Method and system for calculating height of waterproof coal-rock pillar and height of bursting zone

By introducing equivalent thickness mining and neural network models, combining geological parameters and aquifer parameters, calculating the height of coal rock columns and cracking zones, the problems of cumbersome and inaccurate calculations in the existing technology are solved, and more accurate predictions are achieved and safety assessments have improved the safety and resource recovery rate of coal mining.

CN118939944APending Publication Date: 2024-11-12HUAIBEI MINING CO LTD +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411150424.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

When predicting and calculating the height and distribution of cracking zones during coal mine mining under water, the calculation is complicated and error-prone, making it difficult to accurately judge the conditions for the mine water inrush, which affects the recovery rate of coal resources and the safe production of mine.

Method used

Using the concept of equivalent thickness mining and pre-trained neural network model, combining geological parameters and aquifer water-rich parameters, the neural network structure is optimized through the BP algorithm, the height of the water-proof coal rock column and the height of the cracking zone are calculated, and the calculation results are carried out. An early warning signal is sent when the safety threshold is exceeded.

Benefits of technology

It improves the accuracy and reliability of calculations, reduces interference from human factors, can handle more accurate predictions under complex geological conditions, issue early warnings in a timely manner, and improves the safety of coal mining and resource recovery rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118939944A_ABST
    Figure CN118939944A_ABST
Patent Text Reader

Abstract

The invention relates to a method and a system for calculating the height of a waterproof coal-rock pillar and the height of a bursting zone. The method comprises the following steps: acquiring geological parameters of a mining coal seam; wherein the geological parameters comprise the coal seam thickness, the coal seam inclination angle, the coal seam burial depth and the coal seam roof and floor lithology; calculating the equivalent mining thickness of the mining coal seam according to the geological parameters; and according to the equivalent mining thickness of the mining coal seam, the height of the waterproof coal-rock pillar and the height of the burst zone are calculated by using the pre-trained neural network model. According to the method, the concept of equivalent mining thickness is introduced, and the influence of the coal seam occurrence state on the mining influence range is considered, so that the height of the water-proof and waterproof coal rock pillar and the height of the burst zone are calculated more accurately. The pre-trained neural network model is used for calculation, and more complex and changeable geological conditions can be processed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of coal mining, and in particular to a method and system for calculating the height of a water-proof coal rock pillar and a height of a fracturing zone. Background Art

[0002] At present, safe mining under water and prevention of mine water hazards have become major practical and theoretical issues that need to be urgently resolved in the production of various mining areas. In recent years, many coal mines in my country have experienced many abnormal water inrush accidents in coal mines, although they have left a waterproof coal rock pillar of sufficient thickness when mining under the adjacent overlying loose aquifer. According to expert analysis, most of the causes of abnormal water inrush accidents are special geological factors such as the existence of faults, relatively developed primary fissures, or the lowering of the bottom interface of the loose confined aquifer, which connect the water-conducting cracks caused by mining in the roof with the loose confined aquifer at the top of the bedrock, causing water inrush disasters.

[0003] The fractures caused by mining in rock formations are channels for water inrush in mines. Studying the evolution law of fractures in the mining rock structure is an important theoretical basis for judging the conditions for water inrush in mines, predicting water inrush in mines, and formulating measures for preventing and controlling water hazards in mines. Studying and predicting the height and distribution of the fracture zone in mining under water bodies has very important theoretical and practical engineering value for rationally solving the contradiction between coal development and utilization under water bodies and mine safety production, improving resource recovery rate, extending the production life of mines, and improving the economic benefits of enterprises.

[0004] Normally, when studying and predicting the height of the fracturing zone and its distribution pattern in mining under water bodies, relevant empirical formulas or experience reviews are often used. In the past, when predicting or estimating it, manual calculations were mostly used; due to the large statistical workload, cumbersome calculations, slow operations, and easy errors, it is not conducive to coal mining safety and the protection of coal resources. Summary of the invention

[0005] In view of this, it is necessary to provide a method and system for calculating the height of waterproof coal rock pillars and the height of fracture zones to solve the above-mentioned defects of the prior art.

[0006] In order to solve the above problems, in a first aspect, an embodiment of the present invention provides a method for calculating the height of a waterproof coal rock pillar and the height of a fracturing zone, comprising:

[0007] Obtaining geological parameters of the mining coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology;

[0008] According to the geological parameters, the equivalent mining thickness of the mined coal seam is calculated, and the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining impact range;

[0009] According to the equivalent mining thickness of the mined coal seam, the height of the waterproof coal rock pillar and the height of the fracturing zone are calculated using a pre-trained neural network model; wherein the neural network model is trained using pre-collected training sample data.

[0010] Preferably, the calculation of the equivalent mining thickness of the mined coal seam includes:

[0011] The actual mining thickness of each coal seam is corrected by the inclination angle to obtain the equivalent mining thickness of each coal seam; the calculation formula of the equivalent mining thickness is: equivalent mining thickness = actual mining thickness × cosθ, θ is the inclination angle of the coal seam;

[0012] The equivalent mining thickness of each coal seam is weighted and summed to obtain the equivalent mining thickness of the mined coal seam. The weight is determined according to the burial conditions of each coal seam. The deeper the burial and the harder the lithology of the coal seam, the greater the weight.

[0013] Preferably, before calculating the height of the waterproof coal rock pillar and the height of the fracturing zone using the neural network model, the method further includes: acquiring monitoring data of the coal seam mining site;

[0014] Among them, the monitoring data at the coal seam mining site includes the water-richness parameters of the aquifer adjacent to the coal seam mining site; the water-richness parameters of the aquifer include the permeability coefficient, water supply degree, water pressure and water quality type of the aquifer.

[0015] Preferably, the neural network model includes an input layer, a hidden layer and an output layer;

[0016] Among them, the number of neurons in the input layer is the sum of the number of equivalent mining thickness and aquifer water richness parameters. The input data is normalized to map parameters of different dimensions to the interval [0, 1]; the number of neurons in the output layer is 2, corresponding to the height of the waterproof coal rock pillar and the height of the fracturing zone, respectively. The output value is denormalized and restored to the original dimension; the number of layers of the hidden layer and the number of neurons in each layer are determined according to the training sample data, and the trial and error method is used to optimize the network structure, with the minimum mean square error as the goal.

[0017] Preferably, the neural network model is trained using a BP algorithm, and the loss function is the mean square error between the predicted value and the measured value of the waterproof coal rock pillar height and the fracture zone height;

[0018] Among them, the BP algorithm includes: calculating the output of each layer of neurons through forward propagation, calculating the gradient of the loss function to the weight and bias through back propagation, and using the gradient descent method to update the weight and bias until the loss function converges below the set threshold.

[0019] Preferably, after obtaining the geological parameters of the mined coal seam, the method further comprises:

[0020] The geological parameters are dimensionally non-dimensionalized, and geological parameters of different dimensions are converted into the same dimension.

[0021] Preferably, the training sample data of the neural network model includes:

[0022] The measured data on waterproof coal rock pillar height and fracture zone height in different mining areas and under different geological conditions, as well as the corresponding equivalent mining thickness and aquifer water richness parameters; the data sources of the training sample data include the on-site monitoring data of the mining area and similar data from adjacent mining areas.

[0023] Preferably, after calculating the height of the waterproof coal rock pillar and the height of the fracturing zone using the pre-trained neural network model, the method further comprises:

[0024] Compare the calculated results of the waterproof coal rock pillar height and the cracking zone height with the preset safety threshold; wherein the safety threshold is determined according to the water richness of the aquifer and the waterproof requirements of the coal mining face;

[0025] When the calculated result exceeds the safety threshold, a warning signal will be issued through sound and light alarms, mobile phone text messages or emails, and the warning information will be transmitted to the ground monitoring center.

[0026] In a second aspect, the present invention provides a system for calculating the height of a waterproof coal rock pillar and the height of a cracking zone, comprising:

[0027] A data acquisition module is used to obtain geological parameters of the mined coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology;

[0028] An equivalent mining thickness determination module is used to calculate the equivalent mining thickness of the mined coal seam according to the geological parameters, and the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining influence range;

[0029] A calculation module is used to calculate the height of the waterproof coal rock pillar and the height of the fracturing zone according to the equivalent mining thickness of the mined coal seam using a pre-trained neural network model; wherein the neural network model is trained by pre-collected training sample data;

[0030] The safety assessment module is used to compare the calculated results of the waterproof coal rock pillar height and the fracturing zone height with the preset safety threshold. When the calculated results exceed the safety threshold, an early warning signal is issued.

[0031] In a third aspect, the present invention further provides an electronic device, including a memory and a processor, wherein:

[0032] The memory is used to store programs;

[0033] The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone as described in the embodiment of the first aspect of the present invention.

[0034] Compared with the prior art, the calculation method of the waterproof coal rock pillar height and the cracking zone height provided by the present invention has the following beneficial effects:

[0035] 1) The present invention introduces the concept of equivalent mining thickness and considers the influence of coal seam occurrence (such as coal seam inclination, coal seam thickness, etc.) on the mining impact range, making the calculation of waterproof coal rock pillar height and fracture zone height more accurate. This method that considers the complexity of geological conditions helps to reduce calculation errors caused by differences in geological parameters.

[0036] 2) The use of pre-trained neural network models for calculations can handle more complex and changeable geological conditions. The neural network model can capture the nonlinear relationship between geological parameters and the height of waterproof coal rock pillars and the height of the fracturing zone through learning from a large amount of training sample data, thereby providing more accurate prediction results under complex geological conditions.

[0037] 3) Traditional calculation methods often rely on engineers’ experience and judgment, which is highly subjective. However, the present invention uses a neural network model to automatically calculate, which reduces the interference of human factors and improves the objectivity and reliability of the calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flow chart of the method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone provided by the present invention;

[0039] Figure 2 A structural block diagram of a calculation system for the height of a water-proof coal rock pillar and a height of a fracturing zone provided by the present invention;

[0040] Figure 3 This is a structural block diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0042] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0043] Normally, existing technologies often refer to relevant empirical formulas or experience evaluation when studying and predicting the height of the fracturing zone and its distribution pattern in mining under water. In the past, when predicting or estimating it, it was mostly done by hand calculation; due to the large statistical workload, cumbersome calculations, slow operations, and easy errors, it is not conducive to coal mining safety and the protection of coal resources.

[0044] In view of this, the present invention provides a method for calculating the height of the waterproof coal rock pillar and the height of the fracture zone, which introduces the concept of equivalent mining thickness and considers the influence of the coal seam occurrence state on the mining impact range, so that the calculation of the height of the waterproof coal rock pillar and the height of the fracture zone is more accurate. The following will be explained and introduced through multiple embodiments.

[0045] The development and formation mechanism of the caving zone is analyzed as follows: after the coal seam is mined, the surrounding rock mass moves. When the movement deformation exceeds the limit deformation of the rock mass, the rock mass is destroyed. Since the water conductivity of the rock mass is improved after the destruction, it is very important for coal mining under water. Therefore, in coal mining under water, the overlying rock strata are generally divided into "three zones", namely the caving zone, the fracture zone and the curved sinking zone.

[0046] The caving zone and the fracture zone are collectively called the caving zone, also known as the water-conducting fracture zone. The relevant concepts of the caving zone and the fracture zone are as follows:

[0047] ① Caving zone: Above the goaf, the rock strata are broken into pieces and then fall to fill the goaf. This part of the rock strata is called the caving zone, also known as the collapse zone. The destruction characteristics of the rock strata in this zone are irregular. Except for the extremely hard roof that will fall over a large area, the rock blocks that fall from the roof are generally of varying sizes and in a disorderly state. Therefore, the caving zone is mostly an irregular caving zone. The rock blocks that fall upward gradually become larger and layered, but have been separated from the parent rock strata and are discontinuously covered on the irregular caving zone. This part can be called a regular caving zone. It has the property of fragmentation and expansion. After the roof collapses, due to the fragmentation, the volume increases, resulting in fragmentation and expansion. Its initial fragmentation and expansion coefficient is 1.08-1.99, and the residual fragmentation and expansion coefficient is about 1.02-1.5. The fragmentation and expansion of the rock mass affects the height of the caving zone and stops the caving phenomenon by itself.

[0048] ② Fracture zone: The rock layers above the caving zone have cracks, delamination and fractures due to the support of the caving zone, but still maintain the original layered structure. This part of the rock layer is called the fracture zone, also known as the fracture zone or curved fracture zone. The rock layers in the fracture zone have cracks or disconnections perpendicular to the layer direction or delamination, but the overall layer still maintains the original layer. The lower part of the fracture zone has the most developed cracks, strong connectivity, and serious water leakage, which gradually weakens as it goes up. The fracture zone generally only conducts water but not sand.

[0049] Since there is no obvious boundary between the caving zone and the fissure zone, the caving zone and the fissure zone are collectively called the caving zone. Because of the severe damage and strong water conductivity, the fissure zone is also called the water-conducting fissure zone. The maximum height of the water-conducting fissure zone is referred to as the crack height. It is a very important parameter for coal mining under water. It is calculated according to the highest height of the development of cracking damage and is the main basis for determining the waterproof coal rock pillar. Generally speaking, the maximum height of the water-conducting fissure zone, for gently inclined and inclined coal seams, refers to the normal height calculated from the top of the coal seam; for steeply inclined coal seams, it refers to the vertical height calculated from the upper limit of mining.

[0050] Figure 1 A flow chart of the method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone provided by the present invention.

[0051] like Figure 1 As shown, the calculation method of the height of the waterproof coal rock pillar and the height of the fracturing zone includes steps S1 to S3, wherein:

[0052] Step S1, obtaining geological parameters of the mining coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology.

[0053] Specifically, the thickness of the coal seam can be measured by drilling or geophysical prospecting methods. The dip of the coal seam can be measured by a geological compass or inclinometer. The buried depth of the coal seam can be measured by drilling or seismic prospecting methods. The lithology of the top and bottom plates of the coal seam can be determined by drilling core observation or geophysical logging methods.

[0054] Step S2, calculating the equivalent mining thickness of the mined coal seam according to the geological parameters, wherein the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining influence range.

[0055] Specifically, in order to calculate the equivalent mining thickness of the mined coal seam, first, the actual mining thickness of each coal seam is corrected for the inclination to obtain the equivalent mining thickness of each coal seam; the calculation formula for the equivalent mining thickness is: equivalent mining thickness = actual mining thickness × cosθ, θ is the inclination of the coal seam; when the inclination of the coal seam is greater than 45°, the full thickness calculation is adopted; the "full thickness calculation" here means that when the inclination of the coal seam is large, since the coal seam may be close to or reach a natural collapse state, the equivalent thickness is no longer converted according to the above formula, but the actual mining thickness of the coal seam is directly used as the basis for calculation or evaluation, that is, no inclination correction is performed.

[0056] Next, the equivalent mining thickness of each coal seam is weighted and summed to obtain the equivalent mining thickness of the mined coal seam. The weight is determined according to the burial conditions and lithology of each coal seam. Generally speaking, the deeper the burial and the harder the lithology of the coal seam, the greater the impact range on the surrounding rock mass during the mining process, and therefore its weight is correspondingly larger.

[0057] Assume that the equivalent mining thickness of the i-th coal seam is d i , the weight of the i-th coal seam is w i , then the equivalent mining thickness D of the entire mining coal seam can be expressed as

[0058]

[0059] This embodiment calculates the equivalent mining thickness of the mined coal seam based on the collected geological parameters. The equivalent mining thickness takes into account the impact of the coal seam occurrence state on the mining impact range, and can more accurately reflect the actual state of the coal seam during the mining process.

[0060] Step S3, according to the equivalent mining thickness of the mined coal seam, the height of the waterproof coal rock pillar and the height of the fracturing zone are calculated using a pre-trained neural network model; wherein the neural network model is trained by pre-collected training sample data.

[0061] Specifically, first, before using the neural network model to calculate the height of the waterproof coal rock pillar and the height of the fracture zone, ensure that the neural network model has been fully trained through the pre-collected training sample data. Among them, the training sample data include the measured waterproof coal rock pillar height and fracture zone height data in different mining areas and different geological conditions, as well as the corresponding equivalent mining thickness and aquifer water-richness parameters; the aquifer water-richness parameters here include the permeability coefficient, water supply degree, water pressure and water quality type of the aquifer. In this embodiment, the training sample data covers various typical coal seam occurrence conditions and aquifer characteristics, and the amount of data is not less than 1,000 groups. The data sources of the training sample data include the on-site monitoring data of the mining area and similar data from adjacent mining areas.

[0062] Next, the equivalent mining thickness of the mined coal seam and the water-richness parameters of the aquifer are processed to meet the input requirements of the neural network model. Data processing includes data cleaning, data normalization and data dimensionality reduction.

[0063] Furthermore, the processed input data is input into a pre-trained neural network model, and the neural network model performs a complex calculation process internally based on the input data, and outputs the predicted values ​​of the height of the waterproof coal rock pillar and the height of the fracturing zone.

[0064] The calculation method of the height of the waterproof coal rock pillar and the height of the fracture zone provided by the present invention comprehensively considers the geological parameters of the coal seam and the influence of mining, and uses an advanced neural network model for prediction, thereby providing strong technical support for safety assessment in the coal mining process.

[0065] In a preferred embodiment of the present invention, the neural network model includes an input layer, a hidden layer and an output layer;

[0066] Specifically, the number of neurons in the input layer is the sum of the number of equivalent mining thickness and water-bearing layer water-richness parameters. The input data needs to be normalized before entering the neural network model, that is, the parameters of different dimensions are mapped to the interval [0, 1]. Normalization helps to speed up the training speed of the model and improve the convergence of the model.

[0067] The number of neurons in the output layer is 2, corresponding to the height of the waterproof coal rock pillar and the height of the fracturing zone. After the model calculation is completed, the output value needs to be denormalized to restore it to the original dimensional unit for easy engineering application and understanding.

[0068] The number of hidden layers and the number of neurons in each layer are determined according to the training sample data, and the network structure is optimized by trial and error (also known as grid search, parameter tuning). The core idea of ​​the trial and error method is to continuously try different network structures (such as changing the number of layers, the number of neurons in each layer, the activation function, etc.), and use the validation set to evaluate the performance of each structure (such as mean square error, accuracy, etc.), and finally select the network structure with the best performance. In this embodiment, the goal is to minimize the mean square error, that is, the difference between the model prediction value and the measured value is minimized.

[0069] In a preferred embodiment of the present invention, the neural network model is trained using a BP algorithm, and the loss function is the mean square error between the predicted value and the measured value of the waterproof coal rock pillar height and the fracture zone height;

[0070] Among them, the BP algorithm includes: calculating the output of each layer of neurons through forward propagation, calculating the gradient of the loss function to the weight and bias through back propagation, and using the gradient descent method to update the weight and bias until the loss function converges below the set threshold.

[0071] Specifically, the BP (Back Propagation) algorithm is a supervised learning algorithm used to train a multi-layer feedforward neural network. It calculates the gradient of the loss function with respect to the weights and biases in the network and uses these gradients to update the weights and biases to minimize the loss function.

[0072] In this embodiment, in the forward propagation stage, the input data (normalized equivalent mining thickness and aquifer water richness parameters) are sent to the input layer, and then calculated through each layer in the network (including the hidden layer and the output layer) until the predicted value of the output layer (the predicted value of the height of the waterproof coal rock pillar and the height of the fracturing zone) is generated.

[0073] The loss function is used to evaluate the difference between the model prediction value and the measured value. In this embodiment, the loss function is set to the mean square error (MSE) between the predicted value and the measured value of the waterproof coal rock pillar height and the fracture zone height. MSE is a commonly used regression problem loss function, which calculates the average value of the square of the difference between the predicted value and the measured value.

[0074] During the back-propagation phase, the gradient of the loss function (i.e., the partial derivative of the loss function with respect to the network weights and biases) is calculated. This process starts from the output layer and back-propagates to each layer until the input layer. The gradient calculation relies on the chain rule, which allows us to multiply the gradient of the loss function with respect to a layer's output with the gradient of the layer's output with respect to its input to obtain the gradient of the loss function with respect to the layer's input.

[0075] Once the gradient of the loss function with respect to the weights and biases is calculated, gradient descent can be used to update these parameters.

[0076] The entire process of forward propagation, loss calculation, backpropagation, and weight update is repeated until the full loss function converges below the set threshold.

[0077] In this embodiment, by using the BP algorithm for training, the neural network model can learn the complex mapping relationship from geological parameters and water-bearing layer water-richness parameters to the height of the waterproof coal rock pillar and the height of the fracture zone. This mapping relationship is learned based on a large amount of training data and can reflect the laws of mining impact under different geological conditions.

[0078] In a preferred embodiment of the present invention, after obtaining the geological parameters of the mining coal seam in step S1, the method further comprises:

[0079] The geological parameters are dimensionally non-dimensionalized, and geological parameters of different dimensions are converted into the same dimension.

[0080] Specifically, in this embodiment, the Z-score standardization method can be used for dimensionless processing to convert geological parameters of different dimensions into the same dimension. Further, the principal component analysis (PCA) method is used for data dimension reduction. In the application of geological parameters, the principal component analysis method can help synthesize multiple related geological parameters into a few unrelated comprehensive parameters, which represent the main information in the original data.

[0081] In a preferred embodiment of the present invention, after calculating the height of the waterproof coal rock pillar and the height of the fracturing zone using the pre-trained neural network model, the method further includes:

[0082] The calculated results of the waterproof coal rock pillar height and the fracturing zone height are compared with the preset safety threshold; wherein the safety threshold can be determined based on the water richness of the aquifer and the waterproofing requirements of the coal mining face.

[0083] When the calculation result exceeds the safety threshold, an early warning signal is issued through sound and light alarms, mobile phone text messages or emails, and the early warning information is transmitted to the ground monitoring center. The ground monitoring center is the command center for coal mine safety production, responsible for coordinating and guiding the safety production work of the entire mine. By transmitting early warning information, the ground monitoring center can timely understand the safety status of the mine and make corresponding decisions and deployments.

[0084] In this embodiment, by establishing a comparison mechanism between the calculation results of the height of the waterproof coal rock pillar and the height of the fracture zone and the safety threshold, and triggering early warning signals and emergency response measures when the threshold is exceeded, the safety and reliability of coal mining can be improved.

[0085] In a preferred embodiment of the present invention, after calculating the height of the waterproof coal rock pillar and the height of the fracturing zone using a pre-trained neural network model, the embodiment of the present invention further provides a method for setting a waterproof coal rock pillar, comprising:

[0086] According to the calculated height of the waterproof coal rock pillar, determine the burial depth, thickness and range of the waterproof coal rock pillar. Among them, the burial depth should be greater than the difference between the height of the fracturing zone and the burial depth of the coal mining face to ensure that the fracturing zone does not touch the aquifer, thereby preventing the occurrence of floods. The thickness of the waterproof coal rock pillar should be greater than the height of the waterproof coal rock pillar to increase safety redundancy and ensure effective water isolation under various geological conditions. The range of the waterproof coal rock pillar should cover the entire coal mining face and its affected area to prevent the risk of water seepage due to partial uncoveredness.

[0087] Before mining at the coal mining face, waterproof coal rock pillars are reserved according to the determined burial depth, thickness and range. The reservation methods include no mining, partial mining, grouting reinforcement, etc. Among them, no mining means that for the area determined to be waterproof coal rock pillars, mining operations are not carried out directly, and the original coal rock is retained as a waterproof barrier. Partial mining means that waterproof coal rock pillars are mined to a limited extent without affecting the waterproof function to improve the resource recovery rate. Grouting reinforcement refers to grouting reinforcement of coal rock pillars to improve the strength and waterproof performance of the coal rock mass.

[0088] At the same time, monitoring points are set up in the waterproof coal rock pillar to monitor the stress and deformation state of the coal rock pillar in real time. Through real-time monitoring, abnormal changes in the coal rock pillar, such as stress concentration, increased displacement, accelerated seepage, etc., can be discovered in time to provide data support for taking emergency measures.

[0089] Figure 2 The structural block diagram of the calculation system of the water-proof coal rock pillar height and the cracking zone height provided by the present invention is shown in FIG. Figure 2 In a preferred embodiment of the present invention, the present invention provides a calculation system 200 for the height of waterproof coal rock pillar and the height of fracture zone, comprising:

[0090] The data acquisition module 201 is used to obtain geological parameters of the mining coal seam; wherein the geological parameters include the thickness of the coal seam, the inclination of the coal seam, the buried depth of the coal seam and the lithology of the top and bottom plates of the coal seam;

[0091] An equivalent mining thickness determination module 202 is used to calculate the equivalent mining thickness of the mined coal seam according to the geological parameters, where the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining influence range;

[0092] The calculation module 203 is used to calculate the height of the waterproof coal rock pillar and the height of the fracturing zone according to the equivalent mining thickness of the mined coal seam using a pre-trained neural network model; wherein the neural network model is trained by pre-collected training sample data;

[0093] The safety assessment module 204 is used to compare the calculation results of the waterproof coal rock pillar height and the fracturing zone height with the preset safety threshold, and issue a warning signal when the calculation results exceed the safety threshold.

[0094] The calculation system for the height of the waterproof coal rock pillar and the height of the fracture zone provided by the present invention executes the calculation method for the height of the waterproof coal rock pillar and the height of the fracture zone provided by the above-mentioned embodiments through various modules of the system. The calculation method for the height of the waterproof coal rock pillar and the height of the fracture zone has been described in detail in the above-mentioned embodiments, and will not be repeated in this embodiment.

[0095] Figure 3 The structural block diagram of the electronic device provided by the present invention is as follows: Figure 3 As shown, the present invention also provides an electronic device, and the electronic device 300 can be a computing device such as a mobile terminal, a desktop computer, a notebook, a palm computer, and a server. The electronic device 300 includes a processor 301 and a memory 302, wherein the memory 302 stores a calculation program 305 for the height of the waterproof coal rock pillar and the height of the fracturing zone.

[0096] In some embodiments, the memory 302 may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory 302 may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Furthermore, the memory 302 may also include both an internal storage unit of a computer device and an external storage device. The memory 302 is used to store application software and various types of data installed on the computer device, such as program codes for installing the computer device. The memory 302 may also be used to temporarily store data that has been output or is to be output. In one embodiment, when the calculation program 305 for the height of the waterproof coal rock column and the height of the fracturing zone is executed by the processor 301, the following steps are implemented:

[0097] Obtaining geological parameters of the mining coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology;

[0098] According to the geological parameters, the equivalent mining thickness of the mined coal seam is calculated, and the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining impact range;

[0099] According to the equivalent mining thickness of the mined coal seam, the height of the waterproof coal rock pillar and the height of the fracturing zone are calculated using a pre-trained neural network model; wherein the neural network model is trained using pre-collected training sample data.

[0100] In some embodiments, the processor 301 can be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 302, such as executing the calculation program of the height of the waterproof coal rock column and the height of the fracturing zone.

[0101] This embodiment further provides a computer-readable storage medium, on which a calculation program for the height of the waterproof coal rock pillar and the height of the fracturing zone is stored. When the calculation program for the height of the waterproof coal rock pillar and the height of the fracturing zone is executed by a processor, the following steps are implemented:

[0102] Obtaining geological parameters of the mining coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology;

[0103] According to the geological parameters, the equivalent mining thickness of the mined coal seam is calculated, and the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining impact range;

[0104] According to the equivalent mining thickness of the mined coal seam, the height of the waterproof coal rock pillar and the height of the fracturing zone are calculated using a pre-trained neural network model; wherein the neural network model is trained using pre-collected training sample data.

[0105] In summary, the calculation method of the waterproof coal rock pillar height and the cracking zone height provided by the present invention has the following beneficial effects compared with the prior art:

[0106] 1) The present invention introduces the concept of equivalent mining thickness and considers the influence of coal seam occurrence (such as coal seam inclination, coal seam thickness, etc.) on the mining impact range, making the calculation of waterproof coal rock pillar height and fracture zone height more accurate. This method that considers the complexity of geological conditions helps to reduce calculation errors caused by differences in geological parameters.

[0107] 2) The use of pre-trained neural network models for calculations can handle more complex and changeable geological conditions. The neural network model can capture the nonlinear relationship between geological parameters and the height of waterproof coal rock pillars and the height of the fracturing zone through learning from a large amount of training sample data, thereby providing more accurate prediction results under complex geological conditions.

[0108] 3) Traditional calculation methods often rely on engineers’ experience and judgment, which is highly subjective. However, the present invention uses a neural network model to automatically calculate, which reduces the interference of human factors and improves the objectivity and reliability of the calculation results.

[0109] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating the height of waterproof coal rock pillar and the height of fracture zone, characterized in that: include: Obtaining geological parameters of the mining coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology; Calculate the equivalent mining thickness of the mined coal seam based on the geological parameters; According to the equivalent mining thickness of the mined coal seam, the height of the waterproof coal rock pillar and the height of the fracturing zone are calculated using a pre-trained neural network model; wherein the neural network model is trained using pre-collected training sample data.

2. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 1, characterized in that: The calculation of the equivalent mining thickness of the mined coal seam includes: The actual mining thickness of each coal seam is corrected by the inclination angle to obtain the equivalent mining thickness of each coal seam; the calculation formula of the equivalent mining thickness is: equivalent mining thickness = actual mining thickness × cosθ, θ is the inclination angle of the coal seam; The equivalent mining thickness of each coal seam is weighted and summed to obtain the equivalent mining thickness of the mined coal seam. The weight is determined according to the burial conditions of each coal seam. The deeper the burial and the harder the lithology of the coal seam, the greater the weight.

3. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 1, characterized in that: Before using the pre-trained neural network model to calculate the height of the waterproof coal rock pillar and the height of the fracture zone, it also includes: obtaining the water-richness parameters of the aquifer adjacent to the mined coal seam; the water-richness parameters of the aquifer include the permeability coefficient, water supply degree, water pressure and water quality type of the aquifer.

4. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 1, characterized in that: The neural network model includes an input layer, a hidden layer and an output layer; Among them, the number of neurons in the input layer is the sum of the number of equivalent mining thickness and aquifer water richness parameters. The input data is normalized to map parameters of different dimensions to the interval [0, 1]; the number of neurons in the output layer is 2, corresponding to the height of the waterproof coal rock pillar and the height of the fracturing zone, respectively. The output value is denormalized and restored to the original dimension; the number of layers of the hidden layer and the number of neurons in each layer are determined according to the training sample data, and the trial and error method is used to optimize the network structure, with the minimum mean square error as the goal.

5. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 4, characterized in that: The neural network model is trained using the BP algorithm, and the loss function is the mean square error between the predicted value and the measured value of the water-proof coal rock pillar height and the fracture zone height; Among them, the BP algorithm includes: calculating the output of each layer of neurons through forward propagation, calculating the gradient of the loss function to the weight and bias through back propagation, and using the gradient descent method to update the weight and bias until the loss function converges below the set threshold.

6. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 1, characterized in that: After obtaining the geological parameters of the mining coal seam, it also includes: The geological parameters are dimensionally non-dimensionalized, and geological parameters of different dimensions are converted into the same dimension.

7. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 1, characterized in that: The training sample data of the neural network model includes: The measured data on waterproof coal rock pillar height and fracture zone height in different mining areas and under different geological conditions, as well as the corresponding equivalent mining thickness and aquifer water richness parameters; the data sources of the training sample data include the on-site monitoring data of the mining area and similar data from adjacent mining areas.

8. The method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone according to claim 1, characterized in that: After calculating the height of the waterproof coal rock pillar and the height of the fracture zone using the pre-trained neural network model, it also includes: Compare the calculated results of the waterproof coal rock pillar height and the cracking zone height with the preset safety threshold; wherein the safety threshold is determined according to the water richness of the aquifer and the waterproof requirements of the coal mining face; When the calculated result exceeds the safety threshold, a warning signal will be issued through sound and light alarms, mobile phone text messages or emails, and the warning information will be transmitted to the ground monitoring center.

9. A calculation system for the height of a waterproof coal rock pillar and the height of a fracturing zone used in the calculation method for the height of a waterproof coal rock pillar and the height of a fracturing zone as claimed in any one of claims 1 to 8, characterized in that: include: A data acquisition module is used to obtain geological parameters of the mined coal seam; wherein the geological parameters include coal seam thickness, coal seam inclination, coal seam burial depth and coal seam top and bottom lithology; An equivalent mining thickness determination module is used to calculate the equivalent mining thickness of the mined coal seam according to the geological parameters, and the equivalent mining thickness takes into account the influence of the coal seam occurrence state on the mining influence range; A calculation module is used to calculate the height of the waterproof coal rock pillar and the height of the fracturing zone according to the equivalent mining thickness of the mined coal seam using a pre-trained neural network model; wherein the neural network model is trained by pre-collected training sample data; The safety assessment module is used to compare the calculated results of the waterproof coal rock pillar height and the fracturing zone height with the preset safety threshold. When the calculated results exceed the safety threshold, an early warning signal is issued.

10. An electronic device, It is characterized in that comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for calculating the height of the waterproof coal rock pillar and the height of the fracturing zone as described in any one of claims 1 to 8 above.

Citation Information

Patent Citations

  • Setting method of thick loose water-bearing layer sand prevention safe coal and rock pillar under water pressure effect

    CN106194185A

  • Method and device for calculating equivalent minable thickness ratio of coal mine goaf for overhead transmission line

    CN106777655A

  • Method for determining thickness of deep mining safety coal pillar protective layer

    CN117211762A

  • Water disaster prevention and control method for coal mine with multiple aquifers

    CN117852877A