Method for detecting content, area and particle size distribution of quartz sand inclusion

Abstract

The invention discloses a method for detecting the content, area and particle size distribution of quartz sand inclusions. The method comprises the following steps: S1, obtaining an optical microscope photo of quartz sand; s2, acquiring the total area of the quartz sand in the optical microscope picture; s3, obtaining the area and particle size distribution of the inclusion in the optical microscope photo, and obtaining the total area of the inclusion; s4, dividing the total area of the inclusions by the total area of the quartz sand to determine the content of the inclusions in the quartz sand; the inclusion content in the quartz sand is defined as inclusion content = inclusion total area / quartz sand total area. The problems that existing quartz sand inclusion detection is low in precision and low in speed can be solved.

Description

Technical Field

[0001] The invention relates to the technical field of quartz sand inclusion detection, and in particular to a method for detecting the content, area and particle size distribution of quartz sand inclusions. Background Art

[0002] High-purity quartz sand is a basic raw material widely used in integrated circuits, photovoltaics, civil engineering and other fields. It is mainly used to prepare high-purity quartz crucibles for Czochralski single crystal silicon and various process auxiliary materials in semiconductor and photovoltaic process manufacturing, such as quartz glass tubes, rods, plates, etc.

[0003] Quartz sand is made of siliceous minerals such as quartz, pegmatite and vein quartz through crushing and a series of processing procedures. Therefore, the inclusions inherent in siliceous minerals are also widely distributed in quartz sand. These inclusions will significantly affect the bubble content in quartz glass products, and then affect the properties such as transmittance, thermal stability, mechanical strength, and affect the performance and stability of the finished product. Therefore, it is very important to test the inclusion content, inclusion area, and particle size distribution in quartz sand and select quartz sand with less inclusion content as the preparation raw material.

[0004] For example, in the Chinese invention patent application with publication number CN112858097A, quartz sand is observed using an optical microscope, and the inclusion content is measured by the ratio of the number of quartz sand particles containing inclusions to the total number of quartz sand particles in the optical microscope photo. This solution has low accuracy and requires manual calculation of the total number of quartz sand particles, resulting in a slow detection speed.

[0005] For example, the Chinese invention patent application with publication number CN113340780A uses an optical microscope to take a bright field background image of a sample and multiple groups of images to be tested, obtains the cumulative probability density of different transmittances, and calculates the fluid inclusion index. This solution has complex steps, and the definition of the inclusion index is not intuitive. It also has the problems of low detection accuracy and slow speed.

[0006] Therefore, realizing a method to improve the detection accuracy of inclusions in quartz sand and shorten the detection time is crucial for the quality assessment of quartz sand and the selection and screening of quartz ore sources. Summary of the invention

[0007] In view of the above technical problems and the shortcomings in the field, the present invention provides a method for detecting the content, area and particle size distribution of quartz sand inclusions, which can solve the problems of low accuracy and slow speed in existing quartz sand inclusion detection.

[0008] The present invention defines the inclusion content in quartz sand for the first time as: inclusion content = total area of ​​inclusions / total area of ​​quartz sand. This definition is more scientific and accurate than the existing definition of inclusion content that ignores the size of inclusions and only uses the number of inclusions.

[0009] The specific technical solutions are as follows:

[0010] [1] A method for detecting the content, area and particle size distribution of quartz sand inclusions, comprising the steps of:

[0011] S1, obtain an optical microscope photo of quartz sand;

[0012] S2, obtain the total area of ​​quartz sand in the optical microscope photo;

[0013] S3, obtaining the area and particle size distribution of the inclusions in the optical microscope photograph, and obtaining the total area of ​​the inclusions;

[0014] S4, dividing the total area of ​​the inclusions by the total area of ​​the quartz sand to determine the inclusion content in the quartz sand; the inclusion content in the quartz sand is defined as: inclusion content = total area of ​​inclusions / total area of ​​quartz sand.

[0015] When obtaining the optical microscope photograph of the quartz sand, a transparent agent can be used to increase the refractive index between the objective lens and the glass slide, so that light can better penetrate the quartz sand sample. Further, the transparent agent can include at least one of clove oil, kerosene, wintergreen oil, etc., preferably clove oil.

[0016] For any optical microscope photo, the total area of ​​quartz sand can be obtained by a method including the following steps:

[0017] (1) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos are used as the basic data set, and quartz sand particles are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected. The preprocessed data set is input into the machine learning and deep learning model for training, and a quartz sand classifier is obtained to distinguish quartz sand from the background of the optical microscope photo;

[0018] (2) Inputting an optical microscope photo of quartz sand to be tested, loading the trained quartz sand classifier, and distinguishing the quartz sand from the background of the optical microscope photo;

[0019] (3) Use image recognition software to measure the area of ​​the distinguished quartz sand and obtain the total area of ​​the quartz sand.

[0020] For any optical microscope photo, the total area of ​​the inclusions can be obtained by a method including the following steps:

[0021] 1) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos of quartz sand containing inclusions are used as the basic data set, and quartz sand particles containing inclusions are manually screened as prior knowledge for data set preprocessing. A suitable machine learning and deep learning model is selected, and the preprocessed data set is input into the machine learning and deep learning model for training to obtain a target detection model for detecting quartz sand containing inclusions, which can greatly reduce the subsequent calculation burden;

[0022] 2) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos of quartz sand containing inclusions are used as the basic data set, the inclusions are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected. The preprocessed data set is input into the machine learning and deep learning model for training to obtain an inclusion classifier for distinguishing inclusions from quartz sand background;

[0023] 3) Input an optical microscope photo of quartz sand containing inclusions to be detected, load the trained target detection model and inclusion classifier, and distinguish the inclusions from the quartz sand background;

[0024] 4) Use image recognition software to measure the area and particle size distribution of the well-identified inclusions and obtain the total area of ​​the inclusions.

[0025] In step 1), the YOLOv5 target detection algorithm can be used to detect quartz sand containing inclusions, which can significantly reduce computational overhead and improve the efficiency of the model in complex scenes. The YOLOv5 target detection algorithm can accurately identify gravel areas containing black spots by annotating images, training models, and optimizing hyperparameters, and provide input for subsequent U-Net segmentation.

[0026] In step 2), the U-Net deep learning network segmentation model can be used to segment the inclusions and the edges of the quartz sand, accurately obtain the contours of the quartz sand and the inclusions, and thus more accurately identify the inclusions.

[0027] [2] Application of the method described in [1] in measuring the inclusion area, particle size distribution and inclusion content of inclusion-containing minerals. Further, the inclusion-containing mineral may include at least one of quartzite, vein quartz, natural quartz sand, quartz sandstone, etc.

[0028] Since the particle size distribution, composition and content of inclusions in each mineral are different, classifiers and target detection models can be trained separately for inclusion content analysis of a specific mineral.

[0029] [3] A computer device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, wherein when the computer program is executed, the processor executes the method described in [1].

[0030] [4] A computer-readable storage medium storing a program or instruction, which, when executed by a computer device, causes the computer device to execute the method described in [1].

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention can determine the inclusion content in quartz sand by quickly obtaining the total area of ​​quartz sand and the total area of ​​inclusions in optical microscope photos, and then dividing the obtained total area of ​​inclusions by the total area of ​​quartz sand. This solves the current problems of low accuracy and slow speed in detecting the inclusion content in quartz sand, and provides a more efficient method for quickly detecting and screening high-quality quartz sand. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flow chart of a method for detecting the content, area and particle size distribution of quartz sand inclusions according to the present invention;

[0034] Figure 2 The optical microscope photo of quartz sand (a), the quartz sand differentiation diagram (b) and the inclusion differentiation diagram (c) of Example 1 disclosed in the present invention;

[0035] Figure 3 The optical microscope photo (a) of quartz sand, the quartz sand differentiation diagram (b) and the inclusion differentiation diagram (c) of Example 2 disclosed in the present invention;

[0036] Figure 4 The optical microscope photo (a) of quartz sand, the quartz sand differentiation diagram (b) and the inclusion differentiation diagram (c) of Comparative Example 1 disclosed in the present invention;

[0037] Figure 5 The optical microscope photo (a) of quartz sand, the quartz sand differentiation diagram (b) and the inclusion differentiation diagram (c) of Comparative Example 2 disclosed in the present invention;

[0038] Figure 6 The optical microscope photograph (a) and inclusion differentiation diagram (b) of quartz sand of comparative example 3 disclosed in the present invention are shown. DETAILED DESCRIPTION

[0039] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention.

[0040] See also Figure 1 A method for detecting the content, area and particle size distribution of quartz sand inclusions comprises the steps of:

[0041] S1, obtaining an optical microscope photograph of quartz sand. For example, quartz sand particles are sprinkled on a glass slide, and then a dropper is used to drop a certain amount of clove oil, and the quartz sand particles are observed at an appropriate magnification, and an optical microscope photograph is taken.

[0042] S2, obtaining the total area of ​​quartz sand in the optical microscope photo, specifically comprising the steps of:

[0043] (1) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos are used as the basic data set, and quartz sand particles are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected. The preprocessed data set is input into the machine learning and deep learning model for training, and a quartz sand classifier is obtained to distinguish quartz sand from the background of the optical microscope photo;

[0044] (2) Inputting an optical microscope photo of quartz sand to be tested, loading the trained quartz sand classifier, and distinguishing the quartz sand from the background of the optical microscope photo;

[0045] (3) Use image recognition software to measure the area of ​​the distinguished quartz sand and obtain the total area of ​​the quartz sand.

[0046] S3, obtaining the area and particle size distribution of the inclusions in the optical microscope photo, and obtaining the total area of ​​the inclusions, specifically comprising the steps of:

[0047] 1) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos of quartz sand containing inclusions are used as the basic data set, and the quartz sand particles containing inclusions are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected. The preprocessed data set is input into the machine learning and deep learning model for training to obtain a target detection model for detecting quartz sand containing inclusions. For example, using the YOLOv5 target detection algorithm for target detection of quartz sand containing inclusions can significantly reduce the computational overhead and improve the efficiency of the model in complex scenes. The YOLOv5 target detection algorithm can accurately identify the gravel area containing black spots by annotating the image, training the model, and optimizing the hyperparameters, and provide input for the subsequent U-Net segmentation.

[0048] 2) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos of quartz sand containing inclusions are used as the basic data set, and the inclusions are manually screened as prior knowledge for data set preprocessing. The appropriate machine learning and deep learning models are selected, and the preprocessed data sets are input into the machine learning and deep learning models for training to obtain an inclusion classifier for distinguishing inclusions from the quartz sand background. For example, the U-Net deep learning network segmentation model is used to segment the inclusions and quartz sand edges, accurately obtain the outline of the quartz sand and the inclusion outline, and thus more accurately identify the inclusions. The output of the U-Net model is a two-dimensional probability map of the same size as the input image, predicting the probability that each pixel belongs to the target category (such as inclusions or quartz sand background). For each pixel i, the predicted probability p i It can be expressed as: i =σ(z i ), where z i is the original output of U-Net, σ is the Sigmoid function, which is used to map the output to the range of [0,1], indicating the probability that the pixel belongs to the positive class (inclusion), and then the probability map is converted into a binary segmentation result through a threshold (such as 0.5).

[0049] 3) Input the optical microscope photo of the quartz sand containing inclusions to be detected, load the trained target detection model and inclusion classifier, and distinguish the inclusions from the quartz sand background.

[0050] 4) Use image recognition software to measure the area and particle size distribution of the well-identified inclusions and obtain the total area of ​​the inclusions.

[0051] S4, dividing the total area of ​​the inclusions by the total area of ​​the quartz sand to determine the inclusion content in the quartz sand; the inclusion content in the quartz sand is defined as: inclusion content = total area of ​​inclusions / total area of ​​quartz sand.

[0052] Based on the above-described method for detecting the content, area and particle size distribution of quartz sand inclusions, the following describes an embodiment of the quartz sand content detection software: The quartz sand content detection software includes three modules, namely, a classifier training module, a calculation module and an output module. The classifier training module can use optical microscope photos as the basic data set, manually screen the region of interest (quartz sand or inclusions) as prior knowledge to preprocess the data set, select a suitable machine learning and deep learning model, and input the preprocessed data set into the machine learning and deep learning model for training to obtain a quartz sand (or inclusion) classifier. The calculation module can use the classifier to separate the region of interest (quartz sand or inclusions) from the background in the optical microscope photo to be detected, and then calculate the area, particle size distribution and total area of ​​the region of interest. The output module can perform data statistics and analysis, and then output the results required by the user.

[0053] In addition, the method for detecting the content, area and particle size distribution of quartz sand inclusions of the present invention can be used for the measurement of the inclusion area, particle size distribution and inclusion content of a variety of inclusion-containing minerals, including but not limited to: quartzite, vein quartz, natural quartz sand, quartz sandstone, etc. Since the particle size distribution, composition and content of inclusions in each mineral are different, classifiers can be trained separately for inclusion content analysis of a specific mineral.

[0054] The following are specific examples and some related comparative examples of using the above method for detecting the content, area and particle size distribution of quartz sand inclusions.

[0055] Example 1

[0056] The quartz sand used in this embodiment comes from a vein quartz ore in India, and an optical microscope photo of the quartz sand is shown in FIG. Figure 2 As shown in a.

[0057] After obtaining multiple optical microscope photos, these photos are used as the basic data set for training to obtain a quartz sand classifier specifically for vein quartz ore from a certain place in India. Then input Figure 2 The optical microscope photo shown in a is loaded with the quartz sand classifier to obtain the quartz sand photo after classification ( Figure 2 b).

[0058] Measurement using image recognition software Figure 2 The total area of ​​quartz sand in b is 409715 μm 2 .

[0059] After obtaining multiple optical microscope photos, these photos are used as the basic data set and trained using the U-Net deep learning network segmentation model to obtain a classifier specifically for inclusions in vein quartz ore from a certain location in India. Then input Figure 2 The optical microscope photo shown in a is loaded with the inclusion classifier to obtain the inclusion photo after classification ( Figure 2 c).

[0060] Measurement using image recognition software Figure 2 The total area of ​​inclusions in c is 1037 μm 2 The total number of inclusions is 177, and the inclusion content is 0.25%:

[0061] In terms of area distribution, the inclusion area is mainly distributed in the range of 0 to 20 μm. 2 In range: Area 0~10μm 2 The number of inclusions is 156; the area is 10-20 μm 2 The number of inclusions is 12. The largest inclusion area is 108.9 μm 2; The minimum inclusion area is 0.05μm 2 .

[0062] In terms of particle size distribution, the inclusions are mainly distributed in the range of 0-6μm: the number of inclusions with a particle size of 0-2μm is 94; the number of inclusions with a particle size of 2-4μm is 44; the number of inclusions with a particle size of 4-6μm is 24. The maximum inclusion particle size is 22.8μm; the minimum inclusion particle size is 0.3μm.

[0063] Example 2

[0064] The quartz sand used in this embodiment comes from a granite pegmatite ore from a certain place in India, and an optical microscope photo thereof is shown in FIG. Figure 3 As shown in a.

[0065] After obtaining multiple optical microscope photos, these photos are used as the basic data set for training to obtain a quartz sand classifier specifically for granite pegmatite ore in a certain area of ​​India. Then input Figure 3 The optical microscope photo shown in a is loaded with the quartz sand classifier to obtain the quartz sand photo after classification ( Figure 3 b).

[0066] Measurement using image recognition software Figure 3 The total area of ​​quartz sand in b is 428126 μm 2 .

[0067] After obtaining multiple optical microscope photos, these photos are used as the basic data set and trained using the U-Net deep learning network segmentation model to obtain a classifier specifically for inclusions in granite pegmatite ore from a certain area in India. Then input Figure 3 The optical microscope photo shown in a is loaded with the inclusion classifier to obtain the inclusion photo after classification ( Figure 3 c).

[0068] Measurement using image recognition software Figure 3 The total area of ​​inclusions in c is 7475 μm 2 The total number of inclusions is 1487, and the inclusion content is 1.75%:

[0069] In terms of area distribution, the inclusion area is mainly distributed in the range of 0 to 40 μm. 2 In range: Area 0~10μm 2 The number of inclusions is 1306; the area is 10-20 μm 2 The number of inclusions is 103; the area is 20-30 μm 2 The number of inclusions is 28; the area is 30-40 μm 2 The number of inclusions is 15. The largest inclusion area is 159.0 μm 2; The minimum inclusion area is 0.05μm 2 .

[0070] In terms of particle size distribution, the inclusions are mainly distributed in the range of 0-10μm: the number of inclusions with a particle size of 0-2μm is 820; the number of inclusions with a particle size of 2-4μm is 352; the number of inclusions with a particle size of 4-6μm is 141; the number of inclusions with a particle size of 6-8μm is 75; the number of inclusions with a particle size of 8-10μm is 43. The maximum inclusion particle size is 35.4μm; the minimum inclusion particle size is 0.3μm.

[0071] Comparative Example 1

[0072] The quartz sand used in this comparative example comes from a vein quartz ore in India. Figure 4 a (In order to eliminate interference, Figure 4 a and Figure 2 a using the same photo).

[0073] by Figure 4 A single photo is used as the basic data set for training, and a quartz sand classifier dedicated to vein quartz ore from a certain place in India is obtained. Then input Figure 4 The optical microscope photo shown in a is loaded with the quartz sand classifier to obtain the quartz sand photo after classification ( Figure 4 b).

[0074] Measurement using image recognition software Figure 4 The total area of ​​quartz sand in b is 342481 μm 2 .

[0075] by Figure 4 A single photo is used as the basic data set, and the U-Net deep learning network segmentation model is used for training to obtain a classifier specifically for inclusions in vein quartz ore from a certain place in India. Then input Figure 4 The optical microscope photo shown in a is loaded with the inclusion classifier to obtain the inclusion photo after classification ( Figure 4 c).

[0076] Measurement using image recognition software Figure 4 The total area of ​​inclusions in c is 558 μm 2 The total number of inclusions is 134, and the inclusion content is 0.16%:

[0077] In terms of area distribution, the inclusion area is mainly distributed in the range of 0 to 20 μm. 2 In range: Area 0~10μm 2 The number of inclusions is 120; the area is 10-20 μm 2 The number of inclusions is 10. The largest inclusion area is 50.6 μm2 ; The minimum inclusion area is 0.05μm 2 .

[0078] In terms of particle size distribution, the inclusions are mainly distributed in the range of 0-6μm: the number of inclusions with a particle size of 0-2μm is 73; the number of inclusions with a particle size of 2-4μm is 33; the number of inclusions with a particle size of 4-6μm is 19. The maximum inclusion particle size is 14.0μm; the minimum inclusion particle size is 0.3μm.

[0079] Comparative Example 2

[0080] The quartz sand used in this comparative example comes from a granite pegmatite ore from a certain place in India. Figure 5 a (In order to eliminate interference, Figure 5 a and Figure 3 a using the same photo).

[0081] by Figure 5 A single photo is used as the basic data set for training, and a classifier for granite pegmatite ore quartz sand in a certain area of ​​India is obtained. Then input Figure 5 The optical microscope photo shown in a is loaded with the quartz sand classifier to obtain the quartz sand photo after classification ( Figure 5 b).

[0082] Measurement using image recognition software Figure 5 The total area of ​​quartz sand in b is 334293 μm 2 .

[0083] by Figure 5 a single photo is used as the basic data set, and the U-Net deep learning network segmentation model is used for training to obtain a classifier specifically for inclusions in granite pegmatite ore from a certain property in India. Then input Figure 5 The optical microscope photo shown in a is loaded with the inclusion classifier to obtain the inclusion photo after classification ( Figure 5 c).

[0084] Measurement using image recognition software Figure 5 The total area of ​​inclusions in c is 4353 μm 2 The total number of inclusions is 795, and the inclusion content is 1.30%:

[0085] In terms of area distribution, the inclusion area is mainly distributed in the range of 0 to 40 μm. 2 In range: Area 0~10μm 2 The number of inclusions is 696; the area is 10-20 μm 2 The number of inclusions is 48; the area is 20-30 μm 2The number of inclusions is 16; the area is 30-40 μm 2 The number of inclusions is 10. The largest inclusion area is 143.3 μm 2 ; The minimum inclusion area is 0.05μm 2 .

[0086] In terms of particle size distribution, the inclusions are mainly distributed in the range of 0-10μm: the number of inclusions with a particle size of 0-2μm is 431; the number of inclusions with a particle size of 2-4μm is 201; the number of inclusions with a particle size of 4-6μm is 72; the number of inclusions with a particle size of 6-8μm is 37; the number of inclusions with a particle size of 8-10μm is 16. The maximum inclusion particle size is 34.5μm; the minimum inclusion particle size is 0.3μm.

[0087] Examples 1 and 2 use multiple optical microscope photos as the basic training set, and the total area of ​​quartz sand counted is 409715 μm 2 and 428126μm 2 The total area of ​​the inclusions was 1037 μm 2 and 7475 μm 2 ; The total number of inclusions is 177 and 1487 respectively; The inclusion content is 0.25% and 1.75% respectively. It can be seen that the inclusion content of the granite pegmatite ore from a certain place in India used in Example 2 is much greater than that of the vein quartz ore from a certain place in India. The two are basically consistent in the inclusion area distribution and particle size distribution, and both are dominated by small area and small particle size inclusions.

[0088] Compared with Comparative Examples 1 and 2, which use an optical microscope photo as the basic training set, the total area of ​​quartz sand counted is 342481 μm 2 and 334293μm 2 The total area of ​​the inclusions was 558 μm 2 and 4353 μm 2 ; The total number of inclusions is 134 and 795 respectively; The inclusion content is 0.16% and 1.30% respectively. Due to the lack of enough optical microscope photos as training sets, all indicators have decreased relative to the examples. After manual inspection and confirmation, many inclusions in the comparative examples were not identified and counted, reflecting the phenomenon of incomplete statistics. After manual inspection and confirmation, the inclusions in the examples were basically identified and counted, highlighting the importance of using sufficient data as the basic training set.

[0089] Comparative Example 3

[0090] The quartz sand used in this comparative example comes from a vein quartz ore in India. Figure 6 a (In order to eliminate interference, Figure 6 a and Figure 2 a using the same photo).

[0091] After obtaining multiple optical microscope photos, we used these photos as the basic data set and used the same model as the quartz sand classifier instead of the U-Net deep learning network segmentation model training to obtain a classifier specifically for inclusions in vein quartz ore from a certain location in India. Then we input Figure 6 The optical microscope photo shown in a is loaded with the inclusion classifier to obtain the inclusion photo after classification ( Figure 6 b).

[0092] from Figure 6 As can be seen from Figure 2, the inclusion photos obtained by using the same model as the quartz sand classifier without using the U-Net deep learning network segmentation model contain more quartz sand edges and the recognition accuracy is very low. This comparison illustrates the importance of using a deep learning model for fine segmentation.

[0093] In addition, it should be understood that after reading the above description of the present invention, those skilled in the art may make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the claims attached to this application.

Claims

1. A method for detecting the content, area and particle size distribution of quartz sand inclusions, characterized in that: Includes steps: S1, obtain an optical microscope photo of quartz sand; S2, obtain the total area of ​​quartz sand in the optical microscope photo; S3, obtaining the area and particle size distribution of the inclusions in the optical microscope photograph, and obtaining the total area of ​​the inclusions; S4, dividing the total area of ​​the inclusions by the total area of ​​the quartz sand to determine the inclusion content in the quartz sand; the inclusion content in the quartz sand is defined as: inclusion content = total area of ​​inclusions / total area of ​​quartz sand.

2. The method according to claim 1, characterized in that When obtaining the optical microscope photograph of the quartz sand, a transparent agent is used to increase the refractive index between the objective lens and the glass slide, so that light can better penetrate the quartz sand sample; The transparent agent includes at least one of clove oil, kerosene and wintergreen oil.

3. The method according to claim 1, characterized in that For any optical microscope photo, the total area of ​​quartz sand is obtained by a method including the following steps: (1) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos are used as the basic data set, and quartz sand particles are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected. The preprocessed data set is input into the machine learning and deep learning model for training, and a quartz sand classifier is obtained to distinguish quartz sand from the background of the optical microscope photo; (2) Inputting an optical microscope photo of quartz sand to be tested, loading the trained quartz sand classifier, and distinguishing the quartz sand from the background of the optical microscope photo; (3) Use image recognition software to measure the area of ​​the distinguished quartz sand and obtain the total area of ​​the quartz sand.

4. The method according to claim 1, characterized in that: For any optical microscope photo, the total area of ​​the inclusions is obtained using a method comprising the following steps: 1) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos of quartz sand containing inclusions are used as the basic data set, and quartz sand particles containing inclusions are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected, and the preprocessed data set is input into the machine learning and deep learning model for training to obtain a target detection model for detecting quartz sand containing inclusions; 2) Using machine learning and deep learning methods, during the training process, one or more optical microscope photos of quartz sand containing inclusions are used as the basic data set, the inclusions are manually screened as prior knowledge for data set preprocessing, and a suitable machine learning and deep learning model is selected. The preprocessed data set is input into the machine learning and deep learning model for training to obtain an inclusion classifier for distinguishing inclusions from quartz sand background; 3) Input an optical microscope photo of quartz sand containing inclusions to be detected, load the trained target detection model and inclusion classifier, and distinguish the inclusions from the quartz sand background; 4) Use image recognition software to measure the area and particle size distribution of the well-identified inclusions and obtain the total area of ​​the inclusions.

5. The method according to claim 4, characterized in that In step 1), the YOLOv5 target detection algorithm is used to detect the quartz sand containing inclusions.

6. The method according to claim 4, characterized in that In step 2), the U-Net deep learning network segmentation model is used to segment the inclusions and the edges of the quartz sand, and the contours of the quartz sand and the inclusions are accurately obtained, so as to more accurately identify the inclusions.

7. Application of the method according to any one of claims 1 to 6 in measuring the inclusion area, particle size distribution and inclusion content of inclusion-containing minerals.

8. The use according to claim 7, characterized in that: The inclusion-containing mineral includes at least one of quartzite, vein quartz, natural quartz sand, and quartz sandstone.

9. A computer device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, wherein: When the computer program is executed, the processor is enabled to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by a computer device, the computer device executes the method according to any one of claims 1 to 6.

Images