Mine ventilation network solution method and device, electronic equipment and storage medium

Abstract

The mine ventilation network solution method and device, as well as the electronic device and storage medium provided by the present disclosure, relate to the field of intelligent mine ventilation network systems. The method includes: obtaining a ventilation network diagram of the target mine, and determining the residual tree branches, tree branches and nodes of the ventilation network based on the ventilation network diagram; formulating the theoretical air volume value of the residual tree branches and calculating the theoretical air volume value of the tree branches, and using the theoretical air volume value of the residual tree branches and the theoretical air volume value of the tree branches as the initial solution of the wind pressure balance equation; correcting the search direction, determining the actual air volume approximate solution of the residual tree branches and the tree branches; calculating the actual air volume and wind pressure values ​​of the residual tree branches and the tree branches, and calculating the actual operating parameters of the fan. The mine ventilation network solution method provided by the present disclosure can converge to obtain the optimal solution at a faster speed and can reduce oscillation.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent mine ventilation network systems, and in particular to a mine ventilation network solution method and device, as well as electronic equipment and storage media. Background Art

[0002] Mine ventilation network calculations typically employ the Scott-Hinsley method, widely used in mine ventilation systems. The Scott-Hinsley method typically constructs a system of multivariate nonlinear equations based on Kirchhoff's air volume balance law, Kirchhoff's air pressure balance law, the resistance law, and the number of branches and nodes. Ideally, this method can yield an optimal solution. However, for complex ventilation network systems, the presence of fixed air volume branches causes imbalance errors during air volume regulation to be excessively concentrated in the loops containing these fixed air volume branches, complicating effective air volume regulation and slowing convergence.

[0003] Therefore, in order to effectively solve the problem that the Scott-Hinsley method does not consider the existence of fixed air volume branches in the ventilation network, the present disclosure provides a wind network solution method based on the improved Scott-Hinsley method, which combines the Nesterov accelerated gradient optimization algorithm with the correction method of the Scott-Hinsley method, and is suitable for the NAGCSH algorithm for mine ventilation network solution. It flexibly adjusts the step size of the gradient update, thereby converging to the optimal solution at a faster speed and reducing oscillation. Summary of the Invention

[0004] The mine ventilation network solution method provided by the present disclosure can converge to obtain the optimal solution at a faster speed and can reduce oscillation.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for solving a mine ventilation network is provided, the method comprising:

[0006] Obtaining a ventilation network diagram of a target mine, and determining residual tree branches, tree branches, and nodes of the ventilation network based on the ventilation network diagram;

[0007] Formulate the theoretical wind volume values ​​of the remaining tree branches and calculate the theoretical wind volume values ​​of the tree branches, and use the theoretical wind volume values ​​of the remaining tree branches and the theoretical wind volume values ​​of the tree branches as the initial solutions of the wind pressure balance equation;

[0008] Correcting the search direction and determining an approximate solution of the actual wind volume of the remaining tree branch and the tree branch;

[0009] Calculate the actual wind volume and pressure values ​​of the remaining tree branches and the tree branches, and calculate the actual operating parameters of the fan.

[0010] In one embodiment, determining the remaining tree branches, tree branches, and nodes of the ventilation network according to the ventilation network graph includes:

[0011] Obtaining grid structure and network data, including the number of branches N, the number of nodes J, the number of fixed air volume branches NK, the number of fans F, the wind resistance value R of each branch, the air volume value Q of the fixed air volume branch, and the coordinate values ​​of the high-efficiency region fitting point of the fan pressure-energy characteristic curve;

[0012] The remaining tree branches, tree branches and nodes are determined according to the grid structure and network data, and the remaining tree branches, tree branches and nodes are numbered.

[0013] In one embodiment, the formulating the theoretical air volume value of the remaining tree branches and calculating the theoretical air volume value of the tree branches includes:

[0014] Determine the number of the remaining tree branches, the number of the tree branches and the number of the nodes respectively according to the numbers of the remaining tree branches, the tree branches and the nodes;

[0015] Assigning initial values ​​to the remaining tree branches according to the number of the remaining tree branches to obtain theoretical wind volume values ​​of the remaining tree branches;

[0016] Calculating theoretical wind pressure values ​​of the tree branches according to a wind pressure balance equation and the number of tree branches;

[0017] The theoretical wind volume value of the tree branch is calculated according to the theoretical wind pressure value of the tree branch.

[0018] In one embodiment, the correcting the search direction and determining the approximate solution of the actual wind volume of the residual tree branch and the tree branch includes:

[0019] Determine the total wind pressure f that can make M branches i q tends to 0 infinitely i , i=1,2,…,M:

[0020]

[0021] Among them, A i is the unbalance error factor, which is a positive number;

[0022] Calculate the number of branches H with adjustable air volume using the following formula:

[0023] H = ML;

[0024] Among them, M is the number of branches of the remaining tree, and L is the number of branches with fixed air volume;

[0025] Calculate the gradient of the node number J:

[0026]

[0027]

[0028] Among them, q f is the fan air volume;

[0029] Update search direction v i :

[0030] v i =γν i-1 +μg(qθ-γν i-1 );

[0031] Among them, the hyperparameter γ is the update of the search direction v i The decay weight, μ is the learning efficiency; update solution:

[0032] q θ ( k )=q θ ( k-1 )-υ i ;

[0033] Among them, q θ ( k ) is the kth iteration calculation q v ;

[0034] Set the convergence threshold ε and set the iteration error to e,

[0035]

[0036] When e≤ε, the convergence condition is met.

[0037] In one embodiment, the calculating of the wind pressure values ​​of the remaining branches and each branch and the actual operating parameters of the wind turbine includes:

[0038] Calculate the wind pressure value of the remaining tree branches and the wind pressure value of each tree branch according to the resistance law;

[0039] The actual operating parameters of the fan are calculated based on the quadratic polynomial and the actual air volume of the fan.

[0040] According to a second aspect of an embodiment of the present disclosure, a mine ventilation network solution device is provided, the device comprising:

[0041] An acquisition module, which acquires a ventilation network diagram of a target mine and determines residual tree branches, tree branches, and nodes of the ventilation network according to the ventilation network diagram;

[0042] A drafting module drafts the theoretical wind volume values ​​of the remaining tree branches and calculates the theoretical wind volume values ​​of the tree branches, and uses the theoretical wind volume values ​​of the remaining tree branches and the theoretical wind volume values ​​of the tree branches as the initial solutions of the wind pressure balance equation;

[0043] A determination module is used to correct the search direction and determine an approximate solution of the actual wind volume of the remaining tree branch and the tree branch;

[0044] The calculation module calculates the actual wind volume and wind pressure values ​​of the remaining tree branches and the tree branches, and calculates the actual operating parameters of the fan.

[0045] In one embodiment, the acquisition module includes:

[0046] An acquisition submodule acquires the grid structure and network data, including the number of branches N, the number of nodes J, the number of fixed air volume branches NK, the number of fans F, the wind resistance value R of each branch, the air volume value Q of the fixed air volume branch, and the coordinate values ​​of the high-efficiency zone fitting point of the fan pressure-energy characteristic curve;

[0047] The processing submodule determines the residual tree branches, tree branches and nodes according to the grid structure and network data, and numbers the residual tree branches, tree branches and nodes.

[0048] In one embodiment, the drafting module further includes:

[0049] A determination submodule is configured to determine the number of the remaining tree branches, the number of the tree branches, and the number of the nodes according to the numbers of the remaining tree branches, the tree branches, and the nodes;

[0050] an assignment submodule, assigning initial values ​​to the remaining tree branches according to the number of the remaining tree branches, and obtaining theoretical air volume values ​​of the remaining tree branches;

[0051] A first calculation submodule calculates a theoretical wind pressure value of the tree branch according to a wind pressure balance equation and the number of tree branches;

[0052] The second calculation submodule calculates the theoretical air volume value of the tree branch according to the theoretical wind pressure value of the tree branch.

[0053] According to a third aspect of an embodiment of the present application, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0054] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0055] The mine ventilation network solution method provided by the present invention can not only solve the wind network without air volume branches, but also solve the wind network with fixed air volume branches. Compared with the existing wind network solution method that only uses the Scott-Hinsley method, the iteration time of the mine ventilation network solution method provided by the present invention is reduced by 33.09%. Therefore, it can be concluded that the mine ventilation network solution method provided by the present invention can accelerate the convergence speed, thereby greatly improving the wind network solution speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flow chart of a mine ventilation network solution method provided for the implementation of the present disclosure.

[0057] Figure 2 A flow chart of a mine ventilation network solution method provided for the implementation of the present disclosure.

[0058] Figure 3 An example diagram of a mine ventilation network provided in this disclosure.

[0059] Figure 4 An architectural diagram of a mine ventilation network solution device provided for the implementation of the present disclosure.

[0060] Figure 5 An architectural diagram of a mine ventilation network solution device provided for the implementation of the present disclosure.

[0061] Figure 6 An architectural diagram of a mine ventilation network solution device provided for the implementation of the present disclosure.

[0062] Figure 7 A schematic diagram of the computer device structure provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0063] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0064] Figure 1 This is a flow chart of a mine ventilation network solution method provided by an embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0065] Step 101: Obtain a ventilation network diagram of a target mine, and determine residual tree branches, tree branches, and nodes of the ventilation network according to the ventilation network diagram;

[0066] In one embodiment, determining the remaining tree branches, tree branches, and nodes of the ventilation network according to the ventilation network graph includes:

[0067] Obtaining grid structure and network data, including the number of branches N, the number of nodes J, the number of fixed air volume branches NK, the number of fans F, the wind resistance value R of each branch, the air volume value Q of the fixed air volume branch, and the coordinate values ​​of the high-efficiency region fitting point of the fan pressure-energy characteristic curve;

[0068] The remaining tree branches, tree branches and nodes are determined according to the grid structure and network data, and the remaining tree branches, tree branches and nodes are numbered.

[0069] In this embodiment, after obtaining the mine ventilation network diagram, it is necessary to calibrate the airflow direction and uniformly number all branches and nodes; obtain the network structure and network data, mainly including the number of branches N, the number of nodes J, the number of fixed air volume branches NK, the number of fans F, the wind resistance value R of each branch, the air volume value Q of the fixed air volume branch, the coordinate value of the high-efficiency zone fitting point of the fan pressure-energy characteristic curve (air volume FQ, pressure energy FH) and other basic data.

[0070] The number of residual tree loops M of the ventilation network is calculated based on the number of branches N and the number of nodes J:

[0071] M = N - J + 1;

[0072] According to the air volume balance law, the algebraic sum of the air volume flowing into and out of a node is 0, so:

[0073]

[0074] Among them, a ij Indicates the inflow and outflow direction of the air volume with node number i and branch number j. If it is inflow, it is recorded as 1, and if it is outflow, it is recorded as -1. Q j Indicates the air volume value of the j-th branch. If a ij =0 means branch j is not under node i;

[0075] According to the resistance law: any branch or network loop in the ventilation network follows:

[0076] h i =R i Q i 2 ;

[0077] Among them, h i is the branch pressure energy, R i is the wind resistance of the branch, Q i is the branch air volume.

[0078] According to the wind pressure balance law: the algebraic sum of the pressure energy of each branch in the ventilation network loop is zero or the algebraic sum of the natural pressure energy and the fan pressure energy in the network ventilation network loop is zero, and combined with the resistance law and the number of residual tree loops, M wind pressure balance equations are listed:

[0079]

[0080] Among them, R ij ,q ij are the wind resistance and air volume of the jth branch contained in the i-th residual tree loop, h f 、f n They are respectively the fan pressure energy and natural wind pressure, and are 0 if there is no pressure in the circuit.

[0081] A quadratic polynomial is usually used to fit the fan pressure-energy characteristic curve. Three sets of coordinate values, F1(q1,h1), F2(q2,h2) and F3(q3,h3), are taken in the high-efficiency region of the fan pressure-energy characteristic curve to obtain the coefficients of the quadratic polynomial:

[0082] h f =c1+c2q+c3q 2 ;

[0083] c3=h3(q1-q2)+h2(q3-q1)+h1(q2-q3) / (q1-q2)(q3-q1)(q2-q3);

[0084]

[0085] c1=h2-c2q2-c3q2 2 ;

[0086] Among them, c1, c2 and c3 are the three coefficients of the quadratic polynomial of the fan pressure-energy characteristic curve, q is the fan air volume, h f is the fan pressure energy.

[0087] Step 102: Draft theoretical wind volume values ​​of the remaining tree branches and calculate the theoretical wind volume values ​​of the tree branches, and use the theoretical wind volume values ​​of the remaining tree branches and the theoretical wind volume values ​​of the tree branches as the initial solutions of the wind pressure balance equation;

[0088] In one embodiment, the formulating the theoretical air volume value of the remaining tree branches and calculating the theoretical air volume value of the tree branches includes:

[0089] Determine the number of the remaining tree branches, the number of the tree branches and the number of the nodes respectively according to the numbers of the remaining tree branches, the tree branches and the nodes;

[0090] Assigning initial values ​​to the remaining tree branches according to the number of the remaining tree branches to obtain theoretical wind volume values ​​of the remaining tree branches;

[0091] Calculating theoretical wind pressure values ​​of the tree branches according to a wind pressure balance equation and the number of tree branches;

[0092] The theoretical wind volume value of the tree branch is calculated according to the theoretical wind pressure value of the tree branch.

[0093] In this step, the Scott-Hinsley method within the NAGCSH algorithm is used to determine the remaining branch airflow and calculate the airflow for each branch. First, the remaining branches in the ventilation network are identified using the edge addition method. Then, initial airflow is determined. Typically, a set of initial values ​​is assigned to the remaining branches, and the initial airflow for each branch is calculated. Specifically, the initial value for a fixed airflow branch is the fixed value, while the initial value for a fan branch is the airflow at the second point on the fan's pressure-energy characteristic curve. The assigned initial values ​​and the calculated initial airflow are used as the initial solution to the pressure balance equation.

[0094] Step 103: Correct the search direction and determine the approximate solution of the actual wind volume of the remaining tree branch and the tree branch;

[0095] In this step, the search direction is corrected and the solution is updated using the NAG algorithm within the NAGCSH algorithm. NAG improves upon the momentum term, which in turn improves upon the stochastic gradient descent (SGD) algorithm. The momentum term ensures that the direction of each solution update depends not only on the gradient of the current position but also on the direction of the solution update in the previous iteration, undoubtedly accelerating convergence. The NAG algorithm, on the other hand, approximates the properties of second-order derivatives using the difference form of first-order derivatives. This approximation of the target function information, like the second-order derivative, significantly improves convergence, achieving better results than the momentum term.

[0096] Specifically, choose a suitable q i (i=1,2,…,M) so that the total wind pressure f of M independent circuits i Infinitely tends to 0:

[0097]

[0098] Where A i is the unbalanced error factor, which is a positive number and functions to share the error and avoid the error of the independent branch loop being too large and unable to converge quickly. i When it is 1, it means that all circuits are required to share the unbalanced error; when A i When some values ​​in are large positive numbers, it means that only some loops do not share the unbalanced error.

[0099] In any ventilation network, it can be determined that the fixed air volume branch must exist in the residual tree branch. Assuming that its number is L, then in the M residual tree branches, they are named qM ,q M-1 …q M-L+1 , so the number of adjustable branches is H = ML, which are named q H ,q H-1 …q1, thereby determining the wind volume of the M remaining tree branches.

[0100] Calculate the gradient g(θ) at point J:

[0101]

[0102]

[0103] Among them, q f is the fan air volume;

[0104] Then update the search direction v i :

[0105] v i =γν i-1 +μg(qθ-γν i-1 );

[0106] In the formula, the hyperparameter γ represents the update of the search direction v in the last update i The decay weight is generally between 0 and 1, and is set to about 0.9 here. μ represents the learning rate. The smaller the learning rate, the less information is obtained from the last iteration to update the gradient.

[0107] Update solution:

[0108] q θ ( k )=q θ ( k-1 )-υ i

[0109] Where q θ ( k ) is the kth iteration to calculate q v ;

[0110] ε, and set the iteration error to e,

[0111] When the iteration error The convergence condition is reached when .

[0112] Step 104: Calculate the actual wind volume and wind pressure values ​​of the remaining tree branches and the tree branches, and calculate the actual operating parameters of the fan.

[0113] In one embodiment, the calculating of the wind pressure values ​​of the remaining branches and each branch and the actual operating parameters of the wind turbine includes:

[0114] Calculate the wind pressure value of the remaining tree branches and the wind pressure value of each tree branch according to the resistance law;

[0115] The actual operating parameters of the fan are calculated based on the quadratic polynomial and the actual air volume of the fan.

[0116] In this embodiment, the wind pressure value of each branch is calculated by the resistance law, and the actual operating parameters of the fan are calculated based on the calculated quadratic polynomial and the actual air volume of the fan.

[0117] The mine ventilation network solution method provided by the present disclosure will be described in detail below with specific examples.

[0118] Figure 2 This is a flow chart for solving the mine ventilation network provided by the present disclosure. Figure 2 As shown, the mine ventilation network solution method provided by the present disclosure includes the following steps:

[0119] Step S1: Obtain a mine ventilation network diagram, and obtain the network structure and data;

[0120] Step S2: Draft independent branch air volume and calculate the air volume of each tree branch, and use the air volume values ​​of all branches obtained this time as the initial solution;

[0121] Step S3: Correct the search direction and update the solution until an approximate solution for the actual air volume of each branch is determined;

[0122] Step S4: Calculate the wind pressure value of each branch and the actual operating parameters of the fan.

[0123] Figure 3 This is an example diagram of a mine ventilation network provided by the present disclosure. Figure 3 As shown, the number of branches N is 9, namely b1, b2, b3, b4, b5, b6, b7, b8, b9, and the number of nodes J is 6, namely n1, n2, n3, n4, n5, n6. The total required air volume of the wind network is 20m 3 / s, wind resistance of each branch R i They are 1.42, 1.368, 4.025, 1.168, 0.769, 0.89, 8.73, 0.59, and 2.98 (N·s 2 / m 8 ), where a fan is installed on branch b9, the convergence threshold ε=0.001, and the unbalance error A of all loops i Both are 1.

[0124] The number of independent circuits in the ventilation network is not calculated, M = H-J + 1 = 4, according to Figure 3 It can be seen that the independent loop L is selected l1:b1, b6, b4, b2, the independent branch is b1; select independent loop L l2 :b4, b5, b3, the independent branch is b3; select independent loop L l3 :b6, b5, b8, b7, the independent branch is b8; select independent loop L l4 : b9, b1, b7, the independent branch is b9.

[0125] The following two assumptions are made based on whether there is a fixed air volume branch:

[0126] (1) Assuming that there is no fixed air volume branch in the wind network, the number of independent loops with adjustable air volume is 4. The disclosed algorithm is applied to solve the wind network. After 67 iterations, the conditions are met and the iteration is terminated.

[0127] The iteration error at this time is e=1.8957E-5, and the air volume verification errors of independent branches b1, b3, b8, and b9 are: 5.8945E-9, 1.5641E-8, 7.3125E-9, 1.0352E-8, respectively, and their wind pressure verification errors are: -7.5623E-7, -9.8523E-7, -6.5289E-7, -8.0138E-7, respectively.

[0128] The air volumes of each branch are 9.9917, 10.2056, 5.1521, 8.8129, 9.9005, 4.9053, 5.2319, 14.0125, and 20.0094 respectively.

[0129] (2) Assume that there is a fixed air volume branch in the air network, namely b9. According to the characteristics of the fixed air volume branch, its air volume value is 20.01m 3 / s, therefore, the independent circuit with only adjustable branches in the wind network is L l1 , L l2 , L l3 , the disclosed algorithm is applied to solve the wind network. After 93 iterations, the conditions are met and the iteration is terminated.

[0130] The iteration error at this time is e=2.8848E-5, and the air volume verification errors of independent branches b1, b3, and b8 are: 9.6851E-9, 2.0109E-10, 7.2103E-9, respectively, and their wind pressure verification errors are: -1.2561E-4, 0.8922E-4, 1.0891E-4, respectively.

[0131] The air volumes of each branch are 9.9921, 10.2055, 5.1524, 8.8131, 9.9003, 4.9055, 5.2320, 14.0122, and 20.001 respectively.

[0132] (3) In assumption (2), only the Scott-Hinsley method is used to solve the wind network. After 139 iterations, the conditions are met and the iteration is terminated.

[0133] The iteration error at this time is e=9.2563E-4, and the air volume verification errors of independent branches b1, b3, and b8 are: 1.0451E-5, 3.0859E-5, 9.8526E-6, respectively, and their wind pressure verification errors are: 0.8895E-2, 1.0582E-2, 1.1034E-2, respectively.

[0134] The air volumes of each branch are 9.9923, 10.2058, 5.1520, 8.8125, 9.9010, 4.9057, 5.2322, 14.0121, and 20.001 respectively.

[0135] Judging from the above wind network solution results, the wind network solution method based on the improved Scott-Hinsley method provided by the present disclosure can not only solve the wind network without air volume branches, but also solve the wind network with fixed air volume branches. Compared with the wind network solution method using only the Scott-Hinsley method, the iteration time is reduced by 33.09%, which proves that the wind network solution method based on the improved Scott-Hinsley method provided by the present disclosure can accelerate convergence, thereby greatly improving the wind network solution speed.

[0136] Figure 4 This is a diagram of the architecture of a mine ventilation network solution device provided by an embodiment of the present disclosure. Figure 4 As shown, the device includes: an acquisition module 401, a formulation module 402, a determination module 403 and a calculation module 404; wherein, the acquisition module 401 is used to obtain the ventilation network diagram of the target mine, and determine the residual tree branches, tree branches and nodes of the ventilation network according to the ventilation network diagram; the formulation module 402 is used to formulate the theoretical air volume values ​​of the residual tree branches and calculate the theoretical air volume values ​​of the tree branches, and use the theoretical air volume values ​​of the residual tree branches and the theoretical air volume values ​​of the tree branches as the initial solutions of the wind pressure balance equation; the determination module 403 is used to correct the search direction and determine the approximate solutions of the actual air volume of the residual tree branches and the tree branches; the calculation module 404 is used to calculate the actual air volume and wind pressure values ​​of the residual tree branches and the tree branches, and calculate the actual operating parameters of the fan.

[0137] Figure 5 This is a diagram of the architecture of a mine ventilation network solution device provided by an embodiment of the present disclosure. Figure 5As shown, the device includes an acquisition module 501, a planning module 502, a determination module 503 and a calculation module 504; wherein, the acquisition module 501 includes an acquisition submodule 5011 and a processing submodule 5012; wherein, the acquisition submodule 5011 is used to obtain grid structure and network data, and the network data includes the number of branches N, the number of nodes J, the number of fixed air volume branches NK, the number of fans F, the wind resistance value R of each branch, the air volume value Q of the fixed air volume branch, and the coordinate value of the high-efficiency zone fitting point of the fan pressure-energy characteristic curve; the processing submodule 5012 is used to determine the residual tree branches, tree branches and nodes according to the grid structure and network data, and number the residual tree branches, tree branches and nodes.

[0138] Figure 6 This is a diagram of the architecture of a mine ventilation network solution device provided by an embodiment of the present disclosure. Figure 6 As shown, the device includes an acquisition module 601, a formulation module 602, a determination module 603 and a calculation module 604; wherein, the determination module 603 includes a determination submodule 6031, an assignment submodule 6032, a first calculation submodule 6033 and a second calculation submodule 6034; wherein, the determination submodule 6031 is used to determine the number of residual tree branches, the number of tree branches and the number of nodes according to the numbers of the residual tree branches, tree branches and nodes respectively; the assignment submodule 6032 is used to assign initial values ​​to the residual tree branches according to the number of residual tree branches, and obtain the theoretical wind volume value of the residual tree branches; the first calculation submodule 6033 is used to calculate the theoretical wind pressure value of the tree branch according to the wind pressure balance equation and the number of tree branches; the second calculation submodule 6034 is used to calculate the theoretical wind volume value of the tree branch according to the theoretical wind pressure value of the tree branch.

[0139] The present disclosure also provides a computer device, the internal structure diagram of which can be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a mine ventilation network solution method as described above. It includes: a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it realizes any step in the mine ventilation network solution method as described above.

[0140] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, any step in the above-mentioned mine ventilation network solution can be implemented.

[0141] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be pre-stored in a computer-readable storage medium. When executed, the program performs the steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0142] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0143] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A mine ventilation network solution method, characterized in that: The method comprises: Obtaining a ventilation network diagram of a target mine, and determining residual tree branches, tree branches, and nodes of the ventilation network based on the ventilation network diagram; Formulate the theoretical wind volume values ​​of the remaining tree branches and calculate the theoretical wind volume values ​​of the tree branches, and use the theoretical wind volume values ​​of the remaining tree branches and the theoretical wind volume values ​​of the tree branches as the initial solutions of the wind pressure balance equation; Correcting the search direction and determining an approximate solution of the actual wind volume of the remaining tree branch and the tree branch; Calculate the actual wind volume and pressure values ​​of the remaining tree branches and the tree branches, and calculate the actual operating parameters of the fan; Determining the remaining tree branches, tree branches, and nodes of the ventilation network according to the ventilation network diagram includes: Obtaining grid structure and network data, including branch number , number of nodes , Number of fixed air volume branches , Number of fans , wind resistance value of each branch , Fixed air volume branch air volume value , the coordinate value of the fitting point of the high efficiency area of ​​the fan pressure-energy characteristic curve; Determine the remaining tree branches, tree branches and nodes according to the grid structure and network data, and number the remaining tree branches, tree branches and nodes; The step of formulating the theoretical air volume values ​​of the remaining tree branches and calculating the theoretical air volume values ​​of the tree branches includes: Determine the number of remaining tree branches, the number of tree branches and the number of nodes respectively according to the numbers of the remaining tree branches, the tree branches and the nodes; Assigning initial values ​​to the remaining tree branches according to the number of the remaining tree branches to obtain theoretical wind volume values ​​of the remaining tree branches; Calculating theoretical wind pressure values ​​of the tree branches according to a wind pressure balance equation and the number of tree branches; Calculating the theoretical air volume value of the tree branch according to the theoretical wind pressure value of the tree branch; The correcting the search direction and determining the approximate solution of the actual wind volume of the remaining tree branch and the tree branch includes: Make sure to make Total wind pressure on Yushu branch road infinitely approaching 0 , : ; in, is the unbalance error factor, which is a positive number; is the natural wind pressure; is the fan pressure energy; Calculate the number of branches with adjustable air volume , the calculation formula is: ; in, is the number of branches in the remaining tree, The number of branches for a fixed air volume; Number of computing nodes Gradient: , ; ; in, For fan air volume; update search direction : ; Among them, the hyperparameters Search direction for last update The decay weight, For learning efficiency; Update solution: ; in, For the Iteration calculation ; Set the convergence threshold , and set the iteration error to , ,exist When , the convergence condition is reached.

2. The method according to claim 1, characterized in that The calculation of the wind pressure values ​​of the remaining branches and each branch and the actual operating parameters of the fan includes: Calculate the wind pressure value of the remaining tree branches and the wind pressure value of each tree branch according to the resistance law; The actual operating parameters of the fan are calculated based on the quadratic polynomial and the actual air volume of the fan.

3. A mine ventilation network solution device, characterized in that: The device comprises: An acquisition module, which acquires a ventilation network diagram of a target mine and determines residual tree branches, tree branches, and nodes of the ventilation network according to the ventilation network diagram; A drafting module drafts the theoretical wind volume values ​​of the remaining tree branches and calculates the theoretical wind volume values ​​of the tree branches, and uses the theoretical wind volume values ​​of the remaining tree branches and the theoretical wind volume values ​​of the tree branches as the initial solutions of the wind pressure balance equation; A determination module is used to correct the search direction and determine an approximate solution of the actual wind volume of the remaining tree branch and the tree branch; A calculation module calculates the actual air volume and pressure values ​​of the remaining tree branches and the tree branches, and calculates the actual operating parameters of the fan; The acquisition module includes: Obtain submodule, obtain grid structure and network data, the network data includes the number of branches , number of nodes , Number of fixed air volume branches , Number of fans , wind resistance value of each branch , Fixed air volume branch air volume value , the coordinate value of the fitting point of the high efficiency area of ​​the fan pressure-energy characteristic curve; A processing submodule, which determines the remaining tree branches, tree branches and nodes according to the grid structure and network data, and numbers the remaining tree branches, tree branches and nodes; The proposed module also includes: Determine a submodule to determine the number of remaining tree branches, the number of tree branches and the number of nodes respectively according to the numbers of the remaining tree branches, the tree branches and the nodes; an assignment submodule, assigning initial values ​​to the remaining tree branches according to the number of the remaining tree branches, and obtaining theoretical air volume values ​​of the remaining tree branches; A first calculation submodule calculates a theoretical wind pressure value of the tree branch according to a wind pressure balance equation and the number of tree branches; A second calculation submodule calculates a theoretical air volume value of the tree branch according to the theoretical wind pressure value of the tree branch; The correcting the search direction and determining the approximate solution of the actual wind volume of the remaining tree branch and the tree branch includes: Make sure to make Total wind pressure on Yushu branch road infinitely approaching 0 , : ; in, is the unbalance error factor, which is a positive number; natural wind pressure; Calculate the number of branches with adjustable air volume , the calculation formula is: ; in, is the number of branches in the remaining tree, The number of branches for a fixed air volume; Number of computing nodes Gradient: , ; ; in, For fan air volume; update search direction : ; Among them, the hyperparameters Search direction for last update The decay weight, For learning efficiency; Update solution: ; in, For the Iteration calculation ; Set the convergence threshold , and set the iteration error to , , exist When , the convergence condition is reached.

4. A computer device comprising: The method comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor implements the steps of the method according to any one of claims 1 to 2 when executing the computer program.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images