Gas disaster cloud early warning method and system based on multi-dimensional data driving

Abstract

The present application relates to the technical field of coal mine safety, a gas disaster cloud early warning method and system based on multidimensional data driving, comprising: confirming discrete data based on multiple historical coal mine data, confirming an influence coefficient based on the discrete data and a pre-constructed correlation analysis algorithm, confirming a gas state monitoring mechanism, obtaining a coal mining working area, confirming gas pressure based on the coal mining working area, a pressure sensor and a hole sealing air bag, confirming a firmness coefficient based on the coal mining working area and a crushing testing machine, confirming a gas emission risk index based on the coal mining working area, a gas flow meter and a gas concentration sensor, calculating a disaster early warning score according to the pressure influence index, the hardness influence index, the emission speed influence coefficient, the gas pressure, the firmness coefficient and the gas emission risk index, confirming a risk level according to the disaster early warning score, and completing gas disaster early warning. The present application can improve the accuracy of gas disaster early warning.

Description

Technical Field

[0001] This invention relates to the field of coal mine safety technology, and in particular to a gas disaster cloud early warning method and system based on multi-dimensional data-driven approach. Background Technology

[0002] With the development of coal mining technology, gas disasters are one of the most common and destructive types of disasters in coal mining, characterized by their suddenness, high concealment, and difficulty in prediction.

[0003] Traditional gas disaster early warning methods mostly rely on a single monitoring parameter, such as gas concentration, gas pressure, or outstanding historical experience.

[0004] While the aforementioned methods can provide early warning of gas disasters, the lack of systematic analysis of the coupled effects of multiple factors leads to insufficient warning sensitivity, high false alarm and false negative rates, and an inability to meet the precise early warning requirements under complex geological conditions. Therefore, a cloud-based early warning method for gas disasters that integrates historical multidimensional data with real-time multi-parameter monitoring technology is urgently needed to construct a scientific, objective, and quantifiable risk assessment model, thereby improving the accuracy of gas disaster early warnings. This has become a pressing issue that needs to be addressed. Summary of the Invention

[0005] This invention provides a cloud-based early warning method for gas disasters based on multidimensional data and a computer-readable storage medium, the main purpose of which is to improve the accuracy of gas disaster early warning.

[0006] To achieve the above objectives, this invention provides a gas disaster cloud early warning method based on multi-dimensional data-driven approach, comprising:

[0007] Acquire data from multiple historical coal mines, including historical gas pressure, historical coal hardness, historical gas emission velocity, and historical gas outburst frequency.

[0008] Discretized data was identified based on data from multiple historical coal mines;

[0009] The influence coefficients were identified based on discretized data and a pre-built correlation analysis algorithm. These influence coefficients include: pressure influence index, hardness influence index, and outflow velocity influence coefficient.

[0010] The gas status monitoring mechanism was identified, which includes: pressure sensor, sealing airbag, crushing test machine, gas flow meter and gas concentration sensor;

[0011] The coal mining area is obtained, and the gas pressure is confirmed based on the coal mining area, pressure sensors, and sealing airbags.

[0012] The firmness coefficient was determined based on the coal mining area and the crushing test machine.

[0013] Based on the coal mining area, gas flow meter, and gas concentration sensor, the gas emission risk index was determined.

[0014] The disaster early warning score is calculated based on the pressure impact index, hardness impact index, outflow velocity impact coefficient, gas pressure, solidity coefficient, and gas outflow risk index.

[0015] Based on the disaster early warning score, the risk level is determined, and the gas disaster early warning is completed.

[0016] Optionally, the discretization of data based on multiple historical coal mine data includes:

[0017] Multiple historical gas pressures, coal hardness, gas emission rates, and gas outburst frequencies were extracted from multiple historical coal mine data.

[0018] Discretized pressure data is determined based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressures.

[0019] Discrete hardness data is determined based on a preset first hardness threshold, a preset second hardness threshold, and multiple historical coal hardness values.

[0020] Discretized velocity data is determined based on a preset first velocity threshold, a preset second velocity threshold, and multiple historical gas emission velocities.

[0021] Discretized frequency data were identified based on a preset first frequency threshold, a preset second frequency threshold, and multiple historical gas outburst frequencies.

[0022] Discretized pressure data, discretized hardness data, discretized speed data, and discretized frequency data are mapped to obtain discretized data, where each of the discretized pressure data, discretized hardness data, discretized speed data, and discretized frequency data corresponds one-to-one.

[0023] Optionally, the step of determining discretized pressure data based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressures includes:

[0024] For each of the multiple historical gas pressures, perform the following operation:

[0025] Compare the historical gas pressure with the first pressure threshold. If the historical gas pressure is greater than or equal to the first pressure threshold, then the preset first value is used as the discrete pressure value.

[0026] If the historical gas pressure is less than the first pressure threshold and the historical gas pressure is greater than the second pressure threshold, then the preset second value will be used as the discrete pressure value.

[0027] Otherwise, the preset third value will be used as the discrete pressure value;

[0028] By summing the discrete pressure values, discretized pressure data is obtained.

[0029] Optionally, the determination of gas pressure based on the coal mining area, pressure sensor, and sealing airbag includes:

[0030] Horizontal drilling was performed in the coal mining area to obtain pressure test holes;

[0031] The test length and test hole diameter are determined based on the pressure test hole, where the test length is the depth of the pressure test hole and the test hole diameter is the inner diameter of the pressure test hole.

[0032] The pressure test hole is uniformly divided based on the preset division length to obtain n test areas;

[0033] Calculate the cavity volume based on the segment length and test aperture;

[0034] Confirm the coal seam temperature and calculate the gas volume based on the cavity volume and coal seam temperature;

[0035] Extract the i-th test region from n test regions;

[0036] A pressure sensor is installed at a preset first position in the i-th test area, and a sealing airbag is installed at a preset second position in the i-th test area to obtain a pressure test area. The sealing airbag includes an air injection port.

[0037] Based on the gas volume and injection port, gas is injected into the pressure test area to obtain the target area;

[0038] The pressure sensor is activated to monitor the pressure in the target area and obtain the area pressure value;

[0039] Return to the step of extracting the i-th test area from n test areas, until i=n, ​​and summarize the area pressure values ​​to obtain multiple area pressure values;

[0040] The gas pressure was determined based on multiple regional pressure values, with the gas pressure being the highest regional pressure value among the multiple regional pressure values.

[0041] Optionally, the determination of the firmness coefficient based on the coal mining area and the crushing test machine includes:

[0042] Coal samples were taken from the coal mining area.

[0043] The coal sample was dried to obtain a dried sample;

[0044] Determine the original weight of the dried sample;

[0045] The dry sample was subjected to impact crushing using a crushing tester to obtain a crushed sample.

[0046] The broken sample is sieved using a pre-constructed sieve to obtain a sieved sample;

[0047] Confirm the sieving weight of the sieved sample;

[0048] The strength factor is calculated based on the original weight and the weight after screening.

[0049] Optionally, the determination of the gas emission risk index based on the coal mining area, gas flow meter, and gas concentration sensor includes:

[0050] The flow guide pipe and negative pressure guide chamber are obtained. The negative pressure guide chamber includes an airflow inlet and an airflow outlet. The monitoring module is identified based on the flow guide pipe, negative pressure guide chamber, gas flow meter and gas concentration sensor.

[0051] Based on the identification of multiple monitoring locations within the coal mining area, the following operations were performed on each of these locations:

[0052] Based on the preset time threshold, monitoring module, and monitoring location, the gas emission index is determined.

[0053] By summing up the gas emission indices, multiple gas emission indices are obtained;

[0054] A gas emission risk index was identified based on multiple gas emission indices, among which the gas emission risk index is the largest gas emission index.

[0055] Optionally, the monitoring module based on the flow guide pipe, negative pressure guide chamber, gas flow meter, and gas concentration sensor includes:

[0056] Connect the flow guide pipe to the airflow inlet of the negative pressure guidance chamber to obtain the target guidance chamber;

[0057] A gas flow meter and a gas concentration sensor are installed at the airflow outlet of the target guidance chamber to obtain a monitoring module.

[0058] Optionally, the process of determining the gas emission index based on a preset time threshold, monitoring module, and monitoring location includes:

[0059] The monitoring module is activated, and the gas flow meter in the activated monitoring module is used to monitor the monitoring location to obtain the first flow velocity;

[0060] The test time is obtained by recording the time in real time starting from the time when the first flow velocity is obtained.

[0061] When the test time reaches the time threshold, the gas flow meter and gas concentration sensor in the monitoring module after startup are used to monitor the monitoring position and obtain the second flow rate and the second concentration.

[0062] The gas emission index is calculated based on the first flow velocity, the second flow velocity, and the second concentration, using the following formula:

[0063] in, Indicates the gas emission index, Indicates the first flow velocity. Indicates the second flow velocity. Indicates the second concentration. It is a natural constant. The preset concentration index, The preset acceleration adjustment parameters, This is the preset acceleration threshold.

[0064] Optionally, the formula for calculating the disaster early warning score is as follows:

[0065] in, Indicates the disaster early warning score. Indicates gas pressure, The stress impact index indicates the impact of stress. Indicates the influence coefficient of outflow velocity. The index indicates the influence of hardness. This indicates the strength coefficient.

[0066] To achieve the above objectives, the present invention also provides a gas disaster cloud early warning system based on multi-dimensional data-driven methods, comprising:

[0067] The historical data processing module is used to acquire multiple historical coal mine data, including historical gas pressure, historical coal hardness, historical gas emission rate, and historical gas outburst frequency. Discretized data is identified based on multiple historical coal mine data.

[0068] The influence coefficient confirmation module is used to confirm the influence coefficients based on discretized data and pre-built correlation analysis algorithms. The influence coefficients include: pressure influence index, hardness influence index and outflow velocity influence coefficient.

[0069] The gas status monitoring module is used to identify the gas status monitoring mechanism, which includes: a pressure sensor, a sealing airbag, a crushing test machine, a gas flow meter, and a gas concentration sensor. It acquires the coal mining area, determines the gas pressure based on the coal mining area, pressure sensor, and sealing airbag, determines the solidity coefficient based on the coal mining area and crushing test machine, and determines the gas emission risk index based on the coal mining area, gas flow meter, and gas concentration sensor.

[0070] The gas disaster early warning module is used to calculate the disaster early warning score based on the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, solidity coefficient, and gas outflow risk index. Based on the disaster early warning score, the risk level is determined, and the gas disaster early warning is completed.

[0071] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0072] Memory, storing at least one instruction; and

[0073] The processor executes the instructions stored in the memory to implement the gas disaster cloud early warning method based on multidimensional data driving described above.

[0074] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned gas disaster cloud early warning method based on multidimensional data-driven processing.

[0075] To address the problems described in the background section, this invention obtains multiple historical coal mine data sets, including historical gas pressure, historical coal hardness, historical gas emission velocity, and historical gas outburst frequency. This invention, by acquiring historical coal mine operational data, facilitates the subsequent determination of the influence coefficients of each indicator based on the historical data. Furthermore, it identifies discretized data based on multiple historical coal mine data sets. This invention also discretizes the historical data to facilitate subsequent analysis using correlation analysis algorithms. Based on the discretized data and a pre-constructed correlation analysis algorithm, influence coefficients are determined, including pressure influence index, hardness influence index, and emission velocity influence index. The impact coefficients show that this embodiment of the invention analyzes discretized data using a pre-built correlation analysis algorithm to identify the pressure influence index, hardness influence index, and outburst velocity influence coefficient. This facilitates the subsequent accurate calculation of disaster early warning scores based on the pressure influence index, hardness influence index, and outburst velocity influence coefficient, improving the accuracy of gas disaster early warning. The gas state monitoring mechanism is also identified, comprising: a pressure sensor, a sealing gasbag, a crushing test machine, a gas flow meter, and a gas concentration sensor. This embodiment of the invention, by identifying the gas state monitoring mechanism, facilitates subsequent measurement of gas pressure using the pressure sensor and sealing gasbag within the gas state monitoring mechanism, and the use of the crushing test machine to measure the coal hardness... The gas emission rate is measured using a gas flow meter and a gas concentration sensor to obtain the coal mining area. Based on the coal mining area, pressure sensor, and sealing airbag, the gas pressure is confirmed. This embodiment of the invention involves drilling holes in the coal mining area and then using a pressure sensor and sealing airbag to confirm the gas pressure. Based on the coal mining area and a crushing test machine, the firmness coefficient is confirmed. This embodiment of the invention further crushes the coal sample using a crushing test machine to calculate the firmness coefficient of the coal sample. Based on the coal mining area, gas flow meter, and gas concentration sensor, the gas emission risk index is confirmed. This embodiment of the invention constructs a monitoring module to accurately measure gas emissions. The flow rate and gas concentration facilitate subsequent comprehensive calculation of the disaster early warning score based on gas pressure and stability coefficient, thus improving the accuracy of gas disaster early warning. The disaster early warning score is calculated based on the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, stability coefficient, and gas outflow risk index. Therefore, this embodiment of the invention comprehensively calculates the disaster early warning score by combining the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, stability coefficient, and gas outflow risk index. Based on the disaster early warning score, the risk level is then determined, completing the gas disaster early warning. Thus, this embodiment of the invention improves the accuracy of gas disaster early warning by determining the risk level through the disaster early warning score and then making deployment arrangements based on the risk level. Therefore, this invention can improve the accuracy of gas disaster early warning. Attached Figure Description

[0076] Figure 1 This is a flowchart illustrating a multi-dimensional data-driven cloud-based early warning method for gas disasters, provided in an embodiment of the present invention.

[0077] Figure 2 This is a functional block diagram of a gas disaster cloud early warning system based on multidimensional data-driven technology, provided in an embodiment of the present invention.

[0078] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the multi-dimensional data-driven gas disaster cloud early warning method according to an embodiment of the present invention.

[0079] Explanation of reference numerals in the attached figures:

[0080] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0081] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0082] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0083] This application provides a multi-dimensional data-driven cloud-based early warning method for gas disasters. The executing entity of this multi-dimensional data-driven cloud-based early warning method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the multi-dimensional data-driven cloud-based early warning method for gas disasters can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0084] Reference Figure 1 The diagram shown is a flowchart illustrating a gas disaster cloud early warning method based on multidimensional data-driven approaches according to an embodiment of the present invention. In this embodiment, the gas disaster cloud early warning method based on multidimensional data-driven approaches includes:

[0085] S1. Obtain multiple historical coal mine data, including: historical gas pressure, historical coal hardness, historical gas emission rate, and historical gas outburst frequency.

[0086] It should be explained that historical coal mine data refers to the collection and recording of relevant gas hazard parameter data in a coal mining area during long-term production. This historical coal mine data includes, but is not limited to, the following: historical gas pressure, used to reflect the static pressure level of gas in coal seams at different locations during historical periods; for example, the historical gas pressure in the mining area can be determined using the borehole pressure measurement method. Historical coal hardness, used to describe the structural strength of the coal body and its influence on the ease of gas accumulation and release; for example, the historical coal hardness of coal samples collected from the mining area can be determined using the drop hammer test. Historical gas emission velocity, used to quantify the gas release capacity per unit time or unit output; for example, a venturi tube can be used to divert gas in the mining area, and an ultrasonic flow meter can be used to measure the gas flow rate, while a methane sensor can be used to measure the gas concentration. The historical gas emission velocity is calculated based on the gas flow rate and gas concentration, as shown in the following formula: ,in, Indicates the historical gas outburst rate, Indicates gas flow rate, Indicates gas concentration. This refers to the minimum cross-sectional area of ​​the constriction throat of the Venturi tube. Historical gas outburst frequency indicates the number of gas outburst accidents that actually occurred in a coal mine within a statistical period; for example, the number of gas outburst accidents can be obtained from the safety production records of a coal mining enterprise.

[0087] For example, Zhang is a coal mine engineer at a coal mining company. He needs to provide early warnings of gas disasters, so he obtains multiple historical coal mine data to facilitate the subsequent identification of influencing parameters.

[0088] S2. Discretized data is identified based on multiple historical coal mine data. Influence coefficients are identified based on the discretized data and a pre-built correlation analysis algorithm. The influence coefficients include: pressure influence index, hardness influence index and outflow velocity influence coefficient.

[0089] Specifically, the discretized data identified based on multiple historical coal mine data includes:

[0090] Multiple historical gas pressures, coal hardness, gas emission rates, and gas outburst frequencies were extracted from multiple historical coal mine data.

[0091] Discretized pressure data is determined based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressures.

[0092] Discrete hardness data is determined based on a preset first hardness threshold, a preset second hardness threshold, and multiple historical coal hardness values.

[0093] Discretized velocity data is determined based on a preset first velocity threshold, a preset second velocity threshold, and multiple historical gas emission velocities.

[0094] Discretized frequency data were identified based on a preset first frequency threshold, a preset second frequency threshold, and multiple historical gas outburst frequencies.

[0095] Discretized pressure data, discretized hardness data, discretized speed data, and discretized frequency data are mapped to obtain discretized data, where each of the discretized pressure data, discretized hardness data, discretized speed data, and discretized frequency data corresponds one-to-one.

[0096] For example, if the historical coal mine data are (0.8 MPa, 0.5, 1 m³ / s, 2 times / year), (1 MPa, 0.6, 1.1 m³ / s, 3 times / year), (1.2 MPa, 0.7, 1.2 m³ / s, 4 times / year), and (1.5 MPa, 0.8, 1.3 m³ / s, 5 times / year), then the four historical gas pressures extracted from the four historical coal mine data are (0.8 MPa, 1 MPa, 1.2 MPa, 1.5 MPa), the four historical coal hardnesses extracted from the four historical coal mine data are (0.5, 0.6, 0.7, 0.8), and the four historical gas emission velocities extracted from the four historical coal mine data are (1 m³ / s, 1.1 m³ / s, 1.2 m³ / s, 1.3 m³ / s). m³ / s), the four historical gas outburst frequencies extracted from the data of four historical coal mines are (2 times / year, 3 times / year, 4 times / year, 5 times / year).

[0097] It is understood that the method for determining discrete hardness data based on a preset first hardness threshold, a preset second hardness threshold, and multiple historical coal hardness values, the method for determining discrete velocity data based on a preset first velocity threshold, a preset second velocity threshold, and multiple historical gas outburst velocities, and the method for determining discrete frequency data based on a preset first frequency threshold, a preset second frequency threshold, and multiple historical gas outburst frequencies are all the same as the method for determining discrete pressure data based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressure values. These will not be elaborated further in this embodiment of the invention.

[0098] It should be explained that the specific method for determining discrete pressure data based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressures is described in subsequent embodiments.

[0099] For example, if the discretized pressure data is (3, 2, 2, 1), the discretized hardness data is (2, 2, 2, 3), the discretized velocity data is (3, 2, 2, 2), and the discretized frequency data is (1, 2, 3, 1), the discretized pressure value at the i-th position in the discretized pressure data, the discretized hardness value at the i-th position in the discretized hardness data, the discretized velocity value at the i-th position in the discretized velocity data, and the discretized frequency value at the i-th position in the discretized frequency data are mapped to obtain the discretized data as (3, 2, 3, 1), (2, 2, 2, 2), (2, 2, 2, 3), (1, 3, 2, 1).

[0100] It should be understood that the first pressure threshold, the second pressure threshold, the first hardness threshold, the second hardness threshold, the first speed threshold, the second speed threshold, the first number threshold, and the second number threshold are all values ​​set manually by coal mine engineers based on their experience.

[0101] For example, firstly, data on gas pressure, coal seam hardness, gas emission velocity, and accident frequency over a past period in the coal mine are acquired, and the average pressure and standard deviation of the gas pressure are calculated. Then, a second pressure threshold is set as the average pressure plus one times the standard deviation, serving as a warning threshold. The first threshold is set to half of the second threshold. It should be understood that the methods for setting the first and second hardness thresholds, the first and second velocity thresholds, and the first and second number thresholds are the same as those for setting the first and second pressure thresholds, and will not be repeated here. In detail, the discretized pressure data identified based on the preset first pressure threshold, the preset second pressure threshold, and multiple historical gas pressures includes:

[0102] For each of the multiple historical gas pressures, perform the following operation:

[0103] Compare the historical gas pressure with the first pressure threshold. If the historical gas pressure is greater than or equal to the first pressure threshold, then the preset first value is used as the discrete pressure value.

[0104] If the historical gas pressure is less than the first pressure threshold and the historical gas pressure is greater than the second pressure threshold, then the preset second value will be used as the discrete pressure value.

[0105] Otherwise, the preset third value will be used as the discrete pressure value;

[0106] By summing the discrete pressure values, discretized pressure data is obtained.

[0107] It should be explained that the discrete pressure value refers to the coding result obtained after classifying historical gas pressure according to the first and second pressure thresholds. The first value of 1 indicates a high-pressure state, that is, the gas pressure is greater than or equal to the first pressure threshold. Under this state, the degree of gas accumulation is high, and there is a significant risk of gas outburst. The second value of 2 indicates a medium-pressure state, that is, the gas pressure is between the second and first pressure thresholds. There is a certain accumulation trend in this area. The third value of 3 indicates a low-pressure state, that is, the gas pressure is less than the second pressure threshold, which is usually an area where gas has been fully released or the gas content is low.

[0108] For example, if the four historical gas pressures are (0.8 MPa, 1 MPa, 1.2 MPa, 1.5 MPa), the first pressure threshold is 1.3 MPa, and the second pressure threshold is 0.9 MPa, then the discretized pressure data confirmed based on the preset first pressure threshold, the preset second pressure threshold, and the multiple historical gas pressures is (3, 2, 2, 1).

[0109] It is understood that the correlation analysis algorithm refers to the Apriori algorithm, which is a publicly available technical solution and will not be elaborated here. The determination of influence coefficients based on discretized data and a pre-built correlation analysis algorithm involves: converting the discretized data into a set of multiple transaction items to obtain a transaction database; performing correlation analysis on the transaction database using the correlation analysis algorithm to obtain three correlation rules; reading the confidence value corresponding to each correlation rule; and obtaining three confidence values. These three confidence values ​​correspond to the correlation strength between pressure, hardness, and gas emission velocity and the occurrence of gas outburst accidents. Therefore, these three confidence values ​​are directly used as the pressure influence index, hardness influence index, and emission velocity influence coefficient to quantify the specific impact of each factor on gas disasters. For example, if the confidence level of the pressure influence index is 0.6, the confidence level of the hardness influence index is 0.85, and the confidence level of the outflow velocity influence coefficient is 0.9, then the pressure influence index is 0.6, the hardness influence index is 0.85, and the outflow velocity influence coefficient is 0.9.

[0110] S3. Identify the gas status monitoring mechanism, which includes: pressure sensor, sealing airbag, crushing test machine, gas flow meter and gas concentration sensor.

[0111] It should be explained that the gas condition monitoring mechanism refers to an organization that integrates a pressure sensor, a sealing airbag, a crushing test machine, a gas flow meter, and a gas concentration sensor to monitor the gas condition. Among them, the pressure sensor is a device that can sense pressure signals and convert them into usable output electrical signals according to a certain rule. The pressure sensor is installed in the exploration hole in the gas working area. Optionally, the Druck UNIK5000 pressure sensing platform is used as the pressure sensor. The sealing airbag is a device used to seal boreholes in coal mine gas pressure measurement. Its main function is to isolate the borehole from the external air. Optionally, the Zhongcheng brand FKZW-133 / 2.0 sealing airbag is used as the sealing airbag. The crushing test machine is an impact test machine. Optionally, the Hesheng HS-XJJ-5J digital display simply supported beam impact test machine is used as the crushing test machine. The gas flow meter is a differential pressure orifice plate flow meter. Optionally, the Dalian Xindongxing orifice plate flow meter is used as the gas flow meter. The gas concentration sensor is a methane sensor. Both the gas flow meter and the gas concentration sensor are pre-installed on the monitoring mechanism. Optionally, the Chicheng Electric QB200N methane gas detector alarm is used as the gas concentration sensor.

[0112] S4. Obtain the coal mining area and confirm the gas pressure based on the coal mining area, pressure sensor, and sealing airbag.

[0113] It should be explained that the coal mining working area refers to the coal mining face.

[0114] Specifically, the determination of gas pressure based on the coal mining area, pressure sensors, and sealing airbags includes:

[0115] Horizontal drilling was performed in the coal mining area to obtain pressure test holes;

[0116] The test length and test hole diameter are determined based on the pressure test hole, where the test length is the depth of the pressure test hole and the test hole diameter is the inner diameter of the pressure test hole.

[0117] The pressure test hole is uniformly divided based on the preset division length to obtain n test areas;

[0118] The cavity volume is calculated based on the segment length and the test aperture, using the following formula:

[0119] in, Indicates the volume of the cavity. Indicates the test aperture. Indicates the segment length;

[0120] Once the coal seam temperature is confirmed, the gas volume is calculated based on the cavity volume and coal seam temperature. The calculation formula is as follows:

[0121] in, Indicates the gas volume, Indicates the temperature of the coal seam. The preset gas constant, The preset target pressure;

[0122] Extract the i-th test region from n test regions;

[0123] A pressure sensor is installed at a preset first position in the i-th test area, and a sealing airbag is installed at a preset second position in the i-th test area to obtain a pressure test area. The sealing airbag includes an air injection port.

[0124] Based on the gas volume and injection port, gas is injected into the pressure test area to obtain the target area;

[0125] The pressure sensor is activated to monitor the pressure in the target area and obtain the area pressure value;

[0126] Return to the step of extracting the i-th test area from n test areas, until i=n, ​​and summarize the area pressure values ​​to obtain multiple area pressure values;

[0127] The gas pressure was determined based on multiple regional pressure values, with the gas pressure being the highest regional pressure value among the multiple regional pressure values.

[0128] It should be explained that the horizontal drilling operation in the coal mining area refers to drilling along the horizontal direction in the coal mining area to form exploration holes, which are pressure testing holes. For ease of understanding, this article simplifies the description of the pressure testing hole as a cylindrical structure.

[0129] Understandably, the injection port refers to the interface used to inject a specific gas medium into the cavity area formed by the sealed airbag after the airbag has been sealed. The phrase "injecting gas into the pressure test area based on the gas volume and the injection port to obtain the target area" means: injecting gas with a volume equal to the gas volume into the pressure test area through the injection port to obtain the target area.

[0130] For example, if the generatrix length of the cylinder corresponding to the pressure test hole is 200cm and the diameter of the base circle is 5cm, then the base circle of the cylinder corresponding to the pressure test hole is used as the first reference surface. Any generatrix of the cylinder corresponding to the pressure test hole is used as a reference edge. The point where the reference edge intersects the base of the cylinder is used as one endpoint of the line segment, and the point where the reference edge intersects the top of the cylinder is used as the other endpoint of the line segment. This identifies a line segment within the range [0, 200cm]. If the segmentation length is 50cm, then the cylinder is divided into four non-overlapping identical cylinders using this segmentation length. The height of each divided cylinder is 50cm, and the diameter of its base circle is 5cm. This segmentation only divides the entire area of ​​the pressure test hole for subsequent analysis, rather than performing a physical division of the pressure test hole.

[0131] It is understandable that the cavity volume is the volume of the cylinder with a bottom diameter of 5cm and a height of 50cm, which is the volume of the test area.

[0132] It should be explained that coal seam temperature refers to the temperature of the coal seam surface. Gas volume refers to the volume of gas to be injected into the test area. Since this embodiment of the invention uniformly divides the pressure test hole into n test areas based on a preset segmentation length, the volumes of the n test areas are consistent, and therefore the gas volumes are also the same, facilitating subsequent comparison of pressure data and extraction of the maximum value. The gas constant is 8.314 J / mol·K, and the target pressure is standard atmospheric pressure, i.e., 1.0 × 10⁻⁶. 5 Pa.

[0133] For example, if the four test regions are: region A, region B, region C, and region D, then the second test region extracted from the four test regions is: region B.

[0134] It should be explained that installing a pressure sensor at a preset first position on the i-th test area means installing the pressure sensor at the preset first position on the i-th test area. Installing a sealing airbag at a preset second position on the i-th test area means sealing the i-th test area using the sealing airbag at the preset second position on the i-th test area. The pressure test area refers to the test area after the pressure sensor is installed and the test area is sealed using the sealing airbag. Injecting gas equal to the volume of gas into the pressure test area through the injection port means injecting gas equal to the volume of gas into the pressure test area through the injection port, and the test area injected with gas equal to the volume of gas is the target area. Optionally, the first position is the midpoint of the generatrix of the cylinder corresponding to the test area, and the second position is the position where the top surface and the side surface of the cylinder corresponding to the test area intersect.

[0135] It is understood that the activation of the pressure sensor to monitor the pressure of the target area means: using the pressure sensor to monitor the air pressure of the target area, and the method of using the pressure sensor to monitor the air pressure of the target area is existing technology, which will not be described in detail here. The air pressure of the target area is the area pressure value.

[0136] S5. The firmness coefficient was determined based on the coal mining area and the crushing test machine.

[0137] Specifically, the determination of the firmness coefficient based on the coal mining area and the crushing test machine includes:

[0138] Coal samples were taken from the coal mining area.

[0139] The coal sample was dried to obtain a dried sample;

[0140] Determine the original weight of the dried sample;

[0141] The dry sample was subjected to impact crushing using a crushing tester to obtain a crushed sample.

[0142] The broken sample is sieved using a pre-constructed sieve to obtain a sieved sample;

[0143] Confirm the sieving weight of the sieved sample;

[0144] The soundness factor is calculated based on the original weight and the sieved weight, using the following formula:

[0145]

[0146] in, Indicates the strength coefficient. Indicates the original weight. This indicates the weight after screening.

[0147] It should be explained that sampling the coal mining area refers to extracting a certain mass of coal from the mining area, which is the coal sample. Drying the coal sample refers to drying the coal sample to remove moisture for subsequent operations; the dried coal sample is the dry sample. Impact crushing the dry sample using a crushing tester refers to applying pressure to the surface of the dry sample using the crushing tester, causing it to break; the crushed dry sample is the broken sample. The original weight refers to the weight of the dry sample, and the sieve weight refers to the weight of the sieved sample. Optionally, the sieve aperture is 0.5 mm.

[0148] For example, a broken sample is placed on a sieve, and the sieve vibrates at a certain frequency to collect the debris that does not pass through the sieve, thus obtaining a sieved sample.

[0149] Understandably, the hardness coefficient reflects the hardness of a coal sample; the higher the hardness coefficient, the harder the coal sample.

[0150] S6. Based on the coal mining area, gas flow meter, and gas concentration sensor, the gas outburst risk index is determined.

[0151] Specifically, the determination of the gas emission risk index based on the coal mining area, gas flow meter, and gas concentration sensor includes:

[0152] The flow guide pipe and negative pressure guide chamber are obtained. The negative pressure guide chamber includes an airflow inlet and an airflow outlet. The monitoring module is identified based on the flow guide pipe, negative pressure guide chamber, gas flow meter and gas concentration sensor.

[0153] Based on the identification of multiple monitoring locations within the coal mining area, the following operations were performed on each of these locations:

[0154] Based on the preset time threshold, monitoring module, and monitoring location, the gas emission index is determined.

[0155] By summing up the gas emission indices, multiple gas emission indices are obtained;

[0156] A gas emission risk index was identified based on multiple gas emission indices, among which the gas emission risk index is the largest gas emission index.

[0157] It should be explained that the guide pipe is a type of Venturi tube, and the negative pressure guiding chamber refers to a closed or semi-closed structure that operates in an environment below atmospheric pressure. It guides gas in from the sampling port, stabilizes the airflow, and ensures the gas flows out steadily through the discharge outlet to the flow meter and concentration sensor, thereby improving the accuracy of subsequent flow and concentration detection. Its housing is equipped with interface flanges and sealing components for sensor installation. The sampling port is the airflow inlet, and the discharge outlet is the airflow outlet.

[0158] It is understood that the identification of multiple monitoring locations based on the coal mining work area means: firstly, the coal mining work area is divided into several monitoring areas, including: the air intake side area, the return air side area, the coal wall front edge area and the goaf boundary area, and then a point is randomly selected in each of the above areas as a monitoring location and the monitoring locations are summarized to obtain multiple monitoring locations.

[0159] It should be explained that the intake airside area refers to the working area on the side of the coal mining area facing the direction of the fresh airflow. It has high airflow velocity, high oxygen content, and low methane concentration, making it suitable for monitoring initial methane diffusion and airflow disturbance. The return airside area refers to the working area on the side of the coal mining area facing the direction of the airflow discharge. It is a concentrated accumulation area of ​​methane and dust at the working face, with significant methane concentration fluctuations, making it a key location for early warning monitoring. The coal face front area refers to the area adjacent to the original coal seam in the coal mining area. It is the main area for initial methane desorption and sudden gas inrush, characterized by stress concentration and structural fragmentation, making it suitable for high-frequency real-time monitoring. The goaf boundary area refers to the transition area between the goaf and the coal mining area. It is prone to methane accumulation or retention and release, and is an important location for judging secondary methane migration and methane anomalies induced by overlying rock collapse.

[0160] Specifically, the monitoring module based on the flow guide pipe, negative pressure guide chamber, gas flow meter, and gas concentration sensor includes:

[0161] Connect the flow guide pipe to the airflow inlet of the negative pressure guidance chamber to obtain the target guidance chamber;

[0162] A gas flow meter and a gas concentration sensor are installed at the airflow outlet of the target guidance chamber to obtain a monitoring module.

[0163] It should be explained that connecting the guide pipe to the airflow inlet of the negative pressure guiding chamber means sealing the outlet end of the guide pipe to the airflow inlet of the negative pressure guiding chamber, allowing the gas to flow directionally into the negative pressure guiding chamber via the guide pipe. The target guiding chamber refers to the negative pressure guiding chamber connected to the guide pipe. Installing the gas flow meter and gas concentration sensor to the airflow outlet of the target guiding chamber means sequentially installing the gas flow meter and gas concentration sensor to the interface flange on the airflow outlet end housing of the negative pressure guiding chamber and sealing them. The monitoring module refers to the target guiding chamber where the gas flow meter and gas concentration sensor are installed.

[0164] Specifically, the process of determining the gas emission index based on a preset time threshold, monitoring module, and monitoring location includes:

[0165] The monitoring module is activated, and the gas flow meter in the activated monitoring module is used to monitor the monitoring location to obtain the first flow velocity;

[0166] The test time is obtained by recording the time in real time starting from the time when the first flow velocity is obtained.

[0167] When the test time reaches the time threshold, the gas flow meter and gas concentration sensor in the monitoring module after startup are used to monitor the monitoring position and obtain the second flow rate and the second concentration.

[0168] The gas emission index is calculated based on the first flow velocity, the second flow velocity, and the second concentration, using the following formula:

[0169]

[0170] in, Indicates the gas emission index, Indicates the first flow velocity. Indicates the second flow velocity. Indicates the second concentration. It is a natural constant. The preset concentration index, The preset acceleration adjustment parameters, This is the preset acceleration threshold.

[0171] It should be explained that, in the context of using the gas flow meter in the monitoring module after startup to monitor the monitoring location and obtain the first flow velocity, the first flow velocity is the gas flow velocity at the monitoring location. Similarly, in the context of using the gas flow meter and gas concentration sensor in the monitoring module after startup to monitor the monitoring location and obtain the second flow velocity and second concentration, the second flow velocity refers to the gas flow velocity at the monitoring location when the test time reaches a time threshold, and the second concentration refers to the gas concentration at the monitoring location when the test time reaches the time threshold. The method of using the gas flow meter and gas concentration sensor in the monitoring module after startup to monitor the gas flow velocity and concentration at the monitoring location is existing technology and will not be elaborated here. Optionally, the time threshold is 1 second.

[0172] For example, if the time threshold is 1 second, and the current time is 10:00:00, the monitoring module is started and the reading of the gas flow sensor in the monitoring module is read immediately. The reading of the gas flow sensor is the first flow rate. When the time is 10:00:01, the test time is 1 second, and the time threshold is reached, the readings of the gas flow sensor and the gas concentration sensor in the monitoring module are read respectively. At this time, the reading of the gas flow sensor is the second flow rate, and the reading of the gas concentration sensor is the second concentration.

[0173] It should be explained that the gas emission index reflects the magnitude of the gas emission risk; the higher the gas emission index, the greater the gas emission risk.

[0174] S7. Calculate the disaster warning score based on the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, solidity coefficient, and gas outflow risk index. Confirm the risk level based on the disaster warning score and complete the gas disaster warning.

[0175] In detail, the calculation formula for the disaster early warning score is as follows:

[0176]

[0177] in, Indicates the disaster early warning score. Indicates gas pressure, The stress impact index indicates the impact of stress. Indicates the influence coefficient of outflow velocity. The index indicates the influence of hardness. This indicates the strength coefficient.

[0178] It should be explained that the firmness coefficient reflects the hardness of the coal sample. The smaller the firmness coefficient, the softer the coal sample, and the more likely it is to cause a gas outburst accident. The gas emission risk index reflects the magnitude of the gas emission risk. The larger the gas emission index, the greater the gas emission risk and the more likely it is to cause a gas outburst accident. Therefore, the disaster warning score is a comprehensive indicator used to assess the risk of gas disasters. The higher the disaster warning score, the greater the risk of gas disasters.

[0179] In detail, the determination of risk level based on disaster early warning score includes:

[0180] Compare the disaster warning score with the preset first warning threshold. If the disaster warning score is greater than or equal to the first warning threshold, the risk level is high risk.

[0181] If the disaster warning score is less than the first warning threshold, then the disaster warning score is compared with the preset second warning threshold. If the disaster warning score is greater than or equal to the first warning threshold, then the risk level is medium risk.

[0182] Otherwise, the risk level is low.

[0183] It should be explained that both the first and second warning thresholds are values ​​set manually by the coal mine engineers at the coal mine plant.

[0184] For example, once the risk level is obtained, Xiao Zhang can formulate corresponding response measures based on the risk level and complete the cloud-based early warning of gas disasters.

[0185] To address the problems described in the background section, this invention obtains multiple historical coal mine data sets, including historical gas pressure, historical coal hardness, historical gas emission velocity, and historical gas outburst frequency. This invention, by acquiring historical coal mine operational data, facilitates the subsequent determination of the influence coefficients of each indicator based on the historical data. Furthermore, it identifies discretized data based on multiple historical coal mine data sets. This invention also discretizes the historical data to facilitate subsequent analysis using correlation analysis algorithms. Based on the discretized data and a pre-constructed correlation analysis algorithm, influence coefficients are determined, including pressure influence index, hardness influence index, and emission velocity influence index. The impact coefficients show that this embodiment of the invention analyzes discretized data using a pre-built correlation analysis algorithm to identify the pressure influence index, hardness influence index, and outburst velocity influence coefficient. This facilitates the subsequent accurate calculation of disaster early warning scores based on the pressure influence index, hardness influence index, and outburst velocity influence coefficient, improving the accuracy of gas disaster early warning. The gas state monitoring mechanism is also identified, comprising: a pressure sensor, a sealing gasbag, a crushing test machine, a gas flow meter, and a gas concentration sensor. This embodiment of the invention, by identifying the gas state monitoring mechanism, facilitates subsequent measurement of gas pressure using the pressure sensor and sealing gasbag within the gas state monitoring mechanism, and the use of the crushing test machine to measure the coal hardness... The gas emission rate is measured using a gas flow meter and a gas concentration sensor to obtain the coal mining area. Based on the coal mining area, pressure sensor, and sealing airbag, the gas pressure is confirmed. This embodiment of the invention involves drilling holes in the coal mining area and then using a pressure sensor and sealing airbag to confirm the gas pressure. Based on the coal mining area and a crushing test machine, the firmness coefficient is confirmed. This embodiment of the invention further crushes the coal sample using a crushing test machine to calculate the firmness coefficient of the coal sample. Based on the coal mining area, gas flow meter, and gas concentration sensor, the gas emission risk index is confirmed. This embodiment of the invention constructs a monitoring module to accurately measure gas emissions. The flow rate and gas concentration facilitate subsequent comprehensive calculation of the disaster early warning score based on gas pressure and stability coefficient, thus improving the accuracy of gas disaster early warning. The disaster early warning score is calculated based on the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, stability coefficient, and gas outflow risk index. Therefore, this embodiment of the invention comprehensively calculates the disaster early warning score by combining the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, stability coefficient, and gas outflow risk index. Based on the disaster early warning score, the risk level is then determined, completing the gas disaster early warning. Thus, this embodiment of the invention improves the accuracy of gas disaster early warning by determining the risk level through the disaster early warning score and then making deployment arrangements based on the risk level. Therefore, this invention can improve the accuracy of gas disaster early warning.

[0186] like Figure 2 The diagram shown is a functional block diagram of a gas disaster cloud early warning system based on multi-dimensional data driving, provided in an embodiment of the present invention.

[0187] The gas disaster cloud early warning system 100 based on multidimensional data-driven technology described in this invention can be installed in an electronic device. Depending on the functions implemented, the gas disaster cloud early warning system 100 may include a historical data processing module 101, an influence coefficient confirmation module 102, a gas status monitoring module 103, and a gas disaster early warning module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0188] The historical data processing module 101 is used to acquire multiple historical coal mine data, including historical gas pressure, historical coal hardness, historical gas emission rate and historical gas outburst frequency, and to identify discretized data based on multiple historical coal mine data.

[0189] The influence coefficient confirmation module 102 is used to confirm the influence coefficients based on discretized data and a pre-built correlation analysis algorithm. The influence coefficients include: pressure influence index, hardness influence index and outflow velocity influence coefficient.

[0190] The gas status monitoring module 103 is used to identify the gas status monitoring mechanism, which includes: a pressure sensor, a sealing airbag, a crushing test machine, a gas flow meter, and a gas concentration sensor. It acquires the coal mining area, identifies the gas pressure based on the coal mining area, the pressure sensor, and the sealing airbag, identifies the solidity coefficient based on the coal mining area and the crushing test machine, and identifies the gas emission risk index based on the coal mining area, the gas flow meter, and the gas concentration sensor.

[0191] The gas disaster early warning module 104 is used to calculate the disaster early warning score based on the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, solidity coefficient, and gas outflow risk index, and to confirm the risk level based on the disaster early warning score, thereby completing the gas disaster early warning.

[0192] In detail, the modules in the multi-dimensional data-driven gas disaster cloud early warning system 100 described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the multi-dimensional data-driven gas disaster cloud early warning method described in the article and can produce the same technical effect, so it will not be repeated here.

[0193] like Figure 3The diagram shown is a structural schematic of an electronic device for implementing a multi-dimensional data-driven cloud-based early warning method for gas disasters, according to an embodiment of the present invention.

[0194] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a gas disaster cloud early warning method program based on multidimensional data driven.

[0195] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a gas disaster cloud early warning method program based on multi-dimensional data driving, but also to temporarily store data that has been output or will be output.

[0196] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a gas disaster cloud early warning method program based on multi-dimensional data driving), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0197] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0198] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0199] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0200] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0201] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0202] The gas disaster cloud early warning method program based on multi-dimensional data driven by memory 11 stored in the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0203] Acquire data from multiple historical coal mines, including historical gas pressure, historical coal hardness, historical gas emission velocity, and historical gas outburst frequency.

[0204] Discretized data was identified based on data from multiple historical coal mines;

[0205] The influence coefficients were identified based on discretized data and a pre-built correlation analysis algorithm. These influence coefficients include: pressure influence index, hardness influence index, and outflow velocity influence coefficient.

[0206] The gas status monitoring mechanism was identified, which includes: pressure sensor, sealing airbag, crushing test machine, gas flow meter and gas concentration sensor;

[0207] The coal mining area is obtained, and the gas pressure is confirmed based on the coal mining area, pressure sensors, and sealing airbags.

[0208] The firmness coefficient was determined based on the coal mining area and the crushing test machine.

[0209] Based on the coal mining area, gas flow meter, and gas concentration sensor, the gas emission risk index was determined.

[0210] The disaster early warning score is calculated based on the pressure impact index, hardness impact index, outflow velocity impact coefficient, gas pressure, solidity coefficient, and gas outflow risk index.

[0211] Based on the disaster early warning score, the risk level is determined, and the gas disaster early warning is completed.

[0212] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0213] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0214] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0215] Acquire data from multiple historical coal mines, including historical gas pressure, historical coal hardness, historical gas emission velocity, and historical gas outburst frequency.

[0216] Discretized data was identified based on data from multiple historical coal mines;

[0217] The influence coefficients were identified based on discretized data and a pre-built correlation analysis algorithm. These influence coefficients include: pressure influence index, hardness influence index, and outflow velocity influence coefficient.

[0218] The gas status monitoring mechanism was identified, which includes: pressure sensor, sealing airbag, crushing test machine, gas flow meter and gas concentration sensor;

[0219] The coal mining area is obtained, and the gas pressure is confirmed based on the coal mining area, pressure sensors, and sealing airbags.

[0220] The firmness coefficient was determined based on the coal mining area and the crushing test machine.

[0221] Based on the coal mining area, gas flow meter, and gas concentration sensor, the gas emission risk index was determined.

[0222] The disaster early warning score is calculated based on the pressure impact index, hardness impact index, outflow velocity impact coefficient, gas pressure, solidity coefficient, and gas outflow risk index.

[0223] Based on the disaster early warning score, the risk level is determined, and the gas disaster early warning is completed.

[0224] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0225] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0226] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0227] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0228] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A gas disaster cloud early warning method based on multidimensional data-driven approach, characterized in that, The method includes: Acquire data from multiple historical coal mines, including historical gas pressure, historical coal hardness, historical gas emission velocity, and historical gas outburst frequency. Discretized data was identified based on data from multiple historical coal mines; The influence coefficients were identified based on discretized data and a pre-built correlation analysis algorithm. These influence coefficients include: pressure influence index, hardness influence index, and outflow velocity influence coefficient. The gas status monitoring mechanism was identified, which includes: pressure sensor, sealing airbag, crushing test machine, gas flow meter and gas concentration sensor; The coal mining area is obtained, and the gas pressure is confirmed based on the coal mining area, pressure sensors, and sealing airbags. The firmness coefficient was determined based on the coal mining area and the crushing test machine. Based on the coal mining area, gas flow meters, and gas concentration sensors, a gas emission risk index was determined, including: The flow guide pipe and negative pressure guide chamber are obtained. The negative pressure guide chamber includes an airflow inlet and an airflow outlet. The monitoring module is identified based on the flow guide pipe, negative pressure guide chamber, gas flow meter and gas concentration sensor. Based on the identification of multiple monitoring locations within the coal mining area, the following operations were performed on each of these locations: Based on preset time thresholds, monitoring modules, and monitoring locations, the gas emission index is determined, including: The monitoring module is activated, and the gas flow meter in the activated monitoring module is used to monitor the monitoring location to obtain the first flow velocity; The test time is obtained by recording the time in real time starting from the time when the first flow velocity is obtained. When the test time reaches the time threshold, the gas flow meter and gas concentration sensor in the monitoring module after startup are used to monitor the monitoring position and obtain the second flow rate and the second concentration. The gas emission index is calculated based on the first flow velocity, the second flow velocity, and the second concentration, using the following formula: ； in, Indicates the gas emission index, Indicates the first flow velocity. Indicates the second flow velocity. Indicates the second concentration. It is a natural constant. The preset concentration index, The preset acceleration adjustment parameters, The preset acceleration threshold; By summing up the gas emission indices, multiple gas emission indices are obtained; A gas emission risk index was identified based on multiple gas emission indices, among which the gas emission risk index is the largest gas emission index among the multiple gas emission indices; The disaster early warning score is calculated based on the pressure impact index, hardness impact index, outflow velocity impact coefficient, gas pressure, solidity coefficient, and gas outflow risk index. Based on the disaster early warning score, the risk level is determined, and the gas disaster early warning is completed.

2. The gas disaster cloud early warning method based on multi-dimensional data-driven approach as described in claim 1, characterized in that, The discretized data identified based on multiple historical coal mine data includes: Multiple historical gas pressures, coal hardness, gas emission rates, and gas outburst frequencies were extracted from multiple historical coal mine data. Discretized pressure data is determined based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressures. Discrete hardness data is determined based on a preset first hardness threshold, a preset second hardness threshold, and multiple historical coal hardness values. Discretized velocity data is determined based on a preset first velocity threshold, a preset second velocity threshold, and multiple historical gas emission velocities. Discretized frequency data were identified based on a preset first frequency threshold, a preset second frequency threshold, and multiple historical gas outburst frequencies. Discretized pressure data, discretized hardness data, discretized speed data, and discretized frequency data are mapped to obtain discretized data, where each of the discretized pressure data, discretized hardness data, discretized speed data, and discretized frequency data corresponds one-to-one.

3. The gas disaster cloud early warning method based on multi-dimensional data-driven approach as described in claim 2, characterized in that, The discretized pressure data, determined based on a preset first pressure threshold, a preset second pressure threshold, and multiple historical gas pressures, includes: For each of the multiple historical gas pressures, perform the following operation: Compare the historical gas pressure with the first pressure threshold. If the historical gas pressure is greater than or equal to the first pressure threshold, then the preset first value is used as the discrete pressure value. If the historical gas pressure is less than the first pressure threshold and the historical gas pressure is greater than the second pressure threshold, then the preset second value will be used as the discrete pressure value. Otherwise, the preset third value will be used as the discrete pressure value; By summing the discrete pressure values, discretized pressure data is obtained.

4. The gas disaster cloud early warning method based on multi-dimensional data-driven approach as described in claim 3, characterized in that, The determination of gas pressure based on the coal mining area, pressure sensors, and sealing airbags includes: Horizontal drilling was performed in the coal mining area to obtain pressure test holes; The test length and test hole diameter are determined based on the pressure test hole, where the test length is the depth of the pressure test hole and the test hole diameter is the inner diameter of the pressure test hole. The pressure test hole is uniformly divided based on the preset division length to obtain n test areas; Calculate the cavity volume based on the segment length and test aperture; Confirm the coal seam temperature and calculate the gas volume based on the cavity volume and coal seam temperature; Extract the i-th test region from n test regions; A pressure sensor is installed at a preset first position in the i-th test area, and a sealing airbag is installed at a preset second position in the i-th test area to obtain a pressure test area. The sealing airbag includes an air injection port. Based on the gas volume and injection port, gas is injected into the pressure test area to obtain the target area; The pressure sensor is activated to monitor the pressure in the target area and obtain the area pressure value; Return to the step of extracting the i-th test area from n test areas, until i=n, ​​and summarize the area pressure values ​​to obtain multiple area pressure values; The gas pressure was determined based on multiple regional pressure values, with the gas pressure being the highest regional pressure value among the multiple regional pressure values.

5. The gas disaster cloud early warning method based on multi-dimensional data-driven approach as described in claim 4, characterized in that, The solidity coefficient determined based on the coal mining area and the crushing test machine includes: Coal samples were taken from the coal mining area. The coal sample was dried to obtain a dried sample; Determine the original weight of the dried sample; The dry sample was subjected to impact crushing using a crushing tester to obtain a crushed sample. The broken sample is sieved using a pre-constructed sieve to obtain a sieved sample; Confirm the sieving weight of the sieved sample; The strength factor is calculated based on the original weight and the weight after screening.

6. The gas disaster cloud early warning method based on multi-dimensional data-driven approach as described in claim 5, characterized in that, The monitoring module, identified based on the flow diversion pipe, negative pressure guiding chamber, gas flow meter, and gas concentration sensor, includes: Connect the flow guide pipe to the airflow inlet of the negative pressure guidance chamber to obtain the target guidance chamber; A gas flow meter and a gas concentration sensor are installed at the airflow outlet of the target guidance chamber to obtain a monitoring module.

7. A multi-dimensional data-driven cloud early warning system for gas disasters used in the method of claim 1, characterized in that, The system includes: The historical data processing module is used to acquire multiple historical coal mine data, including historical gas pressure, historical coal hardness, historical gas emission rate, and historical gas outburst frequency. Discretized data is identified based on multiple historical coal mine data. The influence coefficient confirmation module is used to confirm the influence coefficients based on discretized data and pre-built correlation analysis algorithms. The influence coefficients include: pressure influence index, hardness influence index and outflow velocity influence coefficient. The gas status monitoring module is used to identify the gas status monitoring mechanism, which includes: a pressure sensor, a sealing airbag, a crushing test machine, a gas flow meter, and a gas concentration sensor. It acquires the coal mining area, determines the gas pressure based on the coal mining area, pressure sensor, and sealing airbag, determines the solidity coefficient based on the coal mining area and crushing test machine, and determines the gas emission risk index based on the coal mining area, gas flow meter, and gas concentration sensor. The gas disaster early warning module is used to calculate the disaster early warning score based on the pressure influence index, hardness influence index, outflow velocity influence coefficient, gas pressure, solidity coefficient, and gas outflow risk index. Based on the disaster early warning score, the risk level is determined, and the gas disaster early warning is completed.

Images