Mine mining working face roof mud and sand gushing danger prediction method

Abstract

The invention discloses a mine excavation working face top plate mud and sand gushing danger prediction method. The method comprises the steps of obtaining an initial prediction evaluation index; performing dimensionless preprocessing on the initial prediction evaluation index to obtain a prediction evaluation index; determining a first weight and a second weight by using an entropy weight method and a CRITIC weight analysis method, and combining the first weight and the second weight to obtain a combined weight of the prediction evaluation index; and based on the combined weight, obtaining an evaluation matrix, and utilizing the evaluation matrix to predict the working face roof mud and sand gushing danger level. According to the method, through comprehensive analysis of subjective and objective evaluation indexes such as geologic features of hydrogeological engineering and human factors, the prediction precision of the working face roof mud and sand gushing danger level is effectively improved, so that better service is provided for mine disaster prevention and control work.

Description

Technical Field

[0001] The present invention belongs to the technical field of mine geological disaster prevention and control, and in particular relates to a method for predicting the danger of mud and sand bursting on the roof of a mining working face. Background Art

[0002] As the main resource for my country's energy supply, coal plays a role in promoting the development of the national economy. Large-scale and high-intensity coal mining has led to frequent occurrence of various mining geological disasters, posing a threat to mine safety production. At present, most technical studies are focused on the prediction and evaluation of the hazard of water and sand burst under the loose layer of the Quaternary system in the eastern mining area. However, under the influence of mining disturbance of weakly cemented overburden coal seams in the western mining area, mud and sand burst accidents often occur in the bedrock of the working face collapse zone. There are relatively few studies on the hazard prediction of this type of disaster, and the previous disaster risk level is mostly predicted and evaluated from the internal causes of the accident. Since the weakly cemented overburden in the collapse zone of the working face of the western coal mine has low mechanical strength and strong water sensitivity, the mining technology and water-rock interaction time are also key factors in the occurrence of disasters. However, the previous disaster risk assessment has not considered the impact of mining technology and working face mining interval time on mud and sand burst. For this reason, it is urgent to provide a method for predicting the hazard of mud and sand burst in the roof of the mining working face of the mine to fill the unsolved content of the existing technology. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a method for predicting the danger of mud and sand bursting on the roof of a mining face, so as to solve the problem that the existing disaster risk prediction has not yet considered the impact of mining technology and the intermittent time of working face mining on mud and sand bursting.

[0004] The present invention provides a method for predicting the danger of mud and sand burst in the roof of a mining working face, comprising:

[0005] Obtain initial prediction evaluation indicators;

[0006] Performing dimensionless preprocessing on the initial prediction evaluation index to obtain a prediction evaluation index;

[0007] Determine the first weight and the second weight using the entropy weight method and the CRITIC weight analysis method respectively, combine the first weight and the second weight, and obtain the combined weight of the prediction evaluation index;

[0008] Based on the combined weights, an evaluation matrix is ​​obtained, and the evaluation matrix is ​​used to predict the danger level of mud and sand bursts on the roof of the working face.

[0009] Optionally, the initial prediction evaluation indicators include: thickness of sandstone in the collapse zone, proportion of shale in the collapse zone, thickness of the high-conducting layer entering the aquifer, permeability coefficient of the aquifer, burial depth of the mined coal seam, complexity of geological structure, mining method of the working face and intermittent time of suspension of mining of the working face.

[0010] Optionally, the method for performing dimensionless preprocessing on the initial prediction evaluation index is:

[0011]

[0012] Among them, x ij is a positive indicator, x′ ij is a negative indicator, i is the i-th drilling hole, j is the j-th indicator, k ij is the initial value of the jth indicator for the ith drilling hole.

[0013] Optionally, determining the first weight by using an entropy weight method includes:

[0014] Calculating the proportion and information entropy of the prediction evaluation index, and determining the weight of the prediction evaluation index based on the proportion and information entropy;

[0015] The method for calculating the proportion of the prediction evaluation index is:

[0016]

[0017] The method for calculating the information entropy of the prediction evaluation index is:

[0018]

[0019] The method for calculating the weight of the prediction evaluation index is:

[0020]

[0021] Among them, γ ij is the proportion of evaluation indicators, E j is information entropy, μ j is the first weight, n is the total number of evaluation objects, and m is the total number of evaluation indicators.

[0022] Optionally, determining the second weight by using the CRITIC weight analysis method includes:

[0023] Calculating the correlation coefficient, deviation and conflict matrix between the prediction evaluation indicators;

[0024] Based on the correlation coefficient, deviation and conflict matrix, obtaining the information between the prediction evaluation indicators;

[0025] Based on the amount of information, the second weight is obtained.

[0026] Optionally, a nonlinear combination is adopted when combining the first weight and the second weight.

[0027] Optionally, the combination weight is calculated as follows:

[0028]

[0029] Among them, w j is the combined weight matrix; μ and v are the first and second weights respectively; A is the amount of indicator information without considering the weight; e is the unit matrix; B is the row vector of the sum of the squares of all indicators of all evaluation objects under the two weights; λ is a constant.

[0030] Optionally, based on the combined weights, obtaining the evaluation matrix includes:

[0031] Obtaining the classification standard of the evaluation index, calculating the membership function value in combination with the gradient distribution function, and constructing a fuzzy matrix based on the membership function value;

[0032] The evaluation matrix is ​​obtained by multiplying the fuzzy matrix and the combination weight.

[0033] Optionally, using the evaluation matrix to predict the danger level of mud and sand bursting on the roof of the working face includes:

[0034] Using the evaluation matrix and combining the maximum membership principle, the danger level of mud and sand bursting on the roof of the working face is predicted;

[0035] Among them, the maximum membership principle is to take the risk level corresponding to the maximum absolute value as the final prediction result.

[0036] Compared with the prior art, the present invention has the following advantages and technical effects:

[0037] The present invention not only takes into account the geological structural conditions of mud and sand bursts, the sand and mudstone characteristics in the collapse zone, the permeability coefficient of the aquifer in the water-conducting fracture zone and other objective factors, but also introduces subjective factors such as the mining technology and the interval time of the mining suspension. By comprehensively analyzing the subjective and objective evaluation indicators such as the hydrogeological and engineering geological characteristics and human factors, the prediction accuracy of the mud and sand burst danger level of the working face roof is effectively improved, so as to better serve the mine disaster prevention and control work. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 A schematic diagram of a mud and sand burst accident on the roof of a working face according to an embodiment of the present invention;

[0040] Figure 2 A diagram showing the construction of a mud and sand burst hazard evaluation index system according to an embodiment of the present invention;

[0041] Figure 3 A schematic flow chart of a method for predicting the danger of mud and sand bursting on the roof of a mining working face according to an embodiment of the present invention;

[0042] Figure 4 is the gradient distribution function in the fuzzy comprehensive evaluation method (FCEM) of the embodiment of the present invention;

[0043] Figure 5 A schematic diagram of a geological drilling column and water extraction test according to an embodiment of the present invention;

[0044] Figure 6 It is a contour map of permeability coefficient of aquifer according to an embodiment of the present invention;

[0045] Figure 7 It is a contour map of fractal dimension values ​​of the complexity of geological structures according to an embodiment of the present invention;

[0046] Figure 8 A zoning diagram of the danger level of mud and sand bursting on the roof of a working face according to an embodiment of the present invention;

[0047] Among them, 1. top interface of water-conducting fracture zone; 2. water-conducting fracture; 3. collapse zone; 4. falling objects; 5. conglomerate aquifer; 6. siltstone; 7. mudstone; 8. muddy sandstone; 9. sandy mudstone; 10. medium-coarse sandstone; 11. coal seam; 12. fully mechanized mining hydraulic support; 13. mud-sand gushing mixture in collapse zone; 14. pumping test section; 15. casing eye; 16. cement sealing section; 17. solid casing in the upper part of pumping test section. DETAILED DESCRIPTION

[0048] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0049] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0050] like Figure 1As shown in Figure 1, as the coal seam is continuously excavated, the overlying rock layers within a certain range (collapse zone 3 and fracture zone) undergo plastic failure under the influence of self-weight and stress redistribution. The water from the aquifer flows down along the water-conducting fractures, and the muddy rock layers that are easily disintegrated by water precipitate mud and sand. Under the condition of high potential hydrodynamic force, the mud-sand mixture eventually flows into the mining area. The detailed structure is shown in Figure 1. Figure 1 As shown, there are the top interface 1 of the water-conducting fracture zone, the water-conducting fracture 2, the collapse zone 3, the falling objects 4, the conglomerate aquifer 5, the siltstone 6, the mudstone 7, the muddy sandstone 8, the sandy mudstone 9, the medium-coarse sandstone 10, the coal seam 11, the fully mechanized mining hydraulic support 12, and the mud-sand outburst mixture 13 in the collapse zone.

[0051] The present invention proposes a method for predicting the danger of mud and sand bursting on the roof of a mining working face. Figure 3 As shown, the specific steps include:

[0052] Obtain initial prediction evaluation indicators;

[0053] Perform dimensionless preprocessing on the initial prediction evaluation index to obtain the prediction evaluation index;

[0054] The first weight and the second weight are determined by using the entropy weight method and the CRITIC weight analysis method respectively, and the first weight and the second weight are combined to obtain the combined weight of the prediction evaluation index;

[0055] Based on the combined weights, an evaluation matrix is ​​obtained, and the evaluation matrix is ​​used to predict the hazard level of mud and sand bursting on the roof of the working face.

[0056] Furthermore, if Figure 2 As shown in the figure, the initial prediction and evaluation indicators include: the thickness of sandstone in the collapse zone, the proportion of shale in the collapse zone, the thickness of the aquifer entering the high-conducting layer, the permeability coefficient of the aquifer, the burial depth of the mined coal seam, the complexity of the geological structure, the mining method of the working face and the intermittent time of the working face stopping mining.

[0057] Specifically, step S1, determine the scope of the study area to be evaluated, collect and organize the hydrogeological and engineering geological survey data (geological drilling and water extraction test data, etc.), measured data of coal seam mining water-conducting fracture zones, mining working face planning layout map and mine geological structure outline map, etc., and extract and screen evaluation indicators from the basic data; geological drilling columnar and water extraction test data such as Figure 5 As shown, the conglomerate aquifer 5, fine sandstone 6, mudstone 7, muddy sandstone 8, sandy mudstone 9, medium-coarse sandstone 10, coal seam 11, fully mechanized hydraulic support 12, mud-sand gushing mixture in the collapse zone 13, pumping test section 14, casing eyelet 15, cement sealing section 16, and solid casing 17 on the upper part of the pumping test section;

[0058] S1-1. Through the field measurement of water-conducting fissures in the working face in the past, the collapse ratio (ratio of the collapse zone height to the coal seam mining thickness) and the crack mining ratio (ratio of the water-conducting fissure zone height to the coal seam mining thickness) during coal seam mining are obtained. According to the characteristics of the coal seam thickness variation in the working face to be evaluated, the development range of the collapse zone and the water-conducting fissure zone is determined.

[0059] S1-2. According to the geological drilling exposure of the stratum lithology and aquifer conditions, the sandstone thickness x1 and the sand-mudstone proportion x2 in the collapse zone are counted, and the location of the aquifer development is determined at the same time. According to the spatial position relationship between the top interface of the water-conducting fracture zone and the aquifer, the thickness of each aquifer within the range affected by the mining fracture is determined, that is, the thickness of the water-conducting fracture zone entering the aquifer x3, and the calculation formula is:

[0060] x3=m1+m2+…+m n (m1, m2…m n is the thickness of the 1st to nth aquifer);

[0061] S1-3. Determine the thickness of the aquifer in the water-conducting fracture zone based on the aquifer data revealed by the boreholes in the working face and the relationship between the height of the water-conducting fracture zone and the spatial position of the aquifer; at the same time, combine the hydrogeological survey data to grasp the permeability coefficient of the aquifer within the scope of the water-conducting fracture and calculate the equivalent permeability coefficient of the aquifer;

[0062] The equivalent permeability coefficient of the aquifer is x4, which is calculated as follows:

[0063] (K1, K2…K n is the permeability coefficient of the 1st to nth aquifer);

[0064] In addition, according to the occurrence of coal seams revealed by drilling, the burial depth of the mining coal seams x5 is determined;

[0065] S1-4. Determine the burial depth of the mining coal seam according to the coal seam development characteristics revealed by drilling holes in the working face; at the same time, analyze the complexity of the geological structure in the working face according to the work of tunnel excavation, drilling, geophysical exploration, etc. The fractal dimension value is used to quantitatively represent the complexity of the structure. The larger the fractal dimension value, the more complex the geological structure;

[0066] Based on the summary of previous drilling and geophysical exploration data, the geological structure development in the investigation area was investigated and an outline map of the mine geological structure was drawn. The similar fractal dimension is used to characterize the complexity of the geological structure x6. According to the formula Determine the fractal dimension value Ds of the mine geological structure. Use ArcGIS to draw the fractal dimension value contour map of the mine geological structure, and then extract the fractal dimension value of the geological structure at each drilling location from the map.

[0067] S1-5. According to the mining technical plan of the working face, determine the mining method adopted by the working face (overhead mining - "0", first overhead and then overhead mining - "1", first overhead and then overhead mining - "2", overhead mining - "3"); at the same time, according to the working face recovery plan and daily equipment maintenance arrangements, determine the suspension interval during the mining of the working face coal seam;

[0068] According to the geological description of the working face and the mining safety technical plan, determine the mining method x7 and the intermittent time x8 of the working face.

[0069] Furthermore, the method for dimensionless preprocessing of the initial prediction evaluation index is as follows:

[0070]

[0071] Among them, x ij is a positive indicator, x′ ij is a negative indicator, i is the i-th drilling hole, j is the j-th indicator, k ij is the initial value of the jth indicator for the ith drilling hole.

[0072] Specifically, the selected evaluation indicators such as sandstone thickness in the collapse zone, sand-mudstone ratio, aquifer thickness in the water-conducting fracture zone, permeability coefficient of aquifer within the affected range of the water-conducting fracture, coal seam burial depth, geological structure fractal dimension value, working face mining method and mining suspension interval time were summarized and sorted out;

[0073] Before determining the weights of the evaluation indicators, in order to eliminate the impact of different indicator units on the prediction results, each evaluation indicator needs to be dimensionlessly preprocessed.

[0074] Further, determining the first weight by using the entropy weight method includes:

[0075] Calculate the proportion and information entropy of the prediction evaluation index, and determine the weight of the prediction evaluation index based on the proportion and information entropy;

[0076] The method for calculating the proportion of prediction evaluation indicators is:

[0077]

[0078] The method for calculating the information entropy of the prediction evaluation index is:

[0079]

[0080] The method for calculating the weight of the prediction evaluation index is:

[0081]

[0082] Among them, γ ij is the proportion of evaluation indicators, E jis information entropy, μ j is the first weight, n is the total number of evaluation objects, and m is the total number of evaluation indicators.

[0083] Further, the second weight is determined by using the CRITIC weight analysis method, including:

[0084] Calculate the correlation coefficient, deviation and conflict matrix between each prediction evaluation index;

[0085] Based on the correlation coefficient, deviation and conflict matrix, the information between the prediction and evaluation indicators is obtained;

[0086] Based on the amount of information, a second weight is obtained.

[0087] Specifically, the main calculation formula is as follows:

[0088]

[0089] in, is the mean value of the jth indicator among all evaluation objects, x ik is the value of the kth indicator of the ith evaluation object, is the mean value of the kth indicator among all evaluation objects, x il is the value of the lth indicator of the ith evaluation object, is the mean value of the lth indicator among all evaluation objects, x j is the value of the jth indicator in each evaluation object, r ij is the correlation coefficient between the ith indicator and the jth indicator; t j is the information content of the jth indicator; v j is the weight of the jth indicator.

[0090] Furthermore, the first weight and the second weight are combined to obtain the combined weight of the prediction evaluation index, including:

[0091] The first and second weights are nonlinearly combined to obtain the combined weight of the prediction evaluation index.

[0092] Specifically, the calculation formula is as follows:

[0093]

[0094] Among them, w j is the combined weight matrix; μ and v are the first and second weights respectively; A is the amount of indicator information without considering the weight; e is the unit matrix; B is the row vector of the sum of the squares of all indicators of all evaluation objects under the two weights; λ is a constant.

[0095] Furthermore, based on the combined weights, obtaining the evaluation matrix includes:

[0096] Obtain the classification standard of evaluation indicators, calculate the membership function value in combination with the gradient distribution function, and construct the fuzzy matrix based on the membership function value;

[0097] Based on the fuzzy matrix and the combined weights, an evaluation matrix is ​​obtained.

[0098] Furthermore, the evaluation matrix is ​​used to predict the danger level of mud and sand burst in the working face roof, including:

[0099] Using the evaluation matrix and combining the maximum membership principle, the danger level of mud and sand burst in the working face roof is predicted;

[0100] Among them, the maximum membership principle is to take the risk level corresponding to the maximum absolute value as the final prediction result.

[0101] Specifically, after determining the combined weight W = (w1, w2, ..., w8), the mud and sand outburst hazard level in the study area is divided into four categories according to the variation range of each evaluation index, namely, no risk area (0), low risk area (1), medium risk area (2) and high risk area (3). Figure 4 The gradient distribution function shown calculates the membership function value r(x) and forms a fuzzy matrix The fuzzy comprehensive discriminant matrix F = (f1, f2, f3, f4) is determined by the calculation formula F = W·R, where f1, f2, f3, f4 correspond to no risk, low risk, medium risk and high risk levels respectively. According to the maximum membership principle of the fuzzy comprehensive evaluation method, the risk level corresponding to the maximum absolute value is taken as the final prediction result.

[0102] After determining the risk level of mud and sand burst at each discrete point (evaluation borehole) in the study area, the ArcGIS interpolation method was used to draw the risk index (Risk Index, RI) of mud and sand burst at different locations in the entire study area. According to the equal-interval classification standard, the mud and sand burst risk level is divided into four levels from low to high. The specific classification standards are:

[0103] Risk Level Risk-free zone Low risk area Medium risk area High risk areas Risk Index RI 0≤RI<0.75 0.75≤RI<1.50 1.50≤RI<2.25 2.25≤RI<3.0

[0104] Taking the first division of the seventh mine in Dananhu, Hami, Xinjiang as an example, it is elaborated in detail:

[0105] S1. Preliminary preparation work includes determining the research target area, collecting and collating basic data, and screening prediction and evaluation indicators, as follows:

[0106] S1.1. Based on the mine excavation plan and geological exploration data, the scope of the proposed evaluation study area is delineated, and the location of the working face, distribution of geological drill holes, thickness of coal seams, burial depth and spatial occurrence of aquifers in the area are clarified;

[0107] S1.2. Based on the exploration of mining-induced water-conducting fissures carried out at the first mining working face of the first division - 11701 working face, the collapse ratio and fissure ratio of coal seam mining were determined. According to the thickness of the coal seam exposed by drilling, the scope of the overlying collapse zone and water-conducting fissure zone of the working face was determined, and the cumulative thickness of sandstone in the collapse zone of the working face, the proportion of sand and mudstone, and the thickness of the aquifer overlying the working face were counted;

[0108] S1.3. Based on the borehole water extraction test project in the study area and the thickness of the aquifer revealed by the borehole, the equivalent permeability coefficient of the aquifer disturbed by coal mining is determined by using the formula, and the permeability contour map of the aquifer is drawn by ArcGIS. The permeability contour map of the aquifer is shown in Figure 6 As shown, the value extraction to point tool built into the software is used to determine the permeability coefficient of the aquifer at other borehole locations in the area;

[0109] S1.4. Based on the complex development of geological structures (faults, folds, etc.) depicted in the geological structure outline map of the area, the fractal theory method is used to determine the fractal dimension value Ds of the geological structure in the area. The larger the Ds, the more complex the geological structure. The fractal dimension contour map of the complexity of the geological structure is shown in the figure below: Figure 7 Similarly, the value extraction to point tool of ArcGIS is used to determine the fractal dimension value Ds of the geological structure at the location of the borehole in the area;

[0110] S1.5. Determine the mining method and the interval time of the mining on the working face according to the mining technical plan and equipment maintenance plan;

[0111] S2. Taking the geological boreholes in the area as the evaluation object, each evaluation object includes 8 prediction evaluation indicators. Perform dimensionless preprocessing on the initial values ​​of the prediction evaluation indicators determined in step S1 to eliminate the influence of each evaluation indicator unit on the prediction result;

[0112] S3. Use the entropy weight method EWM and CRITIC weight method to calculate the weight μ of each evaluation index respectively. j and ν j The weights determined by the two methods are nonlinearly combined through the least squares method (LSM) to determine the combined weight of each evaluation index ω j , forming a combined weight matrix W = (w1, w2, ..., w8);

[0113] S4. According to the variation range of each evaluation index, it is divided into four intervals, which correspond to the risk level of mud and sand burst, namely, the risk-free zone, low risk zone, medium risk zone and high risk zone, which are recorded as 0, 1, 2 and 3 respectively. According to the gradient distribution function, the fuzzy matrix R is determined.

[0114] Combined with the combined weight matrix W in step S3, the discriminant matrix F = W·R is calculated to determine the fuzzy comprehensive discriminant matrix F = (f1, f2, f3, f4), where f1, f2, f3, f4 correspond to no risk, low risk, medium risk and high risk levels respectively. According to the maximum membership principle of the fuzzy comprehensive evaluation method, the mud and sand outburst hazard level at each drilling location is determined.

[0115] S5. Based on the mud and sand burst hazard levels near a limited number of drilling locations in the study area, draw a zoning of mud and sand burst hazard levels for the working face roof within the entire study area.

[0116] According to the predictive analysis, Figure 8 As shown in the figure, the risk of mud and sand burst disasters in the inner section of the 11702 working face in the first sub-area is relatively high. During the actual production period, many mud and sand burst disasters have occurred in this area, indicating that its prediction results have a certain degree of reliability.

[0117] The present invention has a different research object from the previous working face water inrush and sand burst risk assessment and prediction methods. Previous technical research mainly focused on the mining areas in the central and eastern parts of my country, and most of them were predictions of water and sand burst risks in the loose aquifers of the Quaternary system where water-conducting fissures developed upward. This study focuses on the weakly cemented strata coal mines in the west. When the mining-induced water-conducting fissures do not affect the overlying loose aquifers or affect the loose aquifers with weak water richness, the risk prediction of mud and sand burst disasters within the collapse zone of the working face is carried out.

[0118] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting the danger of mud and sand inrush in the roof of a mining working face, characterized in that: include: Obtain initial prediction evaluation indicators; Performing dimensionless preprocessing on the initial prediction evaluation index to obtain the prediction evaluation index; Determine the first weight and the second weight using the entropy weight method and the CRITIC weight analysis method respectively, combine the first weight and the second weight, and obtain the combined weight of the prediction evaluation index; Based on the combined weights, an evaluation matrix is ​​obtained, and the evaluation matrix is ​​used to predict the danger level of mud and sand bursts on the roof of the working face.

2. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1, characterized in that: The initial prediction and evaluation indicators include: the thickness of sandstone in the collapse zone, the proportion of shale in the collapse zone, the thickness of the high-conducting aquifer, the permeability coefficient of the aquifer, the burial depth of the mined coal seam, the complexity of the geological structure, the mining method of the working face and the intermittent time of the working face mining.

3. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1, characterized in that: The method for dimensionless preprocessing of the initial prediction evaluation index is: Among them, x ij is a positive indicator, x' ij is a negative indicator, i is the i-th drilling hole, j is the j-th indicator, k ij is the initial value of the jth indicator for the ith drilling hole.

4. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 3, characterized in that: Determining the first weight by using the entropy weight method includes: Calculating the proportion and information entropy of the prediction evaluation index, and determining the weight of the prediction evaluation index based on the proportion and information entropy; The method for calculating the proportion of the prediction evaluation index is: The method for calculating the information entropy of the prediction evaluation index is: The method for calculating the weight of the prediction evaluation index is: Among them, γ ij is the proportion of evaluation indicators, E j is information entropy, μ j is the first weight, n is the total number of evaluation objects, and m is the total number of evaluation indicators.

5. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1, characterized in that: Determining the second weight by using the CRITIC weight analysis method includes: Calculating the correlation coefficient, deviation and conflict matrix between the prediction evaluation indicators; Based on the correlation coefficient, deviation and conflict matrix, obtaining the information between the prediction evaluation indicators; Based on the amount of information, the second weight is obtained.

6. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1, characterized in that: A nonlinear combination is adopted when combining the first weight and the second weight.

7. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1 or 6, characterized in that: The calculation method of the combined weight is: Among them, w j is the combined weight matrix; μ and v are the first and second weights respectively; A is the amount of indicator information without considering the weight; e is the unit matrix; B is the row vector of the sum of the squares of all indicators of all evaluation objects under the two weights; λ is a constant.

8. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1, characterized in that: Based on the combined weights, obtaining the evaluation matrix includes: Obtaining the classification standard of the evaluation index, calculating the membership function value in combination with the gradient distribution function, and constructing a fuzzy matrix based on the membership function value; The evaluation matrix is ​​obtained by multiplying the fuzzy matrix and the combination weight.

9. A method for predicting the danger of mud and sand inrush in the roof of a mining working face according to claim 1, characterized in that: Using the evaluation matrix, the prediction of the danger level of mud and sand burst in the working face roof includes: By using the evaluation matrix and combining the maximum membership principle, the danger level of mud and sand bursting on the roof of the working face is predicted; Among them, the maximum membership principle is to take the risk level corresponding to the maximum absolute value as the final prediction result.

Images