A Multi-Source Information Fusion Method for Predicting and Evaluating High-Level Delamination Water Hazards in Mining-Induced Overburden

Abstract

This invention provides a multi-source information fusion method for predicting and evaluating high-level delamination water hazards in mining-induced overburden. Based on hydrogeological, engineering geological, and coal seam mining data of the study area, a prediction index system for coal seam mining, overburden structure, stratigraphic spatial occurrence, and Cretaceous aquifers is constructed. Through a multi-source information fusion prediction and evaluation model for delamination water hazards using a combination of subjective and objective weights from the analytic hierarchy process (AHP), entropy weight method, and CRITIC method, accurate prediction and evaluation of delamination water hazards are achieved. This reduces the error of traditional delamination water hazard prediction results, significantly reduces the water hazard threat to the longwall face, provides a guarantee for safe coal mining, and effectively guides coal mine water hazard prevention and control measures and safe production.

Description

Technical Field

[0001] This invention relates to the field of water hazard prevention and control in coal mining, and in particular to a method for predicting and evaluating water hazards caused by high-level delamination of mining-induced overburden through multi-source information fusion. Background Technology

[0002] my country has one of the most complex hydrogeological conditions in the world, and water-related accidents are the "second leading killer" after gas accidents. They are also one of the major hazards hindering the safe and economical mining of my country's coal resources. Currently, coal resources in eastern my country are gradually depleting, making the strategic shift of coal production to the west inevitable. The Jurassic coalfields, where water is primarily mined, have complex geological conditions, and the problem of roof delamination and water inrush is becoming increasingly prominent. As a source of mining-induced inrush water, roof delamination water is characterized by large instantaneous volumes, periodicity, and inconspicuous signs, posing a significant hazard and making prevention and control extremely difficult.

[0003] Currently, methods for preventing and controlling overburden water hazards include "interception holes" and "diversion holes" for overburden water during underground construction, and "drainage holes" and "pumping holes" for overburden water during surface construction. Accurate prediction of overburden water hazards can provide guidance for these prevention and control measures. In my country's coal industry, there are two main methods for predicting and evaluating high-level overburden water hazards: ① using empirical formulas (water inrush coefficient method) to evaluate overburden water hazards, but the selection of indicators is limited; ② using a GIS-based zoning and quantification evaluation method, but the indicator weights calculated by its analytic hierarchy process are relatively subjective. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-source information fusion method for predicting and evaluating high-level delamination water hazards in mining-induced overburden, which can achieve accurate prediction and evaluation of delamination water hazards, reduce the error of traditional delamination water hazard prediction results, and provide a guarantee for safe mining in coal mines.

[0005] To achieve the aforementioned objectives, the present invention employs the following technical solution: The present invention provides a multi-source information fusion method for predicting and evaluating water hazards in high-level delamination of mining-induced overburden, comprising the following steps:

[0006] Step 1: Collect hydrogeological, engineering geological and coal seam mining data of the study area, and obtain the spatial occurrence and hydrogeological parameters of coal seam overburden. The parameters include coal seam thickness and burial depth, Cretaceous aquifer thickness, permeability coefficient, unit water yield, overburden lithology characteristics, sand / mudstone thickness of each stratum and distance from coal seam to Cretaceous aquifer.

[0007] Step 2: Construct a multi-source information prediction index system for delamination water hazards, including coal seam mining indicators. I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and Cretaceous aquifer indices I4. Four indicators; Step 3: Standardize the four indicators using the following formula:

[0008] ;

[0009] In the formula, These are the raw data for each indicator; This represents the maximum value of each indicator; This represents the minimum value of each indicator; The normalized values ​​for each indicator are used; Step 4: Determine the subjective weight W1 using the analytic hierarchy process, the objective weight W2 using the entropy weight method, and the objective weight W3 using the CRITIC method. Calculate the comprehensive weight T for each indicator based on the combined weight formula. j The calculation formula is as follows:

[0010] ;

[0011] In the formula, T j For the first j The overall weight of each indicator; W 1j The first one determined by the analytic hierarchy process j Subjective weighting of each indicator; W 2j The first one determined by the entropy weight method j The objective weight of each indicator; W 3j The first one determined by the CRITIC method j The objective weight of each indicator.

[0012] Step 5: Combine the standardized indicator values ​​with the comprehensive weights to construct a multi-source information fusion prediction and evaluation model. The calculation formula is as follows:

[0013] ;

[0014] In the formula, For the first j Standardized values ​​of each predictive evaluation indicator; T j For the first j Step 6: Output the prediction and evaluation results based on the multi-source information fusion prediction and evaluation model to guide the prevention and control of delamination water hazards.

[0015] Preferably, the coal seam mining index I The formula for calculating 1 is: ;

[0016] In the formula, M c This refers to the coal seam thickness, in meters (m). DThis refers to the coal seam burial depth, expressed in meters (m). This is the standardized value for coal seam thickness; This is the standardized value for the coal seam burial depth.

[0017] Preferably, the overburden structure index I The formula for calculating 2 is: ;

[0018] In the formula, R s The proportion of overlying sandstone; R n The proportion of overlying mudstone; The standardized value for the proportion of overlying sandstone; This represents the standardized value for the proportion of overlying mudstone.

[0019] Preferably, the formation spatial occurrence index I The formula for calculating 3 is: ;

[0020] In the formula, D ch The vertical distance between the Cretaceous aquifer and the coal seam is expressed in meters (m). M yz The total thickness of the mudstone in the Yan'an Formation and Zhiluo Formation is given in meters. M a The thickness of the Anding Formation mudstone is given in meters (m). This represents the standardized value of the distance between the Cretaceous strata and the coal seam. The standardized value represents the total thickness of the mudstone in the Yan'an and Zhiluo Formations; The value represents the standardized thickness of the mudstone in the Anding Formation.

[0021] Preferably, the Cretaceous aquifer index I The formula for calculating 4 is: ;

[0022] In the formula, M h The thickness of the aquifer is expressed in meters (m). K The aquifer permeability coefficient is expressed in m / d. q The unit yield of water in the aquifer is expressed in L / (s·m); This is the standardized value for the aquifer thickness; This is the standardized value of the aquifer permeability coefficient; This is the standardized value of the unit inflow rate of the aquifer.

[0023] Preferably, the step of determining subjective weights using the analytic hierarchy process includes: constructing a judgment matrix and calculating the largest eigenvalue and eigenvector, and obtaining the weights after passing a consistency check, specifically:

[0024] Based on the analysis of each indicator, a hierarchical analysis model is constructed; pairwise comparisons are performed between the indicators to establish a judgment matrix. A :

[0025] ;

[0026] In the formula, x ij It is the first j The first indicator i Standardized values ​​for each sample.

[0027] Furthermore, based on the judgment matrix A Find the largest eigenvalue λ max and the corresponding eigenvectors W 1:

[0028] ;

[0029] In the formula, λ max It is a judgment matrix A The largest eigenvalue, the weight vector W 1. Normalization is performed to determine the weights of each indicator. W 1j ;

[0030] In order to determine the judgment matrix A Consistency is determined by the consistency ratio. CR The consistency ratio was tested. CR Calculate according to the formula ：

[0031] ;

[0032] In the formula, RI To determine the average random consistency index of a matrix; CI To determine the consistency index of a matrix, CI Calculate using the following formula:

[0033] .

[0034] Preferably, the step of determining objective weights using the entropy weight method includes: calculating the information entropy of each indicator and assigning weights based on the entropy value differences; specifically:

[0035] The method for calculating the proportion of predictive evaluation indicators is as follows:

[0036] ;

[0037] In the formula, x ij It is the first jThe first indicator i Standardized values ​​for each sample;

[0038] The method for calculating the information entropy of prediction and evaluation indicators is as follows:

[0039] ;

[0040] The method for calculating the weights of the predictive evaluation indicators is as follows:

[0041] .

[0042] Preferably, step four, determining the comprehensive weights, includes: calculating the variability, conflict, and information content of the indicators, and allocating weights based on the information content; specifically:

[0043] Calculate the variability among the various prediction and evaluation indicators:

[0044] ;

[0045] In the formula, For the first j The standardized mean of each indicator; For the first j Standard deviation of each indicator; x ij It is the first j The first indicator i Standardized values ​​for each sample;

[0046] Furthermore, the correlation coefficients between the various prediction and evaluation indicators are calculated:

[0047] ;

[0048] In the formula, For predictive evaluation indicators j and q The correlation coefficient; For the first j The first predictive indicator i Standardized values ​​for each sample; For the first q The first predictive indicator i Standardized values ​​for each sample; For the first j The standardized mean of each indicator; For the first q The standardized mean of each indicator;

[0049] Furthermore, the conflict between the various prediction and evaluation indicators is calculated:

[0050] ;

[0051] Furthermore, obtain the amount of information between the predictive evaluation indicators:

[0052] ;

[0053] Based on the amount of information, the weights of each prediction indicator are obtained:

[0054] ;

[0055] The subjective weights of the tomographic analysis method, along with the objective weights of the entropy weight method and the CRITIC method, are combined to determine the overall weight. T j The calculation formula is as follows:

[0056] ;

[0057] Coal seam mining indicators I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and Cretaceous aquifer indices I 4. Standardize the data and obtain the multi-source information fusion prediction and evaluation model for delamination water damage according to the following formula:

[0058] ;

[0059] In the formula, These are the standardized values ​​for each prediction and evaluation indicator; T j The comprehensive weight of each prediction and evaluation indicator.

[0060] Preferably, the prediction and evaluation results output by the model are used to guide water hazard prevention and control measures at the longwall mining face. Combined with the water inrush situation at the working face, the prediction and evaluation results are divided into three levels: 0.75 < P < 1.0 is a high-risk area for water inrush due to separation; 0.25 ≤ P ≤ 0.75 is a medium-risk area for water inrush due to separation; and 0 < P < 0.25 is a low-risk area for water inrush due to separation.

[0061] In areas with a high risk of water inrush due to separation, the water inrush should be treated by surface pumping and grouting before mining. During mining, the water level of the aquifer should be monitored more frequently to ensure that the working face advances evenly and that the initial support force of each support meets the standard.

[0062] In high-risk areas of water inrush from the aquifer, the water in the aquifer should be drained by surface pumping before each working face is mined, and the working face should be advanced evenly during the mining period. In low-risk areas of water inrush from the aquifer, geophysical exploration should be carried out before each working face is mined, and water should be drained from the low resistivity anomaly area of ​​the aquifer. The working face should be advanced evenly during the mining period.

[0063] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0064] 1. Traditional methods (water inrush coefficient method) rely on a single empirical formula, while GIS methods have multiple indicators but fragmented dimensions. This invention constructs a system of indicators for coal seam mining, overlying rock structure, stratigraphic spatial occurrence, and Cretaceous aquifer prediction based on hydrogeological, engineering geological, and coal seam mining data of the study area, thereby achieving collaborative evaluation of multi-source information.

[0065] 2. This invention achieves accurate prediction and evaluation of delamination water hazards by combining subjective and objective weights of the analytic hierarchy process, entropy weight method, and CRITIC method. This reduces the error of traditional delamination water hazard prediction results, greatly reduces the water hazard threat to the mining face, provides a guarantee for safe mining of coal mines, and effectively guides the design of coal mine drainage and safe production. Attached Figure Description

[0066] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0067] Picture 1 A schematic diagram of the delamination water hazard in the Yonglong Binchang mining area of ​​Shaanxi Province provided in this embodiment of the invention;

[0068] Picture 2 This is a flowchart illustrating a multi-source information fusion method for predicting and evaluating water hazards in high-level delamination of mining-induced overburden, as provided by the present invention. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. Of course, the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0070] Taking the ablation water hazard in the Yonglong Binchang mining area of ​​Shaanxi Province as an example (e.g.) Picture 1 (as shown), see also Picture 2 This invention provides a method for predicting and evaluating water hazards in high-level overburden separation caused by mining based on multi-source information fusion, comprising the following steps:

[0071] Step 1: Collect relevant data on hydrogeology, engineering geology, and coal seam mining in the study area, and statistically analyze the spatial occurrence and hydrogeological parameters of the coal seam overburden, including: coal seam thickness and burial depth, Cretaceous aquifer thickness, Cretaceous aquifer permeability coefficient, Cretaceous aquifer unit yield, coal seam overburden lithological characteristics, thickness of sand / mudstone in each stratum, and vertical distance between the coal seam and the Cretaceous aquifer, etc.

[0072] Step 2: Construct multi-source information prediction indicators for delamination water hazards. This includes coal seam mining indicators. I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and Cretaceous aquifer indices I 4. As a predictive and evaluation index for high-level delamination water hazards; calculate the coal seam mining index for the study area. I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and aquifer indicators I 4. Values ​​of the indicators.

[0073] In this embodiment, because the overlying strata of the caving zone have a certain degree of fragmentation and swelling, the delamination height must be less than the coal seam thickness. The smaller the coal seam thickness, the smaller the scale of overlying strata delamination; the larger the coal seam thickness, the greater the deformation of the overlying strata after mining, the larger the resulting delamination cavity, i.e., the space for water accumulation in the delamination cavity, and the greater the risk of delamination water hazards. Furthermore, as the coal seam burial depth increases, the overlying strata stress also increases, the overlying strata failure strength increases, and the risk of water-conducting fracture zones connecting to the delamination increases. Therefore, in this embodiment, the coal seam mining index is calculated according to the following formula. I 1:

[0074] ;

[0075] In the formula, M c This refers to the coal seam thickness, in meters (m). D This refers to the coal seam burial depth, expressed in meters (m). This is the standardized value for coal seam thickness; This is the standardized value for the coal seam burial depth.

[0076] In this embodiment, the overlying rock structure influences strata movement and the development of water-conducting fractures and delamination. The strata between the coal seam and the aquifer consist of alternating sandstone and mudstone. Sandstone has high mechanical strength, a small deformation and failure range, and is not easily connected to the overlying delamination. However, when the overlying rock structure is mainly mudstone, it is prone to fracture, but as a fracture channel, it is easily blocked by its own rock debris. Therefore, in this embodiment, the overlying rock structure index is calculated according to the following formula. I 2.

[0077] ;

[0078] In the formula, R s The proportion of overlying sandstone; R n The proportion of overlying mudstone; The standardized value for the proportion of overlying sandstone; This represents the standardized value for the proportion of overlying mudstone.

[0079] In this embodiment, delamination water inrush is often accompanied by a large influx of sediment into the working face. The mudstone of the Jurassic Yan'an Formation and Zhiluo Formation is more prone to cementation than sandstone, and the loss of particles further exacerbates delamination water inrush. Furthermore, the mudstone of the Anding Formation acts as an aquitard, inhibiting delamination water inrush. The greater the thickness of the Anding Formation mudstone, the stronger its resistance to water inrush, and the lower the likelihood of delamination water damage. In terms of stratigraphic spatial occurrence, whether delamination results in water inrush is also related to the distance between the Cretaceous aquifer and the coal seam. The smaller the distance between the Cretaceous aquifer and the coal seam, the more easily water-conducting fractures can affect the delamination space. Therefore, in this embodiment, the stratigraphic spatial occurrence index is calculated according to the following formula. I 3.

[0080] ;

[0081] In the formula, D ch The vertical distance from the Cretaceous strata to the coal seam is expressed in meters (m). M yz The total thickness of the mudstone in the Yan'an Formation and Zhiluo Formation is given in meters. M a The thickness of the Anding Formation mudstone is given in meters (m). This represents the standardized value of the distance between the Cretaceous strata and the coal seam. The standardized value represents the total thickness of the mudstone in the Yan'an and Zhiluo Formations; The value represents the standardized thickness of the mudstone in the Anding Formation.

[0082] In this embodiment, the water-bearing capacity of the aquifer directly affects the inflow scale of the aquifer, while traditional water-bearing capacity assessment obtains the unit inflow rate of the borehole through pumping tests. q Evaluation was conducted based on the unit flow rate. q This reflects the water supply capacity of the aquifer. Furthermore, mine water inrush is related not only to the water supply capacity of the aquifer but also to its water-bearing capacity. Thickness and permeability coefficient are the main indicators characterizing the water-bearing capacity of an aquifer; the greater the aquifer thickness and the greater the permeability coefficient, the greater the water-bearing capacity. Therefore, in this embodiment, the aquifer indicators are calculated according to the following formula. I 4:

[0083] ;

[0084] In the formula, M h The thickness of the aquifer is expressed in meters (m). K The aquifer permeability coefficient is expressed in m / d. q The unit yield of water in the aquifer is expressed in L / (s·m); This is the standardized value for the aquifer thickness; This is the standardized value of the aquifer permeability coefficient; This is the standardized value of the unit inflow rate of the aquifer.

[0085] In this embodiment, the standardization of each indicator is performed according to the following formula:

[0086] ;

[0087] In the formula, These are the raw data for each indicator; This represents the maximum value of each indicator; This represents the minimum value of each indicator; These are the normalized values ​​for each indicator.

[0088] Step 3: Construct a multi-source information fusion prediction and evaluation model for coal seam water hazards in the study area, and incorporate coal seam mining indicators... I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and aquifer water-bearing index I 4. The normalized values ​​of the four indicators were substituted into the constructed multi-source information fusion prediction and evaluation model for delamination water hazards to obtain the prediction and evaluation results.

[0089] In this embodiment, the analytic hierarchy process (AHP), entropy weight method, and CRITIC method are used to determine the subjective weight W1, objective weight W2, and objective weight W3. Then, the three weights are combined to obtain the comprehensive weight of each prediction and evaluation index.

[0090] In this embodiment, the steps for determining the subjective weight W1 using the analytic hierarchy process include:

[0091] Based on the analysis of each indicator, a hierarchical analysis model is constructed. Based on expert experience, pairwise comparisons are performed between the indicators to establish a judgment matrix. A :

[0092] ;

[0093] In the formula: x ij It is the first j The first indicator i Standardized values ​​for each sample.

[0094] Furthermore, based on the judgment matrix A Find the largest eigenvalue λ max and the corresponding eigenvectors W 1:

[0095] ;

[0096] In the formula, λ maxIt is a judgment matrix A The largest eigenvalue, the weight vector W 1. Normalization is performed to determine the weights of each factor. W 1j .

[0097] Furthermore, in order to determine the judgment matrix A Consistency is determined by the consistency ratio. CR The consistency ratio was tested. CR Calculate according to the formula ：

[0098] ;

[0099] In the formula, RI To determine the average random consistency index of a judgment matrix, judgment matrices of different orders... RI The values ​​are shown in Table 1; CI To determine the consistency index of a matrix, CI Calculate using the following formula:

[0100] ;

[0101] Table 1 Random Consistency RI Value table:

[0102]

[0103] In this embodiment, the entropy weight method objectively assigns weights to indicators based on the amount of information they contain. Generally, the greater the difference in the values ​​of an indicator, the smaller the information entropy, indicating that the indicator provides a greater amount of effective information, and thus has a greater weight. The steps for determining the objective weight W2 using the entropy weight method include:

[0104] The method for calculating the proportion of predictive evaluation indicators is as follows:

[0105] ;

[0106] In the formula, x ij It is the first j The first indicator i Standardized values ​​for each sample.

[0107] Furthermore, calculate and predict the first j The method for determining the information entropy of an evaluation index is as follows:

[0108] ;

[0109] Furthermore, calculate and predict the first j Weights of each evaluation indicator W 2jThe method is as follows:

[0110] .

[0111] In this embodiment, the CRITIC method comprehensively measures the objective weight of indicators based on the comparative strength and conflict between them. It considers both the magnitude of indicator variability and the correlation between indicators, recognizing that a larger number does not necessarily indicate greater importance, and utilizes the objective attributes of the data itself for scientific evaluation. The steps for determining the objective weight W3 using the CRITIC method include:

[0112] Calculate the variability among the various prediction and evaluation indicators:

[0113] ;

[0114] In the formula, For the first j The standardized mean of each indicator; For the first j Standard deviation of each indicator; x ij It is the first j The first indicator i Standardized values ​​for each sample.

[0115] Furthermore, the correlation coefficients between the various prediction and evaluation indicators are calculated:

[0116] ;

[0117] In the formula, For predictive evaluation indicators j and q The correlation coefficient; For the first j The first predictive indicator i Standardized values ​​for each sample; For the first q The first predictive indicator i Standardized values ​​for each sample; For the first j The standardized mean of each indicator; For the first q The standardized mean of each indicator.

[0118] Furthermore, the conflict between the various prediction and evaluation indicators is calculated:

[0119] ;

[0120] Furthermore, obtain the amount of information between the predictive evaluation indicators:

[0121] ;

[0122] Based on the amount of information, the first... j The weights W of each predictive indicator 3j :

[0123] ;

[0124] In this embodiment, the subjective weights of the tomographic analysis method and the objective weights of the entropy weight method and the CRITIC method are comprehensively calculated to determine the comprehensive weight. T j The calculation formula is as follows:

[0125] ;

[0126] In the formula, T j For the first j The overall weight of each indicator; W 1j The first one determined by the analytic hierarchy process j Subjective weighting of each indicator; W 2j The first one determined by the entropy weight method j The objective weight of each indicator; W 3j The first one determined by the CRITIC method j The objective weight of each indicator.

[0127] In this embodiment, the coal seam mining index I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and Cretaceous aquifer indices I 4. Standardize the data and obtain the multi-source information fusion prediction and evaluation model for delamination water damage according to the following formula:

[0128] ;

[0129] In the formula, For the first j Standardized values ​​of each predictive evaluation indicator; T j For the first j The comprehensive weight of each prediction and evaluation indicator.

[0130] Compared with existing technologies, this embodiment constructs a prediction index system for coal seam mining, overlying strata structure, stratigraphic spatial occurrence, and Cretaceous aquifers based on geological, hydrogeological, engineering geological, and coal seam mining data of the study area. Through a multi-source information fusion prediction and evaluation model for delamination water hazards using a combination of subjective and objective weights from the analytic hierarchy process, entropy weight method, and CRITIC method, it achieves accurate prediction and evaluation of delamination water hazards, reduces the error in predicting delamination water hazards, greatly reduces the water hazard threat to the mining face, provides a guarantee for safe coal mining, and effectively guides coal mine drainage design and safe production.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting and evaluating water hazards in high-level delamination layers of mining-induced overburden based on multi-source information fusion, characterized in that, Includes the following steps: Step 1: Collect hydrogeological, engineering geological and coal seam mining data of the study area, and obtain the spatial occurrence and hydrogeological parameters of coal seam overburden. The parameters include coal seam thickness and burial depth, Cretaceous aquifer thickness, permeability coefficient, unit water yield, overburden lithology characteristics, sand / mudstone thickness of each stratum and vertical distance from coal seam to Cretaceous aquifer. Step 2: Construct a multi-source information prediction index system for delamination water hazards, including coal seam mining indicators. I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and Cretaceous aquifer indices I 4. Four indicators; the coal seam mining indicators I The formula for calculating 1 is: ; In the formula, M c This refers to the coal seam thickness, in meters (m). D This refers to the coal seam burial depth, expressed in meters (m). This is the standardized value for coal seam thickness; This is the standardized value for the coal seam burial depth; The overburden structure index I The formula for calculating 2 is: ; In the formula, R s The proportion of overlying sandstone; R n The proportion of overlying mudstone; The standardized value for the proportion of overlying sandstone; The standardized value for the proportion of overlying mudstone; The spatial occurrence index of the stratigraphy I The formula for calculating 3 is: ; In the formula, D ch The vertical distance between the Cretaceous aquifer and the coal seam is expressed in meters (m). M yz The total thickness of the mudstone in the Yan'an Formation and Zhiluo Formation is given in meters. M a The thickness of the Anding Formation mudstone is given in meters (m). This represents the standardized value of the distance between the Cretaceous strata and the coal seam. The standardized value represents the total thickness of the mudstone in the Yan'an and Zhiluo Formations; The standardized value for the thickness of the mudstone in the Anding Formation; The Cretaceous aquifer index I The formula for calculating 4 is: ; In the formula, M h The thickness of the aquifer is expressed in meters (m). K The aquifer permeability coefficient is expressed in m / d. q The unit yield of water in the aquifer is expressed in L / (s·m); This is the standardized value for the aquifer thickness; This is the standardized value of the aquifer permeability coefficient; This represents the standardized value of the unit inflow rate of the aquifer. Step 3: Standardize the four indicators using the following formula: ； In the formula, These are the raw data for each indicator; This represents the maximum value of each indicator; This represents the minimum value of each indicator; The normalized values ​​for each indicator are used; Step 4: Determine the subjective weight W1 using the analytic hierarchy process, the objective weight W2 using the entropy weight method, and the objective weight W3 using the CRITIC method. Calculate the comprehensive weight T for each indicator based on the combined weight formula. j The calculation formula is as follows: ； In the formula, T j For the first j The overall weight of each indicator; W 1j The first one determined by the analytic hierarchy process j Subjective weighting of each indicator; W 2j The first one determined by the entropy weight method j The objective weight of each indicator; W 3j The first one determined by the CRITIC method j The objective weight of each indicator; Step 5: Combine the standardized indicator values ​​with the comprehensive weights to construct a multi-source information fusion prediction and evaluation model. The calculation formula is as follows: ； In the formula, For the first j Standardized values ​​of each predictive evaluation indicator; T j For the first j Step 6: Output the prediction and evaluation results based on the multi-source information fusion prediction and evaluation model to guide the prevention and control of delamination water hazards.

2. The method for predicting and evaluating water hazards in high-level delamination of mining-induced overburden by multi-source information fusion as described in claim 1, characterized in that, The steps for determining subjective weights using the analytic hierarchy process include: constructing a judgment matrix and calculating the largest eigenvalue and eigenvector; obtaining the weights after passing a consistency check; specifically: Based on the analysis of each indicator, a hierarchical analysis model is constructed; pairwise comparisons are performed between the indicators to establish a judgment matrix. A : ； In the formula, x ij It is the first j The first indicator i Standardized values ​​for each sample; Furthermore, based on the judgment matrix A Find the largest eigenvalue λ max and the corresponding eigenvectors W 1: ； In the formula, λ max It is a judgment matrix A The largest eigenvalue, the weight vector W 1. Normalization is performed to determine the weights of each indicator. W 1j ; In order to determine the judgment matrix A Consistency is determined by the consistency ratio. CR The consistency ratio was tested. CR Calculate according to the formula ： ； In the formula, RI To determine the average random consistency index of a matrix; CI To determine the consistency index of a matrix, CI Calculate using the following formula: 。 3. The method for predicting and evaluating water hazards in high-level delamination of mining-induced overburden by multi-source information fusion according to claim 2, characterized in that, The steps for determining objective weights using the entropy weight method include: calculating the information entropy of each indicator and assigning weights based on the differences in entropy values; specifically: The method for calculating the proportion of predictive evaluation indicators is as follows: ； In the formula, x ij It is the first j The first indicator i Standardized values ​​for each sample; The method for calculating the information entropy of prediction and evaluation indicators is as follows: ； The method for calculating the weights of the predictive evaluation indicators is as follows: 。 4. The method for predicting and evaluating water hazards in high-level delamination of mining-induced overburden by multi-source information fusion as described in claim 3, characterized in that, Step four, determining the overall weights, includes: calculating the variability, conflict, and information content of the indicators, and assigning weights based on the information content; specifically: Calculate the variability among the various prediction and evaluation indicators: ； In the formula, For the first j The standardized mean of each indicator; For the first j Standard deviation of each indicator; x ij It is the first j The first indicator i Standardized values ​​for each sample; Furthermore, the correlation coefficients between the various prediction and evaluation indicators are calculated: ； In the formula, For predictive evaluation indicators j and q The correlation coefficient; For the first j The first predictive indicator i Standardized values ​​for each sample; For the first q The first predictive indicator i Standardized values ​​for each sample; For the first j The standardized mean of each indicator; For the first q The standardized mean of each indicator; Furthermore, the conflict between the various prediction and evaluation indicators is calculated: ； Furthermore, obtain the amount of information between the predictive evaluation indicators: ； Based on the amount of information, the weights of each prediction indicator are obtained: ； The subjective weights of the tomographic analysis method, along with the objective weights of the entropy weight method and the CRITIC method, are combined to determine the overall weight. T j The calculation formula is as follows: ； Coal seam mining indicators I 1. Overburden structure index I 2. Stratigraphic Spatial Occurrence Indicators I 3 and Cretaceous aquifer indices I 4. Standardize the data and obtain the multi-source information fusion prediction and evaluation model for delamination water damage according to the following formula: ； In the formula, These are the standardized values ​​for each prediction and evaluation indicator; T j The comprehensive weight of each prediction and evaluation indicator.

5. The method for predicting and evaluating water hazards in high-level delamination of mining-induced overburden by multi-source information fusion as described in claim 1, characterized in that, The prediction and evaluation results output by the model are used to guide water hazard prevention and control measures in the longwall mining face. Based on the water inrush situation in the working face, the prediction and evaluation results are divided into three levels: 0.75 < P < 1.0 is a high-risk area for water inrush due to separation; 0.25 ≤ P ≤ 0.75 is a medium-risk area for water inrush due to separation; and 0 < P < 0.25 is a low-risk area for water inrush due to separation. In areas with a high risk of water inrush due to separation, the water inrush should be treated by surface pumping and grouting before mining. During mining, the water level of the aquifer should be monitored more frequently to ensure that the working face advances evenly and that the initial support force of each support meets the standard. In high-risk areas of water inrush from the aquifer, the water in the aquifer should be drained by surface pumping before each working face is mined, and the working face should be advanced evenly during the mining period. In low-risk areas of water inrush from the aquifer, geophysical exploration should be carried out before each working face is mined, and water should be drained from the low resistivity anomaly area of ​​the aquifer. The working face should be advanced evenly during the mining period.

Images