Underground water-rich weakly cemented coal seam water damage intensity grading and classifying method

Abstract

The invention discloses an underground water-rich weakly-cemented coal seam water disaster intensity grading and classifying method, which is applied to the technical field of mine water disaster prevention and control, and comprises the following steps: acquiring hydrogeological data of a water-rich weakly-cemented coal seam and roadway construction engineering factor data; respectively acquiring the weights of the hydrogeological data and the roadway construction engineering factor data in a mode of combining an entropy weight method and an analytic hierarchy process, and converting the weights into percentage characteristic values of the hydrogeological data and the roadway construction engineering factor data by combining the standardized values of the hydrogeological data and the roadway construction engineering factor data; and constructing a classification model based on a support vector machine algorithm, and constructing a decision boundary based on the hydrogeological data and the percentage characteristic value of the roadway construction engineering factor data to realize hierarchical classification division of the water disaster intensity. According to the method, the accuracy and reliability of water disaster evaluation of the water-rich weakly cemented coal seam are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mine water hazard prevention and control, and in particular to a method for grading and classifying water hazard intensity in underground water-rich and weakly cemented coal seams. Background Art

[0002] Mine water inrush poses a serious threat to underground production safety. Accurately assessing the intensity of coal mine water hazards is crucial for formulating effective prevention and control measures, ensuring the safety of miners, and reducing property losses. However, existing traditional water hazard assessment methods often rely on the subjective experience and judgment of experts and lack objective quantitative standards, resulting in large subjective biases in the evaluation results. In addition, during coal mining, hydrogeological conditions and engineering activities influence each other and jointly determine the occurrence and development of water hazards. Traditional evaluation methods often consider the two in isolation and ignore their interaction, making the evaluation results unable to fully reflect the actual situation. Insufficient quantification of indicators is also a major drawback of existing methods. Due to the lack of an accurate quantitative indicator system, many key factors are difficult to accurately quantify and evaluate, resulting in limited classification accuracy. When dividing water hazard risk areas, it is impossible to accurately determine the degree of danger of each area, which brings difficulties to the safe production management of coal mines. Water-rich weakly cemented coal seams have unique geological characteristics and hydrogeological conditions. For example, the weak cementation characteristics of coal seams make them prone to collapse under water immersion and pressure. Traditional methods have failed to make special optimization and adjustments for these special conditions, resulting in the inability to accurately reflect the actual danger when evaluating the water hazard intensity of water-rich weakly cemented coal seams.

[0003] To this end, how to provide a method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams that can simultaneously consider the interaction between hydrogeological conditions and engineering activities, and construct an accurate quantitative indicator system for the geological characteristics and hydrogeological conditions of water-rich weakly cemented coal seams, improve the accuracy and reliability of water hazard evaluation of water-rich weakly cemented coal seams, and provide more powerful technical support for coal mine safety production is an issue that technical personnel in this field urgently need to solve. Summary of the Invention

[0004] In view of this, the present invention proposes a classification method for water hazard intensity of underground water-rich weakly cemented coal seams.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for grading and classifying water hazard intensity in underground water-rich and weakly cemented coal seams, comprising:

[0007] Step 1: Obtain hydrogeological data of water-rich and weakly cemented coal seams and data on engineering factors for roadway construction;

[0008] Step 2: Use the entropy weight method and the analytic hierarchy process to obtain the weights of the hydrogeological data and the roadway construction engineering factor data respectively, and combine the standardized values ​​of the hydrogeological data and the roadway construction engineering factor data to convert them into percentage characteristic values ​​of the hydrogeological data and the roadway construction engineering factor data;

[0009] Step 3: Construct a classification model based on the support vector machine algorithm, and based on the percentage eigenvalues ​​of the hydrogeological data and the tunnel construction engineering factor data, construct a decision boundary to achieve the hierarchical classification of water hazard intensity.

[0010] Optionally, in step 1, the hydrogeological data of the water-rich weakly cemented coal seam include: unit water yield of the aquifer, permeability coefficient, aquifer thickness and natural spring flow.

[0011] Optionally, in step 1, the engineering factor data of the roadway construction in the water-rich weakly cemented coal seam include: mining depth, working face advancement speed, support strength index and geological structure complexity score.

[0012] Optionally, in step 2, the entropy weight method and the analytic hierarchy process are combined to obtain the weights of the hydrogeological data and the roadway construction engineering factor data, specifically:

[0013] The entropy weight method is used to obtain the weights of hydrogeological data and roadway construction engineering factor data respectively; the hierarchical analysis method is used to obtain the weights of hydrogeological data and roadway construction engineering factor data respectively;

[0014] Based on the weights of the hydrogeological data and the weights of the roadway construction engineering factor data obtained by the entropy weight method and the hierarchical analysis method, respectively, the comprehensive weights of the hydrogeological data and the roadway construction engineering factor data are calculated using the multiplication synthesis method.

[0015] Optionally, the entropy weight method is used to obtain the weights of the hydrogeological data and the roadway construction engineering factor data, specifically:

[0016] Construct the original matrix of the entropy weight method as follows:

[0017] X=[x ij ] n×m ;

[0018] Where X is the original matrix; x ij is the element in the i-th row and j-th column of the original matrix, representing the i-th sample value of the j-th indicator; n is the number of samples; m is the number of indicators, that is, the number of indicators of hydrogeological data and the number of indicators of tunnel construction engineering factor data;

[0019] The original matrix is ​​normalized by range as follows:

[0020]

[0021] Among them, r ij is x ij The range normalized result of x jmax 、x jmin are the maximum and minimum sample values ​​of the j-th indicator respectively;

[0022] Calculate the information entropy as follows:

[0023]

[0024] Among them, E j is information entropy;

[0025] Based on information entropy, the entropy weight is calculated as follows:

[0026]

[0027] in, is the weight obtained using the entropy weight method.

[0028] Optionally, the weights of the hydrogeological data and the roadway construction engineering factor data are obtained using the analytic hierarchy process, specifically:

[0029] Based on the 1-9 scale method, the indicators are compared pairwise and the matrix of the hierarchical analysis method is constructed as follows:

[0030] A=[a ij ] m×m ;

[0031] Among them, A is the matrix of hierarchical analysis method; a ij is the element in the i-th row and j-th column of the AHP matrix, indicating the relative importance of the i-th indicator to the j-th indicator; m is the number of indicators, i.e., the number of indicators of hydrogeological data and the number of indicators of roadway construction engineering factor data;

[0032] Calculate the weight vector as follows:

[0033]

[0034] in, is the weight obtained by using the hierarchical analysis method.

[0035] Optionally, based on the weights of the hydrogeological data and the weights of the roadway construction engineering factor data obtained using the entropy weight method and the analytic hierarchy process, respectively, the comprehensive weights of the hydrogeological data and the roadway construction engineering factor data are calculated using the multiplication synthesis method as follows:

[0036]

[0037] Among them, W j The comprehensive weights of the hydrogeological data and the tunnel construction engineering factor data calculated using the multiplication synthesis method are: is the weight obtained using the entropy weight method; is the weight obtained by using the hierarchical analysis method; m is the number of indicators, namely the number of indicators of hydrogeological data and the number of indicators of tunnel construction engineering factor data.

[0038] Optionally, in step 2, the standardized values ​​of the hydrogeological data and the roadway construction engineering factor data are combined and converted into percentage characteristic values ​​of the hydrogeological data and the roadway construction engineering factor data as follows:

[0039]

[0040] Where HGI is the percentage characteristic value of hydrogeological data; W q 、W K 、W M 、W Q are the comprehensive weights of the unit yield of aquifer, permeability coefficient, aquifer thickness and natural spring water flow; q, K, M, Q are the values ​​of the unit yield of aquifer, permeability coefficient, aquifer thickness and natural spring water flow; q max , K max 、M max , Q max are the unit yield of aquifer, permeability coefficient, thickness of aquifer and maximum value of natural spring flow;

[0041]

[0042] Where EIF is the percentage eigenvalue of the roadway construction engineering factor data; W D 、W V 、W S 、W F are the comprehensive weights of mining depth, working face advancement speed, support strength index and geological structure complexity score; D, V, S and F are the values ​​of mining depth, working face advancement speed, support strength index and geological structure complexity score respectively; D max 、V max 、S max 、F max They are the maximum values ​​of mining depth, working face advancement speed, support strength index and geological structure complexity score.

[0043] Optionally, in step 3, constructing a classification model based on the support vector machine algorithm further includes: introducing a kernel function based on the support vector machine algorithm, and mapping the data to a higher-dimensional space through the Gaussian kernel, specifically:

[0044] When predicting new samples in the model, it is necessary to measure the relationship between each support vector. The calculation method of the Gaussian kernel is as follows:

[0045] k rbf (x1,x2)=exp(-γ‖x1-x2|| 2 );

[0046] Among them, x1 and x2 are data points; ||x1-x2|| is the Euclidean distance; γ is the parameter that controls the width of the Gaussian kernel.

[0047] Optionally, in step 3, the decision boundary is:

[0048] Strong danger zone: HGI∈[65,100]% and EIF∈[70,100]%;

[0049] Weak danger zone: HGI∈[40,65]% and EIF∈[50,70]%;

[0050] Safe zone: HGI∈[0,40]% and EIF∈[0,50]%.

[0051] Through the above technical solutions, it can be seen that compared with the existing technology, the present invention proposes a method for grading and classifying the water hazard intensity of underground water-rich weakly cemented coal seams. In terms of the technical solution, the hydrogeological data and tunnel construction engineering factor data of water-rich weakly cemented coal seams are first obtained. These multi-dimensional data comprehensively reflect the factors affecting the water hazard intensity; then, the data weights are obtained by combining the entropy weight method and the hierarchical analysis method, and converted into percentage eigenvalues. This quantitative processing method avoids the defects of the traditional method that relies on subjective experience judgment, making the evaluation results more objective and accurate; finally, a classification model based on the support vector machine algorithm is constructed. By introducing the Gaussian kernel function to map the data to a higher dimensional space, the model accuracy is improved, and the decision boundary is constructed based on the percentage eigenvalue to achieve the classification and division of water hazard intensity. Through this technical solution, the interaction between hydrogeological conditions and engineering activities can be simultaneously considered, and an accurate quantitative index system can be constructed for the special geological characteristics and hydrogeological conditions of water-rich weakly cemented coal seams, which effectively improves the accuracy and reliability of water hazard evaluation in water-rich weakly cemented coal seams, provides more powerful technical support for coal mine safety production, and reduces safety accidents and property losses caused by water hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0053] Figure 1 Schematic diagram of the method of the present invention.

[0054] Figure 2 Schematic diagram of the decision boundary of the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] Example 1:

[0057] Example 1 of the present invention discloses a classification method for water hazard intensity of underground water-rich weakly cemented coal seams, such as Figure 1 As shown, including:

[0058] Step 1: Obtain the hydrogeological data of the water-rich and weakly cemented coal seam and the engineering factor data of the roadway construction.

[0059] Hydrogeological data of water-rich weakly cemented coal seams, including: unit water yield of aquifers, permeability coefficient, aquifer thickness and natural spring flow.

[0060] Engineering factor data for roadway construction in water-rich and weakly cemented coal seams include: mining depth, working face advancement speed, support strength index, and geological structure complexity score.

[0061] Step 2: Use the entropy weight method and the hierarchical analysis method to obtain the weights of the hydrogeological data and the roadway construction engineering factor data respectively, and combine the standardized values ​​of the hydrogeological data and the roadway construction engineering factor data to convert them into percentage characteristic values ​​of the hydrogeological data and the roadway construction engineering factor data.

[0062] The entropy weight method and the analytic hierarchy process are combined to obtain the weights of the hydrogeological data and the roadway construction engineering factor data, respectively. Specifically:

[0063] The entropy weight method is used to obtain the weights of hydrogeological data and roadway construction engineering factor data respectively; the hierarchical analysis method is used to obtain the weights of hydrogeological data and roadway construction engineering factor data respectively;

[0064] Based on the weights of the hydrogeological data and the weights of the roadway construction engineering factor data obtained by the entropy weight method and the hierarchical analysis method, respectively, the comprehensive weights of the hydrogeological data and the roadway construction engineering factor data are calculated using the multiplication synthesis method.

[0065] The entropy weight method is used to obtain the weights of hydrogeological data and roadway construction engineering factor data, specifically:

[0066] Construct the original matrix of the entropy weight method as follows:

[0067] X=[x ij ] n×m ;

[0068] Where X is the original matrix; x ij is the element in the i-th row and j-th column of the original matrix, representing the i-th sample value of the j-th indicator; n is the number of samples; m is the number of indicators, that is, the number of indicators of hydrogeological data and the number of indicators of tunnel construction engineering factor data;

[0069] The original matrix is ​​normalized by range as follows:

[0070]

[0071] Among them, r ij is x ij The range normalized result of x jmax 、x jmin are the maximum and minimum sample values ​​of the j-th indicator respectively;

[0072] Calculate the information entropy as follows:

[0073]

[0074] Among them, E j is information entropy;

[0075] Based on information entropy, the entropy weight is calculated as follows:

[0076]

[0077] in, is the weight obtained using the entropy weight method.

[0078] The weights of hydrogeological data and roadway construction engineering factor data are obtained using the analytic hierarchy process, specifically:

[0079] Based on the 1-9 scale method, the indicators are compared pairwise and the matrix of the hierarchical analysis method is constructed as follows:

[0080] A=[a ij ] m×m ;

[0081] Among them, A is the matrix of hierarchical analysis method; a ij is the element in the i-th row and j-th column of the AHP matrix, indicating the relative importance of the i-th indicator to the j-th indicator; m is the number of indicators, i.e., the number of indicators of hydrogeological data and the number of indicators of roadway construction engineering factor data;

[0082] Calculate the weight vector as follows:

[0083]

[0084] in, is the weight obtained by using the hierarchical analysis method.

[0085] Based on the weights of the hydrogeological data obtained by the entropy weight method and the hierarchical analysis method, and the weights of the roadway construction engineering factor data, the comprehensive weights of the hydrogeological data and the roadway construction engineering factor data are calculated using the multiplication synthesis method, as follows:

[0086]

[0087] Among them, W j The comprehensive weights of the hydrogeological data and the tunnel construction engineering factor data calculated using the multiplication synthesis method are: is the weight obtained using the entropy weight method; is the weight obtained by using the hierarchical analysis method; m is the number of indicators, namely the number of indicators of hydrogeological data and the number of indicators of tunnel construction engineering factor data.

[0088] Combining the standardized values ​​of the hydrogeological data and the roadway construction engineering factor data, they are converted into percentage characteristic values ​​of the hydrogeological data and the roadway construction engineering factor data as follows:

[0089]

[0090] Where HGI is the percentage characteristic value of hydrogeological data; W q 、W K 、W M 、W Q are the comprehensive weights of the unit yield of aquifer, permeability coefficient, aquifer thickness and natural spring water flow; q, K, M, Q are the values ​​of the unit yield of aquifer, permeability coefficient, aquifer thickness and natural spring water flow; q max, K max 、M max , Q max are the unit yield of aquifer, permeability coefficient, thickness of aquifer and maximum value of natural spring flow;

[0091]

[0092] Where EIF is the percentage eigenvalue of the roadway construction engineering factor data; W D 、W V 、W S 、W F are the comprehensive weights of mining depth, working face advancement speed, support strength index and geological structure complexity score; D, V, S and F are the values ​​of mining depth, working face advancement speed, support strength index and geological structure complexity score respectively; D max 、V max 、S max 、F max They are the maximum values ​​of mining depth, working face advancement speed, support strength index and geological structure complexity score.

[0093] Step 3: Construct a classification model based on the support vector machine algorithm, and based on the percentage eigenvalues ​​of the hydrogeological data and the tunnel construction engineering factor data, construct a decision boundary to achieve the hierarchical classification of water hazard intensity.

[0094] Building a classification model based on the support vector machine algorithm also includes: introducing a kernel function based on the support vector machine algorithm, mapping the data to a higher-dimensional space through the Gaussian kernel, enhancing the local sensitivity of eigenvalue capture, and improving model accuracy. Specifically:

[0095] When predicting new samples in the model, it is necessary to measure the relationship between each support vector. The calculation method of the Gaussian kernel is as follows:

[0096] k rbf (x1,x2)=exp(-γ||x1-x2|| 2 );

[0097] Among them, x1 and x2 are data points; ||x1-x2‖ is the Euclidean distance; γ is the parameter that controls the width of the Gaussian kernel.

[0098] Optionally, in step 3, the decision boundary, such as Figure 2 As shown, specifically:

[0099] Strong danger zone (blue): HGI∈[65,100]% and EIF∈[70,100[%;

[0100] Weak danger zone (red): HGI∈[40,65]% and EIF∈[50,70]%;

[0101] Safe zone (green): HGI∈[0,40]% and EIF∈[0,50]%.

[0102] The embodiment of the present invention discloses a method for grading and classifying the water hazard intensity of underground water-rich weakly cemented coal seams. In terms of the technical solution, the hydrogeological data of the water-rich weakly cemented coal seams and the data of the engineering factors of the roadway construction are first obtained. These multi-dimensional data comprehensively reflect the factors affecting the water hazard intensity; then, the data weights are obtained by combining the entropy weight method and the hierarchical analysis method, and converted into percentage eigenvalues. This quantitative processing method avoids the defect of the traditional method relying on subjective experience judgment, making the evaluation results more objective and accurate; finally, a classification model based on the support vector machine algorithm is constructed. By introducing the Gaussian kernel function to map the data to a higher dimensional space, the accuracy of the model is improved, and then the decision boundary is constructed according to the percentage eigenvalue to achieve the grading and classification of the water hazard intensity. Through this technical solution, the interaction between hydrogeological conditions and engineering activities can be considered at the same time, and an accurate quantitative index system can be constructed for the special geological characteristics and hydrogeological conditions of the water-rich weakly cemented coal seams, which effectively improves the accuracy and reliability of the water hazard evaluation of the water-rich weakly cemented coal seams, provides more powerful technical support for coal mine safety production, and reduces safety accidents and property losses caused by water hazards.

[0103] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0104] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams, characterized by: include: Step 1: Obtain hydrogeological data of water-rich and weakly cemented coal seams and data on engineering factors for roadway construction; Step 2: Using a combination of entropy weight method and hierarchical analysis method to obtain weights of the hydrogeological data and the roadway construction engineering factor data, respectively, and combining the standardized values ​​of the hydrogeological data and the roadway construction engineering factor data to convert them into percentage characteristic values ​​of the hydrogeological data and the roadway construction engineering factor data; Step 3: Construct a classification model based on the support vector machine algorithm, and based on the percentage eigenvalues ​​of the hydrogeological data and the tunnel construction engineering factor data, construct a decision boundary to achieve hierarchical classification of water hazard intensity.

2. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 1, characterized in that: In step 1, the hydrogeological data of the water-rich weakly cemented coal seam include: unit water yield of the aquifer, permeability coefficient, aquifer thickness and natural spring flow.

3. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 2, characterized in that: In step 1, the engineering factor data of the roadway construction of the water-rich weakly cemented coal seam include: mining depth, working face advancement speed, support strength index and geological structure complexity score.

4. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 1, characterized in that: In step 2, the entropy weight method and the analytic hierarchy process are combined to obtain the weights of the hydrogeological data and the roadway construction engineering factor data, specifically: The weights of the hydrogeological data and the roadway construction engineering factor data are obtained respectively by using the entropy weight method; the weights of the hydrogeological data and the roadway construction engineering factor data are obtained respectively by using the hierarchical analysis method; Based on the weights of the hydrogeological data and the weights of the tunnel construction engineering factor data obtained by using the entropy weight method and the hierarchical analysis method, respectively, the comprehensive weights of the hydrogeological data and the tunnel construction engineering factor data are calculated using the multiplication synthesis method.

5. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 4, characterized in that: The entropy weight method is used to obtain the weights of the hydrogeological data and the roadway construction engineering factor data, specifically: Construct the original matrix of the entropy weight method as follows: X=[x ij ] n×m ; Where X is the original matrix; x ij is the element in the i-th row and j-th column of the original matrix, representing the i-th sample value of the j-th indicator; n is the number of samples; m is the number of indicators, that is, the number of indicators of the hydrogeological data and the number of indicators of the tunnel construction engineering factor data; The original matrix is ​​normalized by range as follows: Among them, r ij is x ij The range normalized result of x jmax 、x jmin are the maximum and minimum sample values ​​of the j-th indicator respectively; Calculate the information entropy as follows: Among them, E j is information entropy; Based on the information entropy, the entropy weight is calculated as follows: in, is the weight obtained using the entropy weight method.

6. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 4, characterized in that: The weights of the hydrogeological data and the roadway construction engineering factor data are obtained using the hierarchical analysis method, specifically: Based on the 1-9 scale method, the indicators are compared pairwise and the matrix of the hierarchical analysis method is constructed as follows: A=[a ij ] m×m ; Wherein, A is the matrix of the hierarchical analysis method; a ij is the element in the i-th row and j-th column of the matrix of the hierarchical analysis method, indicating the relative importance of the i-th indicator to the j-th indicator; m is the number of indicators, i.e., the number of indicators of the hydrogeological data and the number of indicators of the roadway construction engineering factor data; Calculate the weight vector as follows: in, is the weight obtained by using the hierarchical analysis method.

7. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 4, characterized in that: Based on the weights of the hydrogeological data and the weights of the roadway construction engineering factor data obtained by using the entropy weight method and the hierarchical analysis method, respectively, the comprehensive weights of the hydrogeological data and the roadway construction engineering factor data are calculated using the multiplication synthesis method, as follows: Among them, W j The comprehensive weight of the hydrogeological data calculated using the multiplication synthesis method and the comprehensive weight of the tunnel construction engineering factor data calculated using the multiplication synthesis method; is the weight obtained using the entropy weight method; is the weight obtained by using the hierarchical analysis method; m is the number of indicators, that is, the number of indicators of the hydrogeological data and the number of indicators of the tunnel construction engineering factor data.

8. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 3, characterized in that: In step 2, the standardized values ​​of the hydrogeological data and the roadway construction engineering factor data are combined and converted into percentage characteristic values ​​of the hydrogeological data and the roadway construction engineering factor data as follows: Wherein, HGI is the percentage characteristic value of the hydrogeological data; W q 、W K 、W M 、W Q are the comprehensive weights of the unit water yield, permeability coefficient, aquifer thickness and natural spring water flow of the aquifer; q, K, M, Q are the values ​​of the unit water yield, permeability coefficient, aquifer thickness and natural spring water flow of the aquifer; q max , K max 、M max , Q max are the unit yield of the aquifer, the permeability coefficient, the thickness of the aquifer and the maximum value of the natural spring flow rate; Wherein, EIF is the percentage eigenvalue of the tunnel construction engineering factor data; W D 、W V 、W S 、W F are the comprehensive weights of the mining depth, working face advancement speed, support strength index and geological structure complexity score respectively; D, V, S and F are the values ​​of the mining depth, working face advancement speed, support strength index and geological structure complexity score respectively; D max 、V max 、S max 、F max They are respectively the maximum values ​​of the mining depth, working face advancement speed, support strength index and geological structure complexity score.

9. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 1, characterized in that: In step 3, constructing a classification model based on the support vector machine algorithm also includes: introducing a kernel function on the basis of the support vector machine algorithm, and mapping the data to a higher dimensional space through the Gaussian kernel, specifically: When predicting new samples in the model, it is necessary to measure the relationship between each support vector. The calculation method of the Gaussian kernel is as follows: k rbf (x1,x2)=exp(-γ||x1-x2|| 2 ); Among them, x1 and x2 are data points; ||x1-x2|| is the Euclidean distance; γ is the parameter that controls the width of the Gaussian kernel.

10. A method for grading and classifying water hazard intensity of underground water-rich weakly cemented coal seams according to claim 1, characterized in that: In step 3, the decision boundary is specifically: Strong danger zone: HGI∈[65,100]% and FIF∈[70,100]%; Weak danger zone: HGI∈[40,65]% and EIF∈[50,70]%; Safe zone: HGI∈[0,40]% and EIF∈[0,50]%.

Images