A coal seam gas parameter dynamic prediction method based on multi-source data fusion

Abstract

The present application relates to a kind of coal seam gas parameter dynamic prediction method based on multi-source data fusion, belong to coal mine safety field.The method includes the following steps: S1: gas parameter multi-source acquisition, the data obtained is analyzed by multi-source data fusion;S2: to the influencing factor analysis of coal seam gas occurrence, determine the main control factor of coal seam gas occurrence and geological unit division;S3: according to the effective gas parameter, the determined coal seam gas occurrence geological unit division and main control factor are based to establish gas parameter prediction model;S4: gas parameter prediction model is input into GIS platform to automatically generate gas parameter prediction contour;S5: corresponding gas parameter prediction contour is dynamically corrected using Kriging interpolation method on GIS platform.The method provided by the present application can realize timely and accurate control of coal seam gas occurrence state based on the coal seam gas parameters continuously exposed by mining activities, thereby laying a foundation for targeted prevention and control of gas disaster.

Description

Technical Field

[0001] This invention belongs to the field of coal mine safety and relates to a method for dynamic prediction of coal seam gas parameters based on multi-source data fusion. Background Technology

[0002] To ensure safe production in high-gas and outburst-prone mines, gas parameter testing is a crucial foundational task before mining activities and a primary basis for coal mine gas disaster prevention and drainage measures. Currently, coal mine gas parameters are mainly measured directly through drilling. Although significant progress has been made in gas parameter measurement technology and equipment, providing important support for gas disaster prevention, the drawbacks of this method are becoming increasingly apparent in the era of intelligent mining with ever-increasing mining speed and intensity. On the one hand, drilling prediction is complex and time-consuming, exacerbating the conflict between production and safety. On the other hand, drilling prediction is a static, point-based method that cannot provide timely and accurate information on the gas occurrence status of coal seams at the regional level. Therefore, dynamic prediction of gas parameters is of great significance for ensuring safe and efficient coal mining. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide a method for dynamic prediction of coal seam gas parameters based on multi-source data fusion, and to solve the technical problem of how to perform dynamic prediction of gas parameters.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A method for dynamic prediction of coal seam gas parameters based on multi-source data fusion: The method includes the following steps:

[0006] S1: Obtain the measured gas parameters from geological exploration and production, as well as the indirectly calculated gas parameters. Use a multi-source data fusion analysis method to correct the gas parameters obtained from the measured and indirectly calculated gas parameters to obtain the initial effective gas parameters.

[0007] S2: Analyze the influencing factors of coal seam gas occurrence, determine the main controlling factors of coal seam gas occurrence and the division of geological units;

[0008] S3: Based on the initial effective gas parameters obtained in S1, the main controlling factors of coal seam gas occurrence determined in S2, and the geological unit division, establish a gas parameter prediction model;

[0009] S4: Based on the Geographic Information System (GIS), a secondary development is carried out to obtain a GIS platform with automatic prediction function of gas parameters. The GIS platform stores all measured gas parameters, coal seam floor contour lines, and ground elevation point information in a unified database to form a basic information database for the mine.

[0010] Input the parameters of the gas parameter prediction model established in S3 into the data table of the GIS platform, and use the MathAnalyst function in the GIS platform to perform calculations to obtain the gas parameter raster.

[0011] Extract relevant gas parameters and predict contour lines using the ExtractIsoline function in the GIS platform;

[0012] S5: During the coal seam mining process, timely acquisition of measured gas parameters and indirectly calculated gas parameters, and correction of the gas parameters obtained from geological exploration measurement and indirect calculation using multi-source data fusion analysis methods to obtain effective gas parameters;

[0013] The effective gas parameters are input into the data table of the GIS platform. The GIS platform uses the Kriging interpolation method to dynamically correct the corresponding gas parameter prediction contour lines in S4, and continuously obtains the corrected gas parameter contour lines.

[0014] Furthermore, S1 specifically refers to:

[0015] Calculate the gas parameter correction coefficient η:

[0016]

[0017] Where η is the correction coefficient; A1~A n For the actual measured gas parameters of production; a1~a n For measured gas parameters in geological exploration and for indirectly calculated gas parameters; n is the number of comparisons;

[0018] Calculate the corrected effective gas parameters, a1'~a n ':

[0019]

[0020] The final initial effective gas parameters are:

[0021] N = {A1, A2, A3, ..., A} n ,a1',a2' a3' ……a n '} (3).

[0022] Furthermore, the gas parameters are gas content and gas pressure.

[0023] Furthermore, in S2, the influence of geological structural morphology, differences in roof and floor lithology, coal seam thickness and coal quality, magmatic intrusion, and changes in hydrogeological conditions within the mine area on the occurrence state of coal seam gas is analyzed to determine the main controlling factors of coal seam gas occurrence. Based on the comprehensive qualitative and quantitative analysis of gas and geological indicators, the mine gas geological units are divided.

[0024] Furthermore, the calculation formula for the gas parameter prediction model in S3 is as follows:

[0025] Y = f(x1, x2, ..., x) j (3)

[0026] Where f is a univariate or multivariate function; when there is one main controlling factor of gas occurrence, f represents a univariate function; when there are two or more main controlling factors of gas occurrence, f represents a multivariate function; x1, x2, ..., x j These are the main controlling factors of coal seam gas occurrence, and Y is the predicted gas parameter;

[0027] When there is only one controlling factor for gas occurrence: Y = f(x);

[0028] If it is a shallow mine, then it is a linear function in one variable, expressed as Y = ax + b, where a and b are constants;

[0029] For deep mines, a univariate nonlinear function is used, such as a power function, exponential function, logarithmic function, quadratic polynomial, or cubic polynomial. The nonlinear function with the best fit is selected based on the actual situation.

[0030] When there are two or more factors affecting gas occurrence: Y=k0+k1f(x1)+k2f(x2)+......+k n f(x n );

[0031] Where x1, x2, ..., x n These are the main controlling factors of coal seam gas occurrence, k0, k1, ... k n Let f(x1), f(x2), ..., f(x) be the relevant parameters. n () represents a univariate function model with different controlling factors.

[0032] Furthermore, in S5, the interpolation calculation formula for dynamic correction of gas parameters using the Kriging interpolation method is as follows:

[0033]

[0034] Where: Z*(x0) is the gas parameter value of the interpolated point, Z(x i D represents the known gas parameter value of the i-th sampling point, where i = 1, 2, ..., n, and n is the number of sampling points used for gas parameter interpolation. i x is the distance from the interpolated point to the i-th sampling point, x0 is the interpolated point number, x i Let p be the sampling point number, and p be a power of the distance, where p = 2.

[0035] The beneficial effects of this invention are as follows:

[0036] First, the dynamic prediction method for coal seam gas parameters provided by this invention can achieve timely and accurate control of the coal seam gas occurrence state based on the coal seam gas parameters continuously revealed by mining activities, thereby laying the foundation for targeted prevention and control of gas disasters.

[0037] Second, the gas parameter prediction contour lines and raster maps generated by this invention enable automatic prediction of coal seam gas parameters at any point within the mining area, and through the differentiated expression of color blocks, achieve a clear and intuitive expression of coal seam gas occurrence characteristics.

[0038] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0039] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein:

[0040] Fig. 1 This is a flowchart of a dynamic prediction method for coal seam gas parameters based on multi-source data fusion according to the present invention.

[0041] Figure 2 shows the gas parameter prediction model; Figure 2(a) shows the gas content prediction; Figure 2(b) shows the gas pressure prediction.

[0042] Fig. 3 A grid map of gas content;

[0043] Fig. 4 Comparison chart of gas content prediction model before and after update;

[0044] Figure labels: a - predicted contour lines of gas parameters, b - corrected contour lines of gas parameters, c - gas parameter values ​​at the interpolated points. Detailed Implementation

[0045] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0046] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0047] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0048] Please see Figs. 1-4 This is a dynamic prediction method for coal seam gas parameters based on multi-source data fusion.

[0049] This example illustrates the following: A certain mine is a high-gas mine with a designed production capacity of 8 million tons per year. The main coal seam is No. 8 coal seam, and the measured gas parameters of this coal seam are as follows: coal seam depth 122-663m, coal thickness 1.85-9.01m, average thickness 6.02m, average coal seam dip angle 3.5°. The geological structure within the mine area is simple, exhibiting a gently sloping monocline structure, and it has not been eroded by igneous rocks.

[0050] A dynamic prediction method for coal seam gas parameters based on multi-source data fusion includes the following steps:

[0051] Step 1: The system collects the gas content and gas pressure measurement results during the geological exploration of the No. 8 coal seam, the gas content and gas pressure results during the production period that were not affected by mining or were minimally affected by mining, and the indirectly calculated gas pressure and gas content. Using a multi-source data fusion analysis method, the gas parameters obtained from different sources are analyzed, invalid data is eliminated, and the corresponding data are fused and corrected to obtain as much effective gas pressure and gas content data as possible.

[0052] Among them, the measured gas parameters in production are the gas parameters obtained during the production process (new gas parameters are measured every day). The data for generating the measured gas parameters is accurate and does not require correction. The geological exploration measurements are the data obtained during the geological exploration stage in the early stage of mine construction. This data is limited and will not be added. The indirectly calculated gas parameters are obtained by back-calculation based on the basic parameters measured during production (including adsorption constants a and b, gas pressure, K1 value, etc.). The indirectly calculated parameters will also be continuously obtained as production continues.

[0053] Indirect calculations include: calculating gas content based on coal adsorption theory, calculating coal seam gas content based on residual gas content, inverting gas content based on gas emission rate, inverting gas content using the content coefficient method, and mutual inversion between gas pressure and gas content.

[0054] Step 2: Analyze the influencing factors of gas occurrence. The geological structure of this mine is simple, with exposed fault displacements all less than 5m and scour zone incision depths all less than 2m. The geological structure only affects gas occurrence within a small area of ​​the layout. The roof and floor of coal seam No. 8 are mostly coarse, medium, and fine-grained sandstone, with dense lithology and relatively stable lateral development, providing favorable conditions for gas sealing. Therefore, the lithology of the roof and floor has little impact on gas occurrence. The aquifers in the mine area are in a relatively closed state, with long-term stagnant flow and poor recharge conditions. The underground runoff is weak, and it basically maintains its original natural state undisturbed by human activities. Therefore, the hydrogeology has little impact on gas occurrence. The coal seam thickness is mainly thick, with little variation in coal seam occurrence, and there is no significant correlation between coal seam thickness and gas parameters. Therefore, the coal seam thickness has little impact on gas occurrence. The eastern part of the mine is shallower, with correspondingly lower gas parameters, while the southwestern part of the mine is deeper, and the gas parameters are significantly increased. It is evident that gas parameters all show an increasing trend with increasing coal seam depth, indicating a significant impact of coal seam depth on gas occurrence. In conclusion, the main controlling factor for gas occurrence in Coal Seam No. 8 is coal seam depth, and the geological conditions and coal seam occurrence state within the entire mining area are relatively stable, allowing it to be classified as a single geological unit.

[0055] Step 3, the division of gas geological units is the foundation for establishing the gas prediction model. If they are the same geological unit, the same gas pressure and gas content prediction model can be used. If the mining area is divided into multiple geological units, different gas pressure and gas content prediction models should be established according to the different geological units. Based on the analysis results of Step 2, a main controlling factor is obtained, namely the coal seam burial depth. The geological conditions and coal seam occurrence state in the entire mining area are relatively stable, so it can be divided into the same geological unit to establish a prediction model between coal seam burial depth and gas parameters. The results are shown in Figure 2, Figure 2(a), and Figure 2(b).

[0056] The gas content prediction model is as follows: Y W=0.0124H+0.354(R) 2 =0.8015);

[0057] The gas pressure prediction model is: Y P =0.0014H-0.1514(R) 2 =0.9039);

[0058] Among them, Y W Gas content, unit: m³ 3 / t;Y P Gas pressure, unit: MPa; H: coal seam depth, unit: m; R 2 Indicates the goodness of fit.

[0059] Step 4: In the GIS platform, the contour lines of the coal seam floor and the ground elevation points are digitized in advance, and the corresponding raster map is generated. The coal seam depth raster is obtained through automatic raster calculation (coal seam depth = ground elevation - coal seam floor elevation), and the coal seam depth contour lines are automatically extracted. The relevant parameters of the above gas parameter prediction model are input into the GIS platform. The GIS platform automatically generates the corresponding gas parameter prediction contour lines according to the input gas parameters, and can generate the corresponding raster map according to the magnitude of the gas parameters, intuitively displaying the spatial distribution characteristics of the gas parameters within the mining area.

[0060] Step 5: After the contour lines are formed, as mining activities reveal more gas parameters, the obtained effective gas content and gas pressure test results are input into the corresponding data table in the GIS platform. The GIS platform uses Kriging interpolation to dynamically correct the corresponding contour lines, achieving dynamic and accurate prediction of gas parameters; for example... Fig. 4 As shown, with the increasing number of effective gas parameters obtained, the gas prediction contour line a before updating in the GIS platform is continuously corrected to obtain the updated gas contour line b and the gas parameter value c of the interpolated point.

[0061] Table 1 Gas Parameter Data Table

[0062]

[0063] 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 present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for dynamic prediction of coal seam gas parameters based on multi-source data fusion, characterized in that: The method includes the following steps: S1: Obtain gas parameters measured during geological exploration and production, as well as indirectly calculated gas parameters. Use multi-source data fusion analysis to correct the gas parameters obtained from geological exploration measurements and indirect calculations to obtain initial effective gas parameters. The multi-source data fusion analysis method specifically includes: a. Calculate the gas parameter correction coefficient : （1） in, For correction factors; A 1~ A n To measure gas parameters during production; a 1~ a n For measured gas parameters in geological exploration and for indirectly calculated gas parameters; n is the number of comparisons; b. Calculate the corrected effective gas parameters, a1 ， ~a n ， : （2） c. The final initial effective gas parameters are: N={ A 1, A 2, A 3…… A n a1 ， a2 ， a3 ， ……a n ， (3) S2: Analyze the influencing factors of coal seam gas occurrence, determine the main controlling factors of coal seam gas occurrence and the division of geological units; S3: Based on the initial effective gas parameters obtained in S1, the main controlling factors of coal seam gas occurrence determined in S2, and the geological unit division, establish a gas parameter prediction model; S4: Based on the Geographic Information System (GIS), a secondary development is carried out to obtain a GIS platform with automatic prediction function of gas parameters. The GIS platform stores all measured gas parameters, coal seam floor contour lines, and ground elevation point information in a unified database to form a basic information database for the mine. Input the parameters of the gas parameter prediction model established in S3 into the data table of the GIS platform, and use the MathAnalyst function in the GIS platform to perform calculations to obtain the gas parameter raster. Extract relevant gas parameters and predict contour lines using the ExtractIsoline function in the GIS platform; S5: During the coal seam mining process, timely acquisition of measured gas parameters and indirectly calculated gas parameters, and correction of the gas parameters obtained from geological exploration measurement and indirect calculation using multi-source data fusion analysis methods to obtain effective gas parameters; The effective gas parameters are input into the data table of the GIS platform. The GIS platform uses the Kriging interpolation method to dynamically correct the corresponding gas parameter prediction contour lines in S4, and continuously obtains the corrected gas parameter contour lines.

2. The method for dynamic prediction of coal seam gas parameters based on multi-source data fusion according to claim 1, characterized in that: The gas parameters are gas content and gas pressure.

3. The method for dynamic prediction of coal seam gas parameters based on multi-source data fusion according to claim 1, characterized in that: In S2, the influence of geological structural morphology, roof and floor lithology differences, coal seam thickness and coal quality variations, magmatic intrusion, and hydrogeological conditions on the occurrence of coal seam gas within the mine area is analyzed to determine the main controlling factors of coal seam gas occurrence. Based on the comprehensive qualitative and quantitative analysis of gas and geological indicators, the mine gas geological units are divided.

4. The method for dynamic prediction of coal seam gas parameters based on multi-source data fusion according to claim 1, characterized in that: The calculation formula for the gas parameter prediction model in S3 is as follows: （3） in, f For a univariate or multivariate function, when there is only one controlling factor for gas occurrence. f This represents a univariate function; when there are two or more controlling factors for gas occurrence. f Represents a multivariate function; x 1, x 2, …… x j These are the main controlling factors of coal seam gas occurrence. Y To predict gas parameters; When the main controlling factor of gas occurrence is 1: Y = f ( x ); If it is a shallow mine, then it is a univariate linear function, expressed as: Y =a x +b, where a and b are constants; For deep mines, a univariate nonlinear function is used, such as a power function, exponential function, logarithmic function, quadratic polynomial, or cubic polynomial. The nonlinear function with the best fit is selected based on the actual situation. When there are two or more factors affecting gas occurrence: ; in x 1, x 2, …… x n These are the main controlling factors of coal seam gas occurrence. k 0, k 1, …… k n For relevant parameters, f ( x 1), f ( x 2), …… f ( x n () represents a univariate function model with different controlling factors.

5. The method for dynamic prediction of coal seam gas parameters based on multi-source data fusion according to claim 1, characterized in that: In S5, the interpolation calculation formula for dynamic correction of gas parameters using the Kriging interpolation method is as follows: （4） in: Z *( x 0) represents the gas parameter value at the interpolated point. Z ( x i ) is the known first i Gas parameter values ​​at each sampling point i =1, 2, ..., n, where n is the number of sampling points used for gas parameter interpolation. D i The distance from the interpolated point to the i-th sampling point is... Number the interpolated points. Here, p is the sampling point number, and p is the power of the distance. p =2.

Images