High-efficiency coal dressing method

By crushing and grading raw coal, and automatically segmenting coal gangue using optical image processing technology, the problem of existing coal preparation methods relying on manual operations is solved, the coal preparation efficiency and automation level are improved, and the operational cost is reduced.

CN119076424APending Publication Date: 2024-12-06ZHALAI NUOER COAL IND CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411423013.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-12
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing coal preparation methods rely on manual operations, resulting in low efficiency, environmental pollution and operational risks. Mechanical coal preparation technology still requires manual intervention, increasing the possibility of human error.

Method used

By crushing and grading raw coal, optical images are collected and processed to obtain coal gangue segmentation images, automatically capture coal gangue in clean coal and medium coal, and use edge detection, refinement, opening and closing operations and feature extraction algorithms to realize coal gangue. automatic segmentation and separation.

Benefits of technology

It improves coal preparation efficiency, reduces human errors, reduces labor costs, and realizes automated coal detection and sorting, providing real-time sorting results and data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119076424A_ABST
    Figure CN119076424A_ABST
Patent Text Reader

Abstract

The invention discloses a high-efficiency coal dressing method. The high-efficiency coal dressing method comprises the following steps: crushing raw coal; grading the crushed raw coal to obtain clean coal, middling coal and coal gangue; collecting an optical image of at least one of the clean coal and the middling coal, and processing the optical image to obtain a coal gangue segmentation image; and capturing coal gangue in the at least one of the clean coal and the middling coal according to the coal gangue segmentation image. The high-efficiency coal dressing method has the beneficial effects of being high in separation efficiency and the like, and by means of the high-efficiency coal dressing method, human errors can be reduced, the requirement for labor is reduced, and the labor cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of coal preparation, in particular to a high-efficiency coal preparation method. Background Art

[0002] At present, most coal preparation plants use manual coal preparation. However, this method of coal preparation not only causes environmental pollution, but also has low coal preparation efficiency. It requires operators with certain work experience to be competent, and the working conditions of operators are also very poor. The manual coal preparation method has great limitations, and mechanical coal preparation is an inevitable trend.

[0003] Existing mechanical coal preparation technology still relies on manual operation, which increases the possibility of human error and improper use of equipment. In addition, some operators fail to strictly implement rules and regulations in coal preparation work, which not only affects the quality of coal products, but also may increase the operational risks of enterprises. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the present invention proposes a high-efficiency coal preparation method.

[0005] The high-efficiency coal preparation method of the present invention comprises the following steps: crushing the raw coal; classifying the crushed raw coal to obtain clean coal, medium coal and coal gangue; collecting an optical image of at least one of the clean coal and the medium coal, processing the optical image to obtain a coal gangue segmentation image; and capturing the coal gangue in at least one of the clean coal and the medium coal according to the coal gangue segmentation image.

[0006] The high-efficiency coal preparation method of the present invention has the advantage of high sorting efficiency. By utilizing the high-efficiency coal preparation method of the present invention, human errors, the demand for manpower, and the labor cost can be reduced.

[0007] Optionally, processing the optical image includes the following steps: applying an edge detection operator to the image to generate an edge image, in which the boundary between the gangue and the surrounding environment is highlighted; and performing refinement processing on the edge image to reduce the width of the edge of the edge image.

[0008] Optionally, processing the optical image also includes the following steps: setting the color of the pixel points whose grayscale values ​​in the edge image after the refinement processing are greater than a threshold as the foreground color, and setting the color of the pixel points whose grayscale values ​​in the edge image after the refinement processing are less than or equal to the threshold as the background color, so as to obtain a binary image.

[0009] Optionally, processing the optical image also includes the following steps: performing an opening operation on the binary image to remove small objects in the binary image and keep the overall shape of the gangue in the binary image unchanged; and performing a closing operation on the binary image to fill holes, connect broken edges, and smooth the boundaries of the gangue.

[0010] Optionally, processing the optical image further includes the following steps: after performing the opening operation and the closing operation on the binary image, extracting features of the coal gangue in the binary image, the features including grayscale features, shape features and texture features.

[0011] Optionally, the grayscale features include grayscale values ​​and grayscale histograms of the gangue, the shape features include area, perimeter, aspect ratio and circularity of the gangue, and the texture features are extracted using a grayscale co-occurrence matrix.

[0012] Optionally, processing the optical image also includes the following steps: segmenting the binary image according to the grayscale features, the shape features and the texture features; starting from the seed point of the gangue, combining adjacent pixel points according to the similarity between pixels to form a larger area; using a contour extraction algorithm to extract the boundary contour of the gangue to obtain the gangue segmentation image.

[0013] Optionally, the gangue segmentation image is smoothed to remove isolated areas and / or fill holes.

[0014] Optionally, the classification of the crushed raw coal includes the following steps: mixing water and coal slime in a mass ratio of (1-5):1 to prepare a suspension; mixing the crushed raw coal with the suspension to suspend the raw coal in the suspension, and then performing density separation through a separator to obtain the clean coal, the medium coal and the coal gangue.

[0015] Optionally, the separator is one of a heavy medium cyclone, a chute and a flow channel. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a high-efficiency coal preparation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be understood as limiting the present invention.

[0018] The following describes a high-efficiency coal preparation method according to an embodiment of the present invention with reference to the accompanying drawings. Figure 1As shown, the high-efficiency coal preparation method according to an embodiment of the present invention comprises the following steps:

[0019] Crushing the raw coal;

[0020] Classify the crushed raw coal to obtain clean coal, medium coal and coal gangue;

[0021] collecting an image of at least one of the clean coal and the medium coal, and processing the image to obtain a gangue segmentation image; and

[0022] Gangue in at least one of the clean coal and the medium coal is captured according to the gangue segmentation image.

[0023] The high-efficiency coal separation method according to the embodiment of the present invention can automatically and continuously detect coal without human intervention by acquiring the segmented image of coal gangue and grabbing the coal gangue according to the segmented image of coal gangue. This not only greatly improves the separation efficiency and reduces human errors, but also reduces the demand for manpower and reduces labor costs.

[0024] Therefore, the high-efficiency coal preparation method according to the embodiment of the present invention has the advantages of high sorting efficiency, and by utilizing the high-efficiency coal preparation method according to the embodiment of the present invention, human errors can be reduced, the demand for manpower can be reduced, and labor costs can be reduced.

[0025] like Figure 1 As shown, the high-efficiency coal preparation method according to an embodiment of the present invention includes the following steps.

[0026] Crush the raw coal. The raw coal can be transported to the crushing workshop by a belt conveyor. The raw coal can be pre-screened by a vibrating screen, and the raw coal with larger particle size screened out can be crushed by a crusher to reduce the amount of crushing.

[0027] The crushed raw coal is classified to obtain clean coal, medium coal and coal gangue. Optionally, the crushed raw coal is classified including the following steps:

[0028] Mix water and coal slime in a mass ratio of (1-5):1 to prepare a suspension;

[0029] The crushed raw coal is mixed with the suspension to suspend the raw coal in the suspension, and then density separation is performed through a separator to obtain clean coal, medium coal and coal gangue.

[0030] Optionally, the separator is one of a heavy medium cyclone, a chute and a launder. The crushed raw coal particles are fully suspended in the suspension by stirring, washing, etc. Water and coal slime are mixed in a mass ratio of 4:1 to prepare a suspension to improve the effect of density separation.

[0031] After classification, both clean coal and medium coal will contain a small amount of gangue, which needs to be removed in order to improve the quality of clean coal and medium coal.

[0032] An optical image of at least one of the clean coal and the medium coal is collected, and the optical image is processed to obtain a gangue segmentation image. For example, optical images of the clean coal and the medium coal on the conveyor belt can be collected to obtain an optical image.

[0033] Optionally, processing the optical image comprises the following steps:

[0034] The edge detection operator is applied to the optical image to generate an edge image, in which the boundary between the gangue and the surrounding environment is highlighted, thereby identifying the boundary between the gangue and the clean coal and the medium coal in the image.

[0035] The edge image is thinned to reduce the width of the edge of the edge image. Optionally, the width of the edge of the edge image is close to a single pixel width to facilitate subsequent processing of the edge image.

[0036] Processing the optical image also includes the following steps: setting the color of the pixel points whose grayscale value is greater than the threshold in the refined edge image as the foreground color (e.g., white), and setting the color of the pixel points whose grayscale value is less than or equal to the threshold in the refined edge image as the background color (e.g., black), so as to obtain a binary image. In this way, gangue can be effectively distinguished from clean coal and medium coal.

[0037] Optionally, the threshold may be selected according to the grayscale distribution of the edge image.

[0038] Processing the optical image also includes the following steps:

[0039] An opening operation is performed on the binary image to remove small objects in the binary image and keep the overall shape of the gangue in the binary image unchanged.

[0040] The binary image is closed to fill holes, connect broken edges, and smooth the boundaries of gangue, thereby improving the structural features of the binary image and removing noise.

[0041] Optionally, when performing an opening operation on a binary image, erosion may be performed first and then dilation; when performing a closing operation on a binary image, dilation may be performed first and then erosion. Erosion can remove small objects in a binary image and shrink the boundaries of gangue inward. Dilation is the opposite of erosion and expands the boundaries of gangue outward to fill holes and connect broken edges.

[0042] The processing of the optical image also includes the following steps: after performing opening and closing operations on the binary image, extracting the features of the gangue in the binary image, the extracted features of the gangue include grayscale features, shape features and texture features, thereby obtaining features useful for gangue identification.

[0043] Optionally, the grayscale features include features such as grayscale value and grayscale histogram of the gangue. The shape features include features such as area, perimeter, aspect ratio and circularity of the gangue. The texture features are extracted using a grayscale co-occurrence matrix. The texture features include energy, correlation, homogeneity and contrast.

[0044] Processing the optical image also includes the following steps:

[0045] The binary image is segmented according to the grayscale feature, shape feature and texture feature. In other words, the binary image is segmented according to the extracted features of the gangue.

[0046] Then, starting from the seed point of the gangue, adjacent pixels are combined according to the similarity between pixels to form a larger area. Optionally, the similarity between pixels includes grayscale value, texture, etc.

[0047] Next, a contour extraction algorithm (such as Hough transform, chain code tracking, etc.) is used to extract the boundary contour of the gangue to obtain a gangue segmentation image, thereby accurately segmenting the gangue from the binary image.

[0048] Optionally, the gangue segmentation image is smoothed to remove isolated areas and / or fill holes, thereby improving the quality of the gangue segmentation image.

[0049] Gangue in the at least one of the clean coal and the medium coal is captured according to the gangue segmentation image. For example, coordinate data can be obtained according to the gangue segmentation image, and then the gangue is captured according to the coordinate data.

[0050] Optionally, a multi-layer perceptron is used to process the identified optical image (gangue segmentation image) and then output coordinate data.

[0051] Before using the multilayer perceptron for data processing, the multilayer perceptron can be trained using optical images. First, the optical image can be preprocessed to improve the quality of the optical image and improve the efficiency and accuracy of subsequent processing. Specifically, a filter (such as a Gaussian filter, a median filter, etc.) is used to remove noise from the optical image, and the pixel value of the optical image is scaled to a specific range (such as 0 to 1 or -1 to 1) for subsequent processing. The visual effect of the optical image can also be enhanced by methods such as histogram equalization and contrast adjustment to make the target features more obvious.

[0052] Subsequently, features useful for identification are extracted from the preprocessed optical image. First, edge detection operators are used to identify edge information of the target in the optical image. Then, texture analysis and shape analysis are performed to extract texture features and shape features of the target in the optical image. Among them, texture features can be statistical data of gray-level co-occurrence matrices, and shape features can be area, perimeter, circularity, etc. If the optical image is in color, color features such as color histograms and color moments can also be extracted.

[0053] The most useful features for the recognition task can be selected from the features of the extracted target in order to reduce the amount of calculation and improve the recognition accuracy. Specifically, the correlation between the features is calculated to remove redundant features. Then, the importance of each remaining feature is evaluated using a feature selection algorithm (such as principal component analysis PCA, mutual information MI, etc.). Finally, the optimal feature subset is selected based on the importance evaluation result. In this way, the amount of calculation can be reduced and the recognition accuracy can be improved.

[0054] The selected features (optimal feature subset) can be trained using a multilayer perceptron to learn the mapping relationship between input features and output coordinates. Specifically, the data of the selected features and the corresponding coordinate data are divided into a training set and a test set. Then, a multilayer perceptron model is constructed using a deep learning framework (such as TensorFlow, PyTorch, etc.), and parameters such as the number of neurons in the input layer, hidden layer, and output layer and the activation function are set. Next, the multilayer perceptron model is trained using the training set data, and the parameters of the multilayer perceptron model are adjusted through the back propagation algorithm to minimize the loss function. The performance of the multilayer perceptron model is evaluated using the test set data, including indicators such as accuracy and recall.

[0055] Use the trained multi-layer perceptron model to predict the new optical image and extract the coordinate data of the target. Specifically, the optical image to be identified is input into the multi-layer perceptron model, and the input optical image is preprocessed and feature extracted (the feature extraction operation is the same as the training process). Then, the extracted features are input into the trained multi-layer perceptron model for prediction. Next, the coordinate data of the target is extracted from the output of the multi-layer perceptron model. These coordinate data can represent the position of the target in the image (such as the center point coordinates), the coordinates of the bounding box, etc.

[0056] Compared with the prior art, the beneficial effects of the present invention are:

[0057] (1) The present invention can automatically detect coal continuously and quickly without human intervention, which greatly improves the efficiency of sorting and reduces human errors.

[0058] (2) The present invention can automatically complete most of the detection work, thereby reducing the demand for manpower and thus reducing labor costs.

[0059] (3) The present invention can provide real-time sorting results and data, and operators can adjust sorting parameters in time according to this information to optimize the sorting process.

[0060] (4) The present invention can adapt to different coal types and sorting requirements, and can achieve effective sorting of different types of coal by adjusting image processing algorithms and parameters.

[0061] (5) The high-efficiency coal separation method of the present invention can be integrated with other coal separation equipment and systems to form a complete automated separation system, which helps to improve the automation level and efficiency of the entire coal separation process.

[0062] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0063] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0064] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection, an electrical connection, or communication with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0066] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0067] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A high-efficiency coal preparation method, characterized in that: The following steps are involved: Crushing the raw coal; Classify the crushed raw coal to obtain clean coal, medium coal and coal gangue; collecting an optical image of at least one of the clean coal and the medium coal, and processing the optical image to obtain a gangue segmentation image; and Gangue in at least one of the clean coal and the medium coal is captured according to the gangue segmentation image.

2. The high-efficiency coal preparation method according to claim 1, characterized in that: Processing the optical image comprises the following steps: applying an edge detection operator to the image to generate an edge image in which the boundary between the gangue and the surrounding environment is highlighted; and The edge image is thinned to reduce the width of the edge of the edge image.

3. The high-efficiency coal preparation method according to claim 2, characterized in that: Processing the optical image also includes the following steps: setting the color of the pixel points whose grayscale values ​​in the edge image after the refinement processing are greater than a threshold as the foreground color, and setting the color of the pixel points whose grayscale values ​​in the edge image after the refinement processing are less than or equal to the threshold as the background color, so as to obtain a binary image.

4. The high-efficiency coal preparation method according to claim 3, characterized in that: Processing the optical image further comprises the following steps: Performing an opening operation on the binary image so as to remove small objects in the binary image and keep the overall shape of the gangue in the binary image unchanged; and A closing operation is performed on the binary image to fill holes, connect broken edges, and smooth the boundaries of coal gangue.

5. The high-efficiency coal preparation method according to claim 4, characterized in that: Processing the optical image further includes the following steps: after performing the opening operation and the closing operation on the binary image, extracting the features of the gangue in the binary image, the features including grayscale features, shape features and texture features.

6. The high-efficiency coal preparation method according to claim 5, characterized in that: The grayscale features include the grayscale value and grayscale histogram of the gangue, the shape features include the area, perimeter, aspect ratio and circularity of the gangue, and the texture features are extracted using a grayscale co-occurrence matrix.

7. The high-efficiency coal preparation method according to claim 6, characterized in that: Processing the optical image further comprises the following steps: Segmenting the binary image according to the grayscale feature, the shape feature and the texture feature; Starting from the seed point of coal gangue, adjacent pixels are combined according to the similarity between pixels to form a larger area; The boundary contour of the gangue is extracted using a contour extraction algorithm to obtain the gangue segmentation image.

8. The high-efficiency coal preparation method according to claim 7, characterized in that: The gangue segmentation image is smoothed to remove isolated areas and / or fill holes.

9. The high-efficiency coal preparation method according to claim 1, characterized in that: The classification of the crushed raw coal comprises the following steps: Mix water and coal slime in a mass ratio of (1-5):1 to prepare a suspension; The crushed raw coal is mixed with the suspension to suspend the raw coal in the suspension, and then density separation is performed through a separator to obtain the clean coal, the medium coal and the coal gangue.

10. The high-efficiency coal preparation method according to claim 1, characterized in that: The separator is one of a heavy medium cyclone, a chute and a launder.

Citation Information

Cited By

  • Whole-fraction dry coal preparation system based on digital twinning

    CN119549270A