Surface mine transportation scheduling method and device

Abstract

The invention provides a surface mine transportation scheduling method and device, and relates to the technical field of transportation scheduling, and the method can obtain engineering data of a target mining area, and employs a global search algorithm based on a gradient optimizer according to the engineering data and a target function constructed with the lowest total transportation cost as a target. And carrying out iterative optimization on the number of transportation times of each transportation route in the target mining area to obtain a target number of transportation times scheme, and further determining a vehicle scheduling scheme of the target mining area. Therefore, when the vehicle scheduling scheme of the target mining area is determined, a global search algorithm based on a gradient optimizer is adopted, and the problems of low operation efficiency and easy premature convergence of a particle swarm type method for a multi-dimensional optimization problem can be avoided through a gradient search rule and a local escape operator; the early-stage exploration capability and the later-stage development capability can be better balanced, and the optimal scheduling scheme can be quickly and accurately obtained.

Description

Technical Field

[0001] The invention relates to the technical field of transportation scheduling, and in particular to a method and device for transport scheduling in an open-pit mine. Background Art

[0002] Open-pit mining is favored for its large scale of mines, short infrastructure construction period, high degree of mechanization, high production efficiency and good production conditions. In the development of mineral resources, open-pit mining methods are usually preferred as long as the occurrence conditions of the ore deposit are suitable. Traditional open-pit mining operations usually involve blasting the ore rock, loading the ore with shovel-loading equipment such as electric shovels or single-bucket excavators, and then transporting it to the designated location by dump trucks or rail transport vehicles. In recent years, with the continuous advancement of open-pit mining technology, larger and larger mining equipment has significantly improved the production capacity of mines. Practice has shown that the use of large-scale equipment can achieve efficient and large-scale production in mines and bring considerable economic returns to enterprises. However, with the continuous rise in prices, the cost of mining has also increased. In order to reduce the production cost of mining and improve economic benefits, it is crucial to further optimize the multi-objective open-pit mine transportation scheduling system.

[0003] At present, most transportation scheduling system optimizations use hybrid intelligent optimization algorithms. However, because the algorithm process is too complicated and difficult to solve, the actual situation is often contrary to expectations, and problems such as the algorithm operating speed is too slow, premature (i.e., converges too early) or non-convergence occur, which restricts the efficient operation of the transportation scheduling system. Summary of the invention

[0004] The purpose of the present invention is to provide an open-pit mine transportation scheduling method and device to avoid the problems of low computational efficiency and easy premature convergence of particle swarm type methods for multi-dimensional optimization problems, so as to better balance the early exploration capabilities and later development capabilities, and quickly and accurately obtain the optimal scheduling plan.

[0005] In a first aspect, the present invention provides an open-pit mine transportation scheduling method, comprising: Obtain engineering data of the target mining area, including shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; According to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain the target transportation times plan; the global search algorithm based on the gradient optimizer updates the particle position through the gradient search rule and the local escape operator, and the position of each particle is a candidate transportation times plan; the path between a shovel point and a discharge point corresponds to a transportation route; Determine the vehicle dispatching plan for the target mining area based on the target transportation frequency plan, transportation distance information and transportation equipment information.

[0006] Furthermore, according to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain the target transportation times plan, including: Determine the dimension of the number of transport times according to the total number of shoveling points in the shoveling point information and the total number of unloading points in the unloading point information; According to the dimension of transportation times and engineering data, the objective function is constructed with the goal of minimizing the total transportation cost; Generate an initial population based on the transport frequency dimension, the preset transport frequency search range and the population size, and determine the optimal position and the worst position of the initial population based on the objective function; A global search algorithm based on a gradient optimizer is used to iteratively update the particle positions of the initial population to obtain the target population when the iteration is stopped; The optimal position of the target population is determined as the target transportation frequency plan.

[0007] Furthermore, the dimension of transport times is ( h + n )× l , the dimension of the particle is 1×( h + n ) l , h Indicates the total number of unloading points, n Indicates the total number of unloading points, l Indicates the total number of shovel points; The objective functions include: ; The constraints of the objective function include: ; ; ; ; in, g (X) represents the total transportation cost corresponding to the particle position X, T Indicates the full load of the transport equipment. m ij Indicates shovel point i To the unloading point j The single full load transportation cost, m ji Indicates unloading point j To the shovel point i Single empty-load transportation cost,x ij Indicates shovel point i To the unloading point j The number of transports, s ij Indicates shovel point i To the unloading point j The distance m ik Indicates shovel point i To the unloading point k The single full load transportation cost, m ki Indicates the unloading point k To the shovel point i Single empty-load transportation cost, x ik Indicates shovel point i To the unloading point k The number of transports, s ik Indicates shovel point i To the unloading point k The distance Q i Indicates shovel point i The amount of ore produced, P i Indicates shovel point i The amount of rock produced, U j Indicates unloading point j The output, U k Indicates the unloading point k The output, r l Indicates the lower limit of the grade required at the unloading point. r n Indicates the upper limit of the grade required at the unloading point. r i Indicates shovel point i The average grade of the ore, t 1 means loading time, t 2 indicates the unloading time, t 3 represents the working time of a shift.

[0008] Furthermore, a global search algorithm based on a gradient optimizer is used to iteratively update the particle positions of the initial population to obtain the target population when the iteration is stopped, including: When updating the position of the current particle, the initial update position of the current particle is generated through the gradient search rule; Generates the target update position of the current particle based on the initial update position and the local escape operator.

[0009] Furthermore, the initial update position of the current particle is generated by the gradient search rule, including: The first and second positions of the current particle are calculated using the following formula: ; ; ; ; ; ; ; ; ; According to the first position and the second position, the third position of the current particle is calculated by the following formula: ; According to the first position, the second position and the third position, the initial update position of the current particle is calculated by the following formula: ; in, express O The first particle o indivual, e represents the number of iterations, E represents the total number of iterations, Indicates o Particle No. e The first position at the iteration, Indicates o Particle No. e The second position at the iteration, Indicates o Particle No. e The position at the iteration, Indicates o Particle No. e The position at +1 iteration, randn represents normally distributed random numbers, rand represents a random number between [0,1], β min and β max Represents two preset constants, represents the worst position of the current population, represents the optimal position of the current population, e Indicates a preset value greater than zero, express(t + n ) l A random number between [0,1] of dimension, t Indicates the total number of unloading points, n Indicates the total number of unloading points, l represents the total number of shovel points, t 1. t 2. t 3. t 4 means from [0, O ], four integers randomly selected from t 1. t 2. t 3. t 4. o Different from each other, t a , t b Represents two random numbers between [0,1].

[0010] Furthermore, according to the initial update position and the local escape operator, the target update position of the current particle is generated, including: The target update position of the current particle is calculated by the following formula: ; in, f 1 represents a random number between [-1,1], f 2 represents a normally distributed random number, u 1.u2. u 3 represents three random numbers, represents a new random solution, u 1.u2. u 3. is defined as follows: ; ; ; ; ; in, m 1. m 2 represents two random numbers between [0,1], represents the first randomly selected u The position of a particle, , and They respectively represent the maximum and minimum boundaries of the current solution space search corresponding to the search range of the number of transportations.

[0011] Furthermore, according to the target transportation frequency plan, transportation distance information and transportation equipment information, a vehicle dispatching plan for the target mining area is determined, including: According to the transportation distance information and transportation equipment information, the transportation time of each transportation route is calculated; According to the transportation time of each transportation route, calculate the number of times a transportation equipment can be transported on each transportation route; According to the number of times a transport equipment can be transported on each transport route and the target transport frequency plan, the number of transport equipment on each transport route is calculated to obtain the vehicle scheduling plan for the target mining area.

[0012] In a second aspect, the present invention further provides an open-pit mine transportation scheduling device, comprising: An acquisition module is used to acquire engineering data of a target mining area, the engineering data including shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; The optimization module is used to iteratively optimize the transportation times of each transportation route in the target mining area according to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, and obtain the target transportation times plan by using the global search algorithm based on the gradient optimizer; the global search algorithm based on the gradient optimizer updates the particle position through the gradient search rule and the local escape operator, and the position of each particle is a candidate transportation times plan; the path between a shovel point and a discharge point corresponds to a transportation route; The determination module is used to determine the vehicle dispatching plan of the target mining area according to the target transportation frequency plan, transportation distance information and transportation equipment information.

[0013] In a third aspect, the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the open-pit mine transportation scheduling method of the first aspect is implemented.

[0014] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the open-pit mine transportation scheduling method of the first aspect is executed.

[0015] The open-pit mine transportation scheduling method and device provided by the embodiment of the present invention can obtain the engineering data of the target mining area, and the engineering data includes shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; according to the engineering data and the objective function constructed with the minimum total transportation cost as the goal, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain a target transportation time plan; wherein the global search algorithm based on the gradient optimizer updates the particle position through the gradient search rule and the local escape operator, and the position of each particle is a candidate transportation time plan; the path from a shovel point to a unloading point corresponds to a transportation route; according to the target transportation time plan, the transportation distance information and the transportation equipment information, the vehicle scheduling plan of the target mining area is determined. In this way, when determining the vehicle scheduling plan for the target mining area, a global search algorithm based on a gradient optimizer is adopted, wherein the gradient search rule utilizes a gradient-based strategy to improve the exploration capability, thereby accelerating the convergence speed and finding a better position in the search space, and the local escape operator can get rid of the local optimal solution and improve its global search capability. Therefore, the embodiment of the present invention can avoid the problems of low computational efficiency and easy premature convergence of the particle swarm type method for multi-dimensional optimization problems, and can better balance the early exploration capability and the later development capability, and quickly and accurately obtain the optimal scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a flow chart of an open-pit mine transportation scheduling method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of another open-pit mine transportation scheduling method provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an open-pit mine transportation scheduling device provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] An open-pit mine is a large-scale production system with mining as the core and transportation as the connection. All production tasks are achieved through mining and loading equipment and transportation equipment, and real-time scheduling of transportation equipment is particularly required. The optimization method is required to quickly and accurately obtain the optimal scheduling plan.

[0020] Gradient-Based Optimizers (GBO) is a new type of heuristic optimization algorithm proposed by Ahmadianfar and Bozorg-Haddad in 2020. The algorithm uses gradient search rules (GSR) to enhance exploration capabilities and accelerate convergence, so as to find a better position in the search space. In addition, the Local Escape Operator (LEO) enables the algorithm to get rid of the local optimal solution and improve its global search capability. GBO combines the advantages of intelligent optimization algorithms and gradient methods, and has the characteristics of adaptive parameter adjustment, which enables it to achieve a good balance between early exploration of the global optimum and later accelerated convergence. It is simple to implement, has high computational efficiency, and requires few parameters. These characteristics make GBO particularly suitable for the optimization problem of open-pit mine transportation scheduling system. Based on this, an open-pit mine transportation scheduling method and device provided by an embodiment of the present invention adopts a new method for estimating the optimal transportation train number in the transportation scheduling system, that is, using a global search algorithm based on a gradient optimizer instead of the traditional particle swarm algorithm to optimally estimate the transportation train number, which can effectively avoid the low computational efficiency and easy premature convergence of particle swarm type methods for multi-dimensional optimization problems, and can better balance the early exploration and later development capabilities of the algorithm, and obtain the optimal transportation train number estimation value faster and more accurately. Among them, the train number is also called the transportation number, which refers to the number of times or trips that the transportation equipment performs the transportation task; each time a complete transportation cycle is completed from the shovel point to the unloading point (that is, one round trip between the shovel point and the unloading point), it is counted as one train number.

[0021] To facilitate understanding of this embodiment, an open-pit mine transportation scheduling method disclosed in an embodiment of the present invention is first introduced in detail.

[0022] The embodiment of the present invention provides a method for transport scheduling in an open-pit mine, which can be executed by an electronic device with data processing capability. Figure 1The flowchart of a method for transport scheduling in an open-pit mine is shown in FIG. 1 , and the method mainly includes the following steps S110 to S130: Step S110, obtaining engineering data of the target mining area, the engineering data including shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information.

[0023] The target mining area may be a mining area to be mined in an open-pit mine. The shovel point refers to the location where materials such as ore or rock are loaded, and the unloading point refers to the location where the transport vehicle unloads the loaded materials. The unloading point may include the ore unloading point and the rock unloading point. The shovel point information may include the shovel point number, the total number of shovel points, the amount of ore produced by each shovel point, the amount of rock produced by each shovel point, and the average grade of the ore at each shovel point; the unloading point information may include the ore unloading point number, the total number of ore unloading points, the rock unloading point number, the total number of rock unloading points, and the output of each unloading point / rock unloading point; the transportation distance information may include the distance from the shovel point to the unloading point / rock unloading point; the transportation cost information may include the full-load transportation cost from a single shovel point to the unloading point / rock unloading point and the empty-load transportation cost from a single unloading point / rock unloading point to the shovel point; the transportation equipment information may include the full load of the transportation equipment, the average speed of the transportation equipment, the loading time, the unloading time, and the working time of one shift. Among them, the shift refers to the working time unit of the transportation equipment in a working shift, and the time here refers to the duration.

[0024] Step S120, based on the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain a target transportation times plan.

[0025] Among them, the global search algorithm based on the gradient optimizer updates the particle position through the gradient search rule and the local escape operator. The position of each particle is a candidate transportation frequency plan; the path from a shovel point to a unloading point corresponds to a transportation route.

[0026] The gradient optimizer-based method is inspired by the traditional gradient Newton method and uses two main operation factors: the gradient search rule (GSR) and the local escape operator (LEO). GSR uses a gradient-based strategy to improve the exploration ability, thereby accelerating convergence and finding a better position in the search space. LEO helps GBO escape from the local optimal solution. In some possible embodiments, the above step S120 may include the following steps S121 to S125: Step S121, determining the transport frequency dimension according to the total number of shoveling points in the shoveling point information and the total number of unloading points in the unloading point information.

[0027] One shovel point can transport to multiple unloading points, and the total number of shovel points is recorded as l The total number of unloading points is t +n , t Indicates the total number of unloading points, n represents the total number of unloading points, then the vehicle number dimension (i.e., the transportation number dimension) is ( t + n )× l .

[0028] Step S122, constructing an objective function based on the transportation frequency dimension and engineering data with the goal of minimizing the total transportation cost.

[0029] The optimal goal of the transportation scheduling system is to make the total transportation cost within a shift g (X) Minimum, without constraints, the above objective function can be expressed as follows: ; Since the actual production situation of mines is very complicated, it is necessary to constrain the objective function through corresponding mining conditions, output conditions, quality conditions and other factors. The constraints of the objective function can include: ; ; ; ; in, g (X) represents the total transportation cost corresponding to the particle position (i.e., transportation frequency plan) X, T Indicates the full load of the transport equipment. h Represents the total number of unloading points (i.e., the above ( t + n )× l In t ), n Indicates the total number of unloading points, l represents the total number of shovel points, m ij Indicates shovel point i To the unloading point j The single full load transportation cost, m ji Indicates unloading point j To the shovel point i Single empty-load transportation cost, x ij Indicates shovel point i To the unloading point j The number of transports, s ij Indicates shovel point i To the unloading point j The distance m ik Indicates shovel point iTo the unloading point k The single full load transportation cost, m ki Indicates the unloading point k To the shovel point i Single empty-load transportation cost, x ik Indicates shovel point i To the unloading point k The number of transports, s ik Indicates shovel point i To the unloading point k The distance Q i Indicates shovel point i The amount of ore produced, P i Indicates shovel point i The amount of rock produced, U j Indicates unloading point j The output, U k Indicates the unloading point k The output, r l Indicates the lower limit of the grade required at the unloading point. r n Indicates the upper limit of the grade required at the unloading point. r i Indicates shovel point i The average grade of the ore, t 1 indicates loading time, t 2 indicates the unloading time, t 3 represents the working time of a shift.

[0030] The above constraints can be used p (X) represents and adds the above objective function to obtain the objective function of the mine transportation scheduling system under the constraints of actual production conditions: ; In subsequent iterations, each update of the train number X must comply with the regularization p (X) constraints.

[0031] Step S123, generating an initial population according to the transport frequency dimension, the preset transport frequency search range and the population size, and determining the optimal position and the worst position of the initial population according to the objective function.

[0032] The train search range (i.e., the transport search range) can be determined according to the actual situation, for example, 0 to 100. Set the total number of population particles to O , the particle number is o , theno The position of a particle (corresponding to a transport frequency scheme) can be expressed as: ; X o Indicates o The positions of particles, where each row represents an unloading point and each column represents a shoveling point, t Indicates the total number of unloading points, n Indicates the total number of unloading points, l Represents the total number of shovel points, each element x The value range is 0-100. x ij Refers to i Shovel point to j The number of trains (i.e., the number of transports) to each unloading point, 0 is the lower limit of the number of trains, and 100 is the upper limit of the number of trains. Rewrite it into a vector form as follows: ; The dimension of the vector (i.e. the dimension of the particle) is 1×( t + n ) l .

[0033] A population consists of multiple particles. The location of each particle is a potential solution to the objective function. It is necessary to determine the number of vehicles on each transport route and substitute it into the objective function to calculate the fitness value. By constantly changing the particle position (i.e., changing the number of vehicles on each transport route), the fitness value is continuously reduced until convergence, and the optimal predicted position is obtained. The dimension of each particle is 1×( t + n ) l , can calculate the corresponding total transportation cost within a shift, that is, the fitness value.

[0034] Set an appropriate number of particles. The more particles in the population, the stronger the global search capability, but the longer the calculation time. The GBO algorithm does not need as many particles as the particle swarm algorithm, and can complete convergence with fewer particles. Optionally, a group of particles is randomly initialized in the solution space. The total number can be ten times the number of shovel points. The dimension of each particle is 1×( t + n ) l , find the optimal position X of the initial population best and the worst position X worst , the best position and the worst position are the positions of the particles with the largest and smallest fitness values ​​in the population, respectively. Set the number of iterations.

[0035] Step S124, using a global search algorithm based on a gradient optimizer, iteratively updates the particle positions of the initial population to obtain a target population when the iteration is stopped.

[0036] When updating the position of the current particle, the initial update position of the current particle can be generated through the gradient search rule; and then the target update position of the current particle is generated according to the initial update position and the local escape operator.

[0037] Optionally, the initial update position can be obtained as follows: (1) The first position and second position of the current particle are calculated by the following formula: ; ; ; ; ; ; ; ; ; (2) Based on the first position and the second position, the third position of the current particle is calculated using the following formula: : ; (3) Based on the first position, the second position, and the third position, the initial update position of the current particle is calculated using the following formula: ; in, express O The first particle o indivual, e represents the number of iterations, E represents the total number of iterations, Indicates o Particle No. e The first position at the iteration, Indicates o Particle No. e The second position at the iteration, Indicates o Particle No. e The position at the iteration, Indicates o Particle No. e The position at +1 iteration, randnrepresents normally distributed random numbers, rand represents a random number between [0,1], β min and β max Represents two preset constants, represents the worst position of the current population, represents the optimal position of the current population, e Indicates a preset value greater than zero, express( t + n ) l A random number between [0,1] of dimension, t Indicates the total number of unloading points, n Indicates the total number of unloading points, l represents the total number of shovel points, t 1. t 2. t 3. t 4 means from [0, O ], four integers randomly selected from t 1. t 2. t 3. t 4. o Different from each other, t a , t b Represents two random numbers between [0,1].

[0038] Optionally, the target update position of the current particle can be calculated using the following formula: ; in, f 1 represents a random number between [-1,1], f 2 represents a normally distributed random number, u 1.u2. u 3 represents three random numbers, represents a new random solution, u 1.u2. u 3. is defined as follows: ; ; ; ; ; in, m 1. m2 represents two random numbers between [0,1], represents the first randomly selected u The position of a particle, , and They represent the maximum and minimum boundaries of the current solution space search corresponding to the search range of the number of transports, that is, Each element in is a maximum value, such as 100. All elements in have a minimum value of 0.

[0039] The above method can be used to calculate the target update position of the current particle in the next iteration. By continuously iterating and updating the position of the particle, the fitness value will continue to decrease until the predetermined convergence accuracy or number of iterations is reached, at which point the iteration process will stop. The population at the time of stopping the iteration is the target population.

[0040] Step S125, determining the optimal position of the target population as the target transportation frequency plan.

[0041] The optimal position of particles in the target population is the optimal train distribution, which is also the target transportation frequency plan.

[0042] Step S130, determining a vehicle dispatching plan for the target mining area according to the target transportation frequency plan, transportation distance information and transportation equipment information.

[0043] In some possible embodiments, the above step S130 may include the following steps S131 to S133: Step S131, calculating the transportation time of each transportation route according to the transportation distance information and transportation equipment information.

[0044] When calculating the time required for each transport route to complete a transport, each shovel point to each unloading point corresponds to a transport route, and there is no traffic jam in the middle. The transport time required for each transport route is as follows: ; in, T ij and T ik Respectively represent the shovel point i To the unloading point j and shovel point i To the unloading point k One transportation time, s ij and s ik Respectively represent the shovel point i To the unloading point j and shovel point i To the unloading pointk The distance v Indicates the average speed of the transport equipment. t 1. t 2 represent the loading time and unloading time respectively.

[0045] Step S132, based on the transportation time of each transportation route, calculate the number of times a transportation device can transport on each transportation route.

[0046] The following formula can be used to calculate the number of times a transport device can transport on each transport route within a shift without waiting: ; in, N ij and N ik Respectively represent the mine car from the shovel point i To the unloading point k and from the shovel point i To the unloading point k The number of times that can be transported.

[0047] Step S133, according to the number of times a transport device can transport on each transport route and the target transport number plan, the number of transport devices on each transport route is calculated to obtain a vehicle scheduling plan for the target mining area.

[0048] According to the target transportation frequency plan , the number of times a single transport device can transport on each transport route N ij and N ik , calculate the final vehicle dispatching plan as follows: ; in, ceiling () represents the upward rounding function, n ij and n ik That is, the vehicle scheduling plan for each transportation route within a shift.

[0049] The open-pit mine transportation scheduling method provided by the embodiment of the present invention can obtain the engineering data of the target mining area, and the engineering data includes shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; according to the engineering data and the objective function constructed with the minimum total transportation cost as the goal, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain a target transportation time plan; wherein the global search algorithm based on the gradient optimizer updates the particle position through the gradient search rule and the local escape operator, and the position of each particle is a candidate transportation time plan; the path from a shovel point to a unloading point corresponds to a transportation route; according to the target transportation time plan, the transportation distance information and the transportation equipment information, the vehicle scheduling plan of the target mining area is determined. In this way, when determining the vehicle scheduling plan for the target mining area, a global search algorithm based on a gradient optimizer is adopted, wherein the gradient search rule utilizes a gradient-based strategy to improve the exploration capability, thereby accelerating the convergence speed and finding a better position in the search space, and the local escape operator can get rid of the local optimal solution and improve its global search capability. Therefore, the embodiment of the present invention can avoid the problems of low computational efficiency and easy premature convergence of the particle swarm type method for multi-dimensional optimization problems, and can better balance the early exploration capability and the later development capability, and quickly and accurately obtain the optimal scheduling plan.

[0050] For ease of understanding, the above-mentioned open-pit mine transportation scheduling method is introduced in detail below, taking the transportation equipment as a mine car as an example.

[0051] See also Figure 2 FIG. 1 is a flow chart of another open-pit mine transportation scheduling method, the method comprising the following steps: Step 1: Obtain engineering data of the target mining area.

[0052] Including the shovel point number in the shift ( i ), the total number of shovel points ( l ), unloading point number ( j ), the total number of unloading points ( h or t ), unloading point number ( k ), the total number of unloading points ( n ), distance from shovel point to ore unloading point / rock unloading point ( s ij / s ik ), full load transportation cost from a single shovel point to a ore unloading point / rock unloading point ( m ij / m ik ), single unloaded transportation cost from the ore unloading point / rock unloading point to the shovel point ( m ji / m ki ), the amount of ore produced at each shovel point ( Q i ), the amount of rock produced at each shovel point ( P i ), the output of each unloading point / rock unloading point ( U j / U k ), the average grade of ore at the shovel point ( r i ), minecart full load ( T ), the average speed of the minecart ( v ), loading time ( t 1), unloading time ( t 2), working hours of one shift ( t 3).

[0053] Step 2: Determine the train dimension and train search range.

[0054] One shovel point transports to multiple unloading points, the total number of shovel points is l The total number of unloading points is t + n , so the dimension of the train number is ( t + n )× l The train search range is determined according to the actual situation. Generally, 0-100 can be selected. Set the total number of population particles to O , the particle number is o .

[0055] ; X o Indicates o The position of a particle, x The value range of is 0-100, which can be rewritten into vector form as follows: ; The dimension of the vector is 1×( t + n ) l .

[0056] Step 3: Determine the objective function.

[0057] The optimal goal of the transportation scheduling system is to make the total transportation cost within a shift g (X) is the lowest, without constraints, the above objective function is as follows: (1); in, x ij Indicates shovel point iTo the unloading point j The train number, x ik Indicates shovel point i To the unloading point k Since the actual production situation of mines is very complicated, it is necessary to constrain the objective function (1) through corresponding mining conditions, output conditions, quality conditions and other factors: (2); Formula (2) is the production capacity constraint of the shovel point.

[0058] (3); Formula (3) is the planned production constraint of each unloading point.

[0059] (4); Formula (4) is the quality requirement constraint, where: r l Indicates the lower limit of the grade required at the unloading point. r n Indicates the upper limit of grade required at the unloading point.

[0060] (5); Formula (5) is the vehicle no-wait constraint.

[0061] Formulas (2) to (5) are all constraints on the train number X. p (X) is expressed and added into the above objective function formula (1), and the objective function of the mine transportation scheduling system under the constraints of actual production conditions is obtained: (6); During the iteration process, each update of the train number X must comply with the regularization p (X) constraints.

[0062] Step 4: Determine the population size and set the algorithm parameters.

[0063] A population consists of multiple particles. The location of each particle is a potential solution to the objective function. It is necessary to determine the number of vehicles on each transport route and substitute it into the objective function to calculate the fitness value. By constantly changing the particle position (i.e., changing the number of vehicles on each transport route), the fitness value is continuously reduced until convergence, and the optimal predicted position is obtained. The dimension of each particle is 1×( t + n ) l , can calculate the corresponding total transportation cost within a shift, that is, the fitness value.

[0064] Set the appropriate number of particles. The more particles in the population, the stronger the corresponding global search capability, but the longer the calculation time required. The GBO algorithm does not need as many particles as the particle swarm algorithm, and can complete convergence with fewer particles. A group of particles is randomly initialized in the solution space, the total number is ten times the corresponding number of shovel points, and the dimension of each particle is 1×( t + n ) l , find the optimal position X of the initial population best and the worst position X worst . Set the number of iterations.

[0065] Step 5: Apply the gradient search rule for global exploration. By obtaining the three updated positions of the current particle, the update of the current particle in the next iteration is obtained comprehensively.

[0066] The gradient search rule (GSR) enables the algorithm to consider random behavior during the optimization process, thereby promoting the ability of global search. The direction of movement (DM) is used to form a suitable local search trend to improve the convergence efficiency of the GBO algorithm. Based on GSR and DM, the following formula is used to update the first position of the current particle: (7); (8); (9); (10); (11); in, express O The first particle o indivual, e represents the number of iterations, E represents the total number of iterations, Indicates o Particle No. e The position at the iteration, Indicates o Particle No. e The first updated position at iteration , randn represents normally distributed random numbers, rand represents a random number between [0,1], represents the worst position of the current population, represents the optimal position of the current population, e Indicates a preset value greater than zero, such as 2.22×10 -16 , β min andβ max Represents two constants, set to 0.2 and 1.2 respectively.

[0067] (12); (13); (14); (15); in, express( t + n ) l A random number between [0,1] of dimension, t 1. t 2. t 3. t 4. o Different from each other, t 1. t 2. t 3. t 4 means from [0, O ] are four integers randomly selected from the equation. By changing the first and third terms on the right side of equation (8), we get the second updated position of the current particle. : (16); according to and You can get the third updated position of the current particle : (17); The update of the current particle in the next iteration is : (18); t a , t b Represents two random numbers between [0,1].

[0068] Step 6: Apply the local escape operator to obtain the optimal transport schedule within a given range.

[0069] By using the local escape operator (LEO), GBO can continuously jump out of the local optimal solution during the iteration process and finally obtain the optimal transport train number within a given range.

[0070] The algorithm has strong exploration capabilities in the early stage to find suitable particles, and shows efficient development capabilities in the later stage, thus accelerating the convergence process. The local escape operator (LEO) generates superior positions through diverse solutions These solutions include the next updated position of the current particle obtained from step 5 , optimal location , two parameter update positions and , and two random particles in the population and , a new random particle in the search space . Generated by the following process: (19); in, f 1 represents a random number between [-1,1], f 2 represents a normally distributed random number with a variance of 0 and a standard deviation of 1. u 1.u2. u 3 represents three random numbers, defined as follows: (20); (twenty one); (twenty two); in, rand and m 1 represents a random number between [0,1].

[0071] The new random solution in (19) It can be determined by the following formula: (twenty three); (twenty four); in, rand and m 2 represents a random number between [0,1], represents the first randomly selected u The position of a particle, , and They represent the maximum and minimum boundaries of the current solution space search, which are 0-100 here.

[0072] According to formula (19), the target updated position of the current particle in the next iteration can be calculated. By continuously iterating and updating the position of the particle, the fitness value will continue to decrease until the predetermined convergence accuracy or number of iterations is reached, at which point the iteration process will stop. When the iteration stops, the optimal position of the particle in the population is the optimal train number distribution.

[0073] Step 7: Calculate the time required to complete a transport on each transport route.

[0074] There is a transportation route from each shoveling point to each unloading point. There is no traffic jam in between. The transportation time required for each transportation route is as follows: (25); in, T ij and T ik Respectively represent the shovel point i To the unloading point j and shovel point i To the unloading point k One-time transportation time.

[0075] Step 8: Calculate the number of times a mine car can transport on each transport route within a shift without waiting.

[0076] (26); in, N ij and N ik Respectively represent the mine car from the shovel point i To the unloading point k and from the shovel point i To the unloading point k The number of times that can be transported.

[0077] Step 9: Get the final vehicle dispatch plan.

[0078] According to the target transportation frequency plan , the number of times a minecart can transport on each transport route N ij and N ik , calculate the final vehicle dispatching plan as follows: (27); in, ceiling () represents the upward rounding function, n ij and n ik That is, the vehicle scheduling plan for each transportation route within a shift.

[0079] The advantage of the embodiment of the present invention is that it can effectively avoid the problem of low computational efficiency and easy premature convergence of particle swarm type methods for multi-dimensional optimization problems, and can better balance the early exploration and later development capabilities of the algorithm, and obtain the optimal transport vehicle estimation value faster and more accurately. The method based on the gradient optimizer is inspired by the traditional gradient Newton method and uses two main operating factors: the gradient search rule (GSR) and the local escape operator (LEO). GSR uses a gradient-based strategy to improve exploration capabilities, thereby accelerating convergence and finding a better position in the search space.

[0080] Corresponding to the above-mentioned open-pit mine transportation scheduling method, an embodiment of the present invention provides an open-pit mine transportation scheduling device. Figure 3 The schematic diagram of the structure of an open-pit mine transportation dispatching device is shown, and the device comprises: The acquisition module 301 is used to acquire the engineering data of the target mining area, and the engineering data includes shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; The optimization module 302 is used to iteratively optimize the transportation times of each transportation route in the target mining area according to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, and obtain the target transportation times plan by using the global search algorithm based on the gradient optimizer; wherein the global search algorithm based on the gradient optimizer updates the particle position through the gradient search rule and the local escape operator, and the position of each particle is a candidate transportation times plan; the path between a shovel point and a discharge point corresponds to a transportation route; The determination module 303 is used to determine the vehicle dispatching plan of the target mining area according to the target transportation frequency plan, transportation distance information and transportation equipment information.

[0081] The open-pit mine transportation scheduling device provided by the embodiment of the present invention can obtain engineering data of a target mining area, wherein the engineering data includes shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; according to the engineering data and an objective function constructed with the minimum total transportation cost as the goal, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain a target transportation time plan; wherein the global search algorithm based on the gradient optimizer updates the particle position through a gradient search rule and a local escape operator, and the position of each particle is a candidate transportation time plan; the path from a shovel point to a unloading point corresponds to a transportation route; according to the target transportation time plan, the transportation distance information and the transportation equipment information, a vehicle scheduling plan for the target mining area is determined. In this way, when determining the vehicle scheduling plan for the target mining area, a global search algorithm based on a gradient optimizer is adopted, wherein the gradient search rule utilizes a gradient-based strategy to improve the exploration capability, thereby accelerating the convergence speed and finding a better position in the search space, and the local escape operator can get rid of the local optimal solution and improve its global search capability. Therefore, the embodiment of the present invention can avoid the problems of low computational efficiency and easy premature convergence of the particle swarm type method for multi-dimensional optimization problems, and can better balance the early exploration capability and the later development capability, and quickly and accurately obtain the optimal scheduling plan.

[0082] Furthermore, the above-mentioned optimization module 302 is specifically used to: determine the transportation frequency dimension according to the total number of shoveling points in the shoveling point information and the total number of unloading points in the unloading point information; construct an objective function based on the transportation frequency dimension and engineering data with the goal of minimizing the total transportation cost; generate an initial population based on the transportation frequency dimension, a preset transportation frequency search range and a population size, and determine the optimal position and the worst position of the initial population according to the objective function; adopt a global search algorithm based on a gradient optimizer to iteratively update the particle position of the initial population to obtain the target population when the iteration is stopped; and determine the optimal position of the target population as the target transportation frequency plan.

[0083] Furthermore, the above transport times dimension is ( h + n )× l , the dimension of the particle is 1×( h + n ) l , h Indicates the total number of unloading points, n Indicates the total number of unloading points, l Indicates the total number of shovel points; The objective functions include: ; The constraints of the objective function include: ; ; ; ; in, g (X) represents the total transportation cost corresponding to the particle position X, T Indicates the full load of the transport equipment. m ij Indicates shovel point i To the unloading point j The single full load transportation cost, m ji Indicates unloading point j To the shovel point i Single empty-load transportation cost, x ij Indicates shovel point i To the unloading point j The number of transports, s ij Indicates shovel point i To the unloading point j The distance m ik Indicates shovel point i To the unloading point k The single full load transportation cost, m ki Indicates the unloading point k To the shovel point i Single empty-load transportation cost, x ik Indicates shovel point i To the unloading point k The number of transports, s ik Indicates shovel point i To the unloading point k The distance Q i Indicates shovel point i The amount of ore produced, P i Indicates shovel point i The amount of rock produced, U j Indicates unloading point j The output, U k Indicates the unloading point k The output, r l Indicates the lower limit of the grade required at the unloading point. r n Indicates the upper limit of the grade required at the unloading point. r i Indicates shovel pointi The average grade of the ore, t 1 means loading time, t 2 indicates the unloading time, t 3 represents the working time of a shift.

[0084] Furthermore, the optimization module 302 is also used to: generate an initial update position of the current particle through a gradient search rule when updating the position of the current particle; and generate a target update position of the current particle according to the initial update position and the local escape operator.

[0085] Furthermore, the optimization module 302 is also used to calculate the first position and the second position of the current particle by the following formula: ; ; ; ; ; ; ; ; ; According to the first position and the second position, the third position of the current particle is calculated by the following formula: ; According to the first position, the second position and the third position, the initial update position of the current particle is calculated by the following formula: ; in, express O The first particle o indivual, e represents the number of iterations, E represents the total number of iterations, Indicates o Particle No. e The first position at the iteration, Indicates o Particle No. e The second position at the iteration, Indicates o Particle No. e The position at the iteration, Indicates o Particle No. e The position at +1 iteration, randnrepresents normally distributed random numbers, rand represents a random number between [0,1], β min and β max Represents two preset constants, represents the worst position of the current population, represents the optimal position of the current population, e Indicates a preset value greater than zero, express( t + n ) l A random number between [0,1] of dimension, t Indicates the total number of unloading points, n Indicates the total number of unloading points, l represents the total number of shovel points, t 1. t 2. t 3. t 4 means from [0, O ], four integers randomly selected from t 1. t 2. t 3. t 4. o Different from each other, t a , t b Represents two random numbers between [0,1].

[0086] Furthermore, the optimization module 302 is also used to calculate the target update position of the current particle by the following formula: ; in, f 1 represents a random number between [-1,1], f 2 represents a normally distributed random number, u 1.u2. u 3 represents three random numbers, represents a new random solution, u 1.u2. u 3. is defined as follows: ; ; ; ; ; in, m 1. m2 represents two random numbers between [0,1], represents the first randomly selected u The position of a particle, , and They respectively represent the maximum and minimum boundaries of the current solution space search corresponding to the search range of the number of transportations.

[0087] Furthermore, the above-mentioned determination module 303 is specifically used to: calculate the transportation time of each transportation route based on the transportation distance information and the transportation equipment information; calculate the number of times a transportation equipment can be transported on each transportation route based on the transportation time of each transportation route; calculate the number of transportation equipment on each transportation route based on the number of times a transportation equipment can be transported on each transportation route and the target transportation number plan, and obtain the vehicle scheduling plan for the target mining area.

[0088] The open-pit mine transportation scheduling device provided in this embodiment has the same implementation principle and technical effects as those of the aforementioned open-pit mine transportation scheduling method embodiment. For the sake of brief description, for matters not mentioned in the open-pit mine transportation scheduling device embodiment, reference may be made to the corresponding contents in the aforementioned open-pit mine transportation scheduling method embodiment.

[0089] like Figure 4 As shown, an electronic device 400 provided in an embodiment of the present invention includes: a processor 401, a memory 402 and a bus, the memory 402 stores a computer program that can be run on the processor 401, when the electronic device 400 is running, the processor 401 and the memory 402 communicate through the bus, and the processor 401 executes the computer program to implement the above-mentioned open-pit mine transportation scheduling method.

[0090] Specifically, the memory 402 and the processor 401 can be general-purpose memories and processors, which are not specifically limited here.

[0091] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the open-pit mine transportation scheduling method in the above method embodiment is executed. The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk or an optical disk, and other media that can store program codes.

[0092] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0093] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0094] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and a part of a module, a program segment or a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0095] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for transport scheduling in an open-pit mine, characterized in that: include: Acquire engineering data of the target mining area, wherein the engineering data includes shovel point information, unloading point information, transportation distance information, transportation cost information and transportation equipment information; According to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, a global search algorithm based on a gradient optimizer is used to iteratively optimize the transportation times of each transportation route in the target mining area to obtain a target transportation times plan; wherein the global search algorithm based on a gradient optimizer updates the particle position through a gradient search rule and a local escape operator, and the position of each particle is a candidate transportation times plan; the path between a shovel point and an unloading point corresponds to one of the transportation routes; A vehicle dispatching plan for the target mining area is determined according to the target transportation frequency plan, the transportation distance information and the transportation equipment information.

2. The method according to claim 1, characterized in that The method according to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost adopts a global search algorithm based on a gradient optimizer to iteratively optimize the transportation times of each transportation route in the target mining area to obtain a target transportation times plan, including: Determine the transport frequency dimension according to the total number of shoveling points in the shoveling point information and the total number of unloading points in the unloading point information; According to the transportation frequency dimension and the engineering data, the objective function is constructed with the goal of minimizing the total transportation cost; Generate an initial population according to the transport frequency dimension, a preset transport frequency search range and the population quantity, and determine the optimal position and the worst position of the initial population according to the objective function; Using a global search algorithm based on a gradient optimizer, the particle positions of the initial population are iteratively updated to obtain a target population when the iteration is stopped; The optimal position of the target population is determined as the target transportation frequency plan.

3. The method according to claim 2, characterized in that The transport frequency dimension is ( h + n )× l The particle size is 1×( h + n ) l , h Indicates the total number of unloading points, n Indicates the total number of unloading points, l Indicates the total number of shovel points; The objective function includes: ； The constraints of the objective function include: ； ； ； ； in, g (X) represents the total transportation cost corresponding to the particle position X, T Indicates the full load of the transport equipment. m ij Indicates shovel point i To the unloading point j The single full load transportation cost, m ji Indicates unloading point j To the shovel point i Single empty-load transportation cost, x ij Indicates shovel point i To the unloading point j The number of transports, s ij Indicates shovel point i To the unloading point j The distance m ik Indicates shovel point i To the unloading point k The single full load transportation cost, m ki Indicates the unloading point k To the shovel point i Single empty-load transportation cost, x ik Indicates shovel point i To the unloading point k The number of transports, s ik Indicates shovel point i To the unloading point k The distance Q i Indicates shovel point i The amount of ore produced, P i Indicates shovel point i The amount of rock produced, U j Indicates unloading point j The output, U k Indicates the unloading point k The output, r l Indicates the lower limit of the grade required at the unloading point. r n Indicates the upper limit of the grade required at the unloading point. r i Indicates shovel point i The average grade of the ore, t 1 means loading time, t 2 indicates the unloading time, t 3 represents the working time of a shift.

4. The method according to claim 2, characterized in that: The global search algorithm based on the gradient optimizer is used to iteratively update the particle positions of the initial population to obtain the target population when the iteration is stopped, including: When updating the position of the current particle, generating the initial update position of the current particle by using the gradient search rule; A target update position of the current particle is generated according to the initial update position and the local escape operator.

5. The method according to claim 4, characterized in that The step of generating the initial update position of the current particle by using the gradient search rule comprises: The first position and the second position of the current particle are calculated by the following formula: ； ； ； ； ； ； ； ； ； According to the first position and the second position, the third position of the current particle is calculated by the following formula: ； According to the first position, the second position and the third position, the initial update position of the current particle is calculated by the following formula: ； in, express O The first particle o indivual, e represents the number of iterations, E represents the total number of iterations, Indicates o Particle No. e The first position at the iteration, Indicates o Particle No. e The second position at the iteration, Indicates o Particle No. e The position at the iteration, Indicates o Particle No. e The position at +1 iteration, randn represents normally distributed random numbers, rand represents a random number between [0,1], β min and β max Represents two preset constants, represents the worst position of the current population, represents the optimal position of the current population, ε Indicates a preset value greater than zero, express( t + n ) l A random number between [0,1] of dimension, t Indicates the total number of unloading points, n Indicates the total number of unloading points, l represents the total number of shovel points, τ 1. τ 2. τ 3. τ 4 means from [0, O ], four integers randomly selected from τ 1. τ 2. τ 3. τ 4. o Different from each other, τ a , τ b Represents two random numbers between [0,1].

6. The method according to claim 5, characterized in that The step of generating a target update position of the current particle according to the initial update position and the local escape operator comprises: The target update position of the current particle is calculated by the following formula: ； in, f 1 represents a random number between [-1,1], f 2 represents a normally distributed random number, u 1.u2. u 3 represents three random numbers, represents a new random solution, u 1.u2. u 3. is defined as follows: ； ； ； ； ； in, μ 1. μ 2 represents two random numbers between [0,1], represents the first randomly selected u The position of a particle, , and They respectively represent the maximum boundary and minimum boundary of the current solution space search corresponding to the search range of the number of transportations.

7. The method according to claim 1, characterized in that Determining the vehicle dispatching plan for the target mining area according to the target transportation frequency plan, the transportation distance information and the transportation equipment information includes: Calculate the transportation time of each transportation route according to the transportation distance information and the transportation equipment information; According to the transportation time of each transportation route, the number of times a transportation device can be used for transportation on each transportation route is calculated; According to the number of times a transport device can transport on each transport route and the target transport number plan, the number of transport devices on each transport route is calculated to obtain a vehicle scheduling plan for the target mining area.

8. An open-pit mine transportation dispatching device, characterized in that: include: An acquisition module, used to acquire engineering data of a target mining area, wherein the engineering data includes shovel point information, unloading point information, transportation distance information, transportation cost information, and transportation equipment information; The optimization module is used to iteratively optimize the transportation times of each transportation route in the target mining area according to the engineering data and the objective function constructed with the goal of minimizing the total transportation cost, and obtain a target transportation times plan by using a global search algorithm based on a gradient optimizer; wherein the global search algorithm based on a gradient optimizer updates the particle position by using a gradient search rule and a local escape operator, and the position of each particle is a candidate transportation times plan; the path between a shovel point and an unloading point corresponds to one of the transportation routes; The determination module is used to determine the vehicle dispatching plan of the target mining area according to the target transportation frequency plan, the transportation distance information and the transportation equipment information.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the open-pit mine transportation scheduling method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the open-pit mine transportation scheduling method according to any one of claims 1 to 7 is executed.

Images