative relationship between the proportion of intergranular fracture and crushing energy. In step b, select the particles with a median particle size range of -10.000+5.000mm after crushing with different crushing energies for electron microscope scanning. The median range corresponding to the particle size of the particles crushed with different crushing energies is more representative and comparable, and the comparison result is also reasonable. The crushing energies selected in the step b are 226.01J, 376.69J, 527.36J, 640.37J, 753.38J, and 866.38J, respectively. In step b, when the crushing energy is determined to be in the range of 226.01J-640.37J, the proportion of intergranular fracture in the particle fracture type of the magnetite ore is relatively large. When the crushing energy reaches 753.38J, intergranular-transgranular coupled fracture occurs. When the crushing energy reaches 866.38J, the proportion of transgranular fracture in the particle fracture type of the magnetite ore is relatively large.

[0066] c. Select the crushed particles of single-particle magnetite ore under the same crushing energy, classify the crushed magnetite ore particles by screening, obtain the fracture pictures of magnetite ore particles of different particle sizes by scanning with an electron microscope, and count the proportion of intergranular fractures; after screening, observe the proportion of intergranular fractures in particles of different particle sizes by an electron microscope. As the particle size decreases, the proportion of intergranular fractures gradually decreases.

[0067] d. Repeat step c for multiple times, and count the proportion of intergranular fractures of the single magnetite ore particles at different crushing energies and different particle sizes in step b; explore the relationship between different crushing energies and the proportion of intergranular fractures in particles of different particle sizes, and establish a functional relationship through quantitative correspondence.

[0068] e. Summarize the data in step d, plot the points in the coordinate system, and then fit the curve based on the plotted points. Figure 4 , establish the functional relationship between the proportion of intergranular fracture and crushing energy of particles of different particle sizes after single-particle magnetite crushing,

[0069] The particle size classification for the electron microscope observation of the particles after crushing single-particle magnetite ore in step c is: -1.180 + 0.900, -0.900 + 0.600, -0.600 + 0.300, -0.300 + 0.150, -0.150 + 0.074, -0.074 + 0.038, -0.038 + 0.019, with the unit of mm; the functional relationship between the intergranular fracture ratio and the crushing energy for different particle size levels in step e is as follows

[0070] -1.180 + 0.900 y = 227.353 - 28.2791nx R2 = 0.96;

[0071] -0.900 + 0.600 y = 198.995 - 25.304lnx R2 = 0.96;

[0072] -0.600 + 0.300 y = 109.849 - 13.5971nx R2 = 0.95;

[0073] -0.300 + 0.150 y = 48.031 - 5.9751nx R2 = 0.95;

[0074] -0.150 + 0.074 y = 27.055 - 3.185lnx R2 = 0.98;

[0075] -0.074 + 0.038 y = 21.584 - 2.873lnx R2 = 0.95;

[0076] -0.038 + 0.019 y = 9.662 - 1.209lnx R2 = 0.94;

[0077] In each of the above formulas, y is the intergranular fracture ratio, x is the crushing energy, and R2 is the function correlation.

[0078] As shown Figure 4 in the figure, the intergranular fracture ratio of magnetite ore particles gradually decreases as the crushing energy increases. As the crushing energy increases, the intergranular fracture ratio of magnetite decreases, and the proportion of transgranular fracture particles increases. The intergranular fracture ratio of particles in different particle size ranges shows a logarithmic decreasing relationship with the magnitude of the crushing energy, and the equation fitting degree is relatively high. Therefore, the magnitude of the crushing energy can be judged through the intergranular fracture ratio. The intergranular fracture ratio in the -0.074 + 0.038mm and -0.038 + 0.019mm particle size grades is relatively low, mainly transgranular fracture. Therefore, there will be a large error in judging the magnitude of the crushing energy using the intergranular fracture ratio of fine particle size grades,

[0079] while the difference in the intergranular fracture ratio of the -1.180 + 0.900mm particle size grade under different crushing energies is relatively obvious. Therefore, it can be used as the particle size grade for judging the crushing energy.

[0080] In step c, a software for classifying and identifying the fracture surface morphology of magnetite ore is used. The establishment and application steps of this software are as follows;

[0081] 61. Crush the magnetite ore through a crushing device, collect the crushed magnetite ore particles and evenly divide them into N groups. After each group is flattened, perform electron microscopy scanning. Import the N scanned pictures after scanning into a computer, where N≥1000 pictures;

[0082] 62. Manually calibrate the surface morphology of particles in each area of each scanned picture. Different particle morphologies are respectively calibrated as one of the two fracture types: intergranular fracture or transgranular fracture, and summarize and calculate the number of intergranular fracture particles and transgranular fracture particles in this picture. Repeat this step to obtain N calibrated pictures.

[0083] 63. Establish a fully convolutional neural network model based on the SSD algorithm for learning and training the calibrated pictures completed in step 62 in the computer.

[0084] 64. Import most of the calibrated pictures completed in step 62 into the fully convolutional neural network model based on the SSD algorithm in the computer for deep learning training. After deep learning training, form a picture recognition model. Use the remaining calibrated pictures to test this picture recognition model. If the test accuracy meets the requirements, stop the deep learning training and retain the trained model; if the test accuracy does not meet the requirements, continue the deep learning training and testing until the test accuracy meets the requirements, and retain the trained picture recognition model; 65. Establish a connection between the software in the computer and the picture recognition model obtained in the above step 64. 66. Collect the ore particles that have completed the crushing work in step c or f and require particle morphology recognition, flatten them, and take pictures through electron microscopy scanning to form pictures to be recognized.

[0085] 67. Import the pictures to be recognized into the above software through the software, and then use the picture recognition model to perform picture recognition, output the number of transgranular fractures and intergranular fractures of the ore particles in this picture, calculate the intergranular fracture ratio, and output the recognized and calculated data through the software for use in step e or g.

[0086] In step 62, the manual calibration is based on the sample of the surface morphology picture of the ore particles with intergranular fracture. In this sample picture, the fracture surface shows a sugar cube-like pattern and the edges and corners of the fracture surface interface are clear. In step 62, the manual calibration is based on the sample of the surface morphology picture of the ore particles with transgranular fracture. In this sample picture, the fracture surface shows a step pattern, or a river pattern, or a tearing pattern, or a secondary crack pattern.

[0087] In step 64, 70% of the calibrated images are used for deep learning training, and the remaining 30% of the calibrated images are used to test the trained model.

[0088] The required test accuracy rate in step 64 is not less than 94%.

[0089] The software is established through deep learning. An available model is obtained by learning and training with manually calibrated images. Through this model, image recognition can be quickly achieved, the image recognition efficiency can be improved, and the progress speed of step c can be increased.

[0090] In the judgment method of this embodiment, by analyzing the law between the intergranular fracture ratio and the crushing energy in different particle size levels after the magnetite ore is crushed, the functional relationship between the intergranular fracture ratio and the crushing energy of magnetite ore particles at each particle size level is established. In the ore crushing production, this functional relationship can be used to infer the crushing energy through the intergranular fracture ratio, providing quantifiable basic conditions for the further research on the crushing of magnetite ore.

[0091] Embodiment 2: Refer to Figure 5 , Embodiment 2 is basically the same as Embodiment 1, and the same parts will not be repeated. The differences are as follows: Step f in Embodiment 2 is a repeated process of steps b - d in Embodiment 1. The particulate magnetite ore is crushed with different crushing energies, and the crushed particles at each crushing energy are classified. The fracture surface images of each particle size level are obtained through electron microscope scanning, and the intergranular fracture ratio therein is counted; for the particulate magnetite ore, the same method as the above-mentioned single-particle magnetite ore for crushing and electron microscope scanning observation is used. The energy size is continuously adjusted, and the data of the intergranular fracture ratio after the particulate is crushed are obtained through multiple repetitions. g. Summarize the data in step f, and establish the functional relationship between the intergranular fracture ratio and the crushing energy of particles with different particle size levels after the particulate magnetite ore is crushed. After establishing this function, it can be used to guide the adjustment of the crushing energy during ore crushing.

[0092] This embodiment can infer the crushing energy through the intergranular fracture ratio, providing quantifiable basic conditions for the further research on the crushing of magnetite ore.

Claims

1. A new method for determining crushing energy based on mineral fracture morphology, comprising the following steps: a. The magnetite ore sample is crushed multiple times by a heavy hammer tester, and the critical energy of the magnetite ore fracture is determined to be 100.00 J. The fracture morphology of the magnetite ore at this time is obtained by scanning with an electron microscope to obtain the fracture morphology; b. Adjust the heavy hammer test machine and use different crushing energies to crush single-grain magnetite ore. The crushing energy is gradually increased or decreased. The fracture morphology of the magnetite corresponding to each crushing energy is obtained by electron microscope scanning. The fracture morphologies are arranged and compared in sequence to determine the crushing energy level at which the fracture type changes from a larger proportion of intergranular fracture to a larger proportion of transgranular fracture; c. Select the crushed particles of single magnetite ore under the same crushing energy, classify the crushed magnetite ore particles by screening, obtain the fracture pictures of magnetite ore particles of different particle sizes by electron microscope scanning, and count the proportion of intergranular fracture; d. Repeat step c multiple times, and sequentially measure the fracture morphology of the single-grain magnetite ore in step b at different crushing energies and magnetite ore of different particle sizes, and count the proportion of intergranular fractures; e. Summarize the data in step d, plot points in the coordinate system, and then establish a functional relationship between the proportion of along-grain fracture and crushing energy of particles of different particle sizes after single-grain magnetite crushing based on the plotted points fitting curve. f. According to the process of steps bd above, the particle group magnetite is crushed with different crushing energies, and the crushed particles under each crushing energy are classified, and the fracture pictures of each particle size level are obtained by electron microscope scanning, and the proportion of intergranular fracture is counted; g. Summarize the data in step f and establish a functional relationship between the proportion of along-grain fracture of particles of different particle size levels after the magnetite ore is crushed and the crushing energy.

2. According to claim 1, a new method for determining crushing energy based on mineral fracture morphology characteristics is characterized by: The crushing energies selected in the step b are 226.01J, 376.69J, 527.36J, 640.37J, 753.38J, and 866.38J, respectively.

3. The new method for determining crushing energy based on mineral fracture morphology according to claim 1 is characterized in that: In step c, the particle size classification of the single-particle magnetite ore after crushing by electron microscope observation is: -1.180+0.900, -0.900+0.600, -0.600+0.300, -0.300+0.150, -0.150+0.074, -0.074+0.038, -0.038+0.019, in mm; the functional relationship between the intergranular fracture ratio and crushing energy of different particle size levels in step e is as follows -1.180+0.900y=227.353-28.2791nx R 2 =0.96; -0.900+0.600y=198.995-25.304lnx R 2 =0.96; -0.600+0.300y=109.849-13.5971nx R 2 =0.95; -0.300+0.150y=48.031-5.9751nx R 2 =0.95; -0.150+0.074y=27.055-3.185lnx R 2 =0.98; <h2 style=";text-align:left;direction:ltr">-0.074+0.038y = 21.584-2.873lnx R<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> =0.95; <h2 style=";text-align:left;direction:ltr">-0.038+0.019y = 9.662-1.209lnx R<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> =0.94; In the above formulas, y is the intergranular fracture ratio, x is the crushing energy, and R 2 is the function dependency.

4. The new method for determining crushing energy based on mineral fracture morphology according to claim 1 is characterized in that: In step g, the crushing energies of the magnetite ore particle group are 332.59 J, 432.36 J, 532.14 J, 631.25 J, and 731.69 J, respectively; the particle size classification of the crushed particles observed by electron microscope is: -1.180+0900, -0.900+0.600, -0.600+0.300, -0.300+0.150, -0.150+0.074, -0.074+0.038, -0.038+0.019, unit is mm; the functional relationship between the intergranular fracture ratio and crushing energy of different particle size levels is as follows <h2 style=";text-align:left;direction:ltr">-1.180+0.900y = 289.187-37.679lnx R<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> =0.98; -0.900+0.600y=244.894-31.551lnx R 2 =0.98; -0.600+0.300y=198.682-27.8971nx R 2 =0.99; -0.300+0.150y=64.844-8844lnx R 2 =0.96; <h2 style=";text-align:left;direction:ltr">-0.150+0.074y = 36.7084.984lnx R<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> =0.98; -0.074+0.038y=33.116 4.660lnx R 2 =0.96; <h2 style=";text-align:left;direction:ltr">-0.038+0.019y = 14.923-2.096lnx R<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> =0.95; In the above formulas, y is the intergranular fracture ratio, x is the crushing energy, and R 2 is the function dependency.

5. The new method for determining crushing energy based on mineral fracture morphology according to claim 1 is characterized by: In the step b, particles with a median particle size range of -10.000+5.000 mm after being crushed with different crushing energies are selected for electron microscope scanning.

6. The new method for determining crushing energy based on mineral fracture morphology according to claim 1 is characterized by: In the steps c and f, magnetite fracture morphology classification and recognition software is used, and the establishment and application steps of the software are as follows; 61. The magnetite ore is crushed by crushing equipment, and the crushed magnetite ore particles are collected and evenly divided into N groups. Each group is flattened and then scanned by electron microscope. The N scanned images are imported into the computer, and N is ≥ 1000; 62. Manually calibrate the surface morphology of particles in each area of ​​each scanned image. Different particle morphologies are calibrated as one of the two fracture types: intergranular fracture or transgranular fracture. The number of intergranular fracture particles and transgranular fracture particles in the image are calculated. Repeat this step to obtain N calibrated images.

63. Establish a fully convolutional neural network model based on the SSD algorithm in the computer for learning and training the calibrated images after step 62 is completed.

64. Import most of the calibration images completed in step 62 into the fully convolutional neural network model based on the SSD algorithm on the computer for deep learning training. After the deep learning training, an image recognition model is formed. The image recognition model is tested with the remaining calibration images. If the test accuracy meets the requirements, the deep learning training is stopped and the trained model is retained; if the test accuracy does not meet the requirements, the deep learning training and testing are continued until the test accuracy meets the requirements, and the trained image recognition model is retained; 65. The software is established in the computer to interface with the image recognition model obtained in step 64 above.

66. After the crushing work is completed in step c or f, the ore particles that need to be identified are collected, spread out and photographed by electron microscope scanning to form photos to be identified.

67. Import the photo to be identified into the above software through software, and then apply the image recognition model to perform image recognition, output the number of transgranular fractures and intergranular fractures of the ore particles in the image, calculate the proportion of intergranular fractures, and output the identified and calculated data through the software for use in step e or g.

7. A new method for determining crushing energy based on mineral fracture morphology according to claim 6, characterized in that: The manual calibration in step 62 is performed based on a sample of a surface morphology image of an ore particle that has fractured along a crystal. The fracture in the sample of the image is in a rock candy-like pattern, and the edges and corners of the fracture interface are clear.

8. The new method for determining crushing energy based on mineral fracture morphology according to claim 6 is characterized by: The manual calibration in step 62 is performed based on a sample of a surface morphology image of a ore particle with transgranular fracture, wherein the fracture in the sample of the image is a step pattern, a river pattern, a tear pattern, or a secondary crack pattern.

9. The new method for determining crushing energy based on mineral fracture morphology according to claim 6 is characterized by: In step 64, 70% of the calibration images are used for deep learning training, and the remaining 30% of the calibration images are used to test the trained model.

10. The new method for determining crushing energy based on mineral fracture morphology according to claim 6 is characterized by: The accuracy of the test that meets the requirements in step 64 is not less than 94%.

Images