Mine ventilation network air volume distribution optimization method, device and equipment and storage medium

Abstract

The application discloses a mine ventilation network air volume distribution optimization method and device, equipment and a storage medium. The method comprises the following steps: based on the ventilation network structure of the mine ventilation system, a set optimization model for air volume distribution is constructed; according to the set optimization model, optimal position updating is performed through an improved ternary optimization algorithm until the position information of an optimal ternary optimization individual is determined according to a preset maximum iteration number; and based on the position information of the optimal ternary optimization individual, an optimal air volume distribution scheme is obtained. In this way, the solving difficulty of air volume distribution can be effectively reduced through the set optimization model, and the model can be solved based on the improved ternary optimization algorithm, so that good optimization performance and convergence performance can be achieved, the local optimal trap can be effectively avoided, and then the ventilation energy consumption can be effectively reduced under the premise of meeting the air demand of underground operation sites, thereby improving the application performance of the mine ventilation system.

Description

Technical Field

[0001] This application relates to the field of mine ventilation control, and in particular to a method, apparatus, equipment and storage medium for optimizing the air volume distribution of a mine ventilation network. Background Technology

[0002] The primary function of a mine ventilation system is to continuously supply fresh air underground, providing sufficient oxygen for workers and equipment, and expelling toxic and harmful gases, dust, heat, and humidity. As the mining and tunneling area expands, the structure of the mine ventilation network changes accordingly, leading to a redistribution of airflow. This results in some branches having excessive airflow while others have no airflow or insufficient airflow. This not only causes the underground working environment to fail to meet relevant standards but also results in persistently high overall ventilation energy consumption. Therefore, determining a ventilation scheme that meets the air demand of all underground workplaces while minimizing ventilation costs has become one of the most challenging issues in the field of mine ventilation.

[0003] With the rapid development of intelligent algorithms, they have begun to be introduced into the field of mine ventilation optimization. Li Jiang et al. designed a dynamic penalty function and applied a genetic algorithm to solve the ventilation network model, reducing the total ventilation energy consumption by 7.78 kW. Wei G solved the complex path problem of the ventilation network based on the ant colony optimization algorithm. Hao Xiaohong et al. proposed a new transient chaotic neural network solution method to address the shortcomings of traditional mine ventilation network solution methods, achieving an energy saving rate of approximately 3.78%. Guo Yinan et al. optimized the airflow distribution of the mine ventilation network based on the particle swarm optimization algorithm, reducing the total energy consumption by 12 kW. Chen K et al. optimized the airflow regulation of the mine ventilation network based on an improved differential evolution algorithm and the critical path method. Shao Liangshan et al. simulated and optimized the ventilation network of Xintun Mine based on simulated annealing and an improved particle swarm optimization algorithm, reducing ventilation energy consumption by 95.69 kW. Zhang Xingguo et al. studied the airflow distribution optimization based on the ACPSO algorithm, minimizing the energy consumption of the optimized airflow distribution scheme. Wu Xinzong et al. incorporated an elite inverse learning strategy into the fireworks algorithm, enhancing its search capability in the spatial domain and thus improving its global search capability. Song Jialin proposed an improved method combining particle swarm optimization and tabu search algorithms, and applied it to Ronghua No. 1 Mine, reducing the total energy consumption of its ventilation network by 43.27%.

[0004] The intelligent optimization algorithm used in the above research on mine ventilation optimization is a stochastic overall search method that does not calculate derivatives. It has advantages such as simple computation, flexible search strategies, strong adaptability, and ease of programming. However, it still has the following drawbacks: 1) The initial population is randomly generated, making it difficult to quickly approach the optimal solution, resulting in low optimization efficiency; 2) The selection strategy is a greedy or elitist method, causing candidate solutions to become very similar in a short time, lacking diversity; 3) It is extremely prone to falling into local optima traps. These shortcomings make it difficult for the application performance of the mine ventilation system to meet practical application requirements. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method, apparatus, equipment and storage medium for optimizing air volume distribution in a mine ventilation network, aiming to effectively improve the application performance of a mine ventilation system.

[0006] The technical solution of this application embodiment is implemented as follows:

[0007] In a first aspect, embodiments of this application provide a method for optimizing airflow distribution in a mine ventilation network, including:

[0008] Based on the ventilation network structure of the mine ventilation system, a setting optimization model for air volume distribution is constructed.

[0009] Based on the optimization model, the optimal position is updated using an improved tern optimization algorithm until the optimal position information of the tern individual is determined according to the preset maximum number of iterations.

[0010] Based on the location information of the optimal black tern individual, the optimal wind volume allocation scheme is obtained.

[0011] In the above scheme, the optimization model is set with the goal of minimizing the total energy consumption of the mine ventilation system, as detailed below:

[0012] ;

[0013] Where W is the total energy consumption, α is the first penalty parameter, β is the second penalty parameter, γ is the third penalty parameter, and N is the third penalty parameter. f H represents the number of mine ventilation fans operating within the mine. f Q represents the air pressure of each mine ventilation fan within the mine. f H represents the air volume of each mine ventilation fan within the mine. j For the wind pressure at branch j of the tunnel, △h j H represents the resistance value of roadway branch j during the resistance adjustment process. nj H represents the natural wind pressure at branch j of the tunnel. fj Q is the air pressure of the fan at branch j of the tunnel. j Q is the air volume of tunnel branch j. maxQ represents the maximum airflow of each branch. min H represents the minimum airflow in each branch. max H represents the maximum value of the wind pressure in each branch. min H represents the minimum wind pressure of each branch. fmax This refers to the maximum air pressure of the fan; b. The fan efficiency of each mine ventilation fan; kj Given an independent loop matrix, if roadway branch j is in loop b k Above and with loop b k If they are in the same direction, then b kj The value is 1; if the roadway branch j is in loop b k Above and with loop b k Conversely, then b kj The value is -1; if the roadway branch j is not in the loop b k Above, then b kj The value is 0.

[0014] In the above scheme, the step of updating the optimal position using the improved Black-crowned Tern optimization algorithm based on the set optimization model includes:

[0015] Based on the established optimization model, the initial parameters of the improved tern optimization algorithm are set.

[0016] Based on the initial parameters and the uniform reverse initialization strategy, an initial population of black terns is generated.

[0017] For the aforementioned Black Terns population, the current optimal Black Terns individual is obtained by calculating and evaluating based on individual fitness values.

[0018] In the above scheme, generating the initial population of Black-crowned Tern based on the initial parameters and the uniform reverse initialization strategy includes:

[0019] Based on the population size N and the upper boundary UB of the ternary optimization method. k Seeking the best lower boundary LB with the black tern k We obtain the set of k-dimensional subspaces Λ k ;

[0020] For the k-dimensional subspace set Λ k Based on the uniform generation operation, the first initial population is generated;

[0021] For the k-dimensional subspace set Λ k Based on the reverse solution operation of the Black Terns, a second initial population is generated;

[0022] The fitness value of each individual in the first initial population and the second initial population is calculated, and the top N individuals with the highest fitness values ​​are selected to form the initial Black Terns population.

[0023] In the above scheme, the step of calculating and evaluating the current optimal individual black tern based on its fitness value for the black tern population includes:

[0024] For N individuals in the Black-eared Tern population, the individual fitness value is calculated and evaluated, and the individual with the smallest fitness value is taken as the current optimal Black-eared Tern individual;

[0025] The individual fitness value represents the total energy consumption corresponding to the air volume distribution scheme of the mine ventilation system.

[0026] In the above scheme, determining the location information of the optimal individual black tern based on a preset maximum number of iterations includes:

[0027] If it is determined that the number of iterations of the Black-eared Terns population is less than the preset maximum number of iterations, then a new Black-eared Terns population is generated by performing a global search based on migration behavior, a local search based on attack behavior, and a mutation operation based on a genetic algorithm. The population is then returned to the preset maximum number of iterations. Based on the individual fitness values, the current optimal Black-eared Terns are calculated and evaluated to obtain the current optimal Black-eared Terns individual. This process continues until the number of iterations of the Black-eared Terns population is equal to the preset maximum number of iterations, at which point the location information of the optimal Black-eared Terns individual is obtained.

[0028] In the above scheme, the step of calculating and evaluating the fitness values ​​of N individuals in the Black-eared Terns population, and selecting the individual with the lowest fitness value as the current optimal Black-eared Terns, includes:

[0029] Based on a greedy selection strategy, the best and second-best individuals among the N individuals are selected, and the target individual is selected based on a fitness and distance selection strategy.

[0030] Based on the optimal individual, the second-best individual, and the target individual, the current optimal black tern individual is determined.

[0031] Secondly, embodiments of this application provide a mine ventilation network airflow distribution optimization device, comprising:

[0032] The model building module is used to construct a setting optimization model for air volume distribution based on the ventilation network structure of the mine ventilation system.

[0033] The model solving module is used to update the optimal position of the tern based on the set optimization model and the improved tern optimization algorithm until the optimal position information of the tern individual is determined according to the preset maximum number of iterations.

[0034] The airflow allocation module is used to obtain the optimal airflow allocation scheme based on the location information of the optimal tern individual.

[0035] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor, wherein the processor, when running the computer program, executes the steps of the method described in embodiments of this application.

[0036] Fourthly, embodiments of this application provide a storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in embodiments of this application.

[0037] The technical solution provided in this application embodiment constructs a set optimization model for air volume distribution based on the ventilation network structure of the mine ventilation system. According to the set optimization model, an improved tern optimization algorithm is used to update the optimal position until the position information of the optimal tern individual is determined according to a preset maximum number of iterations. Based on the position information of the optimal tern individual, the optimal air volume distribution scheme is obtained. Thus, the set optimization model effectively reduces the difficulty of solving the air volume distribution problem, and the improved tern algorithm provides good optimization and convergence performance, effectively avoiding the trap of local optima. Therefore, while meeting the ventilation needs of underground work areas, it effectively reduces ventilation energy consumption, thereby improving the application performance of the mine ventilation system. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating the method for optimizing airflow distribution in a mine ventilation network according to an embodiment of this application.

[0039] Figure 2 This is a flowchart illustrating the improved Black-and-Tern algorithm in an application example of this application;

[0040] Figure 3 This is a schematic diagram of the ventilation network of a mine ventilation system according to an application embodiment of this application;

[0041] Figure 4 This is an iterative diagram illustrating the improved tern optimization algorithm in an application example of this application;

[0042] Figure 5 This is a schematic diagram of the structure of the mine ventilation network air volume distribution optimization device according to an embodiment of this application;

[0043] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0044] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0046] The method for optimizing airflow allocation in a mine ventilation network according to embodiments of this application first constructs a setting optimization model for airflow allocation in the mine ventilation network; secondly, based on the Black-and-White optimization algorithm, it improves the initial population generation strategy, selection strategy, and mutation strategy. This results in the airflow allocation optimization method of this application having better optimization and convergence performance, effectively avoiding the trap of local optima, and effectively reducing ventilation energy consumption while meeting the ventilation needs of underground work sites.

[0047] For example, this application provides a method for optimizing airflow distribution in a mine ventilation network, which can be applied to electronic devices with data processing capabilities, such as... Figure 1 As shown, the method includes:

[0048] Step 101: Based on the ventilation network structure of the mine ventilation system, construct a setting optimization model for air volume distribution.

[0049] It should be noted that the mine ventilation system has a complex network with strong coupling between roadways and various constraints. A change in the airflow in one roadway will affect the airflow in other roadways. To simplify the optimization of airflow allocation in the mine ventilation network, and while ensuring optimization accuracy and rationality, the following assumptions are made when constructing the mine ventilation network airflow allocation optimization model (i.e., setting the optimization model):

[0050] 1) The branch airflow in the mine ventilation network is an incompressible fluid, i.e., an ideal gas;

[0051] 2) The airflow in each branch roadway within the mine is steady;

[0052] 3) The airflow in each branch roadway of the mine is in a state of complete turbulence.

[0053] For example, constraints such as the air volume balance law, the resistance law, and the air pressure balance law can be considered, and the decision variables can be optimized and unconstrained to transform the nonlinear constraint problem into a linear problem, thereby establishing an unconstrained optimization model of the ventilation network.

[0054] Step 102: Based on the set optimization model, the optimal position is updated using the improved tern optimization algorithm until the optimal position information of the tern individual is determined according to the preset maximum number of iterations.

[0055] It should be noted that the Sooty Tern Optimization Algorithm (STOA), as a metaheuristic intelligent algorithm, can be used to solve constrained industrial problems. The algorithm is primarily inspired by the migratory and attack behaviors of the sooty tern in nature. Migration is defined as the seasonal movement of sooty terns from one place to another in search of abundant food sources and sufficient energy. Attack behavior refers to the ability of sooty terns to change their speed and attack angle during migration to attack prey, resulting in spiraling movements in the air during these attacks. These behaviors can be correlated with the objective function to be optimized.

[0056] Compared to traditional optimization algorithms such as genetic algorithms, differential algorithms, and immune algorithms, the Black-Tern optimization algorithm has a greater advantage in search performance. Its spiral search method allows for a wider search range and higher search accuracy. However, the Black-Tern optimization algorithm still has the following shortcomings when optimizing the airflow allocation in mine ventilation networks:

[0057] 1) The initial population generated by the random strategy is very likely to be generated within a small range, which cannot meet the optimization conditions and is prone to getting trapped in local optima;

[0058] 2) Using the best individual in a certain generation of the population as the center of the spiral makes the algorithm very easy to fall into the trap of local optima during the solution process;

[0059] 3) Individuals generated in multiple generations of the population are very similar and lack diversity, which affects the search scope.

[0060] This application introduces an improved Black-and-Tern algorithm to solve the set optimization model. Based on the Black-and-Tern optimization algorithm, improvements are made to the initial population generation strategy, selection strategy, and mutation strategy. This results in the airflow allocation optimization method of this application having better optimization and convergence performance, effectively avoiding the trap of local optima, and effectively reducing ventilation energy consumption while meeting the ventilation needs of underground work sites.

[0061] Step 103: Based on the location information of the optimal black tern individual, obtain the optimal wind volume allocation scheme.

[0062] It is understood that the improved tern algorithm based on the embodiments of this application solves the set optimization model and finds the optimal tern individual corresponding to the number of iterations of the tern population being equal to the preset maximum number of iterations. Based on the location information of this individual, the air volume and air pressure of each branch of the mine ventilation system are determined, and the optimal air volume allocation scheme is obtained. This optimal air volume allocation scheme can be understood as the air volume allocation scheme with the minimum total energy consumption of the mine ventilation system.

[0063] The air volume allocation optimization method of this application embodiment can effectively reduce the difficulty of solving the air volume allocation by setting the optimization model, and the model is solved based on the improved U-Tern algorithm, which has good optimization performance and convergence performance, effectively avoiding the trap of local optima, and thus effectively reducing ventilation energy consumption while meeting the ventilation needs of underground work sites, thereby improving the application performance of the mine ventilation system.

[0064] For example, the optimization model is set with the goal of minimizing the total energy consumption of the mine ventilation system, as shown below:

[0065] ;

[0066] Where W is the total energy consumption, α is the first penalty parameter, β is the second penalty parameter, γ is the third penalty parameter, and N is the third penalty parameter. f H represents the number of mine ventilation fans operating within the mine. f Q represents the air pressure of each mine ventilation fan within the mine. f H represents the air volume of each mine ventilation fan within the mine. j For the wind pressure at branch j of the tunnel, △h j H represents the resistance value of roadway branch j during the resistance adjustment process. nj H represents the natural wind pressure at branch j of the tunnel. fj Q is the air pressure of the fan at branch j of the tunnel. j Q is the air volume of tunnel branch j. max Q represents the maximum airflow of each branch. min H represents the minimum airflow in each branch. max H represents the maximum value of the wind pressure in each branch. min H represents the minimum wind pressure of each branch. fmax This refers to the maximum air pressure of the fan; b. The fan efficiency of each mine ventilation fan; kj Given an independent loop matrix, if roadway branch j is in loop b k Above and with loop b k If they are in the same direction, then b kj The value is 1; if the roadway branch j is in loop b k Above and with loop b k Conversely, then b kj The value is -1; if the roadway branch j is not in the loop b k Above, then b kj The value is 0.

[0067] Exemplary, before describing the improved tern optimization algorithm of the present application embodiments, the migration behavior and attack behavior involved in the tern optimization algorithm in the related art are described as follows:

[0068] (1) Migration behavior

[0069] ①During migration, terns flock together. The initial locations of the terns differ, S A Used to calculate new tern locations to avoid collisions with neighboring terns.

[0070]

[0071] In the formula: This is a new location where the Black-tailed Terns do not collide with other Black-tailed Terns. Z represents the current position of the black tern, Z represents the current iteration number, and S represents the current position of the black tern. A This indicates the range of movement of the Black Terrier.

[0072] S A =C f -(z×(C f / Max iterations (2)

[0073] In the formula: z = 0, 1, 2, ..., Max iterations C f It is a control variable. As the number of iterations increases, S... A From C f Reduce to 0.

[0074] ② Within a flock of terns, terns can fly in the direction most suitable for survival, i.e., terns with higher fitness values.

[0075]

[0076] In the formula: Indicating the different positions of the tern With the best black tern Distance of location, C B Let be a random variable, in order to improve the diversity of the global search. R and Represents a random number between [0, 1].

[0077] C B =0.5×R and (4)

[0078] ③ Using the most suitable tern as the base point, other terns can update their initial positions.

[0079]

[0080] In the formula: This indicates the new location of the black tern.

[0081] (2) Aggressive behavior

[0082] The aggressive behavior of the Black-tailed Tern is a common natural spiral phenomenon, as described in equation (6):

[0083]

[0084] In the formula: θ is the center of the spiral, i.e., the optimal position of the black tern; r is the spiral radius; θ is the spiral angle; The current position of the black tern; z is the iteration number; S n It is a helical matrix composed of helical radius and helical angle.

[0085] The spiral matrix in the N-dimensional spiral model is composed of two-dimensional rotation matrices, as shown in (7) to (9):

[0086] S n =r*R (n) (θ) (7)

[0087]

[0088]

[0089] For example, a 3D spiral matrix is ​​obtained by multiplying three 2D spiral matrices, that is:

[0090]

[0091]

[0092]

[0093]

[0094] In this embodiment of the application, by way of example, the step of updating the optimal position according to the set optimization model using the improved black tern optimization algorithm includes:

[0095] Based on the established optimization model, the initial parameters of the improved tern optimization algorithm are set.

[0096] Based on the initial parameters and the uniform reverse initialization strategy, an initial population of black terns is generated.

[0097] For the aforementioned Black Terns population, the current optimal Black Terns individual is obtained by calculating and evaluating based on individual fitness values.

[0098] Here, the initial parameters can include at least one of the following: population size N, dimension D, and maximum number of iterations Max. iterations Helix radius r, helix angle θ, and mutation operator P m .

[0099] For example, generating an initial population of black terns based on the initial parameters and the uniform reverse initialization strategy includes:

[0100] Based on the population size N and the upper boundary UB of the ternary optimization method. k Seeking the best lower boundary LB with the black tern k We obtain the set of k-dimensional subspaces Λ k ;

[0101] For the k-dimensional subspace set Λ k Based on the uniform generation operation, the first initial population is generated;

[0102] For the k-dimensional subspace set Λ k Based on the reverse solution operation of the Black Terns, a second initial population is generated;

[0103] The fitness value of each individual in the first initial population and the second initial population is calculated, and the top N individuals with the highest fitness values ​​are selected to form the initial Black Terns population.

[0104] It should be noted that the initial population of the Black-eared Terns optimization algorithm serves as the starting point for the optimization search of the target problem. The distribution of the initial population in the solution space directly affects the subsequent search process of the Black-eared Terns, and thus has a significant impact on the optimization result. The Black-eared Terns optimization algorithm uses a random strategy to generate the initial Black-eared Terns population. Due to the influence of random errors, this initialization strategy cannot guarantee that the initial Black-eared Terns population can cover the decision space well. Based on this, in this embodiment, a uniform reverse initialization strategy is proposed to generate the Black-eared Terns population by combining the reverse learning method and uniformization. This uniform reverse initialization strategy makes the generated initial population wider in scope and more targeted, providing a good start for subsequent searches and avoiding getting trapped in local optima.

[0105] In one application example, a population of black terns is generated based on a uniform reverse initialization strategy, including:

[0106] Step 1: Let the solution space vector E be... k The upper and lower bounds of the space where (k = 1, 2, ..., D) are respectively UB k LB k Divide the vector space into N equal parts to obtain a set of k-dimensional subspaces Λ k , as in equations (14) and (15).

[0107] ΔK=(UB k -LB k ) / N (14)

[0108] Λ k ={[LB k ,LBk +ΔK],[LB k +ΔK,LB k +2ΔK],…,[LB k +(N-1)ΔK,UB k ]} (15)

[0109] Step 2: In set Λ k A random value is generated within any subinterval in the solution space, which serves as the initial value of the i-th tern in the k-dimensional solution space. Each subinterval has one and only one chance to be randomly selected, as in the operation of equation (16), where i = 1, 2, ..., N.

[0110]

[0111] Step 3: Perform the reverse solution operation for the black tern to obtain the reverse solution point of the i-th black tern in the k-dimensional solution space.

[0112]

[0113] In the formula: λ∈(0,1).

[0114] Step 4: Based on the population size N of the Black-eared Terns and the spatial dimension D, repeat steps 2 and 3 to generate the first-generation Black-eared Terns population. and the corresponding reverse population Where i = 1, 2, ..., N; k = 1, 2, ..., D.

[0115] Step 5: Calculate the fitness value of each of the 2N individuals in the population set {X, X'}, and select the top N individuals with the highest fitness values ​​to form the initial black tern population, providing the initial search point for optimizing the objective function.

[0116] For example, the step of calculating and evaluating the current optimal individual black tern based on its fitness value for the black tern population includes:

[0117] For N individuals in the Black-eared Tern population, the individual fitness value is calculated and evaluated, and the individual with the smallest fitness value is taken as the current optimal Black-eared Tern individual;

[0118] The individual fitness value represents the total energy consumption corresponding to the air volume distribution scheme of the mine ventilation system.

[0119] It should be noted that the aggressive behavior of the Black-eared Terns optimization algorithm, namely its local search function, involves using the optimal individual in the population as the center of a spiral, guiding other individuals to move in a spiral pattern. This approach is very prone to getting trapped in local optima and converging prematurely. For example, in this embodiment, the step of calculating and evaluating the fitness values ​​of N individuals in the Black-eared Terns population, and selecting the individual with the smallest fitness value as the current optimal Black-eared Tern individual, includes:

[0120] Based on a greedy selection strategy, the best and second-best individuals among the N individuals are selected, and the target individual is selected based on a fitness and distance selection strategy.

[0121] Based on the optimal individual, the second-best individual, and the target individual, the current optimal black tern individual is determined.

[0122] In one application example, a three-point center selection method can be used to make the spiral center not uniquely determined within a bounded region, giving it the ability to escape local optima. The first two points are selected based on a greedy selection strategy to find the optimal point. (i.e., the aforementioned optimal individual) and second-best. (i.e., the aforementioned suboptimal individual), the third point selects the optimal point based on the fitness-distance balance (FDB) selection strategy. (i.e., the aforementioned target individual). Finally, the spiral center is determined according to equation (18).

[0123]

[0124] In the formula, r1 and r2 are random numbers in the range [0,1].

[0125] For example, the implementation steps of the FDB selection strategy are as follows:

[0126] Step 1: Calculate the fitness value of each individual and normalize it.

[0127] G = f(x1,x2,…,x) m (19)

[0128]

[0129]

[0130]

[0131] In the formula: G represents the objective function, i.e., G i =G(P iP represents the population, with n individuals and a dimension of m; F is the normalized representation of the objective function value for each individual; norm is the data normalization process.

[0132] Step 2: Calculate the distance between each individual and the optimal individual using the Euclidean distance (EU) method. The distance between them is normalized.

[0133]

[0134]

[0135] In the formula: d i =norm(D pi ), D p This is the normalized representation of the distance between each individual and the optimal individual.

[0136] Step 3: Weight the two distances and take S. FDBp The largest individual is considered the optimal individual.

[0137]

[0138]

[0139] For example, determining the location information of the optimal individual black tern based on a preset maximum number of iterations includes:

[0140] If it is determined that the number of iterations of the Black-eared Terns population is less than the preset maximum number of iterations, then a new Black-eared Terns population is generated by performing a global search based on migration behavior, a local search based on attack behavior, and a mutation operation based on a genetic algorithm. The population is then returned to the preset maximum number of iterations. Based on the individual fitness values, the current optimal Black-eared Terns are calculated and evaluated to obtain the current optimal Black-eared Terns individual. This process continues until the number of iterations of the Black-eared Terns population is equal to the preset maximum number of iterations, at which point the location information of the optimal Black-eared Terns individual is obtained.

[0141] It should be noted that, since the Black-tailed Tern optimization algorithm performs a spiral search, it is prone to falling into local optima. Therefore, this application introduces a mutation strategy (i.e., mutation operation based on a genetic algorithm) in its embodiments. During the search process, the mutation operator alters the population distribution, thereby increasing population diversity. The mutation operator can be understood as: for each individual in the population, with a certain probability (such as a predetermined mutation operator P),... m The position of one or more individuals is changed. For the variation of real values, the corresponding position value is replaced with other random values ​​within the range of values.

[0142] Figure 2The following is a flowchart illustrating the improved Black Terrier algorithm in an application example of this application, as shown below. Figure 2 As shown, the processing flow of this improved tern algorithm can specifically include:

[0143] Step 1: Algorithm Parameter Setting. Based on the complexity of the ventilation network, set the initial parameters of the improved Black-crowned Tern algorithm, including: population size N, dimension D, and maximum number of iterations Max. iterations Helix radius r, helix angle θ, and mutation operator P m .

[0144] Step 2: Initialize the population parameter S of the Black-eared Tern A and C B The initial calculation formulas are (2) and (4).

[0145] Step 3: Population Initialization. Based on the number and range of independent decision variables, plan the solution space dimension and boundary conditions. Within the solution space, use a uniform reverse initialization strategy to generate an initial Black-crowned Terns population X = {x}. n Set the iteration count z = 0.

[0146] Step 4: Calculate individual fitness values. Based on the information carried by each individual in the initial population, calculate the ventilation network and output the ventilation parameters such as airflow, air pressure, and air resistance of the ventilation network at the current location of each individual in the initial population, and then calculate the total power of the fans.

[0147] Step 5: Individual fitness evaluation. The greedy principle is used to select the best individual from the initial population. and suboptimal individuals Then, the FDB selection strategy is used to select the optimal individuals in the initial population. Its calculation formula is Equation (26); finally, the spiral center is determined by Equation (18). That is, the optimal individual in the initial population.

[0148] Step 6: Determine if the iteration count z is less than the maximum iteration count Max. iterations If yes, proceed to the next step; otherwise, proceed to step 9.

[0149] Step 7: Determine if the maximum population size N has been reached. If not, perform a global search through migration behavior and a local search through attack behavior, and perform mutation operations to update the location of the Black-crowned Terns population, thus obtaining a new population. If so, calculate and evaluate the fitness of individual individuals in the population. If there is a better fitness value than the optimal value of the old population, then update the population. And update parameter S A and C B

[0150] Step 8: Change the iteration number z to z+1 and return to step 6.

[0151] Step 9: If the termination iteration condition is met, output the information carried by the best individual of the last generation of black terns, calculate the air volume, air pressure and optimal power of each branch of the ventilation network, and output the ventilation network air volume allocation optimization scheme.

[0152] The air volume allocation optimization method of this application embodiment will be illustrated below with reference to an application example.

[0153] Figure 3 A schematic diagram of the ventilation network of the mine ventilation system in this application embodiment is shown. This experimental model is a simplified version of an actual mine ventilation network and has good experimental reference value. The mine ventilation network has 23 branches, 18 nodes, and 6 independent loops. Branches 10, 15, and 21 are working face branches, requiring an air volume of 8 m³ / s. 3 / s; Branch 13 is the fan branch, consisting of two identical fans connected in series; Branch 23 is the atmospheric branch (pseudo-branch), with zero air resistance. The parameters of the mine ventilation network experimental model are shown in Table 1, and the independent loops are shown in Table 2.

[0154] Table 1. Parameters of the Mine Ventilation Network Experimental Model

[0155]

[0156]

[0157]

[0158] Table 2 Independent Loop Table of Mine Ventilation Network Experimental Model

[0159]

[0160] An improved ternary optimization algorithm was used to optimize an experimental model of a mine ventilation network. The main parameters of the improved ternary optimization algorithm were: population size N = 120, solution space vector dimension D = 3, and maximum number of iterations Max. iterations =500, C f =1.1, mutation operator P m =0.2, helix radius r = 0.99, helix angle θ = π / 3. The experiment was repeated 50 times, and the curve with the minimum optimized power value was selected as the experimental result. The optimization results of the traditional solution method and the improved tern optimization algorithm are compared in Tables 3 and 4 below:

[0161] Table 3 Comparison of optimization results between traditional solution method and improved tern optimization algorithm

[0162] Traditional solution method 106.88 106.88 Improved Black-and-Tern Optimization Algorithm 69.409 69.988

[0163] Table 4 Comparison of ventilation network parameters between traditional solution method and improved tern optimization algorithm

[0164]

[0165]

[0166] As shown in Table 3, the improved tern optimization algorithm significantly reduces the optimal total power and average total power compared to the traditional solution method, by 37.47 kW and 36.9 kW respectively. The improved tern optimization algorithm has better convergence and higher convergence accuracy.

[0167] For example, the iterative diagram of the improved Black Terrier optimization algorithm is shown below. Figure 4 As shown. In Figure 4 As can be seen, the improved Black-and-White tern optimization algorithm enters the local search stage after 25 iterations. The iteration curve of the improved Black-and-White tern optimization algorithm shows a rapid downward trend, indicating that it can quickly find the vicinity of the optimal value. Therefore, the STOA algorithm improved based on the uniform back-learning strategy, FDB search strategy, and mutation strategy has better optimization performance.

[0168] To implement the method of this application embodiment, this application embodiment also provides a mine ventilation network air volume distribution optimization device, which is installed in electronic equipment, such as... Figure 5 As shown, the mine ventilation network air volume distribution optimization device includes: a model building module 501, a model solving module 502, and an air volume distribution module 503. The model building module 501 is used to build a set optimization model for air volume distribution based on the ventilation network structure of the mine ventilation system. The model solving module 502 is used to update the optimal position according to the set optimization model using an improved black tern optimization algorithm until the position information of the optimal black tern individual is determined according to the preset maximum number of iterations. The air volume distribution module 503 is used to obtain the optimal air volume distribution scheme based on the position information of the optimal black tern individual.

[0169] For example, the optimization model is set with the goal of minimizing the total energy consumption of the mine ventilation system, as shown below:

[0170] ;

[0171] Where W is the total energy consumption, α is the first penalty parameter, β is the second penalty parameter, γ is the third penalty parameter, and N is the third penalty parameter. f H represents the number of mine ventilation fans operating within the mine. f Q represents the air pressure of each mine ventilation fan within the mine. fH represents the air volume of each mine ventilation fan within the mine. j For the wind pressure at branch j of the tunnel, Δh j H represents the resistance value of roadway branch j during the resistance adjustment process. nj H represents the natural wind pressure at branch j of the tunnel. fj Q is the air pressure of the fan at branch j of the tunnel. j Q is the air volume of branch j of the tunnel. max Q represents the maximum airflow of each branch. min H represents the minimum airflow in each branch. max H represents the maximum value of the wind pressure in each branch. min H represents the minimum wind pressure of each branch. fmax This refers to the maximum air pressure of the fan; b. The fan efficiency of each mine ventilation fan; kj Given an independent loop matrix, if roadway branch j is in loop b k Above and with loop b k If they are in the same direction, then b kj The value is 1; if the roadway branch j is in loop b k Above and with loop b k Conversely, then b kj The value is -1; if the roadway branch j is not in the loop b k Above, then b kj The value is 0.

[0172] For example, the model solving module 502 updates the optimal position according to the set optimization model using an improved black tern optimization algorithm, including:

[0173] Based on the established optimization model, the initial parameters of the improved tern optimization algorithm are set.

[0174] Based on the initial parameters and the uniform reverse initialization strategy, an initial population of black terns is generated.

[0175] For the aforementioned Black Terns population, the current optimal Black Terns individual is obtained by calculating and evaluating based on individual fitness values.

[0176] For example, the model solving module 502 generates an initial population of black terns based on the initial parameters and the uniform reverse initialization strategy, including:

[0177] Based on the population size N and the upper boundary UB of the ternary optimization method. k Seeking the best lower boundary LB with the black tern k We obtain the set of k-dimensional subspaces Λ k ;

[0178] For the k-dimensional subspace set Λ k Based on the uniform generation operation, the first initial population is generated;

[0179] For the k-dimensional subspace set Λ k Based on the reverse solution operation of the Black Terns, a second initial population is generated;

[0180] The fitness value of each individual in the first initial population and the second initial population is calculated, and the top N individuals with the highest fitness values ​​are selected to form the initial Black Terns population.

[0181] For example, the model solving module 502 calculates and evaluates the individual fitness values ​​of the Black-eared Terns population to obtain the current optimal Black-eared Terns individual, including:

[0182] For N individuals in the Black-eared Tern population, the individual fitness value is calculated and evaluated, and the individual with the smallest fitness value is taken as the current optimal Black-eared Tern individual;

[0183] The individual fitness value represents the total energy consumption corresponding to the air volume distribution scheme of the mine ventilation system.

[0184] For example, the model solving module 502 determines the location information of the optimal individual black tern based on a preset maximum number of iterations, including:

[0185] If it is determined that the number of iterations of the Black-eared Terns population is less than the preset maximum number of iterations, then a new Black-eared Terns population is generated by performing a global search based on migration behavior, a local search based on attack behavior, and a mutation operation based on a genetic algorithm. The population is then returned to the preset maximum number of iterations. Based on the individual fitness values, the current optimal Black-eared Terns are calculated and evaluated to obtain the current optimal Black-eared Terns individual. This process continues until the number of iterations of the Black-eared Terns population is equal to the preset maximum number of iterations, at which point the location information of the optimal Black-eared Terns individual is obtained.

[0186] For example, the model solving module 502 calculates and evaluates N individuals in the Black-eared Terns population based on their individual fitness values, and selects the individual with the smallest fitness value as the current optimal Black-eared Terns individual, including:

[0187] Based on a greedy selection strategy, the best and second-best individuals among the N individuals are selected, and the target individual is selected based on a fitness and distance selection strategy.

[0188] Based on the optimal individual, the second-best individual, and the target individual, the current optimal black tern individual is determined.

[0189] In practical applications, the model building module 501, the model solving module 502, and the air volume distribution module 503 can be implemented by a processor in an electronic device. Of course, the processor needs to run a computer program in memory to perform its functions.

[0190] It should be noted that the mine ventilation network airflow distribution optimization device provided in the above embodiments is only illustrated by the division of the above-described program modules when optimizing the airflow distribution of the mine ventilation network. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the mine ventilation network airflow distribution optimization device and the mine ventilation network airflow distribution optimization method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0191] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide an electronic device. Figure 6 This is only an exemplary structure of the device, not the entire structure; it can be implemented as needed. Figure 6 The structure shown may be part or all of the structure.

[0192] like Figure 6 As shown, the device 600 provided in this embodiment includes at least one processor 601, a memory 602, a user interface 603, and at least one network interface 604. The various components in the electronic device 600 are coupled together via a bus system 605. It can be understood that the bus system 605 is used to implement communication between these components. In addition to a data bus, the bus system 605 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 6 The general designated all buses as Bus System 605.

[0193] The user interface 603 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.

[0194] The memory 602 in this embodiment is used to store various types of data to support the operation of the electronic device. Examples of such data include any computer program used to operate on the electronic device.

[0195] The mine ventilation network airflow allocation optimization method disclosed in this application embodiment can be applied to, or implemented by, processor 601. Processor 601 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the mine ventilation network airflow allocation optimization method can be completed by the integrated logic circuits in the hardware of processor 601 or by instructions in software form. The processor 601 can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 601 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules can be located in a storage medium, specifically memory 602. Processor 601 reads information from memory 602 and, in conjunction with its hardware, completes the steps of the mine ventilation network airflow allocation optimization method provided in the embodiments of this application.

[0196] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned methods.

[0197] It is understood that memory 602 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0198] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a memory 602 that stores a computer program. The computer program can be executed by a processor 601 of an electronic device to complete the steps described in the method of this application embodiment. The computer-readable storage medium can be a ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM, etc.

[0199] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0200] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0201] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for optimizing airflow distribution in a mine ventilation network, characterized in that, include: Based on the ventilation network structure of the mine ventilation system, a setting optimization model for air volume distribution is constructed. Based on the optimization model, the optimal position is updated using an improved tern optimization algorithm until the optimal position information of the tern individual is determined according to the preset maximum number of iterations. Based on the location information of the optimal black tern individual, the optimal wind volume allocation scheme is obtained; The optimization model is designed to minimize the total energy consumption of the mine ventilation system, as detailed below: ； Where W is the total energy consumption, α is the first penalty parameter, β is the second penalty parameter, γ is the third penalty parameter, and N is the third penalty parameter. f H represents the number of mine ventilation fans operating within the mine. f Q represents the air pressure of each mine ventilation fan within the mine. f H represents the air volume of each mine ventilation fan within the mine. j For the wind pressure at branch j of the tunnel, △h j H represents the resistance value of roadway branch j during the resistance adjustment process. nj H represents the natural wind pressure at branch j of the tunnel. fj Q is the air pressure of the fan at branch j of the tunnel. j Q is the air volume of tunnel branch j. max Q represents the maximum airflow of each branch. min H represents the minimum airflow in each branch. max H represents the maximum value of the wind pressure in each branch. min H represents the minimum wind pressure of each branch. fmax This refers to the maximum air pressure of the fan; b. The fan efficiency of each mine ventilation fan; kj Given an independent loop matrix, if roadway branch j is in loop b k Above and with loop b k If they are in the same direction, then b kj The value is 1; if the roadway branch j is in loop b k Above and with loop b k Conversely, then b kj The value is -1; if the roadway branch j is not in the loop b k Above, then b kj The value is 0; The step of updating the optimal position according to the set optimization model using the improved tern optimization algorithm includes: Based on the established optimization model, the initial parameters of the improved tern optimization algorithm are set. Based on the initial parameters and the uniform reverse initialization strategy, an initial population of black terns is generated. For the aforementioned Black Terns population, the current optimal Black Terns individual is obtained by calculating and evaluating based on individual fitness values; The generation of the initial Black-eared Tern population based on the initial parameters and the uniform reverse initialization strategy includes: Based on the population size N and the upper boundary of the optimal search for terns. Seeking the best at the lower boundary with the black tern We obtain the set of k-dimensional subspaces. ; For the set of k-dimensional subspaces Based on the uniform generation operation, the first initial population is generated; For the set of k-dimensional subspaces Based on the reverse solution operation of the Black Terns, a second initial population is generated; The fitness value of each individual in the first initial population and the second initial population is calculated, and the top N individuals with the highest fitness values ​​are selected to form the initial Black Terns population.

2. The method according to claim 1, characterized in that, The optimal individual tern is obtained from the aforementioned tern population based on individual fitness values ​​through calculation and evaluation, including: For N individuals in the Black-eared Tern population, the individual fitness value is calculated and evaluated, and the individual with the smallest fitness value is taken as the current optimal Black-eared Tern individual; The individual fitness value represents the total energy consumption corresponding to the air volume distribution scheme of the mine ventilation system.

3. The method according to claim 1, characterized in that, The step of determining the location information of the optimal individual black tern based on a preset maximum number of iterations includes: If it is determined that the number of iterations of the Black-eared Terns population is less than the preset maximum number of iterations, then a new Black-eared Terns population is generated by performing a global search based on migration behavior, a local search based on attack behavior, and a mutation operation based on a genetic algorithm. The population is then returned to the preset maximum number of iterations. Based on the individual fitness values, the current optimal Black-eared Terns are calculated and evaluated to obtain the current optimal Black-eared Terns individual. This process continues until the number of iterations of the Black-eared Terns population is equal to the preset maximum number of iterations, at which point the location information of the optimal Black-eared Terns individual is obtained.

4. The method according to claim 2, characterized in that, The step of calculating and evaluating the fitness values ​​of N individuals in the Black-eared Terns population, and selecting the individual with the lowest fitness value as the current optimal Black-eared Terns, includes: Based on a greedy selection strategy, the best and second-best individuals among the N individuals are selected, and the target individual is selected based on a fitness and distance selection strategy. Based on the optimal individual, the second-best individual, and the target individual, the current optimal black tern individual is determined.

5. A mine ventilation network air volume distribution optimization device, characterized in that, include: The model building module is used to construct a setting optimization model for air volume distribution based on the ventilation network structure of the mine ventilation system. The model solving module is used to update the optimal position of the tern based on the set optimization model and the improved tern optimization algorithm until the optimal position information of the tern individual is determined according to the preset maximum number of iterations. The airflow distribution module is used to obtain the optimal airflow distribution scheme based on the location information of the optimal tern individual; The optimization model is designed to minimize the total energy consumption of the mine ventilation system, as detailed below: ； Where W is the total energy consumption, α is the first penalty parameter, β is the second penalty parameter, γ is the third penalty parameter, and N is the third penalty parameter. f H represents the number of mine ventilation fans operating within the mine. f Q represents the air pressure of each mine ventilation fan within the mine. f H represents the air volume of each mine ventilation fan within the mine. j For the wind pressure at branch j of the tunnel, △h j H represents the resistance value of roadway branch j during the resistance adjustment process. nj H represents the natural wind pressure at branch j of the tunnel. fj Q is the air pressure of the fan at branch j of the tunnel. j Q is the air volume of tunnel branch j. max Q represents the maximum airflow of each branch. min H represents the minimum airflow in each branch. max H represents the maximum value of the wind pressure in each branch. min H represents the minimum wind pressure of each branch. fmax This refers to the maximum air pressure of the fan; b. The fan efficiency of each mine ventilation fan; kj Given an independent loop matrix, if roadway branch j is in loop b k Above and with loop b k If they are in the same direction, then b kj The value is 1; if the roadway branch j is in loop b k Above and with loop b k Conversely, then b kj The value is -1; if the roadway branch j is not in the loop b k Above, then b kj The value is 0; The step of updating the optimal position according to the set optimization model using the improved tern optimization algorithm includes: Based on the established optimization model, the initial parameters of the improved tern optimization algorithm are set. Based on the initial parameters and the uniform reverse initialization strategy, an initial population of black terns is generated. For the aforementioned Black Terns population, the current optimal Black Terns individual is obtained by calculating and evaluating based on individual fitness values; The generation of the initial Black-eared Tern population based on the initial parameters and the uniform reverse initialization strategy includes: Based on the population size N and the upper boundary of the optimal search for terns. Seeking the best at the lower boundary with the black tern We obtain the set of k-dimensional subspaces. ; For the set of k-dimensional subspaces Based on the uniform generation operation, the first initial population is generated; For the set of k-dimensional subspaces Based on the reverse solution operation of the Black Terns, a second initial population is generated; The fitness value of each individual in the first initial population and the second initial population is calculated, and the top N individuals with the highest fitness values ​​are selected to form the initial Black Terns population.

6. An electronic device, characterized in that, include: A processor and memory for storing computer programs that can run on the processor, wherein, The processor, when running a computer program, performs the steps of the method according to any one of claims 1 to 4.

7. A storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images