Method and device for predicting water inflow of coal mine roadway tunneling

Abstract

The invention provides a coal mine roadway tunneling water inflow prediction method and device, and the method comprises the following steps: 1, carrying out the exploration and obtaining of the geological key parameters of a coal mine roadway tunneling section, and collecting the water inflow in a tunneling roadway through a collection device; step 2, establishing a roadway tunneling water inflow prediction data sample; 3, extracting main features of the water inflow prediction data; 4, performing training based on the feature vector samples to construct a plurality of prediction models; 5, obtaining an optimal value of the predicted parameters of the model; step 6, constructing a plurality of optimized prediction models; and step 7, inputting key parameter survey values of an untunneled area of the roadway, and obtaining a prediction result of the coal mine roadway tunneling water inflow. The water inflow value can be quickly obtained based on the water inflow collection device, and the prediction accuracy of the coal mine tunnel tunneling water inflow is effectively improved by considering the water inflow prediction result of the multiple characteristic parameters.

Description

Technical Field

[0001] The invention belongs to the technical field of tunnel construction, and in particular relates to a method and a device for predicting water inflow during tunneling of a coal mine. Background Art

[0002] During the coal mine tunnel excavation process, water gushing is an event that is often encountered during the excavation process. When the amount of water gushing is too large, it is very easy to cause water gushing disasters. Therefore, it is necessary to accurately predict the water gushing in coal mine tunnel excavation and take effective countermeasures to ensure the safety of tunnel construction.

[0003] At present, a research method consisting of analytical, empirical and numerical methods is often used to estimate the water inrush of the roadway. However, the analytical solution depends on the given hydrogeological assumptions and cannot predict the water flow under complex hydrogeological conditions, such as fractured rock formations. In addition, the problem of water inrush in the roadway under various complex geological conditions can also be analyzed by numerical simulation. However, the numerical model requires a real generalized model based on the input geological data. In addition, they either do not take into account the assessment of the risk of water inrush or do not deeply reveal the quantitative relationship between water inrush and influencing factors. Therefore, due to the given hydrogeological assumptions and the simplification of these heterogeneous media, the prediction of possible water inrush in the roadway using analytical solutions and numerical tools often fails. At the same time, the above methods will have the problem of slow computational efficiency when calculating the water inrush. In fact, the entire geological conditions can be regarded as a chaotic system. Therefore, the general exploration methods cannot accurately detect the hydrogeological characteristics.

[0004] Based on this, a method and device for predicting water inrush during coal mine tunnel excavation are proposed. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and device for predicting water inflow in coal mine tunnel excavation in view of the deficiencies of the above-mentioned prior art, so as to solve the problems raised in the above-mentioned background technology.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] In a first aspect, a device for predicting water inflow during tunneling in a coal mine includes a first collecting trough, a second collecting trough, a movable partition, and a telescopic third collecting trough;

[0008] The first collection trough is composed of a partition, a top steel mesh and a front steel mesh. The top steel mesh is arranged on the top surface of the partition. The top steel mesh is used to receive the fallen rocks with larger particle sizes on the top and ensure that the water in the tunnel can flow into the water inflow collection device. The front steel mesh is arranged at the front end of the partition. The front steel mesh is used to filter the sand and stones in the tunnel water.

[0009] The second collecting tank is provided with a tank depth height scale inside, and a buoyancy ball is also provided inside the second collecting tank;

[0010] The movable partition is provided with a groove, a stretching rod, a rotating shaft, a rotating rod, a compression rod, and a compression U-shaped rod are arranged inside the groove, and a first spring and a second spring are arranged at the connection between the movable partition and the second collection slot;

[0011] The third collecting trough is provided with a groove depth scale, the third slide groove on the first partition of the third collecting trough is a convex slide groove, the third slide groove is located on the inner side of the first partition, the first slide groove of the second collecting trough is a concave slide groove, the first slide groove is located on the outer side of the second collecting trough, the third slide groove and the first slide groove are buckled together to realize the connection and sliding of the first partition, the fourth slide groove on the second partition is a convex slide groove, the fourth slide groove is located on the inner side of the second partition, the second slide groove of the second collecting trough is a concave slide groove, the second slide groove is located on the outer side of the second collecting trough, the fourth slide groove and the second slide groove are buckled together to realize the connection and sliding of the second partition, and the volume of the third collecting trough is changed by telescoping the first partition and the second partition;

[0012] The buoyancy ball in the second collection groove is connected to the stretching rod through a connecting rod. When the water gushing in the second collection groove reaches its capacity value, the water gushing continues to increase and drives the buoyancy ball to rise above its allowed height. The rising of the buoyancy ball drives the stretching rod to pull, and the sliding operation of the movable partition is completed by the movement of the compression rod and the compression U-shaped rod driven by the rotating rod, so that the gushing water in the second collection groove flows into the third collection groove, and the movable partition moves to compress the first spring and the second spring. When the water gushing in the second collection groove recovers to the allowed height, the buoyancy ball falls back, and the first spring and the second spring drive the movable partition to close, so that the gushing water in the second collection groove no longer flows into the third collection groove.

[0013] In a second aspect, a prediction method of a coal mine tunnel excavation water inflow prediction device comprises the following steps:

[0014] Step 1: Exploring and acquiring key geological parameters of the coal mine tunnel section, and collecting water inflow in the coal mine tunnel through a prediction device;

[0015] Step 2: Establish a data sample for predicting water inflow during tunnel excavation in coal mines;

[0016] Step 3, extracting the main features of water inflow prediction data;

[0017] Step 4: construct multiple prediction models through training based on feature vector samples, and establish a nonlinear mapping relationship between input parameters and output parameters through multiple prediction models;

[0018] The mapping relationship is expressed as S = TR (Z)

[0019] In the formula, S is the predicted output parameter, i.e., the water inflow data.

[0020] TR is the expression form of the established mapping relationship;

[0021] Z is the parameter of prediction input, Z = [z1, z2, z3, z4, z5, z6], z1 is the degree of development of surrounding rock fractures, z2 is the water permeability of broken surrounding rock, z3 is the distance between the overlying broken zone and the top of the roadway, z4 is the water-rich characteristic of the surrounding rock aquifer, z5 is the pore water pressure of the overlying rock stratum, and z6 is the depth of the roadway;

[0022] Step 5: Use the improved machine optimization algorithm to obtain the optimal values ​​of the number of prediction models Q and the maximum feature number L of the prediction model parameters;

[0023] Step 6: assign the optimal prediction model number Q and the maximum feature number L obtained by the improved machine optimization algorithm to the above prediction model, train the established feature vector samples, and obtain the optimized prediction model;

[0024] Step 7: Input the survey values ​​of key parameters of the unconstructed area of ​​the tunnel, predict the water inflow in the unconstructed area of ​​the tunnel through the optimized prediction model, obtain the prediction results of water inflow in the later tunnel excavation, and formulate corresponding treatment measures based on the prediction results of water inflow.

[0025] As a further illustration of the present invention, the key geological parameters described in step 1 include the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the top plate of the tunnel, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock formation, and the tunnel depth.

[0026] As a further explanation of the present invention, the specific data of water inflow collection in step 1 is as follows:

[0027] The water inflow S' i =A×B1×H1+A×B2×H2

[0028] Where: A is the width of the prediction device;

[0029] B1: the width of the second collection slot;

[0030] H1 is the water level height of the second collection tank;

[0031] B2 is the width of the third collection slot;

[0032] H2 is the water level height of the third collection tank.

[0033] As a further illustration of the present invention, the data sample described in step 2 includes input parameters and output parameters;

[0034] The input parameters include the degree of development of surrounding rock fractures, the water permeability of broken surrounding rock, the distance between the overlying broken zone and the roadway roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock formation, and the roadway depth;

[0035] The output parameter is the water inflow during coal mine tunnel excavation.

[0036] As a further explanation of the present invention, the main feature of extracting the water inflow prediction data in step 3 is to use a convolution pooling operation to extract key parameter feature values ​​from the above-collected prediction data samples to form feature vector samples, and forming the feature vector samples includes the following steps:

[0037] The collected data, including the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the tunnel roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock strata, the tunnel depth and the amount of water inflow during tunnel excavation, are divided into samples and standardized. Through convolution and pooling operations, a one-dimensional feature sequence is output to form a feature vector sample.

[0038] As a further illustration of the present invention, step 5 comprises the following steps:

[0039] Initialize the population position, set the population size to have n optimizers, and each position to have W i =(L i , Q i ) represents, and sets the fitness value, and the fitness value function is set as:

[0040]

[0041] Where: S i is the true value of water inflow;

[0042] S' i is the predicted value of water inflow;

[0043] n represents the nth sample;

[0044] Select some individuals with higher fitness values ​​as discoverers for search results. The search range of the discoverer is larger than the search range of the joiner. In each iterative optimization process, the position is updated according to the following formula:

[0045]

[0046] Where: is the position of the i-th optimizer in the k-th dimension at the t+1-th iteration;

[0047] is the position of the i-th optimizer in the k-th dimension at the t-th iteration;

[0048] V is a random number that obeys the normal distribution;

[0049] H is a 1×d-dimensional sequence whose elements are all 1;

[0050] Y Z is the warning value, and its value range is [0, 1];

[0051] A Z is a safe value, A Z The value range is [0.5, 1].

[0052]

[0053] Joiners make judgments based on the quality and position of the results and obtain energy. When a joiner notices that the discoverer has obtained a better result, he will compete for it. If he succeeds in the competition, he can replace the discoverer. Joiners are updated according to the following formula:

[0054]

[0055] Where: is the global optimal position at the tth iteration;

[0056] γ is the step size and direction control parameter, which is a random number that follows a standard normal distribution;

[0057] η is a random number, and its value range is [-1, 1],

[0058] F o is the fitness value of the global optimal position;

[0059] F b is the fitness value of the global worst position; ω is the minimum constant.

[0060] As a further illustration of the present invention, the formation process of the prediction model after optimization in step 6 is as follows:

[0061] Generate Q training sets with different characteristics from the established feature vector samples by replacement sampling, and establish Q prediction models with different characteristics;

[0062] The total dimension of the feature is set to L, and the nodes are split based on the optimal splitting strategy to maximize the use of information and minimize errors, and further form multiple optimized prediction models;

[0063] The weighted average method is used to realize the prediction of a single optimized prediction model. By obtaining the average value of the prediction results of multiple optimized prediction models, the mapping relationship between the key geological parameters of the excavation section and the water inflow of the tunnel excavation is finally established.

[0064] As a further illustration of the present invention, the prediction process of the water inflow in the unexplored area of ​​the coal mine tunnel by the optimized prediction model in step 7 is as follows:

[0065] The key parameters of the unexcavated section of the coal mine tunnel, such as the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the tunnel roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock strata, and the tunnel depth, are surveyed in advance, and the above survey parameters are input into the optimized prediction model. The output of the predicted value of the water inflow in the unexcavated section is realized through the optimized prediction model. According to the predicted results of the water inflow, corresponding disposal measures are formulated in advance to ensure the smooth progress of safe generation.

[0066] Compared with the prior art, the present invention has the following advantages:

[0067] The present invention can realize the rapid and relatively accurate acquisition of the water inflow in the unexcavated section of the coal mine tunnel, can effectively guide the formulation of excavation support measures and drainage measures, and is of great significance to promoting safe production. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a flow chart of the method of the present invention;

[0069] Figure 2 It is a schematic diagram of the prediction device of the present invention;

[0070] Figure 3 This is a schematic diagram of the internal structure connection of the movable partition of the present invention;

[0071] Figure 4 This is a schematic diagram of the buoyancy ball connection structure of the present invention;

[0072] Figure 5 Establishing a graph for the feature vector samples of the present invention;

[0073] Figure 6 Establishing a graph for the prediction model of the present invention;

[0074] Figure 7 This is a comparison chart of the prediction results and monitoring results of the present invention.

[0075] Description of reference numerals:

[0076] The first collecting trough 1, the second collecting trough 2, the movable partition 3, the telescopic third collecting trough 4, the partition 1-1, the top steel bar leakage net 1-2, the front steel bar leakage net 1-3, the groove depth height scale 2-1, the buoyancy ball 2-2, the groove 3-1, the stretching rod 3-2, the rotating shaft 3-3, the rotating rod 3-4, the compression rod 3-5, the compression U-shaped rod 3-6, the first spring 3-7, the second spring 3-8, the groove depth scale 4-1, the third slide groove 4-2, the fourth slide groove 4-3; the first partition 4-4; the second partition 4-5. DETAILED DESCRIPTION

[0077] 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.

[0078] like Figure 1-7 As shown, the present invention provides a technical solution: a device for predicting water inflow during tunnel excavation in a coal mine, comprising a first collecting trough 1 and a second collecting trough 2, a movable partition 3 and a telescopic third collecting trough 4;

[0079] The first collecting trough 1 is composed of a partition 1-1, a top steel mesh 1-2 and a front steel mesh 1-3. The top steel mesh 1-2 is arranged on the top surface of the partition 1-1, and the front steel mesh 1-3 is arranged at the front end of the partition 11. The top steel mesh 1-2 is disassembled and replaced according to the actual particle size in the coal mine tunnel. The top steel mesh 1-2 is used to receive the fallen rocks with larger particle sizes on the top, and at the same time ensure that the tunnel water can flow into the water inflow collection device. The front steel mesh 1-3 is disassembled and replaced according to the sand and gravel particle size in the first collecting trough. The front steel mesh is used to filter the sand and gravel in the tunnel water, ensure the filtration of the tunnel water and gravel, and ensure the accuracy of the collected water inflow value.

[0080] The second collecting tank 2 is provided with a tank depth height scale 2-1, and a buoyancy ball 2-2 is also provided inside the second collecting tank 2;

[0081] The movable partition 3 is provided with a groove 3-1, and a stretching rod 3-2, a rotating shaft 3-3, a rotating rod 3-4, a compression rod 3-5, and a compression U-shaped rod 3-6 are arranged inside the groove 3-1. The connection between the movable partition 3 and the second collecting slot 2 is provided with a first spring 3-7 and a second spring 3-8;

[0082] The third collecting trough 4 is provided with a groove depth scale 4-1, the third slide groove 4-2 on the first partition 4-4 of the third collecting trough 4 is a convex slide groove, the third slide groove 4-2 is located on the inner side of the first partition 4-4, the first slide groove 2-4 of the second collecting trough 2 is a concave slide groove, the first slide groove 2-4 is located on the outer side of the second collecting trough 2, the third slide groove 4-2 and the first slide groove 2-4 are buckled together to realize the connection and sliding of the first partition 4-4, the fourth slide groove 4-3 on the second partition 4-5 is a convex slide groove, the fourth slide groove 4-3 is located on the inner side of the second partition 4-5, the second slide groove 2-5 of the second collecting trough 2 is a concave slide groove, the second slide groove 2-5 is located on the outer side of the second collecting trough 2, the fourth slide groove 4-3 and the second slide groove 2-5 are buckled together to realize the connection and sliding of the second partition 4-5, and the volume of the third collecting trough 4 is changed by telescoping the first partition 4-4 and the second partition 4-5;

[0083] The buoyancy ball 2 in the second collecting groove 2 is connected to the stretching rod 3-2 through the connecting rod 2-3. When the water gushing in the second collecting groove 2 reaches its capacity value, the water gushing continues to increase, driving the buoyancy ball 2-2 to rise above its allowed height. The rising of the buoyancy ball drives the stretching rod 3-2 to pull, and the rotating rod 3-4 drives the compression rod 3-5 and the compression U-shaped rod 3-6 to complete the sliding operation of the movable partition 3, creating an opening, so that the gushing water in the second collecting groove 2 flows into the third collecting groove 4, and the movable partition moves to compress the first spring 3-7 and the second spring 3-8. When the water gushing in the second collecting groove 2 returns to the allowed height, the buoyancy ball falls back to 2-2, and the first spring 3-7 and the second spring 3-8 drive the movable partition 3 to close, and the gushing water in the second collecting groove 2 no longer flows into the third collecting groove 4.

[0084] The prediction method of the above-mentioned coal mine tunnel excavation water inflow prediction device comprises the following steps:

[0085] Step 1: Exploring and acquiring key geological parameters of the coal mine tunnel section, and collecting water inflow in the coal mine tunnel through a prediction device;

[0086] The key geological parameters include the degree of development of surrounding rock fissures, the water permeability of broken surrounding rock, the distance between the overlying broken zone and the roadway roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock layer, and the roadway depth;

[0087] The specific data of water inflow collection are as follows:

[0088] The water inflow S' i =A×B1×H1+A×B2×H2

[0089] Where: A is the width of the prediction device;

[0090] B1: the width of the second collection slot;

[0091] H1 is the water level height of the second collection tank;

[0092] B2 is the width of the third collection slot;

[0093] H2 is the water level height of the third collection tank.

[0094] Step 2: Establish a data sample for predicting water inflow during tunnel excavation in coal mines;

[0095] The data sample includes input parameters and output parameters;

[0096] The input parameters include the degree of development of surrounding rock fractures, the water permeability of broken surrounding rock, the distance between the overlying broken zone and the roadway roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock formation, and the roadway depth;

[0097] The output parameter is the water inflow during coal mine tunnel excavation.

[0098] Step 3, extracting the main features of water inflow prediction data;

[0099] The main feature of extracting the water inflow prediction data is to use convolution pooling operation to extract the key parameter characteristic values ​​from the prediction data samples collected above to form a characteristic vector sample. The formation of the characteristic vector sample includes the following steps:

[0100] The collected data, including the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the tunnel roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock strata, the tunnel depth and the amount of water inflow during tunnel excavation, are divided into samples and standardized. Through convolution and pooling operations, a one-dimensional feature sequence is output to form a feature vector sample.

[0101] Step 4: construct multiple prediction models through training based on feature vector samples, and establish a nonlinear mapping relationship between input parameters and output parameters through multiple prediction models;

[0102] The mapping relationship is expressed as S = TR (Z)

[0103] In the formula, S is the predicted output parameter, i.e., the water inflow data;

[0104] TR is the expression form of the established mapping relationship;

[0105] Z is the parameter of prediction input, Z = [z1, z2, z3, z4, z5, z6], z1 is the degree of development of surrounding rock fractures, z2 is the water permeability of broken surrounding rock, z3 is the distance between the overlying broken zone and the top of the roadway, z4 is the water-rich characteristic of the surrounding rock aquifer, z5 is the pore water pressure of the overlying rock stratum, and z6 is the depth of the roadway;

[0106] Step 5: Use the improved machine optimization algorithm to obtain the optimal values ​​of the number of prediction models Q and the maximum feature number L of the prediction model parameters;

[0107] The following steps are involved:

[0108] Initialize the population position, set the population size to have n optimizers, and each position to have W i =(L i , Q i ) represents, and sets the fitness value, and the fitness value function is set as:

[0109]

[0110] Where: S i is the true value of water inflow;

[0111] S' i is the predicted value of water inflow;

[0112] n represents the nth sample;

[0113] Select some individuals with higher fitness values ​​as discoverers for search results. The search range of the discoverer is larger than the search range of the joiner. In each iterative optimization process, the position is updated according to the following formula:

[0114]

[0115] Where: is the position of the i-th optimizer in the k-th dimension at the t+1-th iteration;

[0116] is the position of the i-th optimizer in the k-th dimension at the t-th iteration;

[0117] V is a random number that obeys the normal distribution;

[0118] H is a 1×d-dimensional sequence whose elements are all 1;

[0119] Y Z is the warning value, and its value range is [0, 1];

[0120] A Z is a safe value, A Z The value range is [0.5, 1].

[0121]

[0122] Joiners make judgments based on the quality and position of the results and obtain energy. When a joiner notices that the discoverer has obtained a better result, he will compete for it. If he succeeds in the competition, he can replace the discoverer. Joiners are updated according to the following formula:

[0123]

[0124] Where: is the global optimal position at the tth iteration;

[0125] γ is the step size and direction control parameter, which is a random number that follows a standard normal distribution;

[0126] η is a random number, and its value range is [-1, 1],

[0127] F o is the fitness value of the global optimal position;

[0128] F b is the fitness value of the global worst position; ω is the minimum constant.

[0129] Step 6: assign the optimal prediction model number Q and the maximum feature number L obtained by the improved machine optimization algorithm to the above prediction model, train the established feature vector samples, and obtain the optimized prediction model;

[0130] The formation process of the prediction model after optimization in step 6 is as follows:

[0131] Generate Q training sets with different characteristics from the established feature vector samples by replacement sampling, and establish Q prediction models with different characteristics;

[0132] The total dimension of the feature is set to L, and the nodes are split based on the optimal splitting strategy to maximize the use of information and minimize errors, and further form multiple optimized prediction models;

[0133] The weighted average method is used to realize the prediction of a single optimized prediction model. By obtaining the average value of the prediction results of multiple optimized prediction models, the mapping relationship between the key geological parameters of the excavation section and the water inflow of the tunnel excavation is finally established.

[0134] Step 7: Input the survey values ​​of key parameters of the unconstructed area of ​​the tunnel, predict the water inflow in the unconstructed area of ​​the tunnel through the optimized prediction model, obtain the prediction results of water inflow in the later tunnel excavation, and formulate corresponding treatment measures according to the prediction results of water inflow;

[0135] The key parameters of the unexcavated section of the coal mine tunnel, such as the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the tunnel roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock strata, and the tunnel depth, are surveyed in advance, and the above survey parameters are input into the optimized prediction model. The output of the predicted value of the water inflow in the unexcavated section is realized through the optimized prediction model. According to the predicted results of the water inflow, corresponding disposal measures are formulated in advance to ensure the smooth progress of safe generation.

[0136] The present invention can realize the rapid and relatively accurate acquisition of the water inflow in the unexcavated section of the coal mine tunnel, can effectively guide the formulation of excavation support measures and drainage measures, and is of great significance to promoting safe production.

[0137] Experimental example: During the tunnel excavation process of Shandong Wanfu Coal Mine, the key geological parameters of the excavated tunnel were surveyed and collected: z1 is the degree of development of surrounding rock fractures, z2 is the permeability of broken surrounding rock, z3 is the distance between the overlying broken zone and the tunnel roof, z4 is the water-rich characteristic of the surrounding rock aquifer, z5 is the pore water pressure of the overlying rock stratum, and z6 is the depth of the tunnel. The water inflow S at the corresponding collection point was collected through the collection device, and the collected data are shown in the table below.

[0138]

[0139] The unexcavated sections of the tunnel in the study area, ZK91+651~634, a total of 8 sections, were surveyed for key geological parameters and numbered 1~8, and the water inflow was predicted. The prediction results and the actual water inflow results collected after the actual excavation in the later stage are as follows Figure 7 As shown,

[0140] It can be seen from the figure that the predicted results of water inrush at different sections in the unexcavated section are relatively close to the actual water inrush collection results after excavation, which verifies the feasibility and accuracy of the method. Through this prediction method, the preparation of water inrush schemes in the later excavation process can be effectively guided, and the occurrence of water inrush disasters during construction can be effectively avoided.

[0141] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0142] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A device for predicting water inflow during coal mine tunneling, characterized by: It comprises a first collecting trough (1), a second collecting trough (2), a movable partition (3) and a telescopic third collecting trough (4); The first collecting trough (1) is composed of a partition (1-1), a top steel mesh (1-2) and a front steel mesh (1-3); the top steel mesh (1-2) is arranged on the top surface of the partition (1-1); the top steel mesh (1-2) is used to receive fallen rocks with a top particle size larger than the mesh aperture, while ensuring that all water gushing from the tunnel can flow into the water gushing amount collecting device; the front steel mesh (1-3) is arranged at the front end of the partition (11); the front steel mesh (1-3) is used to filter sand and gravel from the water gushing from the tunnel; The second collecting trough (2) is provided with a trough depth height scale (2-1) inside, and a buoyancy ball (2-2) is also provided inside the second collecting trough (2); The movable partition (3) is provided with a groove (3-1), and a stretching rod (3-2), a rotating shaft (3-3), a rotating rod (3-4), a compression rod (3-5), and a compression U-shaped rod (3-6) are provided inside the groove (3-1). A first spring (3-7) and a second spring (3-8) are provided at the connection between the movable partition (3) and the second collecting trough (2); The third collecting trough (4) is provided with a groove depth scale (4-1), the third chute (4-2) on the first partition (4-4) of the third collecting trough (4) is a convex chute, and the third chute (4-2) is located on the inner side of the first partition (4-4), the first chute (2-4) of the second collecting trough (2) is a concave chute, and the first chute (2-4) is located on the outer side of the second collecting trough (2), the third chute (4-2) and the first chute (2-4) are buckled together to realize the connection and sliding of the first partition (4-4), the The fourth chute (4-3) on the second partition (4-5) is a convex chute, and the fourth chute (4-3) is located on the inner side of the second partition (4-5); the second chute (2-5) of the second collecting trough (2) is a concave chute, and the second chute (2-5) is located on the outer side of the second collecting trough (2); the fourth chute (4-3) and the second chute (2-5) are buckled together to realize the connection and sliding of the second partition (4-5), and the volume of the third collecting trough (4) is changed by extending and retracting the first partition (4-4) and the second partition (4-5); The buoyancy ball (2) in the second collection trough (2) is connected to the stretching rod (3-2) via a connecting rod (2-3). When the gushing water volume in the second collection trough (2) reaches its capacity value, the gushing water volume continues to increase, driving the buoyancy ball (2-2) to rise above its allowable height. The rise of the buoyancy ball drives the stretching rod (3-2) to pull, and the rotation rod (3-4) drives the compression rod (3-5) and the compression U-shaped rod (3-6) to move, completing the sliding operation of the movable partition (3), generating an opening, so that the gushing water in the second collection trough (2) flows into the third collection trough (4). The movable partition moves, compressing the first spring (3-7) and the second spring (3-8). When the gushing water volume in the second collection trough (2) returns to the allowable height, the buoyancy ball falls back (2-2), the first spring (3-7) and the second spring (3-8) drive the movable partition (3) to close, and the gushing water in the second collection trough (2) no longer flows into the third collection trough (4).

2. The prediction method of the device for predicting water inflow during tunneling of a coal mine according to claim 1, characterized in that: The following steps are involved: Step 1: Exploring and acquiring key geological parameters of the coal mine tunnel section, and collecting water inflow in the coal mine tunnel through a prediction device; Step 2: Establishing a data sample for predicting water inflow during coal mine tunneling; Step 3: Extract the main features of the water inflow prediction data; Step 4: construct multiple prediction models based on feature vector samples through training, and establish a nonlinear mapping relationship between input parameters and output parameters through multiple prediction models; The mapping relationship is expressed as S=TR(Z) Where S is the predicted output parameter, i.e., the water inflow data. TR is the expression form of the established mapping relationship; Z is the parameter of prediction input, Z = [z1, z2, z3, z4, z5, z6], z1 is the degree of development of surrounding rock fractures, z2 is the water permeability of broken surrounding rock, z3 is the distance between the overlying broken zone and the roadway roof, z4 is the water-rich characteristic of the surrounding rock aquifer, z5 is the pore water pressure of the overlying rock stratum, and z6 is the roadway depth; Step 5: Use the improved machine optimization algorithm to obtain the optimal values ​​of the prediction model parameter number Q and the maximum feature number L of the prediction model; Step 6: assign the optimal prediction model number Q and the maximum feature number L obtained by the improved machine optimization algorithm to the aforementioned prediction model, train the established feature vector samples, and obtain the optimized prediction model; Step 7: Input the survey values ​​of key parameters of the unconstructed area of ​​the tunnel, predict the water inflow in the unconstructed area of ​​the tunnel through the optimized prediction model, obtain the prediction results of the water inflow in the later tunnel excavation, and formulate corresponding treatment measures based on the water inflow prediction results.

3. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 2, characterized in that: The key geological parameters described in step 1 include the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the roadway roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock strata, and the roadway depth.

4. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 2, characterized in that: The specific data of water inflow collection in step 1 are as follows: The water inflow S' i =A×B1×H1+A×B2×H2 Where: A is the width of the prediction device; B1 is the width of the second collection slot; H1 is the water level of the second collection tank; B2 is the width of the third collection slot; H2 is the water level of the third collection tank.

5. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 2, characterized in that: The data sample described in step 2 includes input parameters and output parameters; The input parameters include the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the roadway roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock layer, and the roadway depth; The output parameter is the water inflow during coal mine tunnel excavation.

6. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 5, characterized in that: In step 3, the main features of the water inflow prediction data are extracted by using a convolution pooling operation to extract the characteristic values ​​of key parameters from the above-collected prediction data samples to form a characteristic vector sample. The formation of the characteristic vector sample includes the following steps: The collected data, including the degree of development of surrounding rock fractures, permeability of broken surrounding rock, distance between the overlying broken zone and the roadway roof, water-rich characteristics of the surrounding rock aquifer, pore water pressure of the overlying rock strata, roadway depth and water inflow during roadway excavation, are divided into samples and standardized. Through convolution and pooling operations, a one-dimensional feature sequence is output to form a feature vector sample.

7. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 2, characterized in that: Step 5 includes the following steps: Initialize the population position, set the population size to have n optimizers, and each position has W i =(L i , Q i ) represents, and sets the fitness value, and the fitness value function is set as: Where: S i is the true value of water inflow; S' i is the predicted value of water inflow; n represents the nth sample; Select some individuals with higher fitness values ​​as discoverers for search results. The search range of the discoverer is larger than the search range of the joiner. In each iterative optimization process, the position is updated according to the following formula: Where: is the position of the i-th optimizer in the k-th dimension at the t+1-th iteration; is the position of the i-th optimizer in the k-th dimension at the t-th iteration; V is a random number that obeys the normal distribution; H is a 1×d-dimensional sequence with all elements being 1; Y Z is the warning value, and its value range is [0, 1]; A Z is a safe value, A Z The value range of is [0.5, 1]; Joiners make judgments based on the quality and position of the results and gain energy. When a joiner notices that the discoverer has obtained a better result, they will compete for it. If they succeed in the competition, they can replace the discoverer. Joiners are updated according to the following formula: Where: is the global optimal position at the tth iteration; γ is the step size and direction control parameter, which is a random number that obeys the standard normal distribution; η is a random number, and its value range is [-1, 1], F o is the fitness value of the global optimal position; F b is the fitness value of the global worst position; ω is the minimum constant.

8. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 2, characterized in that: The formation process of the prediction model after optimization in step 6 is as follows: Generate Q unique training sets from the established feature vector samples by replacement sampling, and establish Q unique prediction models; The total dimension of the feature is set to L, and the nodes are split based on the optimal splitting strategy to maximize the use of information and minimize the error, further forming multiple optimized prediction models; The weighted average method is used to realize the prediction of a single optimized prediction model. By obtaining the average value of the prediction results of multiple optimized prediction models, the mapping relationship between the key geological parameters of the excavation section and the water inflow of the tunnel excavation is finally established.

9. The prediction method of the device for predicting water inflow during coal mine tunneling according to claim 2, characterized in that: The process of predicting the water inflow in the unexcavated area of ​​the coal mine tunnel by the optimized prediction model in step 7 is as follows: The key parameters of the unexcavated section of the coal mine tunnel, such as the degree of development of surrounding rock fractures, the permeability of broken surrounding rock, the distance between the overlying broken zone and the tunnel roof, the water-rich characteristics of the surrounding rock aquifer, the pore water pressure of the overlying rock strata, and the tunnel depth, are surveyed in advance, and the above survey parameters are input into the optimized prediction model. The optimized prediction model is used to output the predicted value of the water inflow in the unexcavated section. According to the predicted results of the water inflow, corresponding disposal measures are formulated in advance to ensure the smooth progress of safe generation.

Images