A method, electronic equipment and medium for periodic pressure analysis and early warning of fully mechanized mining working face

Abstract

The present invention provides a method, electronic equipment and medium for analyzing and warning periodic pressure on a fully mechanized mining face, and belongs to the technical field of mine pressure analysis. The method solves the problem in the prior art that the mine pressure prediction and analysis is not combined with the coal cutting cycle, resulting in unclear analysis results. The method comprises the following steps: acquiring coal mining machine position data; identifying a whole coal cutting knife; dividing the working cycle of a support; extracting key features of the support; identifying periodic pressure: determining a pressure threshold, establishing a mine pressure feature matrix based on the key feature extraction results of the support, screening out positions in the mine pressure feature matrix where the mine pressure feature values ​​exceed the pressure threshold as pressure positions, clustering the above discrete pressure positions to obtain pressure areas; calculating historical pressure parameters; predicting and warning pressure. The present invention is applied to the analysis of pressure on fully mechanized mining faces in coal mines.

Description

Technical Field

[0001] The invention provides a method for early warning of periodic pressure analysis on a fully mechanized mining face, electronic equipment and a medium, belonging to the technical field of mine pressure analysis. Background Art

[0002] Mine pressure is the primary cause of roof collapse and frame crushing accidents in fully mechanized mining working faces. Therefore, using the working resistance monitoring data of hydraulic supports in fully mechanized mining working faces to realize the excavation of mine pressure laws and prediction of mine pressure, and to optimize the roof control scheme in the coal mining process in advance, is of great significance to ensure safe production in coal mines. In recent years, the level of intelligent construction of fully mechanized mining in coal mines has been significantly improved, which can realize low-latency, short-interval transmission and long-term storage of various sensor data of hydraulic supports in fully mechanized mining working faces, providing convenient conditions for carrying out relevant work on mine pressure analysis.

[0003] The Chinese invention patent (application number: 201811382926.6) discloses a method and system for predicting and forecasting mine pressure. The characteristic curve is obtained according to the mean and variance of the pressure, and the characteristic Euclidean distance between the characteristic curve and the historical periodic pressure characteristic curve is judged. When the characteristic distance is close, a periodic pressure alarm is issued. The Chinese invention patent (application number: 201911035238.7) discloses a real-time prediction system and method for mine pressure big data based on fully mechanized mining working face. The kernel density estimation algorithm is used to calculate the probability of pressure after continuous coal cutting, and the pressure probability curve is fitted. When the probability of pressure is greater than 50%, it is judged as pressure. The Chinese invention patent (application number: 202010700896.X) discloses a method, device and equipment for predicting mine pressure in time and space under limited data conditions. The periodic change characteristics of the hydraulic support load time series curve and the effective working resistance space series curve are used to predict the mine pressure, and the two prediction results are combined to achieve comprehensive prediction. The Chinese invention patent (application number: 202010141291.1) discloses a mine pressure prediction method, device and electronic equipment, and establishes a mine pressure prediction model for the target hydraulic support through a deep learning model.

[0004] However, the above patents do not combine the mine pressure analysis with the coal cutting cycle. A relatively important parameter involved in the cycle coal cutting is the cycle footage, which refers to the distance the working face advances after completing a cycle of coal mining. A cycle refers to a complete process of coal mining on the working face, starting with coal dropping and ending with moving (removing) the frame. The mine pressure prediction results of the above patents fail to provide the footage information of the predicted pressure, making the prediction results not intuitive. Summary of the invention

[0005] In order to solve the problem in the prior art that the mine pressure prediction and analysis is not combined with the coal cutting cycle, resulting in unclear analysis results, the present invention proposes a periodic pressure analysis and early warning method for a fully mechanized mining face, an electronic device and a medium.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for periodic pressure analysis and early warning of a fully mechanized mining face, comprising the following steps:

[0007] Step 1: Acquisition of coal mining machine location data;

[0008] Step 2: Identification of whole-knife coal cutting: Set the end mark point frame number and the end-end mark point frame number, define the distance between the two consecutive passes of the coal mining machine through the end mark point frame number during the coal cutting process as the end-end return section, and the distance between the two consecutive passes of the coal mining machine through the end-end mark point frame number is the end-end return section. Select the point closest to the midpoint of the fully mechanized mining face in the end-end return section and the point closest to the midpoint of the fully mechanized mining face in the end-end return section as the whole-knife demarcation point for coal cutting;

[0009] Step 3: Support work cycle division: According to the whole-knife dividing point defined in step 2, the time when the coal mining machine first arrives at a certain hydraulic support during each whole-knife coal cutting process is selected, and the first column lowering action end time between the coal mining machine's nth arrival at the hydraulic support and the n+1th arrival at the hydraulic support is used as the work cycle dividing point of the hydraulic support;

[0010] Step 4: Extraction of key features of the support: Based on the working cycle demarcation point of the hydraulic support identified in step 3, extract the key features of the end-of-cycle resistance and cycle working resistance, where the end-of-cycle resistance is the maximum value of the column pressure in a small period of time before the first effective column lowering-rack pulling action in the working cycle, and the cycle working resistance is the average value of the column pressure from the end time of the first effective rack pulling-column raising action to the start time of the first effective column lowering-rack pulling action in the working cycle;

[0011] Step 5: Periodic pressure identification: Determine the pressure threshold. According to the key feature extraction results of the bracket in step 4, establish a mine pressure feature matrix. The matrix column is labeled with the number of cutters and the matrix row is labeled with the bracket position. Filter out the positions where the mine pressure characteristic values ​​in the mine pressure feature matrix exceed the pressure threshold as the pressure position. Cluster the above discrete pressure positions to obtain the pressure area {A1, A2, ······, A n}, A n is the set of pressure position points of the nth pressure;

[0012] Step 6: Calculation of historical pressure parameters: Traverse and identify the starting footage of all pressure areas {Sa1, Sa2, ······, Sa n} and end footage {Ta1, Ta2, ······, Ta n}, calculate the pressure step distance St of the nth pressure n =Sa n -Sa n-1 , the pressure intensity of the nth pressure is Pan A n The average pressure in the stable stage before the nth pressure comes, the pressure strength P * a n For her n-1 to Sa n The pressure average value between the nth pressure and the pressure coefficient C n =Pa n / P * a n ;

[0013] Step 7: Pressure forecast and warning: Predict the pressure step distance of the n+1th pressure =aSt n +(1-a) , where a is the smoothing coefficient, St n is the observed value of the nth pressure step, is the predicted value of the nth pressure step, that is, the smoothed value of the previous period. The current footage S is obtained in real time during the mining process, and the footage Sa of the most recent start is obtained. n And the predicted next pressure step The predicted footage of the next pressure is obtained by superposition , when S approaches Provide early warning.

[0014] The end time of the column lowering action, the frame pulling action, and the column raising action is determined by the time of the column lowering action, the frame pulling action, and the column raising action instructions issued by the electro-hydraulic controller.

[0015] In step 5, the standard deviation method is used to determine the pressure threshold P t , the calculation formula is: t =mP mean +sP std , where m is the mean coefficient, s is the mean square error coefficient, P mean is the mean pressure, P std is the mean square error of pressure.

[0016] The discrete pressure locations in step 5 are clustered using the DBSCAN clustering method to obtain the pressure areas.

[0017] In step 7, the exponential smoothing method is used to predict the pressure step size of the n+1th pressure. ;

[0018] And when S and When the gap is less than 5 knife advance distance, a Level III warning is issued. When the gap is less than 3 blades, a Level II warning is issued. When the gap is less than 1 knife advance distance, a Level I warning will be issued.

[0019] The position data of the coal mining machine in step 1 is obtained through the travel encoder on the coal mining machine.

[0020] The column pressure in step 4 is obtained through the pressure sensor installed on each hydraulic support, and the pressure sensor transmits the collected pressure data to the electro-hydraulic controller. The electro-hydraulic controller filters the data according to the preset sampling frequency and the maximum change range, and transmits the filtered data to the chute main control computer through the electro-hydraulic control server.

[0021] The main control computer of the chute communicates with the electro-hydraulic control server through the CAN network, the electro-hydraulic control server communicates with the electro-hydraulic controller through the CAN network, the pressure sensor communicates with the electro-hydraulic controller through the serial port, the electro-hydraulic control server is arranged on the hydraulic support at the end of the comprehensive mining working face, and each hydraulic support is respectively provided with an electro-hydraulic controller.

[0022] An electronic device comprises a processor and a memory, wherein the memory stores a computer program for a method for analyzing and warning periodic pressure on a fully mechanized mining face, and the processor is used to execute the computer program.

[0023] A computer-readable storage medium stores one or more computer programs, which can be executed by one or more processors to implement a periodic pressure analysis and early warning method for a fully mechanized mining face.

[0024] The beneficial effects of the present invention compared to the prior art are as follows: the method provided by the present invention realizes the fusion analysis of the key characteristics of coal mining cycle-support lifting column cycle-mine pressure, can quickly present the trend of mine pressure changes and identify historical pressure areas from massive mine pressure data, extract historical pressure parameters, and predict the footage of the next pressure. Compared with the mine pressure analysis method that directly uses the original data of column pressure for analysis and prediction, the method of the present invention has the advantages of high efficiency and clear results. Compared with the mine pressure analysis method that uses the original data of single column pressure for analysis and prediction, the method of the present invention has the advantage of being less affected by random interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention will be further described below in conjunction with the accompanying drawings:

[0026] Figure 1 is a flow chart of the method of the present invention;

[0027] Figure 2 It is a schematic diagram of the identification of the whole coal cutting knife of the present invention. DETAILED DESCRIPTION

[0028] like Figure 1 and 2As shown, the present invention provides a method for periodic pressure analysis and early warning of a fully mechanized mining face, comprising the following steps:

[0029] Step 1: Coal mining machine position data collection: The real-time position data of the coal mining machine is obtained through the travel encoder on the coal mining machine, and the real-time position data of the coal mining machine is used to determine whether the coal mining machine has passed the end mark point frame number or the end mark point frame number.

[0030] Step 2: Identification of whole-knife coal cutting: Set the end mark point frame number and the end-end mark point frame number, define the distance between the two consecutive passes of the coal mining machine through the end mark point frame number during the coal cutting process as the end-end return section, and the distance between the two consecutive passes through the end-end mark point frame number as the end-end return section. Select the point closest to the midpoint of the fully mechanized mining face in the end-end return section and the point closest to the midpoint of the fully mechanized mining face in the end-end return section as the whole-knife demarcation point for coal cutting.

[0031] Step 3: Division of the support working cycle: According to the whole-knife dividing point defined in step 2, select the time when the coal mining machine first arrives at a certain hydraulic support during each whole-knife coal cutting process, and use the end time of the first column lowering action between the nth time the coal mining machine arrives at the hydraulic support to the n+1th time it arrives at the hydraulic support as the working cycle dividing point of the hydraulic support.

[0032] The end time of the column lowering action is determined by the time of the column lowering action instruction issued by the electro-hydraulic controller.

[0033] Step 4: Extraction of key features of the support: Based on the working cycle dividing point of the hydraulic support identified in step 3, extract key features such as end-of-cycle resistance and cycle working resistance. The end-of-cycle resistance is the maximum value of the column pressure in a small time period before the start of the first effective column lowering-rack pulling action in the working cycle, and the cycle working resistance is the average value of the column pressure from the end time of the first effective rack pulling-column raising action to the start time of the first effective column lowering-rack pulling action in the working cycle.

[0034] The end time of the rack pulling action and the column raising action is determined by the time of the rack pulling action and the column raising action instructions issued by the electro-hydraulic controller respectively.

[0035] The column pressure data is obtained through the pressure sensor installed on each hydraulic support column. The pressure sensor transmits the collected pressure data to the electro-hydraulic controller, which filters the data according to the preset sampling frequency and the maximum change range, and transmits the filtered data to the chute master computer through the electro-hydraulic control server.

[0036] The electro-hydraulic control server is installed on the hydraulic support at the end of the working face, and each hydraulic support is equipped with an electro-hydraulic controller and a pressure sensor. The main control computer of the chute communicates with the electro-hydraulic control server through the CAN network, the electro-hydraulic control server communicates with the electro-hydraulic controller through the CAN network, and the pressure sensor communicates with the electro-hydraulic controller through the serial port.

[0037] Step 5: Periodic pressure identification: Use the standard deviation method to determine the pressure threshold P t , the calculation formula is: t =mP mean +sP std , where m is the mean coefficient, s is the mean square error coefficient, P mean is the mean pressure, P std is the mean square error of pressure.

[0038] According to the key feature extraction results of the support in step 4, a mine pressure feature matrix is ​​established. The matrix column is labeled with the number of cutters and the matrix row is labeled with the support position. The mine pressure feature matrix contains the mine pressure feature values ​​exceeding the pressure threshold P. t The position of the pressure is taken as the pressure position, and the DBSCAN clustering method is used to cluster the above discrete pressure positions to obtain the pressure area {A1, A2, ······, A n}, A n It is the set of pressure position points of the nth pressure.

[0039] Step 6: Calculation of historical pressure parameters: Traverse and identify the starting footage of all pressure areas {Sa1, Sa2, ······, Sa n} and end footage {Ta1, Ta2, ······, Ta n}, calculate the pressure step distance St of the nth pressure n =Sa n -Sa n-1 , the pressure intensity of the nth pressure is Pa n A n The average pressure in the stable stage before the nth pressure comes, the pressure strength P * a n For her n-1 to Sa n The pressure average value between the nth pressure and the pressure coefficient C n =Pa n / P * a n .

[0040] Step 7: Pressure forecast and warning: Use the exponential smoothing method to predict the pressure step distance of the n+1th pressure. =aSt n +(1-a) , where a is the smoothing coefficient, Stn is the observed value of the nth pressure step, is the predicted value of the nth pressure step, that is, the smoothed value of the previous period. During the mining process, the current footage S is obtained in real time, and the footage Sa of the last start is obtained. n And the predicted next pressure step The predicted footage of the next pressure is obtained by superposition , when S approaches When S and When the gap is less than 5 knife advance distance, a Level III warning is issued. When the gap is less than 3 blades, a Level II warning is issued. When the gap is less than 1 knife advance distance, a Level I warning will be issued.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for periodic pressure analysis and early warning of a fully mechanized mining face, characterized by: The following steps are involved: Step 1: Acquisition of coal mining machine location data; Step 2: Identification of whole-knife coal cutting: Set the end mark point frame number and the end-end mark point frame number, define the distance between the two consecutive passes of the coal mining machine through the end mark point frame number during the coal cutting process as the end-end return section, and the distance between the two consecutive passes of the coal mining machine through the end-end mark point frame number as the end-end return section, and select the point closest to the midpoint of the fully mechanized mining working face in the end-end return section and the point closest to the midpoint of the fully mechanized mining working face in the end-end return section as the whole-knife demarcation point for coal cutting; Step 3: Support work cycle division: According to the whole-knife dividing point defined in step 2, the time when the coal mining machine first arrives at a certain hydraulic support during each whole-knife coal cutting process is selected, and the first column lowering action end time between the coal mining machine's nth arrival at the hydraulic support and the n+1th arrival at the hydraulic support is used as the work cycle dividing point of the hydraulic support; Step 4: Extraction of key features of the support: Based on the working cycle demarcation point of the hydraulic support identified in step 3, extract the key features of the end-of-cycle resistance and cycle working resistance, where the end-of-cycle resistance is the maximum value of the column pressure in a set time period before the first effective column lowering-rack pulling action in the working cycle, and the cycle working resistance is the average value of the column pressure from the end time of the first effective rack pulling-column raising action to the start time of the first effective column lowering-rack pulling action in the working cycle; Step 5: Periodic pressure identification: Determine the pressure threshold. According to the key feature extraction results of the bracket in step 4, establish a mine pressure feature matrix. The matrix column is labeled with the number of cutters and the matrix row is labeled with the bracket position. Filter out the positions where the mine pressure characteristic values ​​in the mine pressure feature matrix exceed the pressure threshold as the pressure position. Cluster the above discrete pressure positions to obtain the pressure area {A1, A2, ······, A n }, A n is the set of pressure position points of the nth pressure; Step 6: Calculation of historical pressure parameters: Traverse and identify the starting footage of all pressure areas {Sa1, Sa2, ······, Sa n } and end footage {Ta1, Ta2, ······, Ta n }, calculate the pressure step distance St of the nth pressure n =Sa n -Sa n-1 , the pressure intensity of the nth pressure is Pa n A n The average pressure in the stable stage before the nth pressure comes, the pressure strength P * a n For her n-1 to Sa n The pressure average value between the nth pressure and the pressure coefficient C n =Pa n / P * a n ; Step 7: Pressure forecast and warning: Predict the pressure step distance of the n+1th pressure =aSt n +(1-a) , where a is the smoothing coefficient, St n is the observed value of the nth pressure step, is the predicted value of the nth pressure step, that is, the smoothed value of the previous period. The current footage S is obtained in real time during the mining process, and the footage Sa of the most recent start is obtained. n And the predicted next pressure step The predicted footage of the next pressure is obtained by superposition , when S approaches Provide early warning.

2. A method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 1, characterized in that: The end time of the column lowering action, the frame pulling action, and the column raising action is determined by the time of the column lowering action, the frame pulling action, and the column raising action instructions issued by the electro-hydraulic controller.

3. A method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 1, characterized in that: In step 5, the standard deviation method is used to determine the pressure threshold P t , the calculation formula is: t =mP mean +sP std , where m is the mean coefficient, s is the mean square error coefficient, P mean is the mean pressure, P std is the mean square error of pressure.

4. A method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 1, characterized in that: The discrete pressure locations in step 5 are clustered using the DBSCAN clustering method to obtain the pressure areas.

5. The method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 1 is characterized by: In step 7, the exponential smoothing method is used to predict the pressure step size of the n+1th pressure. ; And when S and When the gap is less than 5 knife advance distance, a Level III warning is issued. When the gap is less than 3 blades, a Level II warning is issued. When the gap is less than 1 knife advance distance, a Level I warning will be issued.

6. A method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 1, characterized in that: The position data of the coal mining machine in step 1 is obtained through the travel encoder on the coal mining machine.

7. The method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 1 is characterized by: The column pressure in step 4 is obtained through the pressure sensor installed on each hydraulic support, and the pressure sensor transmits the collected pressure data to the electro-hydraulic controller. The electro-hydraulic controller filters the data according to the preset sampling frequency and the maximum change range, and transmits the filtered data to the chute main control computer through the electro-hydraulic control server.

8. A method for periodic pressure analysis and early warning of a fully mechanized mining face according to claim 7, characterized in that: The main control computer of the chute communicates with the electro-hydraulic control server through the CAN network, the electro-hydraulic control server communicates with the electro-hydraulic controller through the CAN network, the pressure sensor communicates with the electro-hydraulic controller through the serial port, the electro-hydraulic control server is arranged on the hydraulic support at the end of the comprehensive mining working face, and each hydraulic support is respectively provided with an electro-hydraulic controller.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program of the method for periodic pressure analysis and early warning of the comprehensive mining working face as described in any one of claims 1 to 5, and the processor is used to execute the above computer program.

10. A computer-readable storage medium, characterized in that: One or more computer programs are stored, and the one or more computer programs can be executed by one or more processors to implement the periodic pressure analysis and early warning method for the comprehensive mining working face as described in any one of claims 1-5 above.

Images