A geological logging method for coal mining faces based on video surveillance images

Abstract

The present invention discloses a method for geological logging of coal mining faces based on video surveillance images. This method uses a pan-tilt camera to collect images of the working face, and uses image recognition and segmentation algorithms to extract geological information from the images. Combining with the data of the mining height, geological logging of the coal mining face is carried out, providing dynamic data for constructing a high-precision coal seam model of the working face. The present invention can carry out geological logging of the coal mining face without geological surveyors going down the well, does not interfere with normal coal mining operations, makes full use of the existing facilities of the intelligent mining working face, and has a small cost investment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent coal mining, and in particular to a method for geological cataloging of coal mining faces based on video surveillance images, which extracts geological information from video surveillance images of coal mining faces, integrates mining height data, and performs dynamic geological cataloging of coal mining faces. Background Art

[0002] Intelligent coal mining is an inevitable requirement for the technological revolution and transformation and upgrading of the coal industry in the new era. Restricted by the technical difficulties of coal rock identification, current intelligent mining is generally carried out in working faces with simple geological conditions such as no large or medium-sized structures, stable coal seam thickness, and nearly horizontal coal seams. However, there are still many technical difficulties in intelligent mining under more complex geological conditions.

[0003] In 2016, the domestic coal industry first proposed a smart mining technology route based on transparent working faces: first, identify the coal seam conditions in the area to be mined in advance and with high precision, and build a high-precision coal seam model; then, simulate the mining process based on the coal seam model, plan the cutting curve of the coal mining machine in advance, and upgrade "memory cutting" to "planned cutting". Since 2019, the 31114 working face of Jinjie Coal Mine, the 43101 working face of Yujialiang Coal Mine, the 431301 working face of Zhangjiamao Coal Mine, the 3301 working face of Guotun Coal Mine, and the 810 working face of Huangling No. 1 Coal Mine have successively carried out planned cutting engineering practices based on transparent geology, and achieved certain results.

[0004] Practice shows that the accuracy of the static coal seam model constructed by static geological data (pre-mining geophysical exploration, drilling and tunnel exposure, etc.) is not enough to provide geological navigation for coal mining machine planning and cutting; the use of high-precision coal seam geological detection / measurement technology to progressively obtain the spatial occurrence information of coal seams exposed by mining and correct the coal seam model can greatly improve the accuracy of the coal seam model in the area to be mined. Therefore, how to efficiently and accurately collect the geological information of coal seam occurrence exposed by mining is one of the key issues to be solved in high-precision modeling of coal mining faces. Summary of the invention

[0005] The technical problem to be solved by the present invention is that in view of the deficiencies in the above-mentioned prior art, the present invention provides a geological cataloging method for coal mining working faces based on video surveillance images, which performs geological cataloging on the full-height working faces of "thin-medium-thick" coal seams.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A method for geological logging of coal mining working faces based on video monitoring images comprises the following steps:

[0008] Automated acquisition steps of the working face image: Control the optical axis of the pan-tilt camera to be perpendicular to the coal wall of the working face, and acquire the working face image;

[0009] Geological structure information extraction steps: According to the overall information of the working face image set, identify the geological structures exposed during mining, mainly including faults and collapse columns;

[0010] Coal seam undulation information extraction steps: According to the information of coal-rock interface, bedding, parting, etc. reflected in the image, estimate the local pseudo-dip angle of the coal seam, and combine with the coal seam geological information exposed in the roadways on both sides of the working face to approximately calculate the roof line of the coal mining face;

[0011] Local coal-rock column information extraction steps of the working face: Manually or using an image recognition algorithm, perform semantic segmentation of the working face image into "coal wall - rock wall - rib protection plate", calculate the proportional relationship between the actual size and the image size of the rib protection plate, and calculate the height of the coal (or rock) wall above the coal-rock interface according to the principle of close-range measurement. Integrate the mining height data, and then calculate the height of the rock (or coal) wall below the coal-rock interface to obtain the local coal-rock column information;

[0012] Geological logging steps of the working face: Integrate the roof line of the working face and the coal-rock column information at each observation point to obtain the geological logging map of the coal mining face.

[0013] Preferably, the automated acquisition steps of the working face image specifically include the following sub-steps:

[0014] Along the coal mining face, arrange an explosion-proof pan-tilt camera at intervals of a certain number of hydraulic supports, and it is recommended to arrange at intervals of 3 - 5 hydraulic supports;

[0015] During the maintenance shift, control the optical axis of the pan-tilt camera on the working face to be perpendicular to the coal wall through the centralized control center, and acquire the working face image.

[0016] Preferably, the geological structure information extraction steps specifically include the following content:

[0017] According to the overall information of the working face image set, identify the faults and collapse columns exposed during mining, and record the starting support number and the ending support number where the faults / collapse columns start to damage the coal seam;

[0018] For faults, use lines different from the color distribution of the working face image to mark the fault plane on the working face image;

[0019] Adopt an image processing algorithm to calculate the fault dip angle according to the fault plane marking information.

[0020] Preferably, the steps of estimating the local pseudo-dip angle of the coal seam in the coal seam undulation information extraction steps specifically include the following steps:

[0021] Identify the objects in the working face image that reflect the false dip of the coal seam manually or using an image recognition algorithm, including but not limited to the coal-rock interface, coal beddings, coal seam partings, etc.;

[0022] Use lines different from the color distribution of the working face image to mark the false dip of the coal seam on the working face image;

[0023] Use an image processing algorithm to calculate the false dip of the coal seam according to the marked information of the false dip of the coal seam.

[0024] Preferably, the calculation of the fault plane and the false dip of the coal seam in the geological structure information extraction step and the coal seam undulation information extraction step specifically includes the following steps:

[0025] According to the difference in pixel color values, screen out the pixel points marking the fault plane and the false dip of the coal seam, and record the column numbers and row numbers of the screened pixel points in the pixel coordinate system;

[0026] Establish an XOY rectangular coordinate system with the pixel point at the lower left corner of the image as the coordinate origin, and convert the row and column numbers of the screened pixel points into the X and Y coordinates in the XOY coordinate system according to Equation (1):

[0027]

[0028] In the formula, m and n are the row and column numbers of the pixel point in the pixel coordinate system respectively, M is the total number of rows, and x and y are the X and Y coordinates of the converted pixel point in the XOY coordinate system respectively;

[0029] In the XOY coordinate system, use a linear function to fit the set of red pixel point coordinates, and record the slope of the fitted line as k;

[0030] When the coal seam extends upward, record the false dip α of the coal seam as positive; when the working face extends downward, record the false dip of the coal seam as negative. According to this positive and negative convention, calculate the false dip of the coal seam according to Equation (2):

[0031]

[0032] Record the fault dip β as the included angle between the fault boundary and the horizontal line to the right (camera view angle), and calculate the fault plane dip according to Equation (3):

[0033]

[0034] Preferably, the calculation of the roof line of the coal mining working face in the coal seam undulation information extraction step specifically includes the following steps:

[0035] The dip angle of the working face is generally small and changes gently. At the same time, considering the distance between adjacent observation points (l i -l i-1) It has a limited length, and the working face roof curve can be approximated by the broken line in Figure (3). The angle between each segment of the broken line and the horizontal line is the dip angle of the working face at each observation point. According to the elevation z0 at the observation point in the left roadway and the dip angle α0 of the working face, the roof height z1 of the right observation point can be calculated according to Equation (4):

[0036] z1 = z0 + (l1 - l0)tanα0 (4)

[0037] For any adjacent observation points:

[0038]

[0039] Introduce the variable Δz i-1,i , and its definition formula is:

[0040] Δz i-1,i = z i - z i-1 (i = 1,..., n) (6)

[0041] From Equation (6), Equation (7) can be obtained:

[0042]

[0043] Ideally, Equation (7) holds. Due to the simplification of the problem and the errors of l i and α i , Equation (7) does not hold. Therefore, an error ε is introduced, and Equation (7) is rewritten as:

[0044]

[0045] The adjustment method is used to average the error ε to each Δz i-1,i , that is:

[0046]

[0047] In the formula, ε i (i = 1,..., n) is the error component of the error ε averaged to each Δz i-1,i .

[0048] Using Equation (10), ε is averaged to each Δz i-1,i :

[0049]

[0050] From Equation (10), ε i (i = 1,..., n) can be solved:

[0051]

[0052] Substituting Equation (8) and Equation (11) into Equation (5), the value of z can be obtained i (for i = 1,..., n - 1):

[0053]

[0054] The unknown variable z can be solved from the above equation i (for i = 1,..., n - 1), and an approximate broken line of the working face roof line can be obtained

[0055] Preferably, the steps for extracting the local coal-rock columnar information of the working face specifically include the following sub-steps:

[0056] Manually or using an image recognition algorithm to perform semantic segmentation on the working face image, and using an image processing algorithm to obtain the distribution ranges of the coal wall, rock wall, and rib protection plate in the working face image;

[0057] Since the optical axis of the camera is perpendicular to the measured object surface, the measured target size and the size of the imaged object satisfy a similarity relationship, as shown in Equation (13):

[0058]

[0059] In the formula, L1 is the size of the standard object in the image, L2 is the actual size of the standard object, a is the size of the measured object in the image, b is the actual size of the measured object, and k is the scale factor;

[0060] For the coal mining working face image, since the actual size of the rib protection baffle of the hydraulic support is known, by processing the semantic segmentation result of the working face image, the pixel coordinate set of the area where the rib protection baffle is located can be obtained, and then the size of the rib protection baffle image can be calculated. Then, according to Equation (13), the scale factor k can be obtained;

[0061] Affected by the bottom floating coal, the bottom boundary of the working face is generally unclear. Therefore, first, according to the image segmentation result, calculate the true height difference Δh from the coal-rock interface to the bottom of the rib protection plate. The calculation formula is:

[0062]

[0063] In the formula, and are respectively the average Y coordinate of the coal-rock interface and the average Y coordinate of the bottom of the rib protection plate in the XOY coordinate system of the image. When the coal-rock interface is above the bottom of the rib protection plate, Δh > 0; when the coal-rock interface is below the bottom of the rib protection plate, Δh < 0;

[0064] Considering the general situation, that is, the rib protection plate is close to the coal and rock walls, and the hydraulic support is in direct contact with the top of the working face. Denote the distance from the bottom of the rib protection plate to the top of the working face as h0. Then, the calculation formula for h0 is:

[0065] h0 = h1 + h2 (15)

[0066] Wherein, h1 is the thickness of the top support plate of the hydraulic support, h2 is the rib protection height of the rib protection plate, and both h1 and h2 are known values;

[0067] From Equation (14) and Equation (15), the height h from the coal-rock interface to the top of the working face can be obtained r as:

[0068] h r = h0 - Δh (16)

[0069] The distance h from the coal-rock interface to the bottom of the working face can be calculated from the recorded mining height f , and the calculation formula is:

[0070] h f = H - h r (17)

[0071] Wherein, H is the cutting height of the shearer, which can be calculated from the shearer boom angle sensor or the hydraulic support height sensor. The above height variables and their relationships are as Figure 5 shown.

[0072] The method of integrating the mining height with image recognition can avoid the adverse effects of floating coal on the working face on identifying the bottom coal wall or rock wall.

[0073] Beneficial effects:

[0074] The present invention makes full use of the existing video monitoring system of the intelligent mining working face, uses a pan-tilt camera to collect images of the working face during the maintenance shift, extracts useful geological information in the working face, and conducts geological logging on the full-height working face of "thin-medium thick" coal seams. This method does not require geological surveyors to go down the well, does not interfere with normal coal mining operations, and has high geological logging accuracy and efficiency; the geological logging results can provide key data support for intelligent coal mining. Brief description of the drawings

[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0076] Figure 1 is the implementation flowchart of the method of the present invention;

[0077] Figure 2 is the schematic diagram of calculating the roof line of the working face in the method of the present invention;

[0078] Figure 3 It is a schematic diagram of the height variables related to the shearer cutting in the method of the present invention;

[0079] Figure 4 It is a case of semantic segmentation of the working face image in the embodiment of the method of the present invention;

[0080] Figure 5 It is the U-net network model architecture adopted by the "coal wall - rock wall - rib protection plate" semantic segmentation model of the present invention;

[0081] Figure 6 It is a case of calculating the local coal - rock columnar information from the semantic segmentation result of the image in the embodiment of the method of the present invention;

[0082] Figure 7 It is a geological logging map based on the image in the embodiment of the method of the present invention. Detailed implementation manners

[0083] Next, the technical solutions and working processes of the present invention will be described in detail in conjunction with the embodiments of the present invention and their accompanying drawings. The protection scope of the present invention is not limited by the following examples.

[0084] I. Working face image acquisition and basic information

[0085] Taking the XY - S working face in Shanxi as the test point, the camera density is 1 camera evenly arranged for every 6 hydraulic supports, and the working face images are collected during the maintenance shift on December 12, 2020. At this time, the shearer has advanced 2355.0 m along one side of the intake airway and mined 2360.8 m along one side of the auxiliary intake airway. The roof elevation of the coal seam in the auxiliary intake airway is 504.82 m, the thickness is 3.13 m, and the pseudo - dip angle is 7.5°. The roof elevation of the coal seam in the intake airway is 517.63 m, the thickness is 2.55 m, and the pseudo - dip angle is 0.4°.

[0086] II. Structure discrimination

[0087] The working face image shows that the area from the 60th to the 95th support of the working face is the affected area of the normal fault. The section from the 65th to the 75th support is the upper coal seam and the lower rock stratum. The 75th support shows the fault plane. The section from the 75th to the 90th support is the full rock wall. The section from the 90th to the 114th support is the upper rock stratum and the lower coal seam section.

[0088] III. Coal seam pseudo - dip angle marking and working face roof line calculation

[0089] The pseudo - dip angle of the coal seam and the dip angle of the rock wall section in the working face image are manually marked, and the marking results are compared with the measured data. The results are shown in Table 1.

[0090] Table 1

[0091]

[0092] Based on the roadway measurement information on both sides of the working face and the pseudo-dip information of the coal seam, the roof line of the working face was calculated using Equation (12).

[0093] IV. Coal-rock columnar information in the rock cutting area

[0094] Taking the calculation of the coal-rock columnar information at the 70# support as an example, the method for extracting the coal-rock columnar information in the rock cutting area is described as follows:

[0095] The U-net convolutional neural network was used to train the semantic segmentation model of the "coal wall - rock wall - rib protection plate" for the working face images, and the images collected by the 70# support camera were semantically segmented. The results are as Figure 4 shown;

[0096] The present invention uses the U-net model to train the semantic segmentation model of the working face images. The U-net model architecture is as Figure 5 shown. This model consists of a left contracting path and a right expanding path. The contracting path part follows the typical convolutional neural network structure and is composed of 4 repeated "3×3 convolutional operations with 2 rectified linear units (ReLU) + 1 2×2 max pooling operation with a stride of 2" and 2 3×3 convolutional operations with ReLU. The role of the contracting path is to extract image features. The expanding path part is composed of 4 repeated upsampling steps and 1 1×1 convolutional operation. A single upsampling includes 1 2×2 deconvolution (up-convolution), 1 feature map stitching and cropping, and 2 3×3 convolutional operations with ReLU. The role of the expanding path is to restore the high-level semantic feature map to the resolution of the original image to obtain the image semantic segmentation map. See Figure 5 shown.

[0097] The model number of the hydraulic support in the XY-S working face is ZY8000 / 18 / 37d. The distance from the bottom of the rib protection plate to the top of the working face is 1.25 m, and the width of the rib protection plate is 1.20 m. According to the length of the rib protection plate in the pixel coordinate axis of the picture and the actual side length, the ratio of the actual size to the image size is calculated to be 0.0045, and the recorded cutting height of the shearer is 3.10 m;

[0098] Based on the image semantic segmentation results, the scale factor k, and the cutting height, the coal-rock columnar diagram as Figure 6 shown was calculated and drawn;

[0099] Referring to the actual measured coal-rock columnar section, the absolute error of the coal wall height of the coal-rock columnar section calculated based on the image is 0.08 m, and the relative error is 3.7%. The absolute error of the rock wall height is 0.08 m, and the relative error is 8.6%.

[0100] Using the same method, the coal-rock columnar information at the observation points 95#, 100#, 105# and 112# in the rock wall pinch-out section was calculated, and the results are shown in Table 2.

[0101] Table 2

[0102]

[0103] V. Geological logging and accuracy analysis of the working face

[0104] Based on the roof line of the working face, the coal-rock columnar section of the rock wall pinch-out section, and the cutting height of the shearer, the geological logging map of the XY-S coal mining working face on December 12th was drawn, Figure 7 as shown.

[0105] Since the shearer records the cutting height data, there is no difference in the height direction between the geological logging based on the image and the geological logging based on the underground measurement. Compared with the roof line of the actual measured section, the maximum error of the roof line calculated based on the image is 0.84 m, and the average value of the absolute error at 17 measuring points is 0.33 m.

Claims

1. A geological logging method for coal mining faces based on video surveillance images, characterized in that, Specifically, it includes the following steps: Automated acquisition step of the working face image: Control the optical axis of the pan-tilt camera to be perpendicular to the coal wall of the working face, and acquire the working face image; Geological structure information extraction step: According to the overall information of the working face image set, identify the geological structures exposed during coal mining, including faults and collapse columns; Coal seam undulation information extraction step: According to the coal-rock interface, bedding, and parting information reflected in the working face image, estimate the local pseudo-dip angle of the coal seam, and calculate the roof line of the coal mining face; Among them, the step of estimating the local pseudo-dip angle of the coal seam specifically includes: Manually or using an image recognition algorithm to identify the objects reflecting the pseudo-dip angle of the coal seam in the working face image, including but not limited to the coal-rock interface, coal seam bedding, and coal seam parting; Use lines different from the color distribution of the working face image to mark the pseudo-dip angle of the coal seam on the working face image; Use an image processing algorithm to calculate the pseudo-dip angle of the coal seam according to the marked information of the pseudo-dip angle of the coal seam; Among them, the step of calculating the roof line of the coal mining face is as follows: Considering the spacing between adjacent observation points, approximate the roof curve of the working face with a broken line. The angle between each segment of the broken line and the horizontal line is the working face dip angle at each observation point. According to the elevation and working face dip angle at the left roadway observation point, calculate the roof height of the right observation point of the working face to obtain the roof line of the working face; Extraction step of local coal-rock columnar information of the working face: Perform semantic segmentation of the working face image into "coal wall - rock wall - rib protection plate", and calculate the local coal-rock columnar information according to the principle of close-range measurement; Geological logging step of the working face: Integrate the roof line of the working face and the coal-rock columnar information at each observation point to obtain the geological logging map of the coal mining face.

2. The geological logging method for coal mining faces based on video surveillance images according to claim 1, characterized in that, The coal seam undulation information extraction step described above: According to the coal-rock interface, bedding, and parting information reflected in the working face image, estimate the local pseudo-dip angle of the coal seam, and combine the coal seam geological information exposed in the roadways on both sides of the working face to calculate the roof line of the coal mining face.

3. The geological logging method for coal mining faces based on video surveillance images according to claim 1, characterized in that, The extraction step of local coal-rock columnar information of the working face described above: Manually or using an image recognition algorithm to perform semantic segmentation of the working face image into "coal wall - rock wall - rib protection plate", calculate the proportional relationship between the actual size and the image size of the rib protection plate, and calculate the height of the coal (or rock) wall above the coal-rock interface according to the principle of close-range measurement. Integrate the data of the mining height, and then calculate the height of the rock (or coal) wall below the coal-rock interface to obtain the local coal-rock columnar information.

4. The geological logging method for coal mining faces based on video surveillance images according to claim 1, characterized in that, The automated acquisition step of the working face image specifically includes: Along the coal mining face, arrange an explosion-proof pan-tilt camera at a certain interval of hydraulic supports; During the maintenance shift, control the optical axis of the pan-tilt camera on the working face to be perpendicular to the coal wall through the centralized control center to acquire the working face image.

5. The geological logging method for coal mining faces based on video surveillance images according to claim 1, characterized in that, The geological structure information extraction step specifically includes: According to the overall information of the working face image, identify the faults and collapse columns exposed during coal mining, record the starting support number and the ending support number where the fault / collapse column starts to damage the coal seam; For faults, use lines different from the color distribution of the working face image to mark the fault plane on the working face image; Use an image processing algorithm to calculate the dip angle of the fault plane according to the marked information of the fault plane.

6. The geological logging method for coal mining faces based on video surveillance images according to claim 5, characterized in that, The fault plane and the calculation steps of the pseudo-dip angle of the coal seam in the geological structure information extraction step and the coal seam undulation information extraction step specifically include: According to the difference in pixel color values, the pixel points marking the fault plane and the pseudo-dip angle of the coal seam are screened out, and the column numbers and row numbers of the screened pixel points in the pixel coordinate system are recorded; Taking the pixel point at the lower left corner of the image as the coordinate origin, an XOY rectangular coordinate system is established, and the row and column numbers of the screened pixel points are converted into the X and Y coordinates in the XOY coordinate system according to Equation (1): In the formula, m and n are the row and column numbers of the pixel points in the pixel coordinate system respectively, M is the total number of rows, and x and y are the X and Y coordinates of the converted pixel points in the XOY coordinate system respectively; In the XOY coordinate system, a unary linear function is used to fit the set of red pixel point coordinates, and the slope of the fitted straight line is denoted as k; When the coal seam extends upward, the pseudo-dip angle α of the coal seam is recorded as positive; when the working face extends downward, the pseudo-dip angle of the coal seam is recorded as negative. According to this positive and negative convention, the pseudo-dip angle of the coal seam is calculated according to Equation (2): Denote the fault dip angle β as the included angle between the fault boundary line and the horizontal line to the right (camera view angle), and calculate the fault plane dip angle according to Equation (3):

7. The geological logging method for coal mining faces based on video surveillance images according to claim 1, characterized in that, The calculation steps of the roof line of the coal mining face in the coal seam undulation information extraction steps specifically include: The dip angle of the working face is generally small and changes gently. At the same time, considering that the distance (l i -l i-1 ) between adjacent observation points is limited, a broken line is used to approximate the curve of the working face roof. The angle between each segment of the broken line and the horizontal line is the dip angle of the working face at each observation point. According to the elevation z0 at the observation point in the left roadway and the dip angle α0 of the working face, the roof height z1 of the working face at the right observation point can be calculated according to Equation (4): z1 = z0 + (l1 - l0)tanα0 (4) For any adjacent observation points: Introduce the variable Δz i-1,i , and its definition is as follows: Δz i-1,i = z i - z i-1 (i = 1, ...,n) (6) From Equation (6), Equation (7) can be obtained: Introduce the error ε, so Equation (7) is rewritten as: The adjustment method is used to average the error ε to each Δz i-1,i That is: where ε i (i = 1,..., n) is the error component of the error ε adjusted to each Δz i-1,i ; Using Equation (10), ε is adjusted to each Δz i-1,i : ε can be solved from Equation (10) i (i = 1,..., n): Substituting Equation (8) and Equation (11) into Equation (5), z can be obtained i (i = 1,..., n - 1) calculation formula: The unknown quantity z can be solved from the above equation. i (i = 1, ..., n - 1), an approximate broken line of the working face roof line is obtained.

8. A geological logging method for a coal mining face based on video surveillance images according to any one of claims 1 or 3, characterized in that, The extraction steps of the local coal-rock columnar information of the working face specifically include: Manually or using an image recognition algorithm to perform "coal wall - rock wall - rib protection plate" semantic segmentation on the working face image, and use an image processing algorithm to obtain the distribution ranges of the coal wall, rock wall, and rib protection plate in the working face image; Since the optical axis of the camera is perpendicular to the measured object surface, the measured target size and the size of the imaged object satisfy a similar relationship, as shown in Equation (13): In the formula, L1 is the size of the standard object in the image, L2 is the actual size of the standard object, a is the size of the measured object in the image, b is the actual size of the measured object, and k is the scale factor; For the coal mining face image, the actual size of the rib protection baffle of the hydraulic support is known. By processing the semantic segmentation result of the working face image, the set of pixel coordinates of the area where the rib protection baffle is located can be obtained, and then the size of the rib protection baffle image can be calculated, and then the scale factor k can be obtained according to Equation (13); Affected by the bottom floating coal, the bottom boundary of the working face is generally unclear. Therefore, first calculate the true height difference Δh from the coal-rock interface to the bottom of the rib protection plate according to the image segmentation result, and the calculation formula is: In the formula, and are respectively the average value of the Y coordinate of the coal-rock interface and the average value of the Y coordinate at the bottom of the rib protection plate in the XOY coordinate system of the image. When the coal-rock interface is above the bottom of the rib protection plate, Δh > 0; when the coal-rock interface is below the bottom of the rib protection plate, Δh < 0. The rib protection plate is close to the coal and rock walls, and the hydraulic support is in direct contact with the top of the working face. Denote the distance from the bottom of the rib protection plate to the top of the working face as h0, then the calculation formula of h0 is: h0 = h1 + h2 (15) In the formula, h1 is the thickness of the top support plate of the hydraulic support, h2 is the rib protection height of the rib protection plate, and both h1 and h2 are known values; From Equation (14) and Equation (15), the height h from the coal-rock interface to the top of the working face can be obtained r as follows: h r = h0 - Δh (16) The distance h from the coal-rock interface to the bottom of the working face can be calculated from the recorded mining height f , and the calculation formula is as follows: h f = H - h r (17) In the formula, H is the cutting height of the shearer, which is calculated by the shearer boom angle sensor or the hydraulic support support height sensor.

Images