Rock unloading hole layout and parameter optimization method based on coal rock cutting convergence

Abstract

The invention discloses a rock unloading hole layout and parameter optimization method based on coal rock cutting convergence, and the method comprises the steps: constructing an unloading hole layout optimization model, inputting to-be-processed rock unloading hole data into the unloading hole layout optimization model, and obtaining an optimal unloading hole layout; drilling and presplitting are conducted on the rock stratum through the optimal unloading hole layout, and the rock stratum compressive strength and the coal seam trend are achieved; wherein the unloading hole layout optimization model is constructed through a neural network model and is obtained through training of a rock stratum unloading hole data set. According to the method, layout optimization is conducted on the unloading holes, high rock stratum compressive strength reduction is achieved with low unloading hole drilling cost, the unloading holes are further formed in the rock stratum, the overall compressive strength of the rock stratum is reduced to be the same as that of a coal seam, and therefore the cutting difficulty of a coal mining machine on a coal-rock boundary layer is reduced, and finally efficient mining is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent coal mining, and in particular to a rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence. Background Art

[0002] As the world's largest energy producer and consumer, coal is the main energy source supporting the development of my country's national economy, an important guarantee for energy security and an important raw material for industrial production. Its high-quality development is the key to my country's energy transformation. In actual coal mining, when the coal mining machine contacts the coal-rock boundary layer, the hard rock layer will reduce the cutting efficiency, cause the pick to wear more severely, and easily generate sparks. These factors pose a threat to the safe mining of coal mines. How to efficiently and safely handle coal mining at the coal-rock boundary layer is one of the important issues in intelligent coal and rock mining.

[0003] Existing technologies usually pre-crack the rock formation to weaken the strength of the rock formation, thereby reducing the cutting pressure of the coal mining machine. They mainly include drilling and blasting, static fracturing and other technologies. The former requires blasting and poses a safety hazard, while the latter has a long fracturing cycle and low efficiency. The patent, entitled "Method for Rapidly Crossing Hard Rock Faults by Hydraulic Fracturing at Coal Mining Faces in Underground Mines", applies hydraulic fracturing technology to rock formation pre-cracks, which better balances the above two shortcomings. However, the patent fails to clearly point out the relationship between rock formation properties and fracturing hole layout parameters, thus failing to achieve the most efficient rock formation pre-cracks.

[0004] Research shows that in coal and rock mining, the crushing of rock formations is mainly achieved by compressing and destroying them with cutting drums. The difficulty of this crushing is mainly related to the compressive strength of the rock formation. According to the stress concentration theory, arranging unloading holes on the rock formation can reduce the overall compressive strength of the rock formation, thereby reducing the difficulty of cutting by the coal mining machine. Based on the above, this patent optimizes the layout of the unloading holes, achieves a higher reduction in the compressive strength of the rock formation at a lower drilling cost of the unloading holes, and further arranges unloading holes on the rock formation, thereby achieving the convergence of the compressive strength of the coal seam and the rock formation, so as to complete efficient mining of the coal-rock boundary layer. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned prior art, the present invention proposes a rock unloading hole layout and parameter optimization method based on the convergence of coal-rock cutting. By optimizing the layout of the unloading holes, a higher reduction in the compressive strength of the rock formation can be achieved with a lower unloading hole drilling cost. Unloading holes are further arranged on the rock formation to reduce the overall compressive strength of the rock formation to be consistent with that of the coal seam, thereby reducing the difficulty of cutting the coal-rock boundary layer by the coal mining machine, and ultimately achieving efficient mining.

[0006] To achieve the above-mentioned purpose, the present invention provides a rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence, including:

[0007] Constructing an unloading hole layout optimization model, inputting the unloading hole data of the rock formation to be processed into the unloading hole layout optimization model, and obtaining an optimal unloading hole layout;

[0008] The rock formation is pre-split by drilling holes through the optimal unloading hole layout, so that the compressive strength of the rock formation is similar to that of the coal seam;

[0009] The unloading hole layout optimization model is constructed by a neural network model and is obtained by training with a rock formation unloading hole data set.

[0010] Preferably, obtaining the rock formation unloading hole data set includes:

[0011] The coal-rock boundary and three-dimensional representation of the coal wall, the compressive strength of the coal seam and the rock layer are obtained respectively, and the rock layer unloading hole data set is constructed based on finite element simulation;

[0012] The compressive strength of the coal seam and the rock layer is obtained by using a rebound method, including:

[0013] The rebound hammer is calibrated, and rebound tests are performed on several test points of the tested coal seam or rock formation. The rebound value of each test point is recorded, and the compressive strength corresponding to each rebound value is converted by table lookup method. The compressive strength of all test points is averaged to obtain the compressive strength of the coal seam or the compressive strength of the rock formation.

[0014] Preferably, constructing the rock formation unloading hole data set includes:

[0015] Extracting a three-dimensional representation of the rock formation based on the coal-rock boundary and the three-dimensional representation of the coal wall, importing the three-dimensional representation of the rock formation into ANSYS software, setting the compressive strength of the rock formation in ANSYS software to the measured compressive strength of the rock formation, using the measured compressive strength of the rock formation as the original compressive strength of the rock formation, meshing the rock formation, applying unloading hole loads of different layouts to the rock formation, running a static solver for analysis, obtaining the compressive strength of the rock formation after the unloading hole load is applied, and using the compressive strength of the rock formation after the unloading hole load is applied as the target compressive strength;

[0016] Recording three-dimensional representations of different rock formations and their original compressive strengths, different unloading hole layouts applied, and the compressive strengths of the rock formations after unloading, together forming the rock formation unloading hole data set;

[0017] The three-dimensional representation of the rock layer is obtained by filtering out the three-dimensional representation of the coal wall that is higher than the coal wall and coal-rock boundary.

[0018] Preferably, in the rock formation unloading hole data set, the rock formation three-dimensional representation, the original compressive strength and the target compressive strength are source data in the rock formation unloading hole data set, and the unloading hole layout is the labeled data in the rock formation unloading hole data set;

[0019] The contents of the unloading hole layout include: unloading hole diameter, unloading hole rows and columns, and unloading hole spacing; the selection range of the unloading hole diameter is the drill bit diameter, the unloading hole rows and columns are the number of unloading hole rows and columns, and the unloading hole spacing is the vertical or horizontal spacing between two unloading holes, and the vertical or horizontal spacing is equal.

[0020] Preferably, the unloading hole layout optimization model comprises an input layer, an intermediate layer and an output layer, the input is a three-dimensional representation of the rock formation, the original compressive strength and the target compressive strength, and the output is the unloading hole layout;

[0021] The input layer is used to convert the input data into a tensor format and scale the input data to a range with a mean of 0 and a standard deviation of 1 through normalization.

[0022] The intermediate layer is composed of several linear layers and regularization layers, and the intermediate layer is used to perform linear combination of features on the data output by the input layer to extract features;

[0023] The output layer is used to generate the unloading hole layout.

[0024] Preferably, training the unloading hole layout optimization model using the rock formation unloading hole data set includes:

[0025] The source data in the rock formation unloading hole data set is input into the unloading hole layout optimization model, and the unloading hole layout result is output through forward propagation; the loss calculation is performed on the unloading hole layout result and the labeled data in the rock formation unloading hole data set to obtain the loss value;

[0026] Back propagation is performed through the loss value, and iterative training is performed repeatedly until the accuracy of the unloading hole layout optimization model reaches a set threshold, and the unloading hole layout optimization model training is completed.

[0027] Preferably, obtaining the optimal unloading hole layout includes:

[0028] Obtaining the coal-rock boundary line and three-dimensional representation of the coal wall in on-site mining, processing the coal-rock boundary line and the three-dimensional representation to obtain the three-dimensional representation of the rock layer to be detected, and measuring the compressive strength of the coal seam and the rock layer by a rebound method, wherein the compressive strength of the coal seam is the target compressive strength to be detected, and the compressive strength of the rock layer is the original compressive strength to be detected;

[0029] The three-dimensional representation of the rock formation to be detected, the original compressive strength to be detected, and the target compressive strength to be detected are input into the unloading hole layout optimization model, and the optimal unloading hole layout is output.

[0030] Preferably, after obtaining the optimal unloading hole layout, the method further includes filtering out useless unloading holes outside the rock formation to obtain a final optimal unloading hole layout;

[0031] Among them, the useless unloading holes outside the rock formation are filtered out, including:

[0032] Based on the coordinates (x, y) of the unloading hole and the diameter d of the unloading hole, a point is taken at every preset angle along the circumference of the unloading hole as the coordinate of the circular edge of the unloading hole, where the coordinates of each point (x dot ,y dot ) = (d / 2·cosθ, d / 2·cosθ), θ is the current interval angle;

[0033] When all the y coordinates of the unloading holes are greater than the y coordinates of the coal-rock boundary line at the same x position of the coal-rock boundary line, the unloading hole is outside the rock formation, i.e., the useless unloading hole, and is filtered out;

[0034] A filtering operation is performed on all unloading holes to obtain the final optimal unloading hole layout.

[0035] Preferably, according to the final optimal unloading hole layout, the rock formation is drilled to achieve pre-splitting of the rock formation.

[0036] Compared with the prior art, the present invention has the following advantages and technical effects:

[0037] The present invention is based on the stress concentration theory and optimizes the layout of the unloading holes to achieve a higher reduction in the compressive strength of the rock formation at a lower drilling cost of the unloading holes. The unloading holes are further arranged on the rock formation to reduce the overall compressive strength of the rock formation to be similar to that of the coal seam, so as to achieve efficient mining of the coal-rock boundary layer. The invention has the characteristics of simple steps and high energy efficiency ratio. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 It is a schematic diagram of the overall process of the rock unloading hole layout and optimization method based on coal-rock cutting convergence according to an embodiment of the present invention;

[0040] Figure 2 This is a structural diagram of a rock unloading hole data set of a rock unloading hole layout and optimization method based on coal-rock cutting convergence according to an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of a process of constructing and training a layout optimization model of unloading holes in a rock unloading hole layout and optimization method based on coal-rock cutting convergence according to an embodiment of the present invention;

[0042] Figure 4 It is a schematic diagram of the flow of obtaining the optimal unloading hole layout based on the rock unloading hole layout and optimization method of coal-rock cutting convergence in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0045] This embodiment proposes a rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence, such as Figure 1 ,include:

[0046] Construct an unloading hole layout optimization model, input the unloading hole data of the rock formation to be processed into the unloading hole layout optimization model, and obtain the optimal unloading hole layout;

[0047] Pre-crack the rock formation by drilling holes through the optimal unloading hole layout, so that the compressive strength of the rock formation is similar to that of the coal seam;

[0048] Among them, the unloading hole layout optimization model is constructed through a neural network model and is obtained through training with the rock formation unloading hole dataset.

[0049] This embodiment optimizes the layout of the unloading holes to achieve a higher reduction in the compressive strength of the rock formation at a lower unloading hole drilling cost, and further arranges the unloading holes on the rock formation to reduce the overall compressive strength of the rock formation to be similar to that of the coal seam, thereby reducing the difficulty of the coal mining machine in cutting the coal-rock boundary layer, and ultimately achieving efficient mining.

[0050] Furthermore, a rock formation unloading hole data set is obtained, including:

[0051] The coal-rock boundary and three-dimensional representation of the coal wall, the compressive strength of the coal seam and the rock stratum are obtained respectively, and the rock stratum unloading hole data set is constructed based on finite element simulation;

[0052] Specifically, the rebound method is used to obtain the compressive strength of coal seams and rock formations, including:

[0053] Calibrate the rebound tester, perform rebound tests on several test points of the tested coal seam or rock formation, record the rebound value of each test point, convert the compressive strength corresponding to each rebound value by table lookup method, calculate the average compressive strength of all test points, and obtain the compressive strength of the coal seam or the compressive strength of the rock formation respectively;

[0054] In this embodiment, the test points are located on the flat and clean surface of the coal seam or rock formation to be measured. At least 5 test points are selected during the measurement process, and the test points should be distributed as evenly as possible on the coal seam or rock formation;

[0055] Converting the compressive strength corresponding to each rebound value by table lookup method includes: inputting the measured rebound value into a rebound value-compressive strength table, and the table outputs the corresponding compressive strength.

[0056] Furthermore, a rock formation unloading hole dataset is constructed, including:

[0057] Finite element simulation can be used to quickly obtain the compressive strength of the rock formation after being loaded with different unloading hole layouts under the original compressive strength, and then construct a rock formation unloading hole data set.

[0058] Specifically, based on the coal-rock boundary and the three-dimensional representation of the coal wall, the three-dimensional representation of the rock formation is extracted, the three-dimensional representation of the rock formation is imported into the ANSYS software, the compressive strength of the rock formation in the ANSYS software is set to the measured compressive strength of the rock formation, the measured compressive strength of the rock formation is used as the original compressive strength of the rock formation, the rock formation is meshed, unloading hole loads of different layouts are applied to the rock formation, a static solver is run for analysis, the compressive strength of the rock formation after the unloading hole load is applied is obtained, and the compressive strength of the rock formation after the unloading hole load is applied is used as the target compressive strength;

[0059] The three-dimensional characterization of different rock formations and their original compressive strength, the different unloading hole layouts applied, and the rock formation compressive strength after unloading are recorded to form the rock formation unloading hole data set, such as Figure 2 ;

[0060] The three-dimensional representation of the rock layer is obtained by filtering out the three-dimensional representation of the coal wall that is higher than the coal wall and coal-rock boundary.

[0061] Further, in the rock formation unloading hole data set of this embodiment, the three-dimensional characterization of the rock formation, the original compressive strength and the target compressive strength are used as source data in the rock formation unloading hole data set, and the unloading hole layout is used as the annotation data in the rock formation unloading hole data set;

[0062] The contents of the unloading hole layout include: unloading hole diameter, unloading hole rows and columns, and unloading hole spacing; the selection range of unloading hole diameter is the commonly used drill bit diameters, including 89mm, 114mm, 152mm, and 200mm; the unloading hole rows and columns are the number of unloading hole rows and columns; the unloading hole spacing is the vertical or horizontal spacing between two unloading holes, and both are equal.

[0063] Furthermore, the unloading hole layout optimization model includes an input layer, an intermediate layer and an output layer, the input is the three-dimensional representation of the rock formation, the original compressive strength and the target compressive strength, and the output is the unloading hole layout;

[0064] The input layer converts the input data of the unloading hole layout optimization model into tensor format, and scales the input data to a range with a mean of 0 and a standard deviation of 1 through normalization to improve the training efficiency and stability of the model.

[0065] The middle layer is mainly composed of multiple linear layers, which perform linear combination of the features of the data output by the input layer to extract features. It also includes a regularization layer to prevent overfitting of the unloading hole layout optimization model during training.

[0066] The output layer generates the predicted output of the unloading hole layout optimization model, i.e., the unloading hole layout.

[0067] Furthermore, the unloading hole layout optimization model is trained using the rock unloading hole dataset, such as Figure 3 ,include:

[0068] The unloading hole layout optimization model is continuously trained and iterated based on the rock formation unloading hole dataset. First, the source data in the rock formation unloading hole dataset is input into the unloading hole layout optimization model, and the unloading hole layout result is output through forward propagation; the unloading hole layout result and the labeled data in the rock formation unloading hole dataset are subjected to loss calculation to obtain the loss value; the loss value is used for back propagation, and iterative training is repeatedly performed until the accuracy of the unloading hole layout optimization model reaches the set threshold, and the unloading hole layout optimization model training is completed.

[0069] Furthermore, the optimal unloading hole layout is obtained, such as Figure 4 ,include:

[0070] Obtain the coal-rock boundary line and three-dimensional representation of the coal wall in on-site mining, process the coal-rock boundary line and the three-dimensional representation to obtain the three-dimensional representation of the rock layer to be tested, and measure the compressive strength of the coal seam and the rock layer by the rebound method. The compressive strength of the coal seam is the target compressive strength to be tested, and the compressive strength of the rock layer is the original compressive strength to be tested;

[0071] The three-dimensional representation of the rock formation to be tested, the original compressive strength to be tested, and the target compressive strength to be tested are input into the unloading hole layout optimization model, and the optimal unloading hole layout is output.

[0072] Furthermore, after obtaining the optimal unloading hole layout, the useless unloading holes outside the rock formation are filtered out to obtain the final optimal unloading hole layout;

[0073] The process of filtering out useless unloading holes includes, for a certain unloading hole, based on the unloading hole coordinates (x, y) and the unloading hole diameter d, taking a point every 10° along the circumference of the unloading hole as the coordinate of the circular edge of the unloading hole, wherein the coordinate of each point (xdot, ydot) = (d / 2·cosθ, d / 2·cosθ), θ is the current interval angle.

[0074] When all the y coordinates of the unloading holes are greater than the y coordinates of the coal-rock boundary line at the same x position of the coal-rock boundary line, the unloading hole is outside the rock formation and is a useless unloading hole, which is filtered out. The above operation is performed on all unloading holes to obtain the final optimal unloading hole layout.

[0075] According to the final optimal layout of unloading holes, the rock stratum is drilled to achieve pre-cracking of the rock stratum. Based on the layout optimization of the unloading holes, the compressive strength of the rock stratum can be reduced to make it similar to the coal seam, thereby reducing the cutting difficulty of the coal mining machine and ultimately improving the overall coal mining efficiency.

[0076] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence, characterized in that: include: Constructing an unloading hole layout optimization model, inputting the unloading hole data of the rock formation to be processed into the unloading hole layout optimization model, and obtaining an optimal unloading hole layout; The rock formation is pre-split by drilling holes through the optimal unloading hole layout, so that the compressive strength of the rock formation is similar to that of the coal seam; The unloading hole layout optimization model is constructed by a neural network model and is obtained by training with a rock formation unloading hole data set.

2. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 1 is characterized in that: Obtaining the rock formation unloading hole data set includes: The coal-rock boundary and three-dimensional representation of the coal wall, the compressive strength of the coal seam and the rock layer are obtained respectively, and the rock layer unloading hole data set is constructed based on finite element simulation; The compressive strength of the coal seam and the rock layer is obtained by using a rebound method, including: The rebound hammer is calibrated, and rebound tests are performed on several test points of the tested coal seam or rock formation. The rebound value of each test point is recorded, and the compressive strength corresponding to each rebound value is converted by table lookup method. The compressive strength of all test points is averaged to obtain the compressive strength of the coal seam or the compressive strength of the rock formation.

3. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 2 is characterized in that: Constructing the rock formation unloading hole data set includes: Extracting a three-dimensional representation of the rock formation based on the coal-rock boundary and the three-dimensional representation of the coal wall, importing the three-dimensional representation of the rock formation into ANSYS software, setting the compressive strength of the rock formation in ANSYS software to the measured compressive strength of the rock formation, using the measured compressive strength of the rock formation as the original compressive strength of the rock formation, meshing the rock formation, applying unloading hole loads of different layouts to the rock formation, running a static solver for analysis, obtaining the compressive strength of the rock formation after applying the unloading hole load, and using the compressive strength of the rock formation after applying the unloading hole load as the target compressive strength; Recording three-dimensional representations of different rock formations and their original compressive strengths, different unloading hole layouts applied, and the compressive strengths of the rock formations after unloading, together forming the rock formation unloading hole data set; The three-dimensional representation of the rock layer is obtained by filtering out the three-dimensional representation of the coal wall that is higher than the coal wall and coal-rock boundary.

4. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 3 is characterized in that: In the rock formation unloading hole data set, the rock formation three-dimensional representation, the original compressive strength and the target compressive strength are source data in the rock formation unloading hole data set, and the unloading hole layout is the labeled data in the rock formation unloading hole data set; The contents of the unloading hole layout include: unloading hole diameter, unloading hole rows and columns, and unloading hole spacing; the selection range of the unloading hole diameter is the drill bit diameter, the unloading hole rows and columns are the number of unloading hole rows and columns, and the unloading hole spacing is the vertical or horizontal spacing between two unloading holes, and the vertical or horizontal spacing is equal.

5. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 1 is characterized in that: The unloading hole layout optimization model comprises an input layer, an intermediate layer and an output layer, wherein the input is a three-dimensional representation of the rock formation, the original compressive strength and the target compressive strength, and the output is the unloading hole layout; The input layer is used to convert the input data into a tensor format and scale the input data to a range with a mean of 0 and a standard deviation of 1 through normalization; The intermediate layer is composed of several linear layers and regularization layers, and the intermediate layer is used to perform linear combination of features on the data output by the input layer to extract features; The output layer is used to generate the unloading hole layout.

6. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 5 is characterized in that: The unloading hole layout optimization model is trained using the rock formation unloading hole data set, including: The source data in the rock formation unloading hole data set is input into the unloading hole layout optimization model, and the unloading hole layout result is output through forward propagation; the loss calculation is performed on the unloading hole layout result and the labeled data in the rock formation unloading hole data set to obtain the loss value; Back propagation is performed through the loss value, and iterative training is performed repeatedly until the accuracy of the unloading hole layout optimization model reaches a set threshold, and the unloading hole layout optimization model training is completed.

7. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 1 is characterized in that: Obtaining the optimal unloading hole layout includes: Obtaining the coal-rock boundary line and three-dimensional representation of the coal wall in on-site mining, processing the coal-rock boundary line and the three-dimensional representation to obtain the three-dimensional representation of the rock layer to be detected, and measuring the compressive strength of the coal seam and the rock layer by a rebound method, wherein the compressive strength of the coal seam is the target compressive strength to be detected, and the compressive strength of the rock layer is the original compressive strength to be detected; The three-dimensional representation of the rock formation to be detected, the original compressive strength to be detected, and the target compressive strength to be detected are input into the unloading hole layout optimization model, and the optimal unloading hole layout is output.

8. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 7 is characterized in that: After obtaining the optimal unloading hole layout, the method further includes filtering out useless unloading holes outside the rock formation to obtain a final optimal unloading hole layout; Among them, the useless unloading holes outside the rock formation are filtered out, including: Based on the coordinates (x, y) of the unloading hole and the diameter d of the unloading hole, a point is taken at every preset angle along the circumference of the unloading hole as the coordinate of the circular edge of the unloading hole, where the coordinates of each point (x dot ,y dot ) = (d / 2·cosθ, d / 2·cosθ), θ is the current interval angle; When all the y coordinates of the unloading holes are greater than the y coordinates of the coal-rock boundary line at the same x position of the coal-rock boundary line, the unloading hole is outside the rock formation, i.e., the useless unloading hole, and is filtered out; A filtering operation is performed on all unloading holes to obtain the final optimal unloading hole layout.

9. The rock unloading hole layout and parameter optimization method based on coal-rock cutting convergence according to claim 8 is characterized in that: According to the final optimal unloading hole layout, the rock formation is drilled to achieve pre-splitting of the rock formation.

Images