Method and System for Optimizing Mine Support Parameters Based on Big Data

Abstract

This application relates to the technical field of mine support, and particularly to a method and system for optimizing mine support parameters based on big data. The method includes: initializing support parameters and constructing a mine support model; performing finite element analysis on the mine support model to obtain the maximum stress and maximum deformation under the support parameters, and taking the minimum value of the difference between the allowable strength limit and the maximum stress, and the difference between the allowable deformation threshold and the maximum deformation as the support stability; constructing a fitness function; using the particle swarm algorithm to iteratively update the support parameters to obtain the target support parameters. Through the technical solution of this application, the mine support parameters can be accurately obtained.

Description

Technical Field

[0001] This application relates to the technical field of mine support, and particularly to a method and system for optimizing mine support parameters based on big data. Background Art

[0002] Mine support is a key technology in mining engineering, mainly used to improve the stability and service life of roadways, stopes or key underground engineering spaces, and prevent geological disasters such as collapses and rock bursts. How to determine mine support parameters to meet the urgent needs of intelligent design, construction and management of mine engineering is an urgent problem to be solved.

[0003] Currently, the patent application document with the publication number of CN118468393A discloses a dynamic design method and device, storage medium, and terminal for mine roadway support. The method includes: obtaining real-time disturbance microseismic monitoring data and reference support parameters of the roadway during the execution stage; updating the refined numerical model according to the reference support parameters, and performing support stability simulation based on the real-time disturbance microseismic monitoring data and the updated refined numerical model to obtain the first simulation result; if the first simulation result does not meet the support stability condition, adjusting each parameter in the reference support parameters respectively according to the support parameter adjustment strategy to obtain multiple first improved support parameters; matching at least one second improved support parameter from the preset support parameter mapping relationship set according to the real-time disturbance microseismic monitoring data; generating multiple groups of candidate support parameters based on the first improved support parameters and the second improved support parameters, and simulating through the updated refined numerical model to obtain the second simulation results corresponding to each candidate support parameter; determining the target support parameter for implementing the roadway support in the target stage from the candidate support parameters according to the second simulation results.

[0004] The above method adjusts each parameter in the reference support parameters respectively according to the support parameter adjustment strategy to obtain the first improved support parameters. During the adjustment process, the fixed strategy adjustment is performed on each parameter individually, ignoring the influence of each parameter in the reference support parameters on the support effect, resulting in the inability to accurately obtain the optimal support parameters and making the mine support parameters inaccurate. Summary of the Invention

[0005] In order to solve the technical problem of inaccurate mine support parameters, this application provides a method and system for optimizing mine support parameters based on big data, which can accurately obtain mine support parameters.

[0006] In the first aspect of the present application, an optimization method for mine support parameters based on big data is provided. The optimization method includes: initializing the support parameters and constructing a mine support model, where the support parameters include bolt parameters, wire mesh parameters, and shotcrete parameters; performing finite element analysis on the mine support model to obtain the maximum stress and maximum deformation under the support parameters, and taking the minimum value of the difference between the allowable strength limit and the maximum stress, and the difference between the allowable deformation threshold and the maximum deformation as the support stability; constructing a fitness function, which is positively correlated with the support stability and negatively correlated with the support cost; using the particle swarm optimization algorithm to iteratively update the support parameters until the fitness function at the global optimal position is greater than a preset value, or the number of iterations is greater than a preset number, to obtain the target support parameters, including: calculating the change amount and fitness contribution value of each support parameter in this iteration; taking the velocity gain of each support parameter after normalization as the inertia weight in this iteration, and updating the real-time position of each particle, where the velocity gain is negatively correlated with the change amount and positively correlated with the fitness contribution value.

[0007] Construct a mine support model according to the initialized support parameters, and obtain the maximum stress and maximum deformation of the mine support model under the support parameters through finite element analysis. When the maximum stress is less than the allowable strength limit and the maximum deformation is less than the allowable deformation threshold, it indicates that the support stability of the support parameters is good; construct a fitness function based on the support stability and support cost. The better the support stability and the lower the support cost, the greater the fitness function of the support parameters. Further, use the particle swarm optimization algorithm to iteratively update the support parameters to obtain the target support parameters corresponding to the maximum value of the fitness function.

[0008] Preferably, the bolt parameters include bolt spacing and bolt length; the wire mesh parameters include mesh density and steel bar diameter; the shotcrete parameters include concrete thickness.

[0009] Preferably, in this iteration the change amount of the support parameters is: where

[0010] , and are the numerical values of the support parameter in the th iteration and the th iteration respectively.

[0011] The greater the change amount of the support parameter , the greater the exploration of the particle swarm optimization algorithm on the support parameter before this iteration, accurately quantifying the exploration of the particle swarm optimization algorithm on the support parameter . The exploration range on

[0012] Preferably, in this iteration the support parameters The method for obtaining the fitness contribution value includes: replacing the value of the support parameters in the n-th iteration with the value of the support parameters in the m-th iteration to obtain the simulated support parameters; calculating the first support stability under the simulated support parameters, the second support stability under the support parameters in the n-th iteration, and the third support stability under the support parameters in the m-th iteration; taking the ratio of the difference between the first support stability and the third support stability to the difference between the second support stability and the third support stability as the fitness contribution value of the support parameters in this iteration n-th iteration. m-th iteration the support parameters in this iteration.

[0013] The greater the fitness contribution value of the support parameters indicates that by changing the support parameters the support effect can be effectively improved, and it accurately quantifies the influence degree of the support parameters on the fitness function.

[0014] Preferably, the velocity gain of the support parameters in this iteration is:

[0015] , and are respectively the fitness contribution value and the change amount of the support parameters in this iteration , and is the Relu activation function.

[0016] If the change amount of any support parameter is larger, it indicates that a large-scale exploration has been carried out on this support parameter before this iteration. In order to make the particle swarm algorithm explore all support parameters and ensure an accurate global optimal solution, the velocity of this support parameter is reduced in this iteration and the velocities of other support parameters are increased; at the same time, if the fitness contribution value of any support parameter is larger, it indicates that the support effect can be effectively improved by changing this support parameter. In this iteration, increasing the velocity of this support parameter can effectively improve the support effect by adjusting the value of this support parameter and accelerate the convergence speed of the particle swarm algorithm to quickly obtain the target support parameters. In summary, the velocities of each support parameter are adjusted by comprehensively considering the change amount and fitness contribution value of each support parameter, which can accelerate the convergence speed of the particle swarm algorithm and ensure an accurate global optimal solution.​

[0017] Preferably, updating the real-time position of each particle includes:

[0018] ;

[0019] ;

[0020] wherein, is the velocity gain vector of the current iteration , including the velocity gains of each support parameter after normalization processing, corresponding to the inertia weight; is the velocity of particle m in the -th iteration, including the velocity components of each support parameter; is the Hadamard product of and , and are the individual factor and social factor of particle m respectively, and are random numbers from 0 to 1, and are the global optimal position and the individual optimal position of particle m in the current iteration respectively, and are the real-time positions of particle m in the -th iteration and the current iteration respectively.

[0021] Preferably, the method for obtaining the individual factor of particle m includes: calculating the outlier of particle m by using the LOF algorithm among the individual optimal positions of all particles in the current iteration, and taking the difference between 1 and the outlier as the individual factor of particle m.

[0022] The individual factor of particle m represents the influence degree of the individual optimal position of particle m on the exploration process. The accuracy of the individual optimal position also affects the convergence speed of the particle swarm algorithm. According to the distribution of the individual optimal positions of all particles, accurately judge the accuracy of the individual optimal position, and then calculate the individual factors of each particle. Assign larger individual factors to particles with larger accuracy to ensure the convergence speed, and at the same time assign smaller individual factors to particles with smaller accuracy to explore the global optimal solution.

[0023] Preferably, the support stability satisfies the relation:

[0024] , and are the allowable strength limit and the maximum stress respectively, and are the allowable deformation threshold and the maximum deformation, respectively.

[0025] Preferably, the fitness function satisfies the relational expression: , is the support stability, is the support cost, is the adjustment coefficient.

[0026] In the second aspect of the present application, a big data-based optimization system for mine support parameters is further provided, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the big data-based optimization method for mine support parameters according to the first aspect of the present application is implemented.

[0027] The technical solution of the present application has the following beneficial technical effects:

[0028] A mine support model is constructed according to the initialized support parameters, and the maximum stress and maximum deformation of the mine support model under the support parameters are obtained by means of finite element analysis. When the maximum stress is less than the allowable strength limit and the maximum deformation is less than the allowable deformation threshold, it indicates that the support stability of the support parameters is good; a fitness function is constructed based on the support stability and the support cost. The better the support stability and the lower the support cost, the larger the fitness function of the support parameters. Further, the particle swarm optimization algorithm is used to iteratively update the support parameters to obtain the target support parameters corresponding to the maximum value of the fitness function.

[0029] Furthermore, in the process of using the particle swarm optimization algorithm to iteratively update the support parameters, the change amount and fitness contribution value of each support parameter in any iteration are calculated; if the change amount of any support parameter is larger, it means that a large-scale exploration has been carried out on this support parameter before this iteration. In order to make the particle swarm optimization algorithm explore all support parameters and ensure an accurate global optimal solution, the speed of this support parameter is reduced in this iteration, and the speeds of other support parameters are increased; at the same time, if the fitness contribution value of any support parameter is larger, it means that the support effect can be effectively improved by changing this support parameter. In this iteration, increasing the speed of this support parameter can effectively improve the support effect by adjusting the value of this support parameter, and accelerate the convergence speed of the particle swarm optimization algorithm to quickly obtain the target support parameters. In summary, the speeds of each support parameter are adjusted by comprehensively considering the change amount and fitness contribution value of each support parameter, accelerating the convergence speed of the particle swarm optimization algorithm and ensuring an accurate global optimal solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flowchart of the big data-based optimization method for mine support parameters according to an embodiment of the present application.

[0031] Figure 2 It is a structural block diagram of a mine support parameter optimization system based on big data according to an embodiment of the present application. Specific embodiments

[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0033] According to the first aspect of the present application, the present application provides a method for optimizing mine support parameters based on big data. Figure 1 It is a flowchart of a method for optimizing mine support parameters based on big data according to an embodiment of the present application. As Figure 1 shown, the method for optimizing mine support parameters based on big data includes steps S101 to S104, which are described in detail below.

[0034] S101, Initialize the support parameters and construct a mine support model. The support parameters include bolt parameters, wire mesh parameters, and shotcrete parameters.

[0035] In one embodiment, the support parameters include bolt parameters, wire mesh parameters, and shotcrete parameters. More specifically, the bolt parameters include bolt spacing and bolt length; the wire mesh parameters include mesh density and steel bar diameter; the shotcrete parameters include concrete thickness.

[0036] Among them, after determining the support parameters, a mine support model can be simulated based on the support parameters.

[0037] S102, Perform finite element analysis on the mine support model to obtain the maximum stress and maximum deformation under the support parameters. Take the minimum value of the difference between the allowable strength limit and the maximum stress, and the difference between the allowable deformation threshold and the maximum deformation as the support stability.

[0038] In one embodiment, after obtaining the mine support model, perform mesh division on the mine support model, and apply the mechanical constraints of the rock mass to the mine support model in the form of uniformly distributed loads, and then perform finite element analysis on the mine support model to obtain the maximum stress and maximum deformation of the mine support model under the support parameters.

[0039] Compare the maximum stress with the allowable strength limit, and the allowable deformation threshold and the maximum deformation respectively. If the maximum stress does not exceed the allowable strength limit and the maximum deformation does not exceed the allowable deformation threshold, it indicates that the current mine support model can effectively support the mine, and further indicates that the corresponding support parameters have good support stability.

[0040] Specifically, the support stability satisfies the relationship: , and are the allowable strength limit and the maximum stress respectively, and are the allowable deformation threshold and the maximum deformation respectively.

[0041] Among them, the allowable strength limit is related to the materials of the anchor bolts and the wire mesh, and the allowable deformation threshold is related to the construction requirements of the mine support.

[0042] In this way, the maximum stress and the maximum deformation under the support parameters are obtained by means of finite element analysis, and then the support stability of the support parameters is accurately evaluated.

[0043] S103. Construct a fitness function, which is positively correlated with the support stability and negatively correlated with the support cost.

[0044] In one embodiment, the purpose of optimizing the mine support parameters is to achieve the maximum support stability with the minimum support cost. Therefore, a fitness function is constructed, which is positively correlated with the support stability and negatively correlated with the support cost; the larger the fitness function, the better the support effect, providing a basis for obtaining the target support parameters by using the particle swarm optimization algorithm subsequently.

[0045] Specifically, the support cost includes the material cost and the construction cost, and the fitness function satisfies the relationship: , is the support stability, is the support cost, is the adjustment coefficient. Among them, the value of the adjustment coefficient is 0.01.

[0046] S104. Use the particle swarm optimization algorithm to iteratively update the support parameters until the fitness function at the global optimal position is greater than the preset value, or when the number of iterations is greater than the preset number of times, the target support parameters are obtained.

[0047] In one embodiment, after constructing the fitness function, multiple initialized support parameters are obtained, and one support parameter corresponds to the position of one particle; exemplarily, the number of particles is 30, that is, 30 different support parameters need to be obtained. The particle swarm optimization algorithm is used to iteratively update the positions of each particle. In one iteration process, the real-time positions of all particles are updated simultaneously. The real-time position with the largest fitness function value in the historical iterations is used as the individual optimal position of the corresponding particle, and the individual optimal position corresponding to the maximum fitness function value among all individual optimal positions is used as the global optimal position.

[0048] Specifically, the iterative update of the support parameters using the particle swarm algorithm includes: calculating the change amount and fitness contribution value of each support parameter in the current iteration; using the velocity gain of each support parameter after normalization as the inertia weight in the current iteration to update the real-time position of each particle, where the velocity gain is negatively correlated with the change amount and positively correlated with the fitness contribution value.

[0049] Among them, in the current iteration the support parameters change amount is: , and are respectively the th iteration and the th iteration of the numerical values of the support parameters .

[0050] Among them, in the current iteration the support parameters the method for obtaining the fitness contribution value includes: replacing the numerical value of the support parameter in the th iteration with the numerical value of the support parameter in the th iteration to obtain the simulated support parameters; calculating the first support stability under the simulated support parameters, the second support stability under the support parameters in the th iteration, and the third support stability under the support parameters in the th iteration; taking the ratio of the difference between the first support stability and the third support stability to the difference between the second support stability and the third support stability as the fitness contribution value of the support parameter in the current iteration .

[0051] It can be understood that the larger the change amount of the support parameter , the greater the exploration of the particle swarm algorithm on the support parameter before the current iteration. In order to enable the particle swarm algorithm to explore all support parameters and ensure an accurate global optimal solution, in the current iteration , the velocity of the support parameter should be reduced, and the velocity of other support parameters except the support parameter should be increased; at the same time, the larger the fitness contribution value of the support parameter , the more effectively the support effect can be improved by changing the support parameter . In the current iteration , increasing the velocity of the support parameter The value range effectively improves the support effect, speeds up the convergence rate of the particle swarm algorithm, and quickly obtains the target support parameters.

[0052] Therefore, in this iteration the support parameters speed gain is:

[0053] , and are respectively the fitness contribution value and the change amount of the support parameters in this iteration , and is the Relu activation function. When the fitness contribution value is less than or equal to 0, it means that the change of the support parameters will make the fitness function smaller. Therefore, the value of is mapped to 0 through the Relu activation function, and the speed gain of the support parameters in this iteration is set to 0.

[0054] In one embodiment, the speed gains of the support parameters in this iteration are normalized. The specific process is as follows: Calculate the ratio of the speed gain of the support parameters in this iteration to the sum of the speed gains of all support parameters in this iteration to obtain the speed gain of the normalized support parameters .

[0055] In one embodiment, after normalizing the speed gains of the support parameters in this iteration , taking particle m as an example, the specific process of updating the real-time position of each particle is described, including:

[0056] ;

[0057] ; where is the speed gain vector of this iteration , including the speed gains of the normalized support parameters; is the speed of particle m in the th iteration, including the speed components of the support parameters; is the Hadamard product of and , and are the individual factor and the social factor of particle m, respectively, and are random numbers from 0 to 1, and are the global optimal position and the individual optimal position of particle m in the current iteration respectively, and are the position of particle m in the th iteration and the current iteration respectively. The velocity gain vector of the current iteration corresponds to the inertia weight in the particle swarm algorithm.

[0058] Among them, is a multi-dimensional vector, including the velocity components of each support parameter in the th iteration. The larger the velocity component, the greater the change in the corresponding support parameter. Similarly, is also a multi-dimensional vector, including the velocity gains of each support parameter after normalization in the current iteration . By calculating the Hadamard product between , the velocity components of each support parameter are adjusted, and then the change amounts of each support parameter in the current iteration are adjusted.

[0059] Among them, the individual factor and the social factor of particle m both take the value of 1.

[0060] In another embodiment, the individual factor of particle m represents the influence degree of the individual optimal position of particle m on the exploration process. The accuracy of the individual optimal position also affects the convergence speed of the particle swarm algorithm. The accuracy of the individual optimal position can be judged according to the distribution of the individual optimal positions of all particles, and then the individual factors of each particle can be calculated. Specifically, the method for obtaining the individual factor of particle m includes: calculating the outlier of particle m using the LOF algorithm among the individual optimal positions of all particles in the current iteration, and taking the difference between 1 and the outlier as the individual factor of particle m.

[0061] In this way, the accuracy of the individual optimal position is judged according to the distribution of the individual optimal positions of all particles in the current iteration, and then the individual factors of the particles are determined. Larger individual factors are assigned to particles with higher accuracy to ensure the convergence speed, while smaller individual factors are assigned to particles with lower accuracy to explore the global optimal solution.

[0062] ​​​​​​In this way, the real-time positions of all particles are iteratively updated until the fitness function of the global optimal position is greater than the preset value, or the number of iterations is greater than the preset number, indicating that the global optimal position meets the mine support requirements. At this time, the global optimal position is used as the target support parameter.

[0063] According to the second aspect of the present application, the present application further provides a big data-based mine support parameter optimization system. Figure 2 It is a structural block diagram of a big data-based mine support parameter optimization system according to an embodiment of the present application. As Figure 2 shown, the system 50 includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the big data-based mine support parameter optimization method according to the first aspect of the present application is implemented. The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be described in detail here.

[0064] It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application.

Claims

1. A method for optimizing mine support parameters based on big data, characterized in that The optimization method includes: Initializing the support parameters and constructing a mine support model, where the support parameters include bolt parameters, wire mesh parameters, and shotcrete parameters; Performing finite element analysis on the mine support model to obtain the maximum stress and maximum deformation under the support parameters, and taking the minimum value of the difference between the allowable strength limit and the maximum stress, and the difference between the allowable deformation threshold and the maximum deformation as the support stability; Constructing a fitness function, which is positively correlated with the support stability and negatively correlated with the support cost; Using the particle swarm algorithm to iteratively update the support parameters until the fitness function at the global optimal position is greater than the preset value, or when the number of iterations is greater than the preset number of times, obtaining the target support parameters, including: calculating the change amount and fitness contribution value of each support parameter in this iteration; taking the velocity gain of each support parameter after normalization as the inertia weight in this iteration, and updating the real-time position of each particle, where the velocity gain is negatively correlated with the change amount and positively correlated with the fitness contribution value; This iteration The intermediate support parameters The change amount of is as follows: , and are respectively the -th iteration and the -th iteration of the numerical values of the support parameters ; This iteration Medium support parameters The method for obtaining the fitness contribution value of The first Support parameters in the iteration The value of Support parameters in the iteration The numerical value of is used to obtain the simulated support parameters; Calculate the first support stability under the simulated support parameters, the second support stability under the support parameters in the second iteration, and the third support stability under the support parameters in the third iteration; Take the ratio of the difference between the first support stability and the third support stability to the difference between the second support stability and the third support stability as the fitness contribution value of the support parameters in this iteration. Support parameters in the middle of this iteration. This iteration Medium support parameters Speed gain Is as follows: , and are the fitness contribution value and change amount of the support parameters in this iteration respectively, and is the Relu activation function; is the Relu activation function; The fitness function satisfies the relational expression: , where is the support stability, is the support cost, and is the adjustment coefficient.

2. The method for optimizing mine support parameters based on big data according to claim 1, wherein The bolt parameters include bolt spacing and bolt length; the wire mesh parameters include mesh density and steel bar diameter; the shotcrete parameters include concrete thickness.

3. The method for optimizing mine support parameters based on big data according to claim 1, wherein The updating the real-time position of each particle includes: ； ； Among them, is the velocity gain vector of this iteration , including the velocity gains of each support parameter after normalization, corresponding to the inertia weight; is the velocity of particle m in the th iteration, including the velocity components of each support parameter; is the and Hadamard product of, and are the individual factor and social factor of particle m respectively, and are random numbers from 0 to 1, and are the global optimal position and the individual optimal position of particle m in this iteration respectively, and are the th iteration and the real-time position of particle m in this iteration respectively.

4. The method for optimizing mine support parameters based on big data according to claim 3, characterized in that Individual factor of particle m The acquisition method includes: Among the individual optimal positions of all particles in this iteration, the LOF algorithm is used to calculate the outlier of particle m, and the difference between 1 and the outlier is used as the individual factor of particle m .

5. The method for optimizing mine support parameters based on big data according to claim 1, wherein Support stability Satisfy the relation: , and are the allowable strength limit and the maximum stress respectively, and are the allowable deformation threshold and the maximum deformation respectively.

6. The mine support parameter optimization system based on big data is characterized in that, Including a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the optimization method for mine support parameters based on big data according to any one of claims 1 to 5 is implemented.

Images