A method for separating coal-bearing kaolinite from coal gangue

Abstract

The present invention relates to the technical field of coal gangue processing, and more particularly to a method for separating coal-bearing kaolinite from coal gangue. The method comprises the following steps: separating the kaolinite in the coal gangue according to the grade of the kaolinite in the coal gangue. For coal gangue containing primary kaolinite, the sample is first analyzed and a separation model is established. Then, the coal gangue is identified and separated using a first X-ray dual-source recognition intelligent separation machine to separate the coal and obtain gangue. Finally, the gangue is identified and separated using a second X-ray dual-source recognition intelligent separation machine to separate the tailings and obtain concentrated kaolinite. For coal gangue containing secondary and tertiary kaolinite, the sample is desulfurized and decarbonized, and then separated using the separation method for coal gangue containing primary kaolinite. This separation method not only solves the problem of gangue pollution in mining areas and improves the ecological environment quality of mining areas, but also the recovered concentrated kaolinite can be directly used as a chemical raw material, thus having high economic and social benefits.

Description

Technical Field

[0001] The invention relates to the technical field of coal gangue processing, in particular to a method for separating coal-bearing kaolinite from coal gangue. Background Art

[0002] Gangue is a solid waste produced during coal mining and washing, accounting for approximately 15% of raw coal production. Large-scale storage of gangue not only wastes land resources but also poses serious environmental risks such as spontaneous combustion, rain damage, and mudification.

[0003] Research has found that gangue contains abundant kaolinite, a key non-metallic mineral resource associated with coal. my country's coal-bearing strata, as well as interbedded gangue and roof and floor slabs, contain significant kaolinite resources. The higher the purity of the kaolinite, the better the physical and chemical properties and process performance of downstream products. This kaolinite can be used in industries such as construction, printing and dyeing, plastics, chemicals and electronics, agriculture, and refractory materials.

[0004] However, at present, coal-bearing kaolinite resources are not mined separately, but are mined together with coal in the form of gangue during the mining process, and then sent to the coal preparation plant for sorting. Some kaolinite products with a diameter of +50mm are manually selected and sent to the kaolinite processing plant for deep processing. Because the density of kaolinite is similar to that of other minerals in the gangue, and due to the attachment of coal powder, it is difficult to distinguish kaolinite by appearance. As a result, most coal preparation plants do not sort kaolinite, but treat it as gangue waste together with other gangue minerals, which not only pollutes the environment but also wastes resources.

[0005] CN116727097A discloses a method and system for separating kaolinite-rich gangue from coal gangue, as well as the kaolinite-rich gangue produced by the method. The method primarily employs screening, ultrasonic washing, flushing, radiographic image recognition, and pneumatic sorting. While the kaolinite-rich gangue produced by the method has high kaolinite content, low loss on ignition, and high calcined whiteness, it does so because kaolinite is classified into multiple grades and is not graded and screened by grade, resulting in a complex sorting process and increased sorting costs.

[0006] In view of this, the present invention is proposed. Summary of the Invention

[0007] The purpose of the present invention is to provide a method for separating coal-bearing kaolinite from coal gangue. This separation method not only solves the problem of gangue pollution in mining areas and improves the ecological environment quality of mining areas, but also the recovered concentrate kaolinite can be directly used as a chemical raw material, with high economic and social benefits.

[0008] The present invention provides a method for separating coal-bearing kaolinite from coal gangue, comprising the following steps:

[0009] The kaolinite in the coal gangue is sorted according to its grade.

[0010] For gangue containing primary kaolinite, the sample is first analyzed and a sorting model is established. Then, the gangue is identified and sorted using a first X-ray dual-source recognition intelligent sorter to separate the coal and obtain gangue. Finally, a second X-ray dual-source recognition intelligent sorter is used to identify and sort the gangue to separate the tailings and obtain the concentrated kaolinite.

[0011] For the gangue containing secondary and tertiary kaolinite, after the samples are desulfurized and decarbonized, they are sorted using the sorting method for gangue containing primary kaolinite.

[0012] As a preferred embodiment of the present technical solution, when sorting the coal gangue containing primary kaolinite, the following steps are included:

[0013] S1. Crushing and screening the coal gangue containing primary kaolinite into two particle sizes of 10-50 mm and 50-300 mm;

[0014] S2. Conducting surface analysis and X-ray imaging analysis on the two particle size coal gangue samples, and establishing a first sorting model; establishing a second sorting model based on the surface appearance, aluminum-silicon ratio and diffraction values ​​of the first-grade kaolinite;

[0015] S3, transporting the first sorting model to a first X-ray dual-source recognition intelligent sorting machine to complete the sorting of coal in the two particle-sized gangue samples, and obtaining two particle-sized gangues respectively;

[0016] S4. The analysis result of the second sorting model is transmitted to the second X-ray dual-source recognition intelligent sorting machine to complete the sorting of tailings in the gangue of two particle sizes, and obtain concentrate kaolin of two particle sizes respectively.

[0017] As a preferred embodiment of the present technical solution, in step S2, when the first sorting model is established, camera imaging and X-ray imaging are performed on the coal and gangue in the two particle size samples respectively. Based on the different appearances of the coal and gangue in the samples and the differences in X-ray imaging, the first sorting model is established and deep learning is performed.

[0018] As a preferred embodiment of the present technical solution, in step S2, when the second sorting model is established, the aluminum-silicon ratio and diffraction values ​​of the tailings and concentrate kaolinite in the two particle size samples are analyzed respectively, and the concentrate kaolinite is imaged by X-ray according to the analysis results, the second sorting model is established, and deep learning is performed.

[0019] As a preferred embodiment of the present technical solution, when separating the coal gangue containing secondary and tertiary kaolinite, the following steps are included:

[0020] T1. First, the coal gangue containing secondary and tertiary kaolinite is crushed and screened into three particle sizes of <5mm, 5-10mm and 10-60mm;

[0021] T2. Conduct surface analysis and X-ray imaging analysis on coal gangue samples of two particle sizes, 5-10 mm and 10-60 mm, and establish a third sorting model; establish a fourth sorting model based on the surface appearance, aluminum-silicon ratio and diffraction values ​​of secondary and tertiary kaolinite;

[0022] T3, transporting the third sorting model to the third X-ray dual-source recognition intelligent sorting machine to complete the desulfurization and decarbonization of the two-size coal gangue;

[0023] T4. The fourth sorting model is transported to the fourth X-ray dual-source recognition intelligent sorting machine to complete the sorting of tailings in two particle-sized gangues, and concentrate kaolin of two particle sizes is obtained respectively.

[0024] As a preferred embodiment of the present technical solution, in step T2, when the third sorting model is established, camera imaging and X-ray imaging are performed on the coal, pyrite and gangue in the two particle size samples respectively. According to the different appearances and X-ray imaging of the coal, pyrite and gangue in the samples, the third sorting model is established and deep learning is performed.

[0025] As a preferred embodiment of the present technical solution, in step T2, when the fourth sorting model is established, the aluminum-silicon ratio and diffraction values ​​of the tailings and concentrate kaolin in the two particle size samples are analyzed respectively, and the concentrate kaolin is imaged by X-ray according to the analysis results, the fourth sorting model is established, and deep learning is performed.

[0026] As a preferred embodiment of this technical solution, the aluminum-silicon ratio threshold of the kaolinite concentrate subjected to X-ray imaging is (0.8-0.9):1, and the diffraction value threshold is 45-52. Using the aluminum-silicon ratio and diffraction value as sorting indicators for the kaolinite concentrate, X-ray imaging is then performed on the kaolinite concentrate that meets both indicators, establishing a second sorting model. This effectively separates the kaolinite concentrate from gangue. Research has shown that the kaolinite concentrate obtained through sorting by this method has a burnt whiteness index of above 80 and can be directly used as a chemical raw material.

[0027] As a preferred embodiment of the present technical solution, the first X-ray dual-source recognition intelligent sorting machine, the second X-ray dual-source recognition intelligent sorting machine, the third X-ray dual-source recognition intelligent sorting machine and the fourth X-ray dual-source recognition intelligent sorting machine all include an industrial camera, an X-ray recognition device and an airflow sorter, wherein the industrial camera is used to take pictures of the coal gangue to be sorted, and the X-ray recognition device is used to use X-rays to irradiate the material and send the obtained X-ray image to the control system, which analyzes the X-ray camera image, and uses the first sorting model, the second sorting model, the third sorting model or the fourth sorting model obtained by the deep learning algorithm to identify and classify the image data of the material, and generate a classification result, and then transmit the classification result to the airflow sorter, which determines the airflow injection flow rate according to the classification result to realize the identification and sorting of the concentrate kaolinite.

[0028] As a preferred embodiment of the present technical solution, when analyzing the sample, the sampling method adopted includes any one of the dichotomy method, the point sampling method and the lateral interception sampling method, which is not strictly limited in the present invention.

[0029] The method for separating coal-bearing kaolinite from coal gangue of the present invention has at least the following beneficial effects:

[0030] The present invention separates kaolinite in the gangue according to its grade. For gangue containing first-grade kaolinite, the pyrite grade is below 1%, which has little effect on the burnt whiteness of the kaolinite. Therefore, only coal and tailings need to be separated. For gangue containing second- and third-grade kaolinite, the pyrite content is higher, which has a greater impact on the burnt whiteness of the kaolinite. Therefore, desulfurization and decarbonization are required before separating the coal and tailings in the gangue with reference to the first-grade kaolinite. When separating the gangue containing first-grade kaolinite, the present invention analyzes the sample and establishes a corresponding separation model. A first X-ray dual-source recognition intelligent separator and a second X-ray dual-source recognition intelligent separator are then used to separate the coal and tailings in the gangue, ultimately yielding high-quality kaolinite concentrate. The separation method of the present invention does not require additional washing and flushing of the coal gangue, which greatly reduces energy consumption. It not only solves the problem of gangue pollution in the mining area and improves the ecological environment quality of the mining area, but also the recovered concentrate kaolinite can be directly used as a chemical raw material, which has high economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 This is a flow chart of separating coal-bearing first-grade kaolinite from coal gangue of the present invention;

[0033] Figure 2 The present invention is a flow chart for separating the second and third grade kaolinite of coal series from coal gangue. DETAILED DESCRIPTION

[0034] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0035] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular also includes the plural. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0036] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] Example 1

[0038] First, the physical and chemical characteristics and basic content of kaolinite in coal gangue were divided and determined. Table 1 shows the analysis results.

[0039] Table 1 Analysis results

[0040]

[0041] The separation of coal gangue containing primary kaolinite includes the following steps:

[0042] S1. Crushing and screening the coal gangue containing primary kaolinite into two particle sizes of 10-50 mm and 50-300 mm;

[0043] S2. Performing surface analysis and X-ray imaging analysis on gangue samples of two particle sizes, respectively. Coal appears black, is light in weight, and has obvious bright reflections on the cross section, while gangue appears gray-black, is heavy in weight, and has a non-reflective surface. Coal appears light blue-green under X-rays, while gangue appears black, gray, and white in color from the center to the outline under X-rays, with slight pyrite spots visible in a small part. Based on the differences in the apparent colors and X-ray images of coal and gangue, camera imaging and X-ray imaging are performed on the coal and gangue in the two particle size samples, respectively. By analyzing the imaging results, a first sorting model is established, and deep learning is performed to obtain an image analysis model for sorting coal from gangue.

[0044] S3. When sorting coal in a batch of gangue, the first sorting model is transmitted to the first X-ray dual-source recognition intelligent sorting machine. The industrial camera and X-ray recognition device in the first X-ray dual-source intelligent sorting machine collect images of the gangue to be processed and transmit the images to the control system. The control system uses the first sorting model obtained by the deep learning algorithm to identify and classify the image data of the coal and gangue, and generates a classification result. The classification result is then transmitted to the airflow sorter. The airflow sorter determines the airflow injection flow rate based on the classification result to achieve identification and sorting of the coal and gangue, and obtain gangue of two particle sizes respectively;

[0045] S4. Analyze the aluminum-silicon ratio and diffraction value of the tailings and concentrate kaolinite in the two particle size gangue samples respectively, perform X-ray imaging on the concentrate kaolinite that meets the aluminum-silicon ratio of (0.8-0.9):1 and the diffraction value of 45-52, establish a second sorting model, and perform deep learning; when sorting the tailings and concentrate kaolinite in batches of gangue, transmit the analysis results of the second sorting model to the second X-ray dual-source recognition intelligent sorting machine, and the industrial camera and X-ray recognition device in the second X-ray dual-source intelligent sorting machine collect images of the gangue to be processed, and send the collection results to the control system. The control system identifies and classifies the image data of the tailings and concentrate kaolinite through the second sorting model obtained by the deep learning algorithm, and generates classification results, and then transmits the classification results to the airflow sorter. The airflow sorter determines the airflow injection flow rate according to the classification results to realize the identification and sorting of the tailings and concentrate kaolinite, and obtains concentrate kaolinite of two particle sizes respectively.

[0046] In this embodiment, sampling and testing were carried out on the kaolinite concentrate obtained by sorting to verify the quality of the kaolinite concentrate obtained by sorting. The test results are shown in Table 2.

[0047] Table 2 Test results of concentrate kaolinite

[0048]

[0049] As shown in Table 2, the kaolinite concentrate obtained by the separation method of the present invention has a burntness degree of over 80, and the aluminum-silicon ratio of the kaolinite concentrate is within the range of (0.8-0.9):1. The recovered kaolinite concentrate can be directly used as a chemical raw material, and the problem of gangue pollution in the mining area is solved. Therefore, the separation method of the present invention can accurately distinguish coal, tailings, and kaolinite concentrate from gangue containing primary kaolinite, thereby improving the accuracy of the separation of coal, tailings, and kaolinite concentrate, and thus improving the separation efficiency of kaolinite concentrate.

[0050] Example 2

[0051] The separation of coal gangue containing secondary and tertiary kaolinite includes the following steps:

[0052] T1. First, the coal gangue containing secondary and tertiary kaolinite is crushed and screened into three particle sizes: <5mm, 5-10mm, and 10-60mm. Among them, the coal gangue with a particle size of <5mm contains 2500 kcal and can be sold directly as raw ore;

[0053] T2. Camera imaging and X-ray imaging were performed on the coal, pyrite, and gangue in the 5-10mm and 10-60mm particle size samples, respectively. Coal appears black, is light, and has obvious bright reflections on the cross section. Gangue appears gray-black, is heavy, and has a non-reflective surface. Coal appears light blue-green under X-rays, and most gangue has pyrite spots, which are dark black in color and have clear ore outlines. Based on the different appearances and X-ray imaging of coal, pyrite, and gangue in the samples, a third sorting model was established and deep learning was performed to obtain an image analysis model for sorting coal and pyrite from gangue.

[0054] T3. When sorting coal and pyrite in batches of coal gangue, the third sorting model is transmitted to a third X-ray dual-source recognition intelligent sorting machine. The industrial camera and X-ray recognition device in the third X-ray dual-source intelligent sorting machine capture images of the coal gangue to be processed, and the imaging model is sent to the control system. The control system uses the third sorting model obtained by the deep learning algorithm to identify and classify the image data of the coal and gangue, and generates a classification result. The classification result is then transmitted to the airflow separator. The airflow separator determines the airflow injection flow rate based on the classification result to separate the coal and pyrite to obtain gangue containing coal-bearing kaolinite;

[0055] T4. Analyze the aluminum-silicon ratio and diffraction values ​​of the tailings and concentrate kaolinite in the two particle size gangue samples respectively. Perform X-ray imaging on the concentrate kaolinite that meets the aluminum-silicon ratio of (0.8-0.9):1 and the diffraction value of 45-52, establish the fourth sorting model, and conduct deep learning;

[0056] T5. When sorting the tailings and concentrate kaolinite in batches of gangue, the analysis results of the fourth sorting model are transmitted to the fourth X-ray dual-source recognition intelligent sorting machine, and the industrial camera and X-ray recognition device in the fourth X-ray dual-source intelligent sorting machine collect images of the gangue to be processed, and send the collection results to the control system. The control system identifies and classifies the image data of the tailings and concentrate kaolinite through the fourth sorting model obtained by the deep learning algorithm, and generates classification results, and then transmits the classification results to the airflow sorter. The airflow sorter determines the airflow injection flow rate according to the classification results to realize the identification and sorting of the tailings and concentrate kaolinite, and obtain concentrate kaolinite of two particle sizes respectively.

[0057] In this embodiment, sampling and testing were carried out on the kaolinite concentrate obtained by sorting to verify the quality of the kaolinite concentrate obtained by sorting. The test results are shown in Table 3.

[0058] Table 3 Test results of concentrate kaolinite

[0059]

[0060] As shown in Table 3, for the coal gangue containing secondary and tertiary kaolinite, the burnt whiteness of the concentrate kaolinite obtained by the separation method of the present invention is above 80, and the aluminum-silicon ratio of the concentrate kaolinite is within the range of (0.8-0.9):1. The recovered concentrate kaolinite can be directly used as a chemical raw material.

[0061] Comparative Example 1

[0062] When analyzing the tailings and concentrate kaolinite in two particle-sized waste rock samples, only the concentrate kaolinite that meets the aluminum-silicon ratio of (0.8-0.9):1 is imaged by X-ray, and a second sorting model is established and deep learning is performed;

[0063] The other steps are basically the same as those in Example 1.

[0064] In this comparative example, the concentrated kaolinite obtained by sorting was sampled and tested to verify the quality of the concentrated kaolinite obtained by sorting. The test results are shown in Table 4.

[0065] Table 4 Test results of concentrate kaolinite

[0066]

[0067] Comparative Example 2

[0068] When analyzing the tailings and concentrate kaolinite in two particle-sized waste rock samples, only the concentrate kaolinite with a diffraction value of 45-52 was imaged with X-rays, and a second sorting model was established, followed by deep learning.

[0069] The other steps are basically the same as those in Example 1.

[0070] In this comparative example, the concentrated kaolinite obtained by sorting was sampled and tested to verify the quality of the concentrated kaolinite obtained by sorting. The test results are shown in Table 5.

[0071] Table 5 Test results of concentrate kaolinite

[0072]

[0073] By comparing Tables 2, 4 and 5, it can be seen that the sorting model in the sorting method of the present invention can effectively realize the sorting of concentrate kaolinite in coal gangue, and the physical properties of the concentrate kaolinite obtained by sorting are significantly improved compared with those of Control Examples 1-2. In addition, the sorting method of the present invention does not require additional washing and flushing of the coal gangue, which greatly reduces energy consumption and improves the application value of kaolinite.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for separating coal-bearing kaolinite from coal gangue, characterized in that: The following steps are involved: The kaolinite in the coal gangue is sorted according to its grade. For gangue containing primary kaolinite, the sample is first analyzed and a sorting model is established. Then, the gangue is identified and sorted using a first X-ray dual-source recognition intelligent sorter to separate the coal and obtain gangue. Finally, the gangue is identified and sorted using a second X-ray dual-source recognition intelligent sorter to separate the tailings and obtain concentrate kaolinite. For the gangue containing secondary and tertiary kaolinite, the samples were desulfurized and decarbonized and then sorted using the same sorting method as the gangue containing primary kaolinite; The separation of coal gangue containing primary kaolinite includes the following steps: S1. Crushing and screening the coal gangue containing primary kaolinite into two particle sizes of 10-50 mm and 50-300 mm; S2. Conducting surface analysis and X-ray imaging analysis on the two particle size coal gangue samples, and establishing a first sorting model; establishing a second sorting model based on the surface appearance, aluminum-silicon ratio and diffraction values ​​of the first-grade kaolinite; S3, transporting the first sorting model to the first X-ray dual-source recognition intelligent sorting machine to complete the sorting of the coal in the two particle sizes of coal gangue, and obtaining two particle sizes of gangue respectively; S4. Transmitting the analysis results of the second sorting model to the second X-ray dual-source recognition intelligent sorting machine to complete the sorting of tailings in the two particle sizes of gangue, and respectively obtain two particle size concentrates of kaolinite; In step S2, when the first sorting model is established, the coal and gangue in the two particle size samples are photographed and imaged by X-rays, respectively. Based on the differences in the appearance of the coal and gangue in the samples and the differences in the X-ray imaging, the first sorting model is established and deep learning is performed; In step S2, when the second sorting model is established, the aluminum-silicon ratio and diffraction value of the tailings and concentrate kaolin in the two particle size samples are analyzed respectively, and X-ray imaging of the concentrate kaolin is performed based on the analysis results to establish the second sorting model and perform deep learning; The separation of coal gangue containing secondary and tertiary kaolinite includes the following steps: T1. First, the coal gangue containing secondary and tertiary kaolinite is crushed and screened into three particle sizes of <5mm, 5-10mm and 10-60mm; T2. Conduct surface analysis and X-ray imaging analysis on coal gangue samples of two particle sizes, 5-10 mm and 10-60 mm, and establish a third sorting model; establish a fourth sorting model based on the surface appearance, aluminum-silicon ratio and diffraction values ​​of secondary and tertiary kaolinite; T3, transporting the third sorting model to the third X-ray dual-source recognition intelligent sorting machine to complete the desulfurization and decarbonization of the two-size coal gangue; T4, transporting the fourth sorting model to the fourth X-ray dual-source recognition intelligent sorting machine to complete the sorting of tailings in the two particle-sized gangues, and obtaining two particle-sized concentrate kaolinites respectively; In step T2, when establishing the third sorting model, the coal, pyrite, and gangue in the two particle size samples are photographed and imaged by X-rays, respectively. Based on the differences in the appearance and X-ray imaging of the coal, pyrite, and gangue in the samples, the third sorting model is established and deep learning is performed; In step T2, when the fourth sorting model is established, the aluminum-silicon ratio and diffraction value of the tailings and concentrate kaolin in the two particle size samples are analyzed respectively, and X-ray imaging of the concentrate kaolin is performed based on the analysis results to establish the fourth sorting model and perform deep learning; The aluminum-silicon ratio threshold of the concentrate kaolinite subjected to X-ray imaging is (0.8-0.9):1, and the diffraction value threshold is 45-52.

2. The method for separating coal-bearing kaolinite from coal gangue according to claim 1, characterized in that: The first X-ray dual-source recognition intelligent sorting machine, the second X-ray dual-source recognition intelligent sorting machine, the third X-ray dual-source recognition intelligent sorting machine and the fourth X-ray dual-source recognition intelligent sorting machine all include an industrial camera, an X-ray recognition device and an airflow sorter.

3. The method for separating coal-bearing kaolinite from coal gangue according to claim 1, characterized in that: When analyzing samples, the sampling methods used include any one of the dichotomy method, point sampling method and horizontal interception sampling method.

Images