Coal Spontaneous Combustion and Gas Coupling Early Warning Method, Device, Medium and Equipment

Abstract

The present invention discloses a coupling early warning method, device, medium and equipment for coal spontaneous combustion and gas in goafs, relating to the technical field of coal mine safety production. The method includes: constructing a dataset of disaster characteristic parameters for the coupling of coal spontaneous combustion and gas in goafs; for each disaster characteristic parameter, training the inversion model corresponding to the disaster characteristic parameter by using multiple alternative training algorithms to obtain multiple trained inversion models, and determining the optimal inversion model based on the multiple trained inversion models; using the optimal inversion model to invert the disaster characteristic parameter to obtain the inversion result of each disaster characteristic parameter; and according to the inversion result, performing hierarchical early warning on the risk of the coupling of coal spontaneous combustion and gas in goafs. Through the above solution, the accuracy of early warning of the risk of the coupling of coal spontaneous combustion and gas in goafs can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine safety production, and particularly to a coupling early warning method, device, medium and equipment for coal spontaneous combustion and gas in a goaf. Background Art

[0002] During the coal mine production process, gas explosion accidents caused by coal spontaneous combustion occur frequently, seriously endangering the safety of workers. The goaf is a high-incidence area of coal spontaneous combustion and also the area most prone to gas accumulation. Therefore, it is the key area for the prevention and control of the coupling disaster risk of coal spontaneous combustion and gas. The coupling of coal spontaneous combustion and gas disasters in the goaf has the characteristics of concealment, dynamics, complexity and suddenness. Its disaster-causing mechanism is extremely complex, and the risk is high, the identification is difficult, and the early warning is difficult.

[0003] Currently, the most commonly used methods for early warning of the coupling disaster risk of coal spontaneous combustion and gas in the goaf are the temperature index method and the gas index method (including the multi-gas combination index method). The core of risk early warning is to infer the risk level based on the monitored values of the indicators. According to the different positions of the index monitoring points, the monitoring methods for the coupling disaster risk of coal spontaneous combustion and gas in the goaf can be divided into two types: internal monitoring in the goaf and external monitoring outside the goaf. "Internal monitoring" means setting measuring points inside the goaf to continuously monitor the temperature or gas component changes at specific positions. Although this method can directly obtain the internal information of the goaf and then directly determine the risk of coal spontaneous combustion and gas disasters near the measuring points, the technical difficulty and cost of setting and maintaining the measuring points are high. Since it cannot be guaranteed that the high-temperature point or explosive point will definitely appear near the measuring points, especially when the measuring points are far from the actual high-temperature point or explosive point, it is easy to underestimate the coupling disaster risk of coal spontaneous combustion and gas in the goaf, resulting in low accuracy in early warning of the coupling disaster risk of coal spontaneous combustion and gas in the goaf. "External monitoring" means setting the measuring points outside the goaf, such as in the intake and return air roadways or intake and return air corners of the mining face, etc. Since the technical difficulty and cost of setting and maintaining the measuring points are small, it is the main method for daily monitoring of the risk of coal spontaneous combustion and gas disasters in the goaf. However, the external monitoring method cannot directly obtain the internal information of the goaf. Due to the very complex flow field inside the goaf and the transport process of various gas components, as well as the evolution mechanism of the coupling disaster of coal spontaneous combustion and gas, the existing early warning methods based on external monitoring of the goaf can only infer the general trend of the oxidation and self-heating of the residual coal in the goaf or the general range of the goaf temperature, and the accuracy of early warning of the coupling disaster risk of coal spontaneous combustion and gas in the goaf is not high.

[0004] In summary, the existing methods cannot accurately early warn the coupling disaster risk of coal spontaneous combustion and gas in the goaf. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, medium and equipment for coupling early warning of coal spontaneous combustion and gas in goafs to solve the technical problem that the existing methods cannot accurately predict the risk of the coupling disaster of coal spontaneous combustion and gas in goafs.

[0006] The present invention adopts the following technical solutions:

[0007] In the first aspect, the present invention provides a method for coupling early warning of coal spontaneous combustion and gas in goafs, and the method includes:

[0008] Construct a dataset of disaster characteristic parameters for the coupling of coal spontaneous combustion and gas in goafs, where the dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters, and the disaster characteristic parameters include high-temperature point characteristic parameters in the goaf and gas explosion hazard area characteristic parameters;

[0009] For each disaster characteristic parameter, using the multiple environmental parameters as inputs and the disaster characteristic parameter as the output, train the inversion model corresponding to the disaster characteristic parameter using multiple alternative training algorithms to obtain multiple trained inversion models, and determine the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; use the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion result of each disaster characteristic parameter;

[0010] According to the inversion result, conduct hierarchical early warning on the risk of the coupling of coal spontaneous combustion and gas in the goaf.

[0011] Further, the high-temperature point characteristic parameters in the goaf include: the temperature value and three-dimensional coordinates of the high-temperature points in the intake half area, and the temperature value and three-dimensional coordinates of the high-temperature points in the return air half area; the gas explosion hazard area characteristic parameters include: the volume of the gas explosion hazard area, the three-dimensional coordinates of the explosion-prone points, and the volume fractions of various types of gases in the mixed gas;

[0012] Among them, the intake half area and the return air half area are divided with the dip center plane of the goaf as the dividing surface; the gas explosion hazard area is the area in the goaf where the porosity is greater than the critical porosity and the mixed gas is explosive, and the mixed gas includes oxygen, methane, carbon monoxide, carbon dioxide and nitrogen; the explosion-prone point is the location where the methane concentration is the maximum in the gas explosion hazard area.

[0013] Further, the multiple environmental parameters include the coal seam parameters, roof parameters, mining parameters, face ventilation parameters, goaf gas emission parameters, remaining coal distribution parameters and face environment parameters of the goaf, and the construction method of the dataset of disaster characteristic parameters specifically includes:

[0014] Determine the levels and level values of the multiple environmental parameters according to the on-site environment of the goaf, and determine the test plan and the number of tests according to the levels and level values;

[0015] Establish a three-dimensional numerical model of the goaf according to the test plan, and perform computer simulation tests on the spontaneous oxidation process of the residual coal in the goaf based on the three-dimensional numerical model and the number of tests to obtain simulation results;

[0016] Based on the simulation results, extract the environmental parameters of the intake corner, return air corner of the mining face and the corresponding disaster characteristic parameter values;

[0017] Based on the environmental parameters of the intake corner, return air corner of the mining face and the disaster characteristic parameter values and the values of each environmental parameter, obtain data samples, and construct the disaster characteristic parameter data set based on the data samples;

[0018] Among them, the coal seam parameters include coal seam thickness and coal seam dip angle; the roof parameters include the thickness of the immediate roof and the length of the caving rock mass of the main roof; the mining parameters include the length of the mining face, the height of the mining face, and the roof control distance; the ventilation parameters of the mining face include the air volume of the mining face, the friction resistance coefficient, and the ventilation method; the gas emission parameters of the goaf include methane emission and carbon dioxide emission; the residual coal distribution parameters include the width and thickness of each residual coal strip; the environmental parameters of the mining face include the temperature and gas concentration of the intake airway, intake corner and return air corner of the mining face.

[0019] Furthermore, for each disaster characteristic parameter, using the multiple environmental parameters as inputs and the disaster characteristic parameter as the output, use multiple alternative training algorithms to train the inversion model corresponding to the disaster characteristic parameter, obtain multiple trained inversion models, and determine the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; use the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion results of each disaster characteristic parameter, specifically including:

[0020] Take the j th disaster characteristic parameter in the disaster characteristic parameter data set as the dependent variable, and take the coal seam parameters, the roof parameters, the mining parameters, the ventilation parameters of the mining face, the residual coal distribution parameters, the intake environment parameters of the mining face, the intake corner environment parameters of the mining face and the return air corner environment parameters of the mining face as independent variables, and use each alternative training algorithm in the multiple alternative training algorithms to train the inversion model of the j th disaster characteristic parameter respectively, to obtain the inversion models of each alternative training algorithm for the jAn inversion model for disaster characteristic parameters, where the alternative training algorithms include a lightweight gradient boosting machine algorithm, a fast tree algorithm, and a fast forest algorithm. j is a positive integer, 1 ≦ j ≦ N, and N is the number of disaster characteristic parameters;

[0021] Obtain the determination coefficient of the inversion model of each alternative training algorithm for the j th disaster characteristic parameter, and determine the inversion model with the largest determination coefficient as the optimal inversion model for the j th disaster characteristic parameter;

[0022] Input the actual values of the independent variables into the optimal inversion model for inversion to obtain the temperature values and three-dimensional coordinates of the high-temperature points in the intake half area of the gob area, the temperature values and three-dimensional coordinates of the high-temperature points in the return air half area, the volume of the gas explosion danger area, the three-dimensional coordinates of the explosion-prone points, and the volume fractions of various types of gases in the mixed gas.

[0023] Furthermore, based on the inversion results, perform hierarchical early warning on the risk of coal spontaneous combustion and gas coupling in the gob area, specifically including:

[0024] Compare the temperature values of the high-temperature points in the intake half area with the temperature values of the high-temperature points in the return air half area, and determine the high-temperature point with the higher temperature value as the high-temperature point of the gob area according to the comparison result, and calculate the Euclidean distance between the high-temperature point and the explosion-prone point;

[0025] Determine the temperature value of the high-temperature point in the gob area, the volume of the gas explosion danger area, the volume fraction of methane at the explosion-prone point, and the Euclidean distance between the high-temperature point and the explosion-prone point as the basic risk factor set, and perform a first-level fuzzy comprehensive evaluation based on the basic risk factor set and the evaluation set to obtain a comprehensive evaluation vector;

[0026] Based on the comprehensive evaluation vector, use the principle of maximum membership degree to determine the current risk early warning level of the gob area.

[0027] Furthermore, after determining the inversion model with the largest determination coefficient as the optimal inversion model for the j th disaster characteristic parameter, it further includes:

[0028] Test the performance of the optimal inversion model for the j th disaster characteristic parameter to obtain a test result;

[0029] In the case where the test result shows that the performance of the optimal inversion model is less than the preset performance index, further optimize the inversion model for the j th disaster characteristic parameter.

[0030] In a second aspect, the present invention provides a coupling early warning device for coal spontaneous combustion and gas in a gob area, comprising:

[0031] A construction module for constructing a dataset of disaster characteristic parameters for the coupling of coal spontaneous combustion and gas in a gob area, where the dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters, and the disaster characteristic parameters include gob high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters;

[0032] An inversion module for, for each disaster characteristic parameter, using multiple alternative training algorithms to train the inversion model corresponding to the disaster characteristic parameter with the multiple environmental parameters as inputs and the disaster characteristic parameter as the output, obtaining multiple trained inversion models, and determining the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; using the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion result of each disaster characteristic parameter;

[0033] An early warning module for grading and warning the risk of the coupling of coal spontaneous combustion and gas in the gob area according to the inversion result.

[0034] The present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the coupling early warning method for coal spontaneous combustion and gas in a gob area is implemented.

[0035] The present invention provides a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the coupling early warning method for coal spontaneous combustion and gas in a gob area is implemented.

[0036] The at least one technical solution adopted by the present invention can achieve the following beneficial effects: By constructing a dataset of disaster characteristic parameters for the coupled coal spontaneous combustion and gas in the goaf, the dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters; for each disaster characteristic parameter, using multiple environmental parameters as inputs and the disaster characteristic parameter as the output, multiple alternative training algorithms are used to train the inversion model corresponding to the disaster characteristic parameter, obtaining multiple trained inversion models, and based on the multiple trained inversion models, the optimal inversion model corresponding to the disaster characteristic parameter is determined; using the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter, obtaining the inversion results of each disaster characteristic parameter; according to the inversion results, a risk classification and early warning for the coupled coal spontaneous combustion and gas in the goaf is carried out. Through the above solution, multiple alternative training algorithms can be used to train the inversion models for each type of disaster characteristic parameter in the dataset of disaster characteristic parameters respectively, obtaining the optimal inversion models with the best inversion effects respectively associated with different types of disaster characteristic parameters, so as to accurately invert different types of disaster characteristic parameters and obtain accurate inversion results of the high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters in the goaf. The accurate inversion results of the high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters in the goaf can not only reflect the coal oxidation self-heating and gas accumulation states in the goaf and the coupled disaster risk of coal spontaneous combustion and gas, but also reveal the evolution process of the high-temperature points and gas explosion hazard areas and the change trend of the coupled disaster risk of coal spontaneous combustion and gas. Carrying out a risk classification and early warning for the coupled coal spontaneous combustion and gas disaster in the goaf according to the accurate inversion results of the high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters in the goaf can improve the accuracy of the early warning for the coupled coal spontaneous combustion and gas disaster in the goaf. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0038] Figure 1 It is a schematic flowchart of the method for warning the coupled coal spontaneous combustion and gas in the goaf provided by the present invention;

[0039] Figure 2 It is a comparison chart of the predicted values and sample values of the inversion model of the disaster characteristic parameters provided by the present invention;

[0040] Figure 3 It is a schematic diagram of the device for warning the coupled coal spontaneous combustion and gas in the goaf provided by the present invention;

[0041] Figure 4 It is a schematic diagram of a computer device for implementing the method for warning the coupled coal spontaneous combustion and gas in the goaf provided by the present invention. Specific Embodiments

[0042] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0043] At present, the server mentioned in the present invention can be a server set up on a service platform, or a device such as a desktop computer or a notebook computer that can execute the solution of the present invention. For the convenience of description, the following will only be described with the server as the execution subject.

[0044] Before introducing the specific embodiments of the present invention in detail, the abbreviations of the terms used in the present invention are explained as follows:

[0045] "Goaf" refers to the goaf of a coal mining face, "mining face" refers to a coal mining face or a longwall face, and "high temperature point" refers to the highest temperature point.

[0046] The following will detail the technical solutions provided by the specific embodiments of the present invention in conjunction with the drawings.

[0047] Figure 1 It is a schematic flow chart of the method for coupling early warning of coal spontaneous combustion and gas in the goaf of the present invention, which specifically includes the following steps:

[0048] S10: Construct a dataset of disaster characteristic parameters for the coupling of coal spontaneous combustion and gas in the goaf. The dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters. The disaster characteristic parameters include high temperature point characteristic parameters in the goaf and gas explosion dangerous area characteristic parameters.

[0049] In this embodiment, the high temperature point characteristic parameters in the goaf include: the temperature value and three-dimensional coordinates of the high temperature point in the intake air half area, and the temperature value and three-dimensional coordinates of the high temperature point in the return air half area; the gas explosion dangerous area characteristic parameters include: the volume of the gas explosion dangerous area, the three-dimensional coordinates of the explosion prone point, and the volume fractions of various types of gases in the mixed gas.

[0050] Among them, the intake air half area and the return air half area are divided with the dip center plane of the goaf as the dividing surface; the gas explosion dangerous area is the area in the goaf where the void ratio is greater than the critical void ratio and the mixed gas is explosive. The mixed gas contains oxygen, methane, carbon monoxide, carbon dioxide and nitrogen; the explosion prone point is the location where the maximum methane concentration in the gas explosion dangerous area is located.

[0051] In this embodiment, the critical void fraction refers to the minimum void fraction that allows the propagation of an explosion flame.

[0052] Specifically, the temperature value of the high-temperature point in the air inlet half-region T 1 and the three-dimensional coordinates ( x 1, y 1, z 1), and the temperature value of the high-temperature point in the return air half-region T 2 and the three-dimensional coordinates ( x 2, y 2, z 2) are determined as the characteristic parameters of the high-temperature points in the gob area. In this embodiment, the three-dimensional coordinates ( x 3 , y 3 , z 3 ) where the maximum value of the methane concentration (volume fraction) is located in the gas explosion hazard area are determined as the explosion-prone points. And the volume V exp of the gas explosion hazard area, the three-dimensional coordinates of the explosion-prone point ( x 3 , y 3 , z 3 ) and the volume fractions of various types of gases (oxygen, methane, carbon monoxide, carbon dioxide, and nitrogen) in the mixed gas are determined as the characteristic parameters of the gas explosion hazard area.

[0053] S20: For each disaster characteristic parameter, using multiple environmental parameters as inputs and the disaster characteristic parameter as the output, train the inversion model corresponding to the disaster characteristic parameter using multiple alternative training algorithms to obtain multiple trained inversion models, and determine the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; use the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion result of each disaster characteristic parameter.

[0054] In this embodiment, the optimal inversion model refers to the inversion model with the best inversion effect for various types of disaster characteristic parameters. The multiple alternative training algorithms include but are not limited to the lightweight gradient boosting machine algorithm, the fast tree algorithm, and the fast forest algorithm. Based on the inversion method of artificial intelligence, select the most suitable inversion model training algorithm for each type of disaster characteristic parameter from the multiple alternative training algorithms, and use the selected most suitable inversion model training algorithm to establish the optimal inversion model corresponding to each type of disaster characteristic parameter with the disaster characteristic parameter dataset.

[0055] S30: According to the inversion results, conduct a risk grading and early warning for the coupling risk of coal spontaneous combustion and gas in the gob area.

[0056] In this embodiment, a risk grading and early warning for the coupling of coal spontaneous combustion and gas in the gob area is carried out, specifically including:

[0057] S301: Compare the temperature value of the high-temperature point in the intake half area with the temperature value of the high-temperature point in the return air half area. According to the comparison result, determine the high-temperature point with the higher temperature value as the high-temperature point in the gob area, and calculate the Euclidean distance between the high-temperature point and the explosion-prone point.

[0058] Exemplarily, if the temperature value of the high-temperature point in the intake half area T 1 is greater than the temperature value of the high-temperature point in the return air half area T 2, then the temperature value of the high-temperature point in the gob area is T max = T 1, and the coordinates are ( x 1, y 1, z 1). The calculation expression of the Euclidean distance between the high-temperature point in the gob area and the explosion-prone point L is:

[0059] L = (1)

[0060] Wherein, L is the Euclidean distance between the high-temperature point in the gob area and the explosion-prone point, x 1, y 1, z 1 are the three-dimensional coordinates of the high-temperature point in the gob area, x 3 , y 3 , z 3 are the three-dimensional coordinates of the explosion-prone point.

[0061] S302: Determine the temperature value of the high-temperature point in the gob area, the volume of the gas explosion dangerous area, the volume fraction of methane at the explosion-prone point, and the Euclidean distance between the high-temperature point and the explosion-prone point as the basic risk factor set, and conduct a first-level fuzzy comprehensive evaluation based on the basic risk factor set and the evaluation set to obtain a comprehensive evaluation vector.

[0062] Specifically, define the basic risk factors for the coupling disaster of coal spontaneous combustion and gas in the gob area as: the highest temperature in the gob area T max , the volume of the gas explosion dangerous area V exp , the volume fraction of methane at the explosion-prone point X CH4 , the distance between the highest temperature point and the explosion-prone point L ; Take the basic factor set U ={T max , V exp , X CH4 , L [[ID=10}}, evaluation set V = {low risk, medium risk, medium-high risk, high risk, extremely high risk}, and conduct a first-level fuzzy comprehensive evaluation to obtain a comprehensive evaluation vector.

[0063] S303: Based on the comprehensive evaluation vector, use the principle of maximum membership degree to determine the current risk warning level of the goaf.

[0064] Specifically, according to the obtained comprehensive evaluation vector, use the principle of maximum membership degree to determine the current risk warning level of the goaf.

[0065] Exemplarily, the obtained comprehensive evaluation vector is B = B 1, B 2, B 3, B 4, B 5]. If B 3 is B the maximum value of 1 to B 5, then the current risk warning level of the coupled disaster of coal spontaneous combustion and gas in the goaf is "medium-high risk".

[0066] Based on Figure 1The gob coal spontaneous combustion and gas coupling early warning method shown. In the present invention, a dataset of disaster characteristic parameters for gob coal spontaneous combustion and gas coupling is constructed. The dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters. For each disaster characteristic parameter, using multiple environmental parameters as inputs and the disaster characteristic parameter as the output, multiple alternative training algorithms are used to train the inversion model corresponding to the disaster characteristic parameter, obtaining multiple trained inversion models, and based on the multiple trained inversion models, the optimal inversion model corresponding to the disaster characteristic parameter is determined. The optimal inversion model corresponding to the disaster characteristic parameter is used to invert the disaster characteristic parameter, obtaining the inversion results of each disaster characteristic parameter. According to the inversion results, a hierarchical early warning of the risk of gob coal spontaneous combustion and gas coupling is carried out. Through the above solution, multiple alternative training algorithms can be used to train the inversion models of each type of disaster characteristic parameter in the dataset of disaster characteristic parameters respectively, obtaining the optimal inversion models with the best inversion effects respectively associated with different types of disaster characteristic parameters, so as to accurately invert different types of disaster characteristic parameters and obtain accurate inversion results of the goaf high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters. The accurate inversion results of the goaf high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters can not only reflect the coal oxidation self-heating and gas accumulation states in the goaf and the risk of coal spontaneous combustion and gas coupling disasters, but also reveal the evolution process of the high-temperature points and gas explosion hazard areas and the change trend of the risk of coal spontaneous combustion and gas coupling disasters. Conducting a hierarchical early warning of the risk of gob coal spontaneous combustion and gas coupling disasters based on the accurate inversion results of the goaf high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters can improve the accuracy of early warning of the risk of gob coal spontaneous combustion and gas coupling disasters.

[0067] When applying the gob coal spontaneous combustion and gas coupling early warning method provided by the present invention, it is not necessary to execute according to Figure 1 the order of the steps shown. The specific execution order of each step can be determined as needed, and the present invention does not limit this.

[0068] In addition, in one or more embodiments of the present invention, the multiple environmental parameters include the coal seam parameters, roof parameters, mining parameters, face ventilation parameters, gob gas emission parameters, remaining coal distribution parameters, and face environment parameters of the gob. The construction method of the dataset of disaster characteristic parameters specifically includes:

[0069] Determine the number of levels and level values of the multiple environmental parameters according to the on-site environment of the gob, and determine the test plan and the number of tests according to the number of levels and level values.

[0070] Establish a three-dimensional numerical model of the gob according to the test plan, and conduct computer simulation tests on the process of remaining coal oxidation self-heating in the gob based on the three-dimensional numerical model and the number of tests to obtain the simulation results.

[0071] Based on the simulation results, extract the environmental parameters of the intake corner, return air corner of the coal face and the corresponding disaster characteristic parameter values.

[0072] Based on the environmental parameters of the intake corner and return air corner of the coal face, the disaster characteristic parameter values and the values of each environmental parameter, obtain data samples, and construct a disaster characteristic parameter data set based on the data samples.

[0073] Among them, the coal seam parameters include coal seam thickness and coal seam dip angle; the roof parameters include the thickness of the immediate roof and the length of the caving rock block of the main roof; the coal mining parameters include the length of the coal face, the height of the coal face and the roof control distance; the ventilation parameters of the coal face include the air volume of the coal face, the friction resistance coefficient and the ventilation method; the gas emission parameters in the goaf include methane emission and carbon dioxide emission; the remaining coal distribution parameters include the width and thickness of each remaining coal strip; the environmental parameters of the coal face include the temperature and gas concentration of the intake airway, intake corner and return air corner of the coal face.

[0074] In this embodiment, the coal seam parameters (thickness and dip angle), roof parameters (thickness of the immediate roof and length of the caving rock block of the main roof), coal mining parameters (length of the coal face, mining height and roof control distance), ventilation parameters of the coal face (air volume, friction resistance coefficient and ventilation method), gas emission parameters in the goaf (methane emission, carbon dioxide emission), remaining coal distribution parameters (width and thickness of each remaining coal strip) and environmental parameters of the coal face (temperature and gas concentration) are used as test variables, and referring to the coal mine site data, select the number of levels and level values of each type of test variable.

[0075] Exemplarily, take 2 levels for the coal seam thickness (9 m and 10 m), take 2 levels for the coal seam dip angle (25° and 30°), take 2 levels for the thickness of the immediate roof (3 m and 6 m), take 2 levels for the length of the caving rock block of the main roof (15 m and 20 m), take 2 levels for the length of the coal face (140 m and 150 m), take 1 level for the height of the coal face (3 m), take 1 level for the roof control distance of the coal face (7.5 m), take 3 levels for the air volume of the coal face (500 m 3 / min, 1500 m 3 / min, 2500 m 3 / min), take 1 level for the friction resistance coefficient of the coal face (0.035 kg / m 3 ), take 2 levels for the ventilation method (upward and downward), take 2 levels for the methane emission in the goaf (1.0 m 3 / min and 2.0 m 3 / min), take 2 levels for the carbon dioxide emission in the goaf (0.5 m 3 / min and 1.0 m 3( / min), one level is taken for the distribution parameters of the residual coal (multiple residual coal strips can be considered, with the width and thickness of each strip remaining unchanged, and specific parameter examples are omitted), and one level is taken for the air inlet environment parameters of the mining face (20 °C, and the volume fractions of oxygen and nitrogen are 0.21 and 0.79 respectively).

[0076] Exemplarily, for the 4 relatively important factors of the length of the caving rock block in the main roof, the air volume in the mining face, the methane emission in the goaf, and the carbon dioxide emission in the goaf, a total of 2×3×2×2 = 24 tests need to be carried out; for other factors, an orthogonal test is carried out. For example, the L8(2 7 ) orthogonal table can be used, and 8 tests need to be carried out; combining the full factorial test and the orthogonal test, a total of n = 24×8 = 192 tests need to be carried out.

[0077] Let the test number be i , and first let i = 1, and the test steps are as follows:

[0078] 1). According to the test conditions of the i -th test to be carried out (that is, the i-th combination of the test factor level values), establish a three-dimensional numerical model of the goaf, and carry out a computer simulation test on the oxidation and self-heating process of the residual coal in the goaf.

[0079] 2). Extract the air inlet and return air corner environment parameter values (temperature and gas concentration) of the mining face and the corresponding 8 characteristic parameter values of high-temperature points and 9 characteristic parameter values of gas explosion dangerous areas from the simulation results, combine them with the test factor values, respectively form a data sample of high-temperature points and a data sample of gas explosion dangerous areas, and add them to the corresponding data sets respectively.

[0080] 3). Let i = i + 1.

[0081] Repeat steps 1), 2), and 3) until i > n .

[0082] So far, a data set of high-temperature points in the goaf and a data set of gas explosion dangerous areas each containing 192 data samples have been established.

[0083] In addition, in one or more embodiments of the present invention, for each disaster characteristic parameter, with multiple environmental parameters as inputs and the disaster characteristic parameter as the output, multiple alternative training algorithms are used to train the inversion model corresponding to the disaster characteristic parameter, obtaining multiple trained inversion models, and based on the multiple trained inversion models, the optimal inversion model corresponding to the disaster characteristic parameter is determined; using the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter, obtaining the inversion results of each disaster characteristic parameter, specifically including:

[0084] Taking the j th disaster characteristic parameter in the disaster characteristic parameter dataset as the dependent variable, and taking coal seam parameters, roof parameters, mining parameters, face ventilation parameters, residual coal distribution parameters, face intake air environment parameters, face intake corner environment parameters, and face return corner environment parameters as independent variables, and respectively using each of the multiple alternative training algorithms in the multiple alternative training algorithms to train the inversion model of the j th disaster characteristic parameter, obtaining the inversion models of each alternative training algorithm with respect to the j th disaster characteristic parameter. The alternative training algorithms include lightweight gradient boosting machine algorithm, fast tree algorithm, and fast forest algorithm. j j is a positive integer, 1 ≤ j ≤ N, and N is the number of disaster characteristic parameters.

[0085] Obtaining the determination coefficients of the inversion models of each alternative training algorithm with respect to the j th disaster characteristic parameter, and determining the inversion model with the largest determination coefficient as the optimal inversion model of the j th disaster characteristic parameter.

[0086] Inputting the actual values of the independent variables into the optimal inversion model for inversion, obtaining the temperature value and three-dimensional coordinates of the high-temperature point in the intake half area of the goaf, the temperature value and three-dimensional coordinates of the high-temperature point in the return air half area, the volume of the gas explosion dangerous area, the three-dimensional coordinates of the explosion-prone point, and the volume fractions of various types of gases in the mixed gas.

[0087] Specifically, a total of 17 disaster characteristic parameter inversion models are established in this embodiment, that is, N is 17. They are respectively used to invert 17 types of disaster characteristic parameters. The 17 types of disaster characteristic parameters include: the temperature value T 1 and three-dimensional coordinates ( x 1, y 1, z 1), the temperature value T 2 and three-dimensional coordinates ( x 2, y 2, z 2), the volume of the gas explosion dangerous area V exp, the three-dimensional coordinates of the explosion-prone point ( x 3 , y 3 , z 3 ), and the oxygen concentration at the explosion-prone point X O2 , the methane concentration at the explosion-prone point X CH4 , the carbon monoxide concentration at the explosion-prone point X CO , the carbon dioxide concentration at the explosion-prone point X CO2 , the nitrogen concentration at the explosion-prone point X N2 .

[0088] a), Exemplarily, the number of known disaster characteristic parameters m = 17. Let the parameter number j = 1. Take the j rd disaster characteristic parameter as the dependent variable. Based on the dataset of disaster characteristic parameters containing the selected dependent variable, take the coal seam parameters, roof parameters, mining parameters, face ventilation parameters, residual coal distribution parameters, face intake air environment parameters, face intake corner environment parameters, and face return corner environment parameters as independent variables, and apply alternative training algorithms to train the inversion models corresponding to the dependent variable respectively, to obtain the inversion models corresponding to each training algorithm respectively.

[0089] b), Obtain the determination coefficients of the inversion models corresponding to each training algorithm respectively, and determine the inversion model with the largest determination coefficient as the optimal inversion model of the j th disaster characteristic parameter.

[0090] In this embodiment, the optimal inversion model refers to the inversion model that is most adapted to the j th disaster characteristic parameter and has the best inversion effect, that is, the optimal inversion model of the j th disaster characteristic parameter. Specifically, compare the determination coefficients ( R 2 ) of the inversion models corresponding to each training algorithm respectively, and take the training algorithm of the inversion model with the largest determination coefficient as the optimal training algorithm, and take the inversion model obtained based on the optimal training algorithm as the optimal inversion model of the j th disaster characteristic parameter.

[0091] c), Input the actual values of the independent variables into the optimal inversion model to invert the temperature values and three-dimensional coordinates of the high-temperature points in the intake half area of the goaf, the temperature values and three-dimensional coordinates of the high-temperature points in the return half area of the goaf, the volume of the gas explosion danger area, the three-dimensional coordinates of the explosion-prone point, and the volume fractions of various types of gases in the mixed gas.

[0092] In this embodiment, for the mined - out area as the evaluation object, the actual values of the independent variables collected (including the monitored values of the environmental parameters at the intake and return air corners of the mining face) are input into the optimal inversion model of the j th disaster characteristic parameter, and the temperature value of the high - temperature point in the intake half - area of the mined - out area, T 1, and the three - dimensional coordinates ( x 1, y 1, z 1) and the temperature value of the high - temperature point in the return - air half - area, T 2, and the three - dimensional coordinates ( x 2, y 2, z 2), the volume of the gas explosion - prone area, V exp , the coordinates of the explosion - prone point ( x 3, y 3, z 3), and the volume fractions of 5 gases in the explosion - prone point ( X O2 , X CH4 , X CO , X CO2 , and X N2 ) are respectively inverted.

[0093] Through this embodiment, the optimal inversion models with the best inversion effects can be constructed for different disaster characteristic parameters respectively, improving the accuracy of inverting various types of disaster characteristic parameters, obtaining more accurate parameters related to the coal spontaneous combustion and gas coupling disasters in the mined - out area, and thus enhancing the accuracy of warning the risk of coal spontaneous combustion and gas coupling disasters in the mined - out area. Moreover, there is no need to set measuring points inside the mined - out area by means of embedding or drilling. Usually, it is only necessary to monitor the environmental parameters of the intake air current and the intake and return air corners of the mining face, which is simple and easy to implement.

[0094] In addition, in one or more embodiments of the present invention, after determining the inversion model with the largest coefficient of determination as the optimal inversion model of the j th disaster characteristic parameter, it further includes:

[0095] Testing the performance of the optimal inversion model of the j th disaster characteristic parameter to obtain the test result.

[0096] In the case where the test result shows that the performance of the optimal inversion model is less than the preset performance index, further optimize the inversion model of the j th disaster characteristic parameter.

[0097] In this embodiment, with reference to Figure 2, with the sample values of the dependent variable (taking the temperature value at the high-temperature point in the air intake half area as an example) as the abscissa x , with the predicted values of the dependent variable as the ordinate y , plot a scatter diagram. If the vast majority of data points are distributed on the straight line y = x nearby, it means that the predicted values of the dependent variable output by the inversion model fit the sample values (actual values) of the dependent variable, indicating that the performance of the inversion model is good. If the vast majority of data points are far from the straight line y = x far away, it means that there is a large deviation between the predicted values of the dependent variable output by the inversion model and the sample values of the dependent variable, and the performance of the inversion model is poor. As can be seen from Figure 3 , the triangles (predicted values of the dependent variable) in the figure are all near the straight line y = x nearby, indicating that the performance of the inversion model is good.

[0098] If the performance of the optimal inversion model is good, let j = j + 1, and repeat steps a), b), and c) until j > m ; if the performance of the optimal inversion model is poor, then return to step 1), consider more test conditions, and expand the dataset of disaster characteristic parameters.

[0099] Through the solution of this embodiment, it can be ensured that the performance of the inversion models corresponding to various types of disaster characteristic parameters reaches the preset threshold, guaranteeing the inversion effect of the disaster characteristic parameters.

[0100] The above is the goaf coal spontaneous combustion and gas coupling early warning method provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding goaf coal spontaneous combustion and gas coupling early warning device, as shown in Figure 3 and includes:

[0101] A construction module for constructing a dataset of disaster characteristic parameters for goaf coal spontaneous combustion and gas coupling. The dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters. The disaster characteristic parameters include goaf high-temperature point characteristic parameters and gas explosion hazard area characteristic parameters.

[0102] An inversion module for, for each disaster characteristic parameter, using multiple environmental parameters as inputs and the disaster characteristic parameter as the output, training the inversion model corresponding to the disaster characteristic parameter using multiple alternative training algorithms to obtain multiple trained inversion models, and determining the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; using the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion results of each disaster characteristic parameter.

[0103] An early warning module for classifying and warning the risk of the coupling of coal spontaneous combustion and gas in the gob area according to the inversion result.

[0104] For the specific limitations of the coupling warning device for coal spontaneous combustion and gas in the gob area, reference can be made to the limitations of the coupling warning method for coal spontaneous combustion and gas in the gob area in the above text, which will not be elaborated here. Each module in the coupling warning device for coal spontaneous combustion and gas in the gob area can be implemented in whole or in part by software, hardware, and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0105] The present invention also provides a computer-readable storage medium storing a computer program, which can be used to execute Figure 1 The coupling warning method for coal spontaneous combustion and gas in the gob area provided.

[0106] The present invention also provides Figure 4 The structural schematic diagram of the computer device shown, as Figure 4 shown, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, other hardware required for other services may also be included. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement Figure 1 The coupling warning method for coal spontaneous combustion and gas in the gob area provided.

[0107] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memories. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. The volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0108] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in the present invention.

Claims

1. A coupling early warning method for coal spontaneous combustion and gas in goaf, characterized in that Including: Construct a dataset of disaster characteristic parameters for the coupled coal spontaneous combustion and gas in the goaf. The dataset of disaster characteristic parameters includes disaster characteristic parameters and multiple environmental parameters. The disaster characteristic parameters include the characteristic parameters of high-temperature points in the goaf and the characteristic parameters of gas explosion dangerous areas; The characteristic parameters of high-temperature points in the goaf include: the temperature values and three-dimensional coordinates of high-temperature points in the intake half area, and the temperature values and three-dimensional coordinates of high-temperature points in the return air half area; The characteristic parameters of gas explosion dangerous areas include: the volume of the gas explosion dangerous area, the three-dimensional coordinates of the explosion-prone points, and the volume fractions of various types of gases in the mixed gas; The multiple environmental parameters include the coal seam parameters, roof parameters, mining parameters, face ventilation parameters, goaf gas emission parameters, remaining coal distribution parameters, and face environment parameters of the goaf; For each disaster characteristic parameter, using the multiple environmental parameters as inputs and the disaster characteristic parameter as the output, use multiple alternative training algorithms to train the inversion model corresponding to the disaster characteristic parameter, obtain multiple trained inversion models, and determine the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; Use the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion results of each disaster characteristic parameter; According to the inversion results, conduct hierarchical early warning on the risk of the coupled coal spontaneous combustion and gas in the goaf; Among them, the construction method of the dataset of disaster characteristic parameters specifically includes: Determine the number of levels and level values of the multiple environmental parameters according to the on-site environment of the goaf, and determine the test plan and the number of tests according to the number of levels and level values; Establish a three-dimensional numerical model of the goaf according to the test plan, and conduct computer simulation tests on the self-heating process of the remaining coal in the goaf based on the three-dimensional numerical model and the number of tests to obtain simulation results; Based on the simulation results, extract the environmental parameters of the intake corner and the return air corner of the face and the corresponding disaster characteristic parameter values; Based on the environmental parameters of the intake corner and the return air corner of the face, the disaster characteristic parameter values, and the values of each environmental parameter, obtain data samples, and construct the dataset of disaster characteristic parameters based on the data samples.

2. The goaf coal spontaneous combustion and gas coupling early warning method according to claim 1, characterized in that, The intake half area and the return air half area are divided with the dip center plane of the goaf as the dividing surface; The gas explosion dangerous area is the area in the goaf where the void ratio is greater than the critical void ratio and the mixed gas is explosive. The mixed gas contains oxygen, methane, carbon monoxide, carbon dioxide, and nitrogen; The explosion-prone point is the location where the maximum methane concentration in the gas explosion dangerous area is located.

3. The goaf coal spontaneous combustion and gas coupling early warning method according to claim 1, characterized in that, The coal seam parameters include coal seam thickness and coal seam dip angle; the roof parameters include the thickness of the immediate roof and the length of the caving rock mass of the main roof; the mining parameters include the face length, face height, and roof control distance; the face ventilation parameters include the face air volume, friction resistance coefficient, and ventilation mode; the gob gas emission parameters include methane emission and carbon dioxide emission; the residual coal distribution parameters include the width and thickness of each residual coal strip; the face environment parameters include the temperature and gas concentration of the face intake airway, intake corner, and return corner.

4. The goaf coal spontaneous combustion and gas coupling early warning method according to claim 3, characterized in that For each disaster characteristic parameter, using the multiple environmental parameters as inputs and the disaster characteristic parameter as the output, multiple alternative training algorithms are used to train the inversion model corresponding to the disaster characteristic parameter, obtaining multiple trained inversion models, and based on the multiple trained inversion models, the optimal inversion model corresponding to the disaster characteristic parameter is determined; the optimal inversion model corresponding to the disaster characteristic parameter is used to invert the disaster characteristic parameter, obtaining the inversion results of each disaster characteristic parameter, specifically including: Taking the j th disaster characteristic parameter in the disaster characteristic parameter dataset as the dependent variable, and taking the coal seam parameters, the roof parameters, the mining parameters, the mining face ventilation parameters, the goaf coal distribution parameters, the intake air environment parameters of the mining face, the intake corner environment parameters of the mining face, and the return air corner environment parameters of the mining face as independent variables, using each of the multiple alternative training algorithms among the multiple alternative training algorithms to train the inversion model for the j th disaster characteristic parameter respectively, obtaining the inversion models of the respective alternative training algorithms for the j th disaster characteristic parameter, the alternative training algorithms including the lightweight gradient boosting machine algorithm, the fast tree algorithm, and the fast forest algorithm, j is a positive integer, 1 ≦ j ≦ N, and N is the number of disaster characteristic parameters; Obtain the determination coefficient of the inversion model of each alternative training algorithm with respect to the j th disaster characteristic parameter, and determine the inversion model with the largest determination coefficient as the optimal inversion model of the j th disaster characteristic parameter; Inputting the actual values of the independent variables into the optimal inversion model for inversion, obtaining the temperature value and three-dimensional coordinates of the high-temperature point in the intake half area of the gob, the temperature value and three-dimensional coordinates of the high-temperature point in the return half area of the gob, the volume of the gas explosion dangerous area, the three-dimensional coordinates of the explosion-prone point, and the volume fractions of various types of gases in the mixed gas.

5. The goaf coal spontaneous combustion and gas coupling early warning method according to claim 2, characterized in that According to the inversion results, the risk of coal spontaneous combustion and gas coupling in the gob is classified and warned, specifically including: Comparing the temperature value of the high-temperature point in the intake half area with the temperature value of the high-temperature point in the return half area, and based on the comparison result, determining the high-temperature point with the higher temperature value as the high-temperature point in the gob, and calculating the Euclidean distance between the high-temperature point and the explosion-prone point; Determining the temperature value of the high-temperature point in the gob, the volume of the gas explosion dangerous area, the volume fraction of methane at the explosion-prone point, and the Euclidean distance between the high-temperature point and the explosion-prone point as the basic risk factor set, and conducting a first-level fuzzy comprehensive evaluation based on the basic risk factor set and the evaluation set to obtain a comprehensive evaluation vector; Based on the comprehensive evaluation vector, using the maximum membership degree principle to determine the current risk warning level of the gob.

6. The goaf coal spontaneous combustion and gas coupling early warning method according to claim 4, characterized in that, After determining the inversion model with the largest coefficient of determination as the optimal inversion model for the j th disaster characteristic parameter, it further includes: Verify the performance of the optimal inversion model for the j th disaster characteristic parameter to obtain the verification results; In the case that the performance of the optimal inversion model is less than the preset performance index for the inspection result, further optimize the inversion model of the j th disaster characteristic parameter.

7. Goaf coal spontaneous combustion and gas coupling early warning device, characterized in that, Including: A construction module for constructing a dataset of disaster characteristic parameters for coal spontaneous combustion and gas coupling in the gob, the dataset of disaster characteristic parameters including disaster characteristic parameters and multiple environmental parameters, and the disaster characteristic parameters including high-temperature point characteristic parameters and gas explosion dangerous area characteristic parameters in the gob; The high-temperature point characteristic parameters in the gob include: the temperature value and three-dimensional coordinates of the high-temperature point in the intake half area, and the temperature value and three-dimensional coordinates of the high-temperature point in the return half area; the gas explosion dangerous area characteristic parameters include: the volume of the gas explosion dangerous area, the three-dimensional coordinates of the explosion-prone point, and the volume fractions of various types of gases in the mixed gas; the multiple environmental parameters include the coal seam parameters, roof parameters, mining parameters, face ventilation parameters, gob gas emission parameters, residual coal distribution parameters, and face environment parameters of the gob. An inversion module, for each disaster characteristic parameter, using the multiple environmental parameters as inputs and the disaster characteristic parameter as the output, training the inversion model corresponding to the disaster characteristic parameter by using multiple alternative training algorithms to obtain multiple trained inversion models, and determining the optimal inversion model corresponding to the disaster characteristic parameter based on the multiple trained inversion models; using the optimal inversion model corresponding to the disaster characteristic parameter to invert the disaster characteristic parameter to obtain the inversion result of each disaster characteristic parameter; A warning module, for grading and warning the risk of the coupling of coal spontaneous combustion and gas in the goaf according to the inversion result; Among them, the construction method of the disaster characteristic parameter data set specifically includes: Determining the number of levels and the level values of the multiple environmental parameters according to the on-site environment of the goaf, and determining the test scheme and the number of tests according to the number of levels and the level values; Establishing a three-dimensional numerical model of the goaf according to the test scheme, and performing a computer simulation test on the spontaneous oxidation and heating process of the residual coal in the goaf based on the three-dimensional numerical model and the number of tests to obtain a simulation result; Based on the simulation result, extracting the environmental parameters of the intake corner and the return corner of the mining face and the corresponding disaster characteristic parameter values; Based on the environmental parameters of the intake corner and the return corner of the mining face, the disaster characteristic parameter values and the values of each environmental parameter, obtaining a data sample, and constructing the disaster characteristic parameter data set based on the data sample.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, it implements the method for warning the coupling of coal spontaneous combustion and gas in the goaf according to any one of claims 1 to 6.

9. A computer device, characterized in that, It includes a memory, a processor and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method for warning the coupling of coal spontaneous combustion and gas in the goaf according to any one of claims 1 to 6.

Images