Water flowing fractured zone development height prediction method under near mining condition

Abstract

The invention belongs to the technical field of coal mining safety, and discloses a method for predicting the development height of a water-flowing fractured zone under an adjacent mining condition, and the method comprises the following steps: S1, collecting target data, S2, collecting drilling data, S3, judging the position of a hard rock layer, S4, calculating the height of the water-flowing fractured zone, S5, dividing a rock layer, and S6, building a damage judgment model. According to the method, the influence of the single-side adjacent goaf on the to-be-mined working face is considered, the water flowing fracture height judgment model is established and verified based on the plate theory, in addition, disordered data and data with large differentiation can be removed through a data cleaning mode, and the prediction accuracy is greatly improved.

Description

Technical Field

[0001] The invention belongs to the technical field of coal mining safety, and in particular relates to a method for predicting the development height of a water-conducting fracture zone under conditions close to mining. Background Art

[0002] The proportion of coal in my country's energy system has declined this year, but its total consumption has continued to increase, and it will occupy the dominant position in my country's energy system for a long time in the future. As the largest integrated coalfield in my country, the Lianghuai mining area has extensive thick loose aquifers above its coal seams. In addition, long-term high-intensity coal mining has led to a more complex evolution process of mining fractures than conventional mining conditions, with more influencing factors. The development of water-conducting fractures not only increases the risk of water inrush at the working face, but also affects the layout of underground pipelines in coal mines, seriously restricting the safe production of coal mines and endangering the safety of coal mine personnel and the economy. In existing studies, empirical formulas, theoretical analysis, indoor simulations, and field monitoring are usually used to study the development height of water-conducting fractures under different mining conditions.

[0003] In the prior art, the prediction of water-conducting fracture zones is generally only carried out through existing data. However, the influencing factors that need to be considered between the height of the water-conducting fracture zone in the existing data and the height of the water-conducting fracture zone to be predicted are different. In the existing data, the height data of the water-conducting fracture zone has been finalized, and it is impossible to judge the influence of other factors on the fracture zone. The height of the fracture zone to be predicted needs to take into account the direct and indirect influence of other factors, which leads to a large error between the prediction based on the existing data and the actual data. In addition, in the process of studying the evolution law of the water-conducting fracture zone in the Lianghuai mining area, it was found that due to the influence of the extremely thick loose aquifer and the increasing mining intensity, the traditional empirical formula is quite different from the actual height of the water-conducting fracture zone. The indoor simulation method is relatively idealized and it is difficult to accurately reflect the development process on site. Only qualitative analysis can be carried out. At the same time, the actual observation method often has a large workload and high cost. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a grouting assembly with multiple grouting ports and a grouting machine thereof, which solves the problems in the prior art.

[0005] The object of the present invention can be achieved by the following technical scheme: A method for predicting the height of water-conducting fracture zone development under near-mining conditions, comprising the following steps: S1, collecting target data, S2, collecting drilling data, S3 judging the position of hard rock layer, S4, calculating the height of water-conducting fracture zone, S5, dividing rock layer, S6, establishing a damage judgment model;

[0006] In step S3, it can be known from the key layer theory that if the first rock layer is a hard rock layer, the rock layers above it to the mth layer deform in coordination with it, and the m+1th rock layer does not deform in coordination with it, then the m+1th rock layer is the second hard rock layer. Since the first to mth rock layers deform in coordination, the curvatures of the rock layers are the same, and the rock layers form a composite beam. The load acting on the first hard rock layer is derived from the composite beam principle as follows;

[0007]

[0008] In the formula, q 1 (x)| is the load formed by the mth rock layer on the first hard rock layer; hi, γi, Ei are the thickness, bulk density, and elastic modulus of the i-th rock layer (i = 1, 2, ..., m);

[0009] If the m+1th layer is a hard rock layer, its deflection is less than the deflection of the lower rock layer, and the rock layer above the m+1th layer no longer needs the lower rock layer to bear the load it bears, then there must be;

[0010] q 1 (x) m+1 <q 1 (x) m

[0011] At this time, from the 1st rock layer upwards, the mth rock layer is the 1st hard rock layer. Starting from the 1st hard rock layer, the position of the 2nd hard rock layer is determined according to the above method, and so on, until the top hard rock layer is determined, which is set as the nth hard rock layer. By determining the position of the hard rock layer, the position of the hard rock layer in the overburden and the soft rock layer group it controls are obtained.

[0012] In some disclosures, in step S1, geological and hydrological data of the target study area are collected to understand the mining conditions and working face parameters in the area, including the planning of the working face, the depth, thickness, mining height, mining width and relative position of the work face of the mineable coal seam, geological structural conditions and hydrogeological conditions. The depth of the coal seam is 480m, the thickness is 2.8m, the mining height is 3m, and the mining width is 300m. When collecting the measured data of the development height of the water-conducting fracture zone, the measured data is also preprocessed, including removing outliers and performing normalization.

[0013] In some disclosures, in step S2, drilling data of the study area is collected, and the thickness of the loose layer in the study area and the division of each layer in the rock formation are determined according to the drilling logging curve. At the same time, the type of working face top plate, the proportion of hard rock lithology in the overburden, and the lithological parameters of each layer are determined, including thickness, bulk density, Poisson's ratio, elastic modulus, tensile strength, and average density.

[0014] In some disclosures, in step S1 and step S2, the mining area data mentioned in step S1 and step S2 are processed, and the processing process includes data cleaning;

[0015] Data cleaning, min-max normalization refers to the process of converting data to the same range. Min-max normalization can be achieved by the following formula:

[0016] X{norm}=frac{XX{min}}{X{max}-X{min}}

[0017] Among them, X{norm} is the normalized data value, X is the original data value, X{min} is the minimum data value, and X{max} is the maximum data value;

[0018] Z-score normalization refers to the process of converting data into a normal distribution. Z-score normalization can be achieved by the following formula:

[0019] Z=X-μσZ=X-μσ

[0020] Among them, Z is the normalized data value, X is the original data value, μ is the mean value, and σ is the standard deviation;

[0021] Mean normalization refers to the process of converting data to a mean value of 0. Mean normalization can be achieved by the following formula:

[0022]

[0023] X std is the standardized data value, X is the original data value, μ is the mean, and σ is the standard deviation.

[0024] In some disclosures, the target data is collected according to step S1 and the drilling data is collected according to step S2, and a preliminary prediction is made on the development height of the water-conducting fracture zone. The development height data of the water-conducting fracture zone is used as a prediction object sample, and the development height of the target water-conducting fracture zone to be predicted is used as a prediction sample. The Euclidean distance is calculated based on the influencing factors in the prediction sample and the prediction object sample. The calculation formula of the Euclidean distance is:

[0025] rt(i)=j=1∑p(di j-dtj)2;

[0026] Where rt(i) represents the Euclidean distance between the predicted sample and the predicted object sample, dij and dtj are the jth influencing factors of the predicted sample and the predicted object sample respectively, and p is the number of influencing factors;

[0027] After calculating the Euclidean distance, the calculated Euclidean distances are arranged from small to large, and the predicted object samples corresponding to the first K minimum distance samples are taken, where K is calculated as follows;

[0028] K=n, K is the number of nearest neighbor samples, n is the number of prediction object samples, and the calculation method of the sample weight is:

[0029] Wj(n+1)=K1,L=1∑KL1;

[0030] Wj(n+1) is the sample weight, j=1,2,…,K, L is the Lth nearest neighbor sample;

[0031] The development height of the water-conducting fracture zone is predicted based on the sample weights, and the calculation formula for the predicted value of the development height of the water-conducting fracture zone is:

[0032] Hpred=j=1∑Kyj·Wj(n+1)

[0033] Among them, Hpred is the predicted value of the development height of the water-conducting fracture zone, yj is the development height of the water-conducting fracture zone of the jth nearest neighbor prediction object sample, and Wj(n+1) is the sample weight corresponding to yj.

[0034] In some disclosures, in step S3, the position of the hard rock layer in the formation is determined based on the key layer theory.

[0035] In some disclosures, in step S4, the height of the water-conducting fracture zone is calculated according to the roof type of the working face to be mined and the empirical formula of the water-conducting fracture zone;

[0036] For gently inclined (<25°) and inclined (25°~45°) coal seams, the height of the water-conducting fracture zone is calculated using the following empirical formula for hard rock formations:

[0037] Formula 1: Hli = 100M / (αM+β)±γ, where α, β, γ are constants and M is the cumulative mining thickness;

[0038] For medium-hard rock formations, the calculation formula is the same as Formula 1, but the values ​​of constants α, β, γ or a, b are different.

[0039] In some disclosures, in the step S5 of dividing the rock strata, the empirical formula for calculating the height of the water-conducting fracture zone of the working face to be mined is used to divide it into low-level rock strata and high-level rock strata according to the distance between the strata and the roof.

[0040] In some disclosures, in the destruction judgment model established in step S6, the rock layer is regarded as an isotropically uniform thin plate. According to the theory of elastic mechanics, its upper and lower horizontal planes are the plate surfaces, and the vertical plane is the plate edge. The vertical distance between the two horizontal planes is the thickness of the plate, defined as h. The long and short sides of the horizontal plane are defined as a and b, respectively. Corresponding to the working face, a is the strike length of the working face, and b is the dip length of the working face. As far as the overlying rock layer on the mining working face is concerned, h<b / 5 is satisfied, which meets the definition of an elastic thin plate.

[0041] In some disclosures, the location of the hard rock formation and the damage and fracture model established in step S6 are combined to determine the development height of the water-conducting fracture zone.

[0042] The nouns, conjunctions or adjectives involved in the above technical solution are explained as follows:

[0043] A fixed connection is one where the parts or components are fixed without any relative movement;

[0044] A rotational connection is a connection between parts that allows the parts to rotate relative to each other;

[0045] Threaded connection is a detachable fixed connection with the advantages of simple structure, reliable connection, and convenient assembly and disassembly. It is widely used in the fields of mechanical engineering and connection structures.

[0046] A sliding connection is a connection between parts that allows the parts to slide against each other;

[0047] The key layer theory refers to the fact that due to the differences in the stratification characteristics of coal-bearing strata, the role of each rock layer in rock mass activity is different. Some relatively hard and thick rock layers play a controlling role in the activity, that is, they play the role of the load-bearing body and skeleton; some relatively weak and thin rock layers only play a loading role in the activity, and most of their deadweight is borne by the hard and thick rock layers. The fracture of the key layer will cause the overall movement of all or a considerable part of the overlying rock layer. There may be more than one sub-key layer in the overlying rock layer, while there is only one main key layer. The key layer in the overlying rock layer of the mining area is generally a relatively thick and hard rock layer. The key layer theory believes that when there are multiple rock layers in the overlying rock layer of the mining area, the rock layer that plays a controlling role in all or part of the rock mass activity is called the key layer. The main basis for distinguishing the key layer is its deformation and fracture characteristics. When the key layer breaks, the sinking deformation of the upper rock layer is coordinated with each other.

[0048] Beneficial effects of the present invention:

[0049] 1. The present invention can reduce data duplication by utilizing data cleaning, thereby ensuring that the collected mining area data can be accurate. In addition, through data cleaning, it can eliminate messy data and data with large differences, greatly increasing the accuracy of the prediction.

[0050] 2. The present invention can greatly reduce errors and improve the accuracy of prediction by predicting sample data and sample object data separately and using weighted calculation.

[0051] 3. The present invention utilizes plate theory and key layer theory to enable the method to predict the height of the water-conducting fracture zone under the conditions of lateral mining of thick loose layers during the prediction process. The method is practical, economical and effective. By establishing a model, the predicted value can be made close to the measured value, which proves the accuracy of the theoretical calculation method. 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 drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 is a schematic diagram of a method flow of an embodiment of the present invention;

[0054] Figure 2 is a schematic diagram of an elastic plate model according to an embodiment of the present invention;

[0055] Figure 3 Schematic diagram of a three-side clamped and one-side simply supported plate model according to an embodiment of the present invention;

[0056] Figure 4 is a schematic diagram of a four-side fixed support plate model according to an embodiment of the present invention;

[0057] Figure 5 Schematic diagram of the relative positions of working surfaces in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0059] See also Figure 2 , Figure 3 , Figure 4 and Figure 5 , Figure 1 is an elastic plate model, where h is the plate thickness, q is the overlying load on the plate, and a and b are the longer and shorter sides of the plate, respectively. Figure 2 It is a plate model with three sides fixed and one side simply supported, corresponding to the low-lying rock layer; Figure 3It is a plate model with four sides fixed, corresponding to the high rock layer. Figure 4 1 is the relative position of the working faces in the embodiment, where 1 is the working face to be mined and 2 is the mined working face.

[0060] See also Figure 1 , Step 1, collect geological and hydrological data of the target study area, and master the mining conditions and working face parameters in the area, including working face planning, depth, thickness, mining height, mining width and relative position of the working face of the mineable coal seam. The depth of the coal seam is 480m, the thickness is 2.8m, the mining height is 3m, the mining width is 300m, and the relative position is shown in Figure 4 .

[0061] Step 2: Collect the drilling data in the study area, and determine the thickness of the loose layer in the study area and the division of each layer in the rock layer according to the drilling logging curve. At the same time, determine the type of the working face roof, the proportion of hard rock in the overburden, and the lithological parameters of each layer (including thickness, bulk density, Poisson's ratio, elastic modulus, tensile strength, and average density). The parameters of the rock layer are shown in the following table:

[0062]

[0063]

[0064] Step 3: Determine the location of the hard rock layer in the stratum based on the key layer theory.

[0065] From the critical layer theory, we know that if the first rock layer is a hard rock layer, the rock layers above it to the mth layer deform in coordination with it, and the m+1th layer does not deform in coordination with it, then the m+1th layer is the second hard rock layer. Since the first to the mth layers deform in coordination, the curvatures of the rock layers are the same, and the rock layers form a composite beam. From the composite beam principle, the load acting on the first hard rock layer can be derived as:

[0066]

[0067] In the formula, q 1 (x)| is the load exerted by the mth rock layer on the first hard rock layer; hi, γi, Ei are the thickness, bulk density, and elastic modulus of the ith rock layer, respectively (i=1, 2,…, m).

[0068] If the m+1th layer is a hard rock layer, its deflection is less than the deflection of the lower rock layer, and the rock layer above the m+1th layer no longer needs the lower rock layer to bear the load it bears, then there must be:

[0069] q 1 (x)| m+1 <q 1 (x)| m

[0070] At this time, from the first rock layer upward, the mth rock layer is the first hard rock layer. Starting from the first hard rock layer, the position of the second hard rock layer is determined according to the above method, and so on, until the top hard rock layer (set as the nth hard rock layer) is determined. By determining the position of the hard rock layer, the position of the hard rock layer in the overburden and the soft rock layer group to which it belongs are obtained.

[0071] Step 4: Calculate the height of the water-conducting fracture zone according to the roof type of the working face to be mined and the empirical formula of the water-conducting fracture zone.

[0072] According to different roof lithology, the prediction formula of collapse zone height is as follows:

[0073]

[0074] The fracture zone height prediction formula is as follows:

[0075]

[0076] In the above formula: ∑M is the cumulative mining thickness, m; the single layer mining thickness is 1 to 3m, and the cumulative mining thickness does not exceed 15m; the ± term is the error; H m is the height of the collapse zone, m; H l is the height of the fracture zone, m.

[0077] The average thickness of the coal seam in the working face of the study area is 3.20m. The roof is mainly sandstone, which is a medium-hard rock. The corresponding formula in the table is substituted into the calculation to obtain the maximum height H of the collapse zone formed after mining. m for:

[0078] H m =9.40±2.2=7.20~12.60m

[0079] Substituting the parameters into the coal seam fracture zone height range, we can get: 36.70±5.6m (Formula 1), 35.78+10m (Formula 2). In summary, according to the results of the empirical formula, the maximum development height of the water-conducting fracture zone of the working face is 54.9m

[0080] Step 5: Calculate the height of the water-conducting fracture zone of the working face to be mined using the empirical formula. According to the distance between the stratum and the roof, those less than 54.9m are classified as low-lying strata, and those greater than 54.9m are classified as high-lying strata.

[0081] Step 6: Establish the damage judgment model of the lower rock layer and the upper rock layer respectively according to the plate theory.

[0082]

[0083] Step 7, determine the height of the water-conducting fracture zone by combining the position of the hard rock layer and the damage and fracture model established in step 6. As shown in the table below: all the low-level rock layers are damaged, the mudstone at the lower end of the high-level rock layer is damaged, and the hard rock layers of sequence numbers 9 and 4 are not damaged. Sequence number 9 can bear the load of the overlying rock layer. Therefore, it is inferred that the theoretical height of the water-conducting fracture zone is 71m. From the measured data, it can be seen that the height of the water-conducting fracture zone of the working face is between 70m and 80m. The predicted value is close to the measured value, which proves the accuracy of the theoretical calculation method.

[0084]

[0085]

[0086]

[0087]

[0088] In step S1 and step S2, the mining area data mentioned in step S1 and step S2 are processed, and the processing process includes data cleaning;

[0089] Data cleaning, min-max normalization refers to the process of converting data to the same range. Min-max normalization can be achieved by the following formula:

[0090] X{norm}=frac{XX{min}}{X{max}-X{min}}

[0091] Among them, X{norm} is the normalized data value, X is the original data value, X{min} is the minimum data value, and X{max} is the maximum data value;

[0092] Z-score normalization refers to the process of converting data into a normal distribution. Z-score normalization can be achieved by the following formula:

[0093] Z=X-μσZ=X-μσ

[0094] Among them, Z is the normalized data value, X is the original data value, μ is the mean value, and σ is the standard deviation;

[0095] Mean normalization refers to the process of converting data to a mean value of 0. Mean normalization can be achieved by the following formula:

[0096]

[0097] X std is the standardized data value, X is the original data value, μ is the mean, and σ is the standard deviation.

[0098] In some disclosures, the target data is collected according to step S1 and the drilling data is collected according to step S2, and a preliminary prediction is made on the development height of the water-conducting fracture zone. The development height data of the water-conducting fracture zone is used as a prediction object sample, and the development height of the target water-conducting fracture zone to be predicted is used as a prediction sample. The Euclidean distance is calculated based on the influencing factors in the prediction sample and the prediction object sample. The calculation formula of the Euclidean distance is:

[0099] rt(i)=j=1∑p(di j-dtj)2;

[0100] Where rt(i) represents the Euclidean distance between the predicted sample and the predicted object sample, dij and dtj are the jth influencing factors of the predicted sample and the predicted object sample respectively, and p is the number of influencing factors;

[0101] After calculating the Euclidean distance, the calculated Euclidean distances are arranged from small to large, and the predicted object samples corresponding to the first K minimum distance samples are taken, where K is calculated as follows;

[0102] K=n, K is the number of nearest neighbor samples, n is the number of prediction object samples, and the calculation method of the sample weight is:

[0103] Wj(n+1)=K1,L=1∑KL1;

[0104] Wj(n+1) is the sample weight, j=1,2,…,K, L is the Lth nearest neighbor sample;

[0105] The development height of the water-conducting fracture zone is predicted based on the sample weights, and the calculation formula for the predicted value of the development height of the water-conducting fracture zone is:

[0106] Hpred=j=1∑KyjWj(n+1)

[0107] Among them, Hpred is the predicted value of the development height of the water-conducting fracture zone, yj is the development height of the water-conducting fracture zone of the jth nearest neighbor prediction object sample, and Wj(n+1) is the sample weight corresponding to yj.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0109] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A method for predicting the height of water-conducting fracture zones under near-mining conditions, characterized in that: The method comprises the following steps: S1, collecting target data, S2, collecting drilling data, S3, determining the position of the hard rock layer, S4, calculating the height of the water-conducting fracture zone, S5, dividing the rock layer, and S6, establishing a damage determination model; In S3, according to the critical layer theory, assuming that the first rock layer is a hard rock layer, the rock layers above it to the mth layer deform in coordination with it, and the m+1th rock layer does not deform in coordination with it, then the m+1th rock layer is the second hard rock layer. Since the first to mth rock layers deform in coordination, the curvatures of the rock layers are the same, and the rock layers form a composite beam. The load acting on the first hard rock layer is derived from the composite beam principle; Where q1(x)| is the load formed by the mth rock layer on the first hard rock layer; hi, γi, Ei are the thickness, bulk density, and elastic modulus of the i-th rock layer (i = 1, 2, ..., m). If the m+1th layer is a hard rock layer, its deflection is less than the deflection of the lower rock layer, and the rock layer above the m+1th layer no longer needs the lower rock layer to bear the load it bears, then there must be; q1(x)| m+1 <q1(x)| m At this time, starting from the 1st rock layer upwards, the mth rock layer is the 1st hard rock layer. Starting from the 1st hard rock layer, the position of the 2nd hard rock layer is determined according to the above method, and so on, until the top hard rock layer is determined and set as the nth hard rock layer. By determining the position of the hard rock layer, the position of the hard rock layer in the overburden and the soft rock layer group it controls are obtained.

2. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1 is characterized in that: In the S1, geological and hydrological data of the target study area are collected to understand the mining conditions and working face parameters in the area, including the planning of the working face, the depth, thickness, mining height, mining width and relative position of the work face of the mineable coal seam, geological structural conditions and hydrogeological conditions. The depth of the coal seam is 480m, the thickness is 2.8m, the mining height is 3m, and the mining width is 300m. When collecting the measured data of the development height of the water-conducting fracture zone, the measured data is also preprocessed, including removing outliers and performing normalization processing.

3. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1 is characterized in that: In S2, the drilling data of the study area are collected, and the thickness of the loose layer in the study area and the division of each layer in the rock layer are determined according to the drilling logging curve. At the same time, the type of the working face roof, the proportion of hard rock in the overburden, and the lithological parameters of each layer are determined, including thickness, bulk density, Poisson's ratio, elastic modulus, tensile strength, and average density.

4. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1 is characterized in that: In S1 and S2, the mining area data mentioned in S1 and S2 are processed, and the processing process includes data cleaning; Data cleaning, min-max normalization refers to the process of converting data to the same range. Min-max normalization can be achieved by the following formula: X{norm}=frac{XX{min}}{X{max}-X{min}} Among them, X{norm} is the normalized data value, X is the original data value, X{min} is the minimum data value, and X{max} is the maximum data value; Z-score normalization refers to the process of converting data into a normal distribution. Z-score normalization can be achieved by the following formula: Z=X-μσZ=X-μσ Among them, Z is the normalized data value, X is the original data value, μ is the mean value, and σ is the standard deviation; Mean normalization refers to the process of converting data to a mean value of 0. Mean normalization can be achieved by the following formula: X std is the standardized data value, X is the original data value, μ is the mean, and σ is the standard deviation.

5. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1, characterized in that: The step S1 collects target data and the step S2 collects drilling data, performs preliminary prediction on the height of the water-conducting fracture zone, takes the water-conducting fracture zone height data as the prediction object sample, takes the target water-conducting fracture zone height to be predicted as the prediction sample, and calculates the Euclidean distance based on the influencing factors in the prediction sample and the prediction object sample. The calculation formula of the Euclidean distance is: rt(i)=j=1∑p(dij-dtj)2; Where rt(i) represents the Euclidean distance between the predicted sample and the predicted object sample, dij and dtj are the jth influencing factors of the predicted sample and the predicted object sample respectively, and p is the number of influencing factors; After calculating the Euclidean distance, the calculated Euclidean distances are arranged from small to large, and the predicted object samples corresponding to the first K minimum distance samples are taken, where K is calculated as follows; K=n, K is the number of nearest neighbor samples, n is the number of prediction object samples, and the calculation method of the sample weight is: Wj(n+1)=K1,L=1∑KL1; Wj(n+1) is the sample weight, j=1,2,…,K, L is the Lth nearest neighbor sample; The development height of the water-conducting fracture zone is predicted based on the sample weights, and the calculation formula for the predicted value of the development height of the water-conducting fracture zone is: Hpred=j=1∑Kyj·Wj(n+1) Among them, Hpred is the predicted value of the development height of the water-conducting fracture zone, yj is the development height of the water-conducting fracture zone of the jth nearest neighbor prediction object sample, and Wj(n+1) is the sample weight corresponding to yj.

6. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1, characterized in that: In S3, the position of the hard rock layer in the stratum is determined based on the key layer theory.

7. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1, characterized in that: In S4, the height of the water-conducting fracture zone is calculated according to the roof type of the working face to be mined and the empirical formula of the water-conducting fracture zone; For gently inclined (<25°) and inclined (25°~45°) coal seams, the height of the water-conducting fracture zone is calculated using the following empirical formula for hard rock formations: Formula: Hli = 100M / (αM+β)±γ, where α, β, γ are constants and M is the cumulative mining thickness; For medium-hard rock formations, the calculation formula is the same as Formula 1, but the values ​​of constants α, β, γ or a, b are different.

8. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1 is characterized in that: In the S5 divided rock formation, the calculation result of the height of the water-conducting fracture zone of the working face to be mined is divided into low-level rock formation and high-level rock formation according to the distance between the formation and the roof.

9. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1, characterized in that: In the damage judgment model established in S6, the rock layer is regarded as an isotropically uniform thin plate. According to the theory of elastic mechanics, its upper and lower horizontal planes are the plate surface, the vertical plane is the plate edge, and the vertical distance between the two horizontal planes is the thickness of the plate, which is defined as h. The long side and the short side of the horizontal plane are defined as a and b respectively. Corresponding to the working face, a is the strike length of the working face, and b is the dip length of the working face. As far as the overlying rock layer on the mining working face is concerned, h<b / 5 is satisfied, which meets the definition of an elastic thin plate.

10. The method for predicting the height of water-conducting fracture zones under near-mining conditions according to claim 1, characterized in that: The development height of the water-conducting fracture zone is determined by combining the location of the hard rock layer and the damage and fracture model established by S6.

Images