Planned cutting curve issuing control method based on predictive coal cutting technology

Abstract

The invention discloses a planned cutting curve issuing control method based on a predictive coal cutting technology, and belongs to the technical field of coal mine collection. Comprising the following steps: acquiring coal mining machine operation cutting data; a mathematical model is established based on the predicted coal cutting data, and a next cutting prediction curve is obtained; monitoring the running state and environmental parameters of the coal mining machine in real time, and generating an optimal cutting planning curve path; an operator judges whether the cutting curve path is optimal or not, if not, the above steps are executed circularly, and if yes, the following steps are executed; and issuing the generated optimal cutting planning curve path to the coal mining machine. The invention provides a planned cutting curve issuing control method based on a predictive coal cutting technology, which can realize generation of a planned cutting curve of a next cut based on historical cutting data, can edit and issue in advance according to geological data, reduces manual intervention in a production process, improves mining efficiency, realizes visualization of a predictive coal cutting curve, and is suitable for popularization and application. And the production process can be controlled, and the mining stability and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mining, and more specifically, to a method for controlling the distribution of a planned cutting curve based on a predicted coal cutting technology. Background Art

[0002] The formation of coal-bearing rock systems must have a certain material source and a certain deposition place. According to their specifications, coal seams can be divided into thin coal seams (thickness ≤ 1.3m), medium-thick coal seams (thickness ≥ 1.3m, ≤ 3.5m), thick coal seams (>3.5m), and extra-thick coal seams (>8.0m).

[0003] In coal mining operations, the smooth transition between two lanes of the working face of medium-thick coal seams has always been a technical problem. The traditional coal cutting process cannot meet this requirement, resulting in low coal mining efficiency and potential safety hazards. Therefore, this patent provides a planning cutting curve control method based on predictive coal cutting technology to solve the above problems. Summary of the invention

[0004] In order to overcome the technical problems raised in the above background, the present invention provides a planning cutting curve control method based on predictive coal cutting technology to solve the smooth transition of two tunnels in the working face of medium and thick coal seams, ensure efficient coal mining and improve safety.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] A method for controlling the distribution of a planned cutting curve based on a predictive coal cutting technology comprises the following steps:

[0007] S1: Obtain the coal mining machine operation and cutting data, and determine the working parameters of the coal mining machine through the automatic control system according to the topological structure characteristics of the coal mining machine electronic control system, including the acquisition of information on the rocker arm length, drum diameter, angle between the rocker arm and the machine body, and the machine body height;

[0008] S2: A mathematical model is established based on the predicted coal cutting data, and a working face geological model is established based on the historical cutting data, including an input layer, a hidden layer, and an output layer. The mathematical model is brought into an AI algorithm module that can calculate H series matrices, P series matrices, Mu series matrices, G series matrices, L / Q series matrices, Z series matrices, and M series matrices, and the next cut prediction curve is obtained by inputting actual cutting data and predicted data;

[0009] S3: monitor the operating status and environmental parameters of the coal mining machine in real time and generate the optimal cutting planning curve path;

[0010] S4: The operator determines whether step S3 is optimal. If not, steps S1-S3 are executed cyclically. If yes, step S5 is executed.

[0011] S5: The generated optimal cutting planning curve path is sent to the coal mining machine. The coal mining machine follows the sent cutting curve and monitors the operating status and environmental parameters of the coal mining machine in real time during the coal mining process through the automatic control system, adjusts the working parameters of the coal mining machine, and automatically controls the operation of the coal mining machine.

[0012] S6: The front and rear rollers of the coal mining machine establish a roller target curve error band according to the cutting curve issued by the coal mining machine in step S5, and adjust the roller control according to the error.

[0013] Preferably, the AI ​​algorithm module in step S2 includes a learning machine, an inference machine and an observer.

[0014] Preferably, the specific cycle steps of step S4 are:

[0015] S11: using the observer to obtain the first step predicted mining height, the first step predicted mining height and the actual mining height are input into the AI ​​algorithm module in the order of learning machine-inference machine-observer to obtain the second step predicted mining height, the second step predicted mining height is input into the mathematical model, and the next cutting prediction curve is obtained;

[0016] S12: The operator determines whether the predicted curve is optimal. If so, the optimal cutting planning curve path is directly sent to the coal mining machine; if not, the historical actual cutting data and the predicted curve are calculated again according to the learning machine-inference machine-observer calculation to form a loop until the optimal curve is generated.

[0017] Preferably, the working parameters of the coal mining machine in step S1 are determined by factors such as the thickness of the coal seam, the distribution of rocks and the performance of the coal mining machine.

[0018] Preferably, the operating status and environmental parameters of the coal mining machine in step S3 include mining height, cutting depth, drum speed, gas concentration and rock hardness.

[0019] The present invention also provides a control system for planning cutting curves based on predictive coal cutting technology, including a coal mining machine, a communication module, and a remote execution module; the remote execution module includes at least one processor and a memory for storing AI algorithm modules and mathematical models, the communication module includes wired communication or wireless communication, and the remote execution module is communicated with the control unit of the coal mining machine through the communication module.

[0020] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0021] 1) The present invention provides a method for controlling the distribution of planned cutting curves based on predictive coal cutting technology, which can realize the generation of the planned cutting curve for the next cut based on historical cutting data, and can be edited and distributed in advance according to the geological data of the working face, thereby reducing manual intervention in the production process and improving mining efficiency; based on the visualization operation of the prediction curve of the entire working face, it not only controls the operation of the production process, but also improves the stability and safety of mining. This method reduces the demand for labor intensity through model calculation and remote control, and further improves the safety and efficiency of coal mining operations. The process follows the operation mode of remote adjustment and local monitoring, which further ensures the safety and stability of coal mining operations;

[0022] 2) In the entire automated coal cutting process, no additional exploration is required. The operation of the coal mining machine is precisely controlled by using the historical cutting data through the mathematical model, achieving the goal of adjusting and issuing the cutting planning curve. This automation technology not only improves coal mining efficiency, but also reduces safety risks, providing a guarantee for the smooth progress of coal mining operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0025] Figure 2 It is a schematic diagram showing the comparison effect of the predicted cutting trajectory and the actual cutting trajectory curve of the top drum of the coal mining machine of the present invention;

[0026] Figure 3 It is a schematic diagram of the comparative effect after the present invention modifies the cutting curve based on the predicted coal cutting and then sends it to the coal mining machine for execution;

[0027] Figure 4 A schematic diagram is established for the data model of the present invention;

[0028] Figure 5 It is a schematic diagram of the AI ​​algorithm module and mathematical model calculation flow of the present invention. DETAILED DESCRIPTION

[0029] In order to better understand the purpose, structure and function of the present invention, the technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific preferred embodiments.

[0030] Embodiment 1:

[0031] like Figure 1-5 As shown, the present invention provides a technical solution: a method for controlling the distribution of a planned cutting curve based on the predicted coal cutting technology, comprising the following steps:

[0032] The coal mining machine operation and cutting data are obtained, and according to the topological structure characteristics of the coal mining machine electronic control system, the working parameters of the coal mining machine are determined through the automatic control system, including the information acquisition of the rocker arm length, drum diameter, angle between the rocker arm and the machine body, and the machine body height.

[0033] Specifically, the operating parameters of the coal mining machine are determined by factors such as the thickness of the coal seam, the distribution of rocks, and the performance of the coal mining machine.

[0034] A mathematical model is established based on the predicted coal cutting data, and a working face geological model is established based on the historical cutting data, which includes an input layer, a hidden layer, and an output layer. The mathematical model is brought into an AI algorithm module that can calculate H series matrices, P series matrices, Mu series matrices, G series matrices, L / Q series matrices, Z series matrices, and M series matrices. The next cut prediction curve is obtained by inputting actual cutting data and predicted data.

[0035] Specifically, Figure 1 As shown, the AI ​​algorithm module includes a learning machine, an inference machine and an observer.

[0036] The process of establishing the cutting data model is as follows:

[0037] like Figure 4 As shown in the figure, during the operation of the coal mining machine, the height of the top and bottom plates of the coal mining machine is tested by the coal mining machine attitude angle.

[0038]

[0039] The system establishes two sets of one-dimensional arrays based on the actual mining height and bottom, combined with the coal machine position coordinates, marked as the working face mining height and bottom height when going up and down respectively:

[0040] Up_RoofHigh[x] / Up_FloorHigh[x];

[0041] Down_RoofHigh[x] / Down_FloorHigh[x];

[0042] Among them, X is the position of the coal mining machine on the working face. Taking the coal mining machine as an example, the height of the left and right drums is:

[0043] Up_Roofhigh[X]=hr n ;

[0044] Up_Roofhigh[X]=hf n ;

[0045] In completing a cycle, the one-dimensional array value and the corresponding data are the mining contour of the working face, that is, the top and bottom plate curves of the working face.

[0046] In the two sets of top and bottom plate curve arrays (actual mining height), the prediction curve is generated by the data obtained by machine reasoning. By comparing the two sets of curves, the change rules are analyzed, and the dynamically adjusted predicted mining height is generated and sent to the coal mining machine. The reasoning process is as follows Figure 5 , the execution process is as follows:

[0047] H series matrix: FOR i: = 0TO n-1DO

[0048] H[i]:=INT_TO_REAL(X[i+1]-X[i]); (*calculate the H series number matrix*)

[0049] END_FOR

[0050] P series matrix: FOR i: = 1TO n-1DO

[0051] P[i]:=H[i] / (H[i]+H[i-1]); (*Calculate the P series number matrix*)

[0052] END_FOR

[0053] Mu series number matrix: P[n-1]:=1;

[0054] Mu[0]:=1;

[0055] FOR i:=1TO n-1DO

[0056] Mu[i]:=1-P[i]; (*Calculate the Mu series matrix*)

[0057] END_FOR

[0058] G series number matrix: G[0]: = 3*(INT_TO_REAL(Y[1]-Y[0])) / H[0];

[0059] FOR i:=1TO n-1DO

[0060] G[i]:=3*(P[i]*(INT_TO_REAL(Y[i]-Y[i-1])) / H[i-1]+Mu[i]*(INT_TO_REAL(Y[i+1]-Y[i])) / H[i]); (*Calculate G series number matrix*)

[0061] END_FOR

[0062] L / Q series number matrix: G[n-1]:=3*(INT_TO_REAL(Y[n-1]-Y[n-2])) / H[n-2];

[0063] Q[0]:=2;

[0064] FOR i:=1TO n DO

[0065] L[i]:=P[i] / Q[i-1];

[0066] Q[i]:=2-Mu[i-1]*L[i]; (*Calculate L / Q series number matrix*)

[0067] END_FOR

[0068] Z series number matrix: Z[0]:=G[0];

[0069] FOR i:=1TO n DO

[0070] Z[i]:=G[i]-L[i]*Z[i-1]; (*calculate the Z series matrix*)

[0071] END_FOR

[0072] M series number matrix: M[n-1]:=Z[n-1] / Q[n-1];

[0073] FOR i:=n-2TO 0BY-1DO

[0074] M[i]:=(Z[i]-Mu[i]*M[i+1]) / Q[i];(*Calculate the M series number matrix*)

[0075] END_FOR;

[0076] FOR i:=1TO n DO

[0077] IF inputX>=X[i-1]AND inputX<=X[i]THEN

[0078] QJ:=i-1;

[0079] EXIT;

[0080] END_IF

[0081] END_FOR

[0082] Take the H series matrix as an example: i loops from 0 to n-1, and by traversing the index of array X from 0 to n-1, calculates the value of H[i] at each position i, which is equal to the difference between the adjacent elements X[i+1] and X[i] in array X, and converts the result to real number type and assigns it to H[i]. This process is actually building a difference array H, in which each element H[i] represents the difference between adjacent elements in the original array X, specifically:

[0083] X = [x0, x1, x2, ..., x n ];

[0084] H=[h0,h1,h2,...,h n ];

[0085] Where H[i]=INT_TO_REAL(X[i+1]-X[i]).

[0086] Monitor the operating status and environmental parameters of the coal mining machine in real time and generate the optimal cutting planning curve path.

[0087] Specifically, the operating status and environmental parameters of the coal mining machine include mining height, cutting depth, drum speed, gas concentration and rock hardness.

[0088] The operator determines whether the prediction curve is optimal. If not, the operator executes the first three steps in a loop. If yes, the operator executes the next step.

[0089] Furthermore, Figure 1 As shown, the specific cycle steps are:

[0090] The observer is used to obtain the first step predicted mining height. The first step predicted mining height and the actual mining height are input into the AI ​​algorithm module in the order of learning machine-inference machine-observer to obtain the second step predicted mining height. The second step predicted mining height is input into the mathematical model to obtain the next knife prediction curve.

[0091] The operator determines whether the predicted curve is optimal. If so, the optimal cutting planning curve path is directly sent to the coal mining machine; if not, the historical actual cutting data and the predicted curve are calculated again according to the learning machine-inference machine-observer calculation to form a loop until the optimal curve is generated.

[0092] The generated optimal cutting planning curve path is sent to the coal mining machine. The coal mining machine follows the sent cutting curve and monitors the operating status and environmental parameters of the coal mining machine in real time through the automated control system during the coal mining process, adjusts the working parameters of the coal mining machine, and automatically controls the operation of the coal mining machine.

[0093] The front and rear rollers of the coal mining machine establish the roller target curve error band according to the cutting curve issued by the coal mining machine, and adjust the roller control according to the error.

[0094] Depend on Figure 2 As shown, Figure 2 Two curves are displayed: the predicted cutting trajectory of the top drum of the coal mining machine and the actual cutting trajectory. The blue prediction data is generated based on the smooth transition of the coal cutting curve, and the actual cutting curve is the actual cutting curve generated by the coal mining machine. Comparing the two data, it can be concluded that the prediction curve is accurate in most areas, but there are deviations in local positions.

[0095] Depend on Figure 3 As shown in the figure, in the sixth step, the front and rear rollers of the coal mining machine establish the roller target curve error band according to the cutting curve issued by the coal mining machine, and adjust the roller control according to the error. The operator can Figure 2 Based on the deviation, the cutting curve is modified based on the predicted coal cutting and then sent to the coal mining machine for execution. The above principle is used to modify the up and down top and bottom plate curves of the coal mining machine and send them to the coal mining machine for execution. The advantage of this step is that it does not need to be executed during machine operation on the basis of continuing to optimize the actual cutting curve. Adjustments can be made after steps one to five are completed, which can further reduce manual intervention in the production process and improve mining efficiency.

[0096] Embodiment 2:

[0097] The present invention also provides a control system for planning cutting curves based on predictive coal cutting technology, including a coal mining machine, a communication module, and a remote execution module; the remote execution module includes at least one processor and a memory for storing AI algorithm modules and mathematical models, the communication module includes wired communication or wireless communication, and the remote execution module is communicated with the control unit of the coal mining machine through the communication module.

[0098] The present invention can realize the generation of the planned cutting curve for the next cut based on historical cutting data, and can be edited and issued in advance according to the geological data of the working face, thereby reducing manual intervention in the production process and improving mining efficiency; based on the visualization operation of the prediction curve of the entire working face, it not only controls the operation of the production process, but also improves the stability and safety of mining. This method reduces the demand for labor intensity through model calculation and remote control, and further improves the safety and efficiency of coal mining operations. The process follows the operation mode of remote adjustment and local monitoring, which further ensures the safety and stability of coal mining operations;

[0099] In the entire automated coal cutting process, no additional exploration is required. The operation of the coal mining machine is precisely controlled by using the historical cutting data through the mathematical model, achieving the goal of adjusting and issuing the cutting planning curve. This automation technology not only improves coal mining efficiency, but also reduces safety risks, providing a guarantee for the smooth progress of coal mining operations. At the same time, this process complies with relevant national and industry standards and specifications, ensuring the safety and quality of coal mining operations.

[0100] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for controlling the distribution of planned cutting curves based on predictive coal cutting technology, characterized in that: The steps include: S1: Obtain the coal mining machine operation and cutting data, and determine the working parameters of the coal mining machine through the automatic control system according to the topological structure characteristics of the coal mining machine electronic control system, including the acquisition of information on the rocker arm length, drum diameter, angle between the rocker arm and the machine body, and the machine body height; S2: A mathematical model is established based on the predicted coal cutting data, and a working face geological model is established based on the historical cutting data, including an input layer, a hidden layer, and an output layer. The mathematical model is brought into an AI algorithm module that can calculate H series matrices, P series matrices, Mu series matrices, G series matrices, L / Q series matrices, Z series matrices, and M series matrices, and the next cut prediction curve is obtained by inputting actual cutting data and predicted data; S3: monitor the operating status and environmental parameters of the coal mining machine in real time and generate the optimal cutting planning curve path; S4: The operator determines whether step S3 is optimal. If not, steps S1-S3 are executed cyclically. If yes, step S5 is executed. S5: The generated optimal cutting planning curve path is sent to the coal mining machine. The coal mining machine follows the sent cutting curve and monitors the operating status and environmental parameters of the coal mining machine in real time during the coal mining process through the automatic control system, adjusts the working parameters of the coal mining machine, and automatically controls the operation of the coal mining machine. S6: The front and rear rollers of the coal mining machine establish a roller target curve error band according to the cutting curve issued by the coal mining machine in step S5, and adjust the roller control according to the error.

2. The method for controlling the planned cutting curve based on the predicted coal cutting technology according to claim 1 is characterized in that: The AI ​​algorithm module in step S2 includes a learning machine, an inference machine and an observer.

3. The method for controlling the distribution of planned cutting curves based on the predicted coal cutting technology according to claim 2 is characterized in that: The specific cycle steps of step S4 are: S11: using the observer to obtain the first step predicted mining height, the first step predicted mining height and the actual mining height are input into the AI ​​algorithm module in the order of learning machine-inference machine-observer to obtain the second step predicted mining height, the second step predicted mining height is input into the mathematical model, and the next cutting prediction curve is obtained; S12: The operator determines whether the predicted curve is optimal. If so, the optimal cutting planning curve path is directly sent to the coal mining machine; if not, the historical actual cutting data and the predicted curve are calculated again according to the learning machine-inference machine-observer calculation to form a loop until the optimal curve is generated.

4. The method for controlling the planned cutting curve based on the predicted coal cutting technology according to claim 1 is characterized in that: The working parameters of the coal mining machine in step S1 are determined by factors such as the thickness of the coal seam, the distribution of rocks and the performance of the coal mining machine.

5. The method for controlling the distribution of planned cutting curves based on the predicted coal cutting technology according to claim 1 is characterized in that: The operating status and environmental parameters of the coal mining machine in step S3 include mining height, cutting depth, drum speed, gas concentration and rock hardness.

6. A control system for sending a planned cutting curve based on a predictive coal cutting technology, which implements the control method for sending a planned cutting curve based on a predictive coal cutting technology according to any one of claims 1 to 5, characterized in that: It includes a coal mining machine, a communication module, and a remote execution module; the remote execution module includes at least one processor and a memory for storing an AI algorithm module and a mathematical model, the communication module includes wired communication or wireless communication, and the remote execution module is communicatively connected to the control unit of the coal mining machine through the communication module.

Images