Mine vehicle dispatching method, device, equipment and storage medium

Abstract

The present invention provides a mine vehicle scheduling method, apparatus, equipment, and storage medium, relating to the field of vehicle scheduling technology. The method comprises: using a computer device to symbolically encode unloading points, excavators, and trucks based on acquired scheduling information, and obtaining corresponding first, second, and third symbolic codes; generating an initial population based on the obtained symbolic codes, wherein individuals in the initial population represent a scheduling solution consisting of a sequence of scheduling paths corresponding to all third symbolic codes; constructing an objective function under a first constraint with minimizing the total transportation cost of the scheduling solution as the optimization goal; and iteratively evolving the initial population using a genetic algorithm based on the objective function to obtain and output an optimal scheduling solution. The present invention realizes automated and intelligent vehicle scheduling, improving the real-time performance and accuracy of scheduling while also reducing costs.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and vehicle dispatching, and in particular to a mine vehicle dispatching method, device, equipment and storage medium. Background Art

[0002] Open-pit mining is widely adopted in the mining industry due to its advantages, including rapid construction, high productivity, low cost, and high safety. However, scheduling management in open-pit mining and large-scale earthmoving projects often lags behind, relying on on-site managers to conduct inspections and manually dispatch tasks via command vehicles. This approach makes it difficult to identify and resolve scheduling issues in real time, and due to the limitations of managers' vision and experience, optimal scheduling is difficult to achieve, resulting in reduced efficiency of construction machinery and increased fuel consumption. Summary of the Invention

[0003] The present invention provides a mine vehicle dispatching method, device, equipment and storage medium to solve the defects in the prior art that open-pit mining vehicle dispatching mostly relies on on-site managers driving command vehicles for inspection and manual dispatching, which makes it difficult to discover and solve dispatching problems in real time, limits the efficiency of engineering machinery, and increases fuel consumption.

[0004] One aspect of the present invention provides a mine vehicle dispatching method, which is applied to a computer device. The method comprises:

[0005] Obtaining scheduling information of a loading point, an excavator, and a truck, and performing symbol coding on the loading point, the excavator, and the truck according to the scheduling information, to obtain a first symbol code corresponding to the loading point, a second symbol code corresponding to the excavator, and a third symbol code corresponding to the truck;

[0006] generating an initial population based on the first symbol code, the second symbol code, and the third symbol code, wherein individuals in the initial population represent a scheduling solution consisting of scheduling path sequences corresponding to all third symbol codes, wherein the scheduling path sequence corresponding to each third symbol code includes at least one scheduling path consisting of a pair of the first symbol code and the second symbol code;

[0007] Taking minimizing the total transportation cost of the scheduling plan as the optimization goal, constructing an objective function under a first constraint condition, where the first constraint condition is a constraint condition of the scheduling plan;

[0008] Based on the objective function, a genetic algorithm is used to iteratively evolve the initial population until a preset termination condition is reached, and an optimal scheduling plan is obtained and output in a preset output mode, so as to schedule the trucks according to the optimal scheduling plan.

[0009] Another aspect of the present invention further provides a mine vehicle dispatching device, the device comprising:

[0010] a code acquisition module, configured to acquire scheduling information of a loading point, an excavator, and a truck, and to perform symbol coding on the loading point, the excavator, and the truck according to the scheduling information, to obtain a first symbol code corresponding to the loading point, a second symbol code corresponding to the excavator, and a third symbol code corresponding to the truck;

[0011] a population generation module, configured to generate an initial population based on the first symbol code, the second symbol code, and the third symbol code, wherein individuals in the initial population represent a scheduling solution consisting of a scheduling path sequence corresponding to all third symbol codes, wherein the scheduling path sequence corresponding to each third symbol code includes at least one scheduling path consisting of a pair of the first symbol code and the second symbol code;

[0012] a function construction module, configured to construct an objective function under a first constraint condition with minimizing the total transportation cost of the scheduling solution as an optimization goal, where the first constraint condition is a constraint condition of the scheduling solution;

[0013] a scheme acquisition module, configured to iteratively evolve the initial population using a genetic algorithm based on the objective function until a preset termination condition is reached to obtain an optimal scheduling scheme; and

[0014] The scheduling module is used to output the optimal scheduling plan in a preset output mode, so as to schedule the trucks according to the optimal scheduling plan.

[0015] In another aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned mine vehicle dispatching method when executing the program.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the mine vehicle dispatching method described above when the computer program is executed by a processor.

[0017] The mine vehicle scheduling method, device, equipment, and storage medium provided by the present invention perform symbolic encoding on unloading points, excavators, and trucks, and generate an initial population containing multiple scheduling path sequences based on these symbolic encodings. Each scheduling path sequence represents a possible truck scheduling solution, including the detailed path of the truck from loading on the excavator to the unloading point. Then, with minimizing the total transportation cost of the scheduling solution as the optimization goal, an objective function of the first constraint condition is constructed. Finally, combined with this objective function, the initial population is iteratively evolved using a genetic algorithm. Under the action of the genetic algorithm, the scheduling paths of the trucks in the scheduling solution will undergo operations such as selection, crossover, and mutation, thereby gradually approaching the optimal solution. When the preset termination condition is reached, an optimal scheduling solution will be output. This achieves the automation and intelligentization of vehicle scheduling in open-pit mining and large-scale earthmoving projects, not only improving the real-time and accuracy of scheduling, but also reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 It is a flow chart of the mine vehicle dispatching method provided by the present invention;

[0020] Figure 2 is a schematic diagram of a cross-operation scenario provided by the present invention;

[0021] Figure 3 is a table of distances between mine loading and unloading points in one embodiment of the present invention;

[0022] Figure 4 is a graph comparing iterative convergence of truck transportation costs when different genetic algorithms are applied in one embodiment of the present invention;

[0023] Figure 5 is a comparison diagram of iterative convergence of truck transportation costs when different genetic algorithms are applied in another embodiment of the present invention;

[0024] Figure 6 is a comparison diagram of iterative convergence of truck transportation cost when different genetic algorithms are applied in another embodiment of the present invention;

[0025] Figure 7 This is a comparison table of truck waiting time and excavator hook time using different algorithms of the present invention;

[0026] Figure 8It is a structural schematic diagram of the mine vehicle dispatching device provided by the present invention;

[0027] Figure 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0029] The improved genetic algorithm (also referred to as the improved genetic algorithm) used in each embodiment of the present invention creatively adopts a selection method combining roulette wheel selection and elite retention strategy to perform selection operations. Among them, the roulette wheel selection mechanism allocates selection opportunities based on the fitness ratio of individuals. Individuals with higher fitness have a greater probability of being selected, which helps to guide the algorithm to evolve in the direction of higher fitness. The elite retention mechanism is a strategy designed to protect the optimal solution from being lost. During the iterative process of the genetic algorithm, the mechanism will screen out the top individuals (or the individuals with the highest fitness) in the current population and pass them directly to the next generation, skipping the crossover and mutation links. Doing so can ensure that the algorithm continues to move towards a better solution domain during its evolutionary journey, while preventing the current optimal solution from being accidentally lost due to crossover and mutation operations. Combining roulette wheel selection with the elite retention strategy can ensure that the algorithm can converge to the global optimal solution while maintaining population diversity.

[0030] Figure 1 FIG. 1 is a flow chart of a mine vehicle dispatching method according to an embodiment of the present invention. Figure 1 As shown, the method is applied to a computer device and includes the following steps performed by the computer device:

[0031] Step 110: Obtain scheduling information of the unloading point, excavator, and truck via a computer device, and perform symbol coding on the unloading point, excavator, and truck based on the scheduling information to obtain a first symbol code corresponding to the unloading point, a second symbol code corresponding to the excavator, and a third symbol code corresponding to the truck;

[0032] In this example, a genetic algorithm is used to solve the open-pit mine truck scheduling problem. Specifically, when using a genetic algorithm to solve the open-pit mine truck scheduling problem, it is first necessary to determine a coding scheme for each component of the problem (i.e., unloading points, excavators, and trucks) so that the genetic algorithm can handle them. The excavator is equivalent to the digging point. A mine typically has multiple digging points, each of which is assigned an excavator. The digging point is also the loading point for the truck.

[0033] The dispatch information for unloading points, excavators, and trucks may include, but is not limited to: unloading point identification information, loading point identification information, one or more of the following information: the number, name, model, and load capacity of the excavators that can be configured at the loading point; and one or more of the following information: the number, model, and name of the trucks that can be dispatched. The dispatch information may be input by a user through the input / output device of the computer device (such as a keyboard, microphone, or touch screen display). Alternatively, the dispatch information may be stored on a cloud server or a central control device of a mine vehicle dispatch platform. The computer device may utilize its own network communication interface to obtain the dispatch information from the cloud server or the central control device via a wireless or wired network.

[0034] The symbol encoding used in the encoding process, in addition to {0,1}, also includes symbols without actual numerical meaning. These symbols can usually be selected from the alphabet, number table or code table, such as: {a,b,c,d…}, {1,2,3,4…} or {a1,a2,a3,a4…}. Symbol encoding can be used to avoid the need for subsequent decoding steps.

[0035] In one example, each unloading point is assigned a unique symbol. These symbols are usually lowercase letters, forming a symbol code of the unloading point, i.e., the first symbol code. For example, if there are three unloading points, they can be represented by 'a', 'b', and 'c' respectively.

[0036] In one example, each excavator (i.e., loading point) is also assigned a unique symbol. Unlike unloading points, the excavator symbol code can be represented by uppercase letters, forming the excavator symbol code, i.e., the second symbol code. For example, if there are three excavators, they can be represented by 'A', 'B', and 'C' respectively.

[0037] In one example, a unique symbol is assigned to each truck to form a symbol code of the truck, i.e., the third symbol code. For example, if there are four trucks, they can be represented by the numbers 1, 2, 3, and 4.

[0038] According to the actual transportation scheduling, trucks travel back and forth between loading and unloading points. Therefore, the symbol encoding corresponds to three vector sets:

[0039] Unloading point set: x_name = ['abc'];

[0040] Excavator collection: z_name = ['ABC'];

[0041] Truck set: k_name = [1, 2, 3, 4].

[0042] Based on the above steps, we obtain the symbolic codes corresponding to the unloading point, excavator, and truck. These symbolic codes serve as the genes of the chromosomes in the genetic algorithm, used for subsequent genetic operations (such as selection, crossover, and mutation) and fitness evaluation. In this way, the genetic algorithm can more efficiently handle the truck scheduling problem without the complex decoding process.

[0043] Step 120: Generate an initial population based on the first symbol code, the second symbol code, and the third symbol code, where the individuals in the initial population represent a scheduling solution consisting of scheduling path sequences corresponding to all third symbol codes, wherein each scheduling path sequence corresponding to the third symbol code includes at least one scheduling path consisting of a pair of the first symbol code and the second symbol code;

[0044] Here, the initial population consists of multiple individuals, each representing a possible scheduling solution. Each individual (i.e., chromosome) is composed of a scheduling path sequence corresponding to all trucks (third symbol code). Each truck's scheduling path sequence contains at least one scheduling path consisting of a first symbol code (unloading point) and a second symbol code (excavator), which describes the truck's transportation process from a certain excavator (loading point) to a certain unloading point.

[0045] For example, a scheduling scheme for a truck with the third symbol coded as 1 within a specific time period can be expressed as "AaBbCc", which means that the truck with the third symbol coded as 1 loads cargo from excavator A and unloads cargo at unloading point a, then goes to excavator B to load cargo and unloads cargo at unloading point b, finally goes to excavator C to load cargo and finally unloads cargo at unloading point c.

[0046] For example, a scheduling plan for all 4 trucks within a specific time period can be expressed as:

[0047]

[0048] Among them, each row is the scheduling plan for each truck, and the number of rows is equal to the number of trucks; each column is the loading point (excavator) and unloading point that each truck passes through.

[0049] That is, the vehicle dispatch plan of truck number 1 is represented as 'AaBbCc', and its dispatch path sequence is AaBbCc, which includes three dispatch paths composed of first symbol codes and second symbol codes: excavator A and unloading point a, excavator B and unloading point b, and excavator C and unloading point c;

[0050] The vehicle dispatch plan for truck number 2 is denoted as 'AbCaBc'. Its dispatch path sequence is AbCaBc, which includes three dispatch paths consisting of first and second symbolic codes: excavator A and unloading point b, excavator C and unloading point a, and excavator B and unloading point c.

[0051] The vehicle dispatch plan for truck number 3 is denoted as 'BcAaCb', and its dispatch path sequence is BcAaCb, which includes three dispatch paths consisting of first and second symbolic codes: excavator B and unloading point c, excavator A and unloading point a, and excavator C and unloading point b.

[0052] The vehicle dispatch plan for truck number 4 is represented as 'CbAa', and its dispatch path sequence is CbAa, which includes two dispatch paths consisting of first and second symbol codes: excavator C and unloading point b, and excavator A and unloading point a.

[0053] The specific number of columns can be determined according to the actual parameters of the transportation scheduling process. The scheduling plan composed of the scheduling path sequence of all trucks determined in this way is an individual.

[0054] Step 130: Taking minimizing the total transportation cost of the scheduling plan as the optimization goal, construct an objective function under a first constraint condition, where the first constraint condition is a constraint condition of the scheduling plan;

[0055] It should be understood that the optimization goal of the open-pit mine truck scheduling problem is to reduce the total transportation cost, including but not limited to reducing idle driving distance, waiting time, and idle time of trucks and excavators. By optimizing the scheduling solution, we can ensure the most efficient use of resources, thereby reducing overall transportation costs.

[0056] Specifically, to quantify transportation costs, an objective function is constructed. The objective function is usually constructed based on multiple variables, such as the truck's travel distance, travel time, waiting time, loading and unloading time, etc.

[0057] In addition, when constructing the objective function, a series of preset first constraint conditions need to be considered to ensure the feasibility and effectiveness of the scheduling plan. The first constraint conditions include but are not limited to: time constraints (working hours, rest hours, etc. of trucks and excavators), capacity constraints (loading capacity of trucks, production capacity of excavators, etc.), path constraints (path selection for trucks to travel, etc.), and resource constraints (number of available trucks and excavators, etc.).

[0058] Step 140: Based on the objective function, use the genetic algorithm to iteratively evolve the initial population until a preset termination condition is reached, obtain the optimal scheduling plan and output it in a preset output manner, so as to schedule the trucks according to the optimal scheduling plan.

[0059] In this embodiment, the objective function is selected as the fitness function to evaluate the quality of feasible solutions in the truck transportation scheduling problem.

[0060] Specifically, according to the objective function, evaluate the fitness of individuals in the population, and select individuals with higher fitness (i.e., scheduling plans with lower costs) as parents for subsequent crossover and mutation operations. Randomly select multiple individuals from the selected parents, and exchange part of the scheduling paths of their scheduling path sequences to generate new offspring individuals. Perform mutation operations on the new offspring individuals to increase the diversity of the population. Finally, combine the new offspring individuals generated after the crossover and mutation operations with some individuals in the parent generation (such as individuals with higher fitness) to form a new population. This new population will be used for the next round of iterative evolution.

[0061] Specifically, in the improved genetic algorithm in this application, new individuals are generated through three mechanisms: selection, crossover, and mutation, which together form a new population of size N'. If the condition N' > N is satisfied, select the first N individuals with the highest fitness to form a new population; if the condition N' < N holds, an additional (N - N') individuals will be randomly generated and added to the new population to ensure that the size of the new population is the same as that of the previous generation.

[0062] Repeat the above processes of selection, crossover, mutation, and new population generation until a preset termination condition is reached, such as reaching the maximum number of iterations, or the fitness of individuals in the population reaches a stable state after consecutive iterations, then select the individual with the highest fitness from the current population as the optimal scheduling plan.

[0063] Furthermore, the computer device outputs the obtained optimal scheduling plan according to a preset output method, so as to schedule the truck according to the optimal scheduling plan. Specifically, the preset output method may include, but is not limited to: outputting the optimal scheduling plan to a cloud server or a central control device of a mine vehicle scheduling platform, so that the user can obtain the optimal scheduling plan through the cloud server or the central control device and schedule the truck based on the optimal scheduling plan; or, when the truck and / or the excavator are unmanned intelligent vehicles, the computer device may also send a scheduling instruction to the truck and / or the excavator according to the optimal scheduling plan, so that the truck and / or the excavator performs the corresponding task according to the scheduling instruction, thereby further realizing all-round intelligent control of the mine vehicle; or, the computer device may also send the optimal scheduling plan to a communication device specified by the user according to the reserved communication information.

[0064] The mine vehicle scheduling method proposed in this embodiment uses symbolic encoding for unloading points, excavators, and trucks, and generates an initial population containing multiple scheduling path sequences based on these symbolic encodings. Each scheduling path sequence represents a possible truck scheduling solution, including the detailed path of the truck from the excavator loading to the unloading point. Next, with minimizing the total transportation cost of the scheduling solution as the optimization goal, an objective function with the first constraint condition is constructed. Finally, based on this objective function, the initial population is iteratively evolved using a genetic algorithm. Under the influence of the genetic algorithm, the scheduling paths of the trucks in the scheduling solution undergo operations such as selection, crossover, and mutation, gradually approaching the optimal solution. When the preset termination condition is met, an optimal scheduling solution is output. This achieves the automation and intelligentization of vehicle scheduling in open-pit mining and large-scale earthmoving projects, not only improving the real-time and accuracy of scheduling, but also reducing costs.

[0065] It should be noted that each implementation method of the present application can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0066] In some embodiments, the objective function under the first constraint is constructed with minimizing the total transportation cost of the scheduling scheme as the optimization goal, including: determining the total transportation cost of the scheduling scheme based on the heavy-load transportation cost and the empty-load transportation cost of the truck corresponding to each of the third symbol codes, and the heavy-load transportation cost and the empty-load transportation cost of the excavator corresponding to each of the second symbol codes in the scheduling path sequence corresponding to each of the third symbol codes; constructing the objective function under the first constraint with minimizing the total transportation cost of the scheduling scheme as the optimization goal; here, the heavy-load transportation cost of the truck refers to the transportation cost of the truck when loaded with goods, and the empty-load transportation cost of the truck refers to the transportation cost of the truck when not loaded with goods. The heavy-load transportation cost of the excavator refers to the transportation cost of the excavator when loaded with goods, and the empty-load transportation cost of the excavator refers to the transportation cost of the excavator when not loaded with goods.

[0067] In this embodiment, the total transportation cost is calculated using the heavy-load transportation cost and the empty-load transportation cost of the truck, and the heavy-load transportation cost and the empty-load transportation cost of the excavator.

[0068] First, define the variables is the unit heavy-load transportation cost of truck k, is the unit heavy-load transportation cost of the excavator g, is the unit empty transport cost of truck k, is the unit heavy-load transportation cost of excavator g, d ij is the distance between nodes i and j.

[0069] Next, define the following decision variables:

[0070] If the heavily loaded truck k goes from node i to node j, the value is 1; if the heavily loaded truck k does not go from node i to node j, the value is 0;

[0071] If the empty truck k goes from node i to node j, the value is 1; if the empty truck k does not go from node i to node j, the value is 0;

[0072] If the overloaded excavator g goes from node i to node j, the value is 1; if the overloaded excavator g does not go from node i to node j, the value is 0;

[0073] If the unloaded excavator g moves from node i to node j, the value is 1; if the unloaded excavator g does not move from node i to node j, the value is 0.

[0074] Based on the above costs, the total transportation cost F1(S) of the scheduling plan is determined as:

[0075]

[0076] Among them, (i,j)∈D represents all possible node pairs.

[0077] Furthermore, in order to minimize the total transportation cost, the objective function under the first constraint is constructed as follows:

[0078]

[0079] Specifically, the first constraint condition includes at least one of the following:

[0080] (1) Path uniqueness constraint: ensure that each demand point is served only once and each path is traversed only once in each mission. Demand points may include unloading points and loading points.

[0081]

[0082] (2) Vehicle load constraint: ensure that the load of each vehicle does not exceed its maximum load, and the load when leaving point i is not less than the load when arriving at point j;

[0083]

[0084]

[0085]

[0086] in, is the loading quantity of truck k at point i, is the loading capacity of excavator g at point i, Q i k is the cargo quantity of truck k when it leaves point i, Q i g is the loading capacity of excavator g when it leaves point i, M is an infinite number, is the maximum load of truck k, is the maximum load of the excavator g, is the cargo volume of truck k arriving at point j, is the cargo volume of truck k arriving at point j.

[0087] (3) Transportation demand constraint: the total shipping volume of all vehicles must not be less than the total demand at the demand point;

[0088]

[0089] (4) Vehicle quantity constraint: the number of assigned vehicles shall not exceed the total number of vehicles;

[0090]

[0091] Among them, K is the total number of trucks, G is the total number of excavators, For truck k from the starting point to point i, is the excavator g from the starting point to point i, For truck k from point j to the unloading point, For truck k from point j to the unloading point.

[0092] (5) Time allocation constraint: the excavator can only be assigned to one area during each period of time;

[0093]

[0094] Where a∈A represents a mining area in the set of all mining areas, t∈T represents the time planning range, g∈G represents the excavator running in the set of all excavators, It means that if the excavator g is located in area a during time period t, it is 1, otherwise it is 0.

[0095] (6) Operating area constraints: restricting the excavator to operate only within one area;

[0096]

[0097] In the formula Indicates the maximum number of excavators operating in the same area.

[0098] (7) Vehicle type quantity constraint: the number of trucks that need to be dispatched is limited;

[0099]

[0100] Where K Min , K Max Indicates the maximum and minimum number of trucks that need to be dispatched in any time period.

[0101] The mine vehicle dispatching method proposed in this embodiment realizes the coordinated operation of trucks and excavators and saves transportation costs through the objective function and the first constraint condition constructed in the above manner.

[0102] In some embodiments, based on the objective function, the initial population is iteratively evolved using a genetic algorithm until a preset termination condition, including: determining the fitness of each individual in the initial population based on the objective function; determining the first individual in the initial population based on the fitness of each individual in the initial population using an elite retention strategy; determining the second individual in the initial population other than the first individual using a roulette wheel selection strategy based on the fitness of each individual in the initial population; performing a crossover operation and a mutation operation on the second individual to obtain a third individual; obtaining a new population based on the third individual and the first individual, and using the new population as the initial population, returning to continue executing the step of determining the fitness of each individual in the initial population based on the objective function until the preset termination condition is reached.

[0103] In this embodiment, a selection method combining a roulette wheel selection strategy and an elite retention strategy is adopted in the selection operation of the genetic algorithm for truck transportation scheduling.

[0104] Specifically, the elite retention strategy is a strategy that prevents the optimal solution from being lost during the evolutionary process. In each generation of a genetic algorithm, the elite retention strategy retains the best individuals (or the few individuals with the highest fitness) in the current population and copies them directly to the next generation without performing crossover or mutation operations. This ensures that the algorithm continuously approaches a more optimal solution space during evolution while preventing crossover and mutation operations from destroying the current optimal solution.

[0105] First, the fitness of each individual is calculated by the objective function f(x i ), where i = 1, 2, ..., n, n is the population size. According to the fitness of each individual f(x i ), select the best individual (or the individuals with the highest fitness) in the current population as the elite individual, that is, the first individual, and the first individual will be directly retained in the next generation population.

[0106] Next, for the individuals in the current population except the first individual, the roulette wheel selection strategy is used for selection.

[0107] Specifically, first calculate the sum of the fitness of all individuals:

[0108]

[0109] Calculate the probability of each individual being selected and inherited into the next generation population:

[0110]

[0111] Calculate the cumulative probability for each individual:

[0112]

[0113] Where j = 1, 2, ..., m, m is the number of iterations, and the cumulative probability q i Represents the sum of the selection probabilities from the first individual to the i-th individual (including the i-th individual).

[0114] Generate a uniformly distributed random number r in the interval [0,1]. Then, starting from the first individual, compare the random number r with the cumulative probability q one by one. i If r is less than or equal to q i , then select the i-th individual as the second individual.

[0115] Next, a crossover operation is performed on the selected second individuals. Specifically, one or more crossover points are randomly selected on the two second individuals. At these crossover points, the third symbol encoding sequences of the two second individuals are swapped to generate a new individual. Then, a random mutation operation is performed on certain sites in the new individual to generate a third individual.

[0116] Finally, the third individual generated through the crossover and mutation operations is combined with the first individual directly transferred through the elite retention strategy to form a new population of the next generation. The above steps are repeated for the new population, that is, the fitness of each individual is recalculated, and then the selection, crossover, and mutation operations are performed until the preset termination condition is met.

[0117] The mine vehicle scheduling method proposed in this embodiment selects individuals by combining roulette wheel selection and elite retention strategy when iteratively evolving the population through a genetic algorithm. This effectively balances the diversity of the population and the convergence of the algorithm, preventing the algorithm from falling into a local optimal solution while ensuring that the algorithm can converge to the global optimal solution, thereby improving the performance and efficiency of the algorithm.

[0118] In some embodiments, the method further includes: performing a second constraint check on a fourth individual generated after the crossover operation; if the fourth individual does not satisfy the second constraint check, cyclically shifting the position of the third symbol code in the fourth individual until the second constraint is satisfied; wherein the second constraint is that the mission start time of the truck corresponding to the third symbol code at the last position in the individual is within a preset time window. The fourth individual may, for example, be obtained by performing a crossover operation on the second individual.

[0119] It should be noted that, to reduce the probability of conflicting missions between vehicles, this embodiment only crosses individuals of the same type, rather than the traditional direct crossover. After the individual crossover operation is complete, the fourth individual generated after the crossover operation is tested for the second constraint. Specifically, the second constraint verifies that the mission start time of each truck corresponding to the third symbol code in the individual falls within a preset time window.

[0120] If the fourth entity is found to not meet the second constraint during verification, meaning that at least one truck's mission start time for the third symbol code exceeds the preset time window, then the third symbol codes in the fourth entity need to be cyclically shifted. Circular shifting here refers to changing the order in which the tasks of the trucks corresponding to the third symbol codes in the fourth entity are executed, trying different permutations of the third symbol codes until a permutation is found that ensures that all trucks corresponding to the third symbol codes complete their missions within the preset time window.

[0121] If after one round of movement, the last truck's trip start time is still not within the preset time window, then the fourth entity is deleted and a new fourth entity is generated. Figure 2 As shown, after the previous generation individual 1 and the previous generation individual 2 are cross-operated, the current individual 1 and the illegal individual 2 are obtained. If the task start time of the truck with the third symbol code #1 at the last position in the illegal individual 2 exceeds the preset time window, the position of the third symbol code in the illegal individual 2 needs to be cyclically moved. After one circle of cyclic movement, if the task start time of the truck with the third symbol code at the last position in the illegal individual 2 still exceeds the preset time window, the illegal individual 2 is deleted.

[0122] In this embodiment, the above method ensures that the generated individuals not only inherit the characteristics of the parent generation but also meet the constraints in actual operation, thereby improving the quality and feasibility of the scheduling solution.

[0123] In some embodiments, the method further includes: determining a fifth individual selected for mutation operation, and randomly selecting a mutation point from the scheduling path sequence corresponding to the fifth individual for mutation; wherein, when the mutation point is the first symbol code corresponding to the first unloading point, the first symbol code corresponding to the first unloading point is randomly replaced with the first symbol code corresponding to the second unloading point; and when the mutation point is the second symbol code corresponding to the first excavator, the second symbol code corresponding to the first excavator is randomly replaced with the second symbol code corresponding to the second excavator.

[0124] The fifth individual is determined from the fourth individual. Optionally, in other embodiments of the present application, determining the fifth individual selected for the mutation operation from the fourth individual includes: randomly generating a random number between (0, 1) for the fourth individual obtained after the crossover operation, and comparing the random number with a preset mutation probability; if the random number is less than the preset mutation probability, determining the fourth individual as the fifth individual to be subjected to the mutation operation.

[0125] Specifically, a random number a between (0, 1) is first generated for the individual after the crossover operation, and the random number is compared with the preset mutation probability Pm. If the random number is less than Pm, the corresponding individual is selected for mutation operation, that is, the fifth individual.

[0126] For example, in the application of improved genetic algorithm in truck transportation scheduling, the mutation operation is as follows: the population of genetic algorithm is set to N, and N random numbers a are randomly generated in (0,1). On this basis, the N a values ​​are compared with the mutation probability P m For comparison, when it is less than P m When , any loading point or unloading point in the dispatching routes of all trucks is mutated.

[0127] For the fifth individual, a position in the individual is randomly selected as a mutation point. This mutation point corresponds to a specific demand point on the scheduling path sequence, such as a unloading point or an excavator.

[0128] If the selected variation point is a unloading point corresponding to the first symbol code (for example, an unloading point with the first symbol code a), then the first symbol code corresponding to another unloading point (for example, an unloading point with the first symbol code b) is randomly selected, and then the original first symbol code is replaced with this new first symbol code.

[0129] If the selected variation point is an excavator corresponding to the second symbol code (for example, the unloading point with the second symbol code A), then the second symbol code corresponding to another unloading point (for example, the unloading point with the first symbol code B) is randomly selected, and then the original second symbol code is replaced with this new second symbol code.

[0130] Mutation can restore and supplement genetic information that may be lost in the crossover operation, while preventing the above algorithm from falling into the local optimal solution, thereby ensuring that the above algorithm has effective local search capabilities.

[0131] In some embodiments, the method further includes: randomly generating a first scheduling path sequence for a first truck based on a third constraint condition; determining a second scheduling path sequence for a second truck other than the first truck based on the first scheduling path sequence of the first truck, wherein the second scheduling path sequence is the same as the first scheduling path sequence; and generating an initial population based on the first scheduling path sequence of the first truck and the second scheduling path sequence of the second truck.

[0132] Among them, the third constraint condition includes: when the truck leaves the loading point corresponding to the current excavator, it goes to the unloading point that is not currently occupied by other trucks; when the truck leaves the current unloading point, it goes to the loading point corresponding to the excavator that is not currently occupied by other trucks, or goes to the loading point corresponding to the excavator that meets the preset loading waiting time.

[0133] In this embodiment, before generating the first dispatching path sequence for the first truck, a series of initial data needs to be collected and determined, including the number of trucks, the number of loading points (excavators), the number of unloading points, various distances, carrying capacity, speed, work efficiency, etc.

[0134] The starting point of the first truck is listed as a loading point in the first dispatching route sequence. Then, a first matching code is randomly selected from the first symbol code corresponding to the unloading point. Then, a second matching code is randomly selected from the second symbol code corresponding to the excavator. Then, a first matching code is randomly selected from the first symbol code corresponding to the unloading point. This process is repeated to randomly generate the first dispatching route sequence for the first truck.

[0135] Here, when randomly generating the first dispatching path sequence of the first truck, the third constraint condition needs to be followed. The third constraint condition includes the following two constraints.

[0136] When a truck leaves the loading point corresponding to the current excavator, it must go to a unloading point that is not currently occupied by other trucks to avoid resource conflicts and ensure that each unloading point is not visited by multiple trucks at the same time, resulting in task saturation.

[0137] When a truck leaves its current unloading point, it can choose to go to a loading point corresponding to an excavator that is not currently occupied by other trucks, or to a loading point corresponding to an excavator that meets the preset loading waiting time. This ensures that the truck can efficiently return to the loading point after completing the task, taking into account the availability and waiting time of the loading point.

[0138] In this embodiment, the above method is used to ensure that each individual in the initial population meets the actual operation restrictions.

[0139] The following will be combined Figures 3 to 7, an example is given to illustrate the advantages of the above mine vehicle scheduling method. Specifically, in an example of the application of the above mine vehicle scheduling method, an open-pit coal mine has a total of 5 loading points and 3 unloading points. Each loading point is equipped with an excavator, and the three unloading points are required to handle 3,500 tons (t) per shift. The distance between each loading point and the unloading point is as follows: Figure 3 As shown, the unit of distance is kilometers (km). The garage has 60 trucks (a varying number of trucks are assigned based on the daily work schedule), each with a maximum load of 50 tons. The costs of an empty and loaded truck are 40 yuan / km and 60 yuan / km, respectively. The average speeds of an empty and loaded truck are 30 km / h and 20 km / h, respectively. The costs of an empty and loaded excavator are 50 yuan / km and 70 yuan / km, respectively. (Since the excavator's position is basically fixed, generally only the cost of a single round trip is considered.) According to the collected data, the excavator loading time is 6 minutes (min), the truck unloading time is 3 minutes, the average waiting time for trucks per shift is 1.25 hours, and the average hook time for excavators per shift is 0.5 hours.

[0140] Assume the population size is 100, the crossover rate is 0.7, the mutation rate is 0.05, and the maximum number of iterations is 100. The number of trucks is 30, 45, and 60, and the number of excavators is 5. Assume the excavators are fixed in position, meaning they are not constantly scheduled. Use MATLAB to implement an improved genetic algorithm and obtain a scheduling solution.

[0141] The comparison of iterative convergence of the genetic algorithm transportation cost with 30 trucks is shown in the figure below. Figure 4 As shown in the figure, the total transportation cost per shift is 136,582 yuan using the traditional genetic algorithm, 129,545 yuan using the improved genetic algorithm, and 141,500 yuan using the on-site fixed solution. The improved genetic algorithm saves 8.4% compared to the on-site fixed solution and 5.2% compared to the conventional genetic algorithm. The figure shows that the improved genetic algorithm converges to a minimum after approximately 40 iterations, while the traditional genetic algorithm converges to a minimum after approximately 60 iterations. The two algorithms have different initial values ​​at iteration 0. This is because different genetic algorithms use different strategies or methods to generate initial solutions when initializing the population. These initial solutions may have different fitness, resulting in different initial values ​​in the iterative convergence graph.

[0142] The comparison of iterative convergence of the genetic algorithm transportation cost with 45 trucks is shown in the figure below. Figure 5As shown in the figure, using the traditional genetic algorithm, the total transportation cost per shift is 202,034 yuan, using the improved genetic algorithm, the total transportation cost per shift is 194,298 yuan, and using the on-site fixed solution, the total transportation cost per shift is 212,250 yuan. The improved genetic algorithm saves 8.5% compared to the on-site fixed solution and 3.8% compared to the traditional genetic algorithm. As can be seen from the figure, the improved genetic algorithm converges to the minimum after about 40 iterations, while the traditional genetic algorithm converges to the minimum after about 80 iterations.

[0143] The comparison of iterative convergence of the genetic algorithm transportation cost with 60 trucks is shown in the figure below. Figure 6 As shown in the figure, using the traditional genetic algorithm, the total transportation cost per shift is 259,581 yuan, using the improved genetic algorithm, the total transportation cost per shift is 249,651 yuan, and using the on-site fixed solution, the total transportation cost per shift is 280,000 yuan. The improved genetic algorithm saves 10.8% compared to the on-site fixed solution and 3.8% compared to the traditional genetic algorithm. As can be seen from the figure, the improved genetic algorithm converges to the minimum after about 50 iterations, while the traditional genetic algorithm converges to the minimum after about 60 iterations.

[0144] The truck waiting time and excavator hook time using the three different methods mentioned above are as follows: Figure 7 As shown in the figure, when the number of trucks is 30, the use of the improved genetic algorithm saves 11.3% compared with the on-site fixed solution and 6.5% compared with the traditional genetic algorithm; when the number of trucks is 45, the use of the improved genetic algorithm saves 12.3% compared with the on-site fixed solution and 5.1% compared with the traditional genetic algorithm; when the number of trucks is 60, the use of the improved genetic algorithm saves 11.5% compared with the on-site fixed solution and 6.2% compared with the traditional genetic algorithm.

[0145] In summary, the improved genetic algorithm of the present invention has a significant improvement in transportation cost, truck waiting time and excavator hook time compared to the on-site fixed solution, and it has also made considerable improvements compared to the traditional genetic algorithm. Figures 4 to 6 It can also be seen from the figure that the improved genetic algorithm converges faster than the traditional genetic algorithm.

[0146] Therefore, compared with the traditional scheduling method, the present invention has the following advantages:

[0147] First, for open-pit mine truck transportation scheduling, a truck scheduling scheme was developed with the goals of minimizing total transportation costs and reducing truck waiting time and excavator hook time. This minimized truck transportation costs, truck waiting time, and excavator hook time. This scheduling scheme addressed the issue of excessive truck waiting time for loading caused by improper optimization of vehicle-shovel collaboration, maximizing production and minimizing equipment idleness to achieve the goal of optimizing truck and excavator collaborative efficiency.

[0148] Second, when using the improved genetic algorithm to solve the truck scheduling solution, variable-length symbol encoding is used. This encoding method allows the length of the code to be flexibly adjusted according to the characteristics and needs of the problem. Compared with fixed-length encoding, variable-length encoding can more efficiently utilize space, especially for problems with large variations in the number of features. For problems that require high-precision representation, variable-length encoding can provide a more sophisticated encoding method. By increasing the length of the code, the accuracy of the representation can be improved, thereby more accurately reflecting the characteristics of the problem;

[0149] Third, in the selection process, a combination of roulette wheel selection and elite retention strategy is adopted. This method can effectively balance the diversity of the population and the convergence of the algorithm in the genetic algorithm, which can not only prevent the algorithm from falling into the local optimal solution, but also ensure that the algorithm can converge to the global optimal solution, thereby improving the performance and efficiency of the algorithm.

[0150] Finally, the problem was solved through simulation, and experiments proved that the above scheduling scheme can better solve the open-pit mine truck scheduling problem.

[0151] Based on any of the above embodiments, the present invention further provides a mining vehicle dispatching device, Figure 8 This is a schematic diagram of the structure of the mine vehicle dispatching device provided by the present invention. Figure 8 As shown, the device includes:

[0152] The code acquisition module 310 is used to obtain the scheduling information of the unloading point, the excavator, and the truck, and to perform symbol coding on the unloading point, the excavator, and the truck according to the scheduling information, to obtain a first symbol code corresponding to the unloading point, a second symbol code corresponding to the excavator, and a third symbol code corresponding to the truck;

[0153] A population generation module 320 is configured to generate an initial population based on the first symbol code, the second symbol code, and the third symbol code, wherein the individuals in the initial population represent a scheduling solution consisting of a scheduling path sequence corresponding to all third symbol codes, wherein the scheduling path sequence corresponding to each third symbol code includes at least one scheduling path consisting of a pair of the first symbol code and the second symbol code;

[0154] A function construction module 330 is configured to construct an objective function under a first constraint condition with minimizing the total transportation cost of the scheduling solution as an optimization goal, where the first constraint condition is a constraint condition of the scheduling solution;

[0155] A solution acquisition module 340 is configured to iteratively evolve the initial population using a genetic algorithm based on the objective function until a preset termination condition is reached to obtain an optimal scheduling solution; and

[0156] The scheduling module 350 is configured to output the optimal scheduling solution in a preset output manner, so as to schedule the trucks according to the optimal scheduling solution.

[0157] The device provided by an embodiment of the present invention performs symbol encoding on the unloading point, excavator, and truck, and generates an initial population containing multiple scheduling path sequences based on these symbol encodings. Each scheduling path sequence represents a possible truck scheduling solution, including the detailed path of the truck from the excavator loading to the unloading point. Then, with the minimization of the total transportation cost of the scheduling solution as the optimization goal, an objective function of the first constraint condition is constructed. Finally, combined with this objective function, the initial population is iteratively evolved by using a genetic algorithm. Under the action of the genetic algorithm, the scheduling path of the truck in the scheduling solution will undergo operations such as selection, crossover, and mutation, thereby gradually approaching the optimal solution. When the preset termination condition is reached, an optimal scheduling solution will be output. This realizes the automation and intelligence of vehicle scheduling in open-pit mining and large-scale earthwork projects, not only improving the real-time and accuracy of scheduling, but also reducing costs.

[0158] The mine vehicle dispatching device described in this embodiment and the mine vehicle dispatching method provided by the present invention described above can refer to each other, and will not be described in detail here.

[0159] Figure 9 An example of a physical structure diagram of an electronic device is shown below. Figure 9 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440. The processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the mine vehicle dispatching method in each of the above embodiments.

[0160] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0161] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the mine vehicle scheduling method in the above-mentioned embodiments.

[0162] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the mine vehicle dispatching method in the above-mentioned embodiments is implemented.

[0163] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0164] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical coding feature diagrams therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A mine vehicle dispatching method, applied to computer equipment, characterized in that: include: Obtaining scheduling information of a loading point, an excavator, and a truck, and performing symbol coding on the loading point, the excavator, and the truck according to the scheduling information, to obtain a first symbol code corresponding to the loading point, a second symbol code corresponding to the excavator, and a third symbol code corresponding to the truck; generating an initial population based on the first symbol code, the second symbol code, and the third symbol code, wherein individuals in the initial population represent a scheduling solution consisting of scheduling path sequences corresponding to all third symbol codes, wherein the scheduling path sequence corresponding to each third symbol code includes at least one scheduling path consisting of a pair of the first symbol code and the second symbol code; Taking minimizing the total transportation cost of the scheduling plan as the optimization goal, constructing an objective function under a first constraint condition, where the first constraint condition is a constraint condition of the scheduling plan; Based on the objective function, the initial population is iteratively evolved using a genetic algorithm until a preset termination condition is reached, an optimal scheduling solution is obtained and output in a preset output mode, so as to schedule the trucks according to the optimal scheduling solution; The optimization goal is to minimize the total transportation cost of the scheduling scheme, and to construct an objective function under the first constraint condition, including: Determining a total transportation cost of the scheduling solution based on the heavy-load transportation cost and the empty-load transportation cost of the truck corresponding to each of the third symbol codes, and the heavy-load transportation cost and the empty-load transportation cost of the excavator corresponding to each of the second symbol codes in the scheduling path sequence corresponding to each of the third symbol codes; Taking minimizing the total transportation cost of the scheduling plan as the optimization goal, constructing an objective function under the first constraint condition; Among them, the first constraint condition includes at least one of path uniqueness constraint, vehicle load constraint, transportation demand constraint, vehicle quantity constraint, unloading point selection constraint, time allocation constraint, operation area constraint, vehicle type quantity constraint, loading point compatibility constraint, area allocation constraint, excavator allocation uniqueness constraint and pit compatibility constraint, and the objective function is used to determine the fitness of each individual in the initial population.

2. The mine vehicle dispatching method according to claim 1, characterized in that: The iterative evolution of the initial population using a genetic algorithm based on the objective function until a preset termination condition is met includes: Determining the fitness of each individual in the initial population based on the objective function; Based on the fitness of each individual in the initial population, an elite retention strategy is adopted to determine the first individual in the initial population; Determine a second individual in the initial population other than the first individual using a roulette wheel selection strategy based on the fitness of each individual in the initial population; Performing a crossover operation and a mutation operation on the second individual to obtain a third individual; Based on the third individual and the first individual, a new population is obtained, and the new population is used as the initial population. The step of determining the fitness of each individual in the initial population based on the objective function is returned to continue until a preset termination condition is reached.

3. The mine vehicle dispatching method according to claim 2, characterized in that: The method further comprises: Performing a crossover operation on the second individual to obtain a fourth individual, and performing a second constraint condition test on the fourth individual; If the fourth individual does not satisfy the second constraint condition, cyclically moving the position of the third symbol code in the fourth individual until the second constraint condition is satisfied; The second constraint condition is that the task start time of the truck corresponding to the third symbol code located at the last position in the individual is within a preset time window.

4. The mine vehicle dispatching method according to claim 3, characterized in that: The method further comprises: Determining a fifth individual selected for mutation from the fourth individual, and randomly selecting a mutation point from the scheduling path sequence corresponding to the fifth individual for mutation; Among them, when the variation point is the first symbol code corresponding to the first unloading point, the first symbol code corresponding to the first unloading point is randomly replaced by the first symbol code corresponding to the second unloading point; when the variation point is the second symbol code corresponding to the first excavator, the second symbol code corresponding to the first excavator is randomly replaced by the second symbol code corresponding to the second excavator.

5. The mine vehicle dispatching method according to claim 4, characterized in that: The fifth individual selected from the fourth individual for the mutation operation comprises: Randomly generating a random number between (0, 1) for the fourth individual obtained after the crossover operation, and comparing the random number with a preset mutation probability; If the random number is less than the preset mutation probability, the fourth individual is determined as the fifth individual to be subjected to the mutation operation.

6. The mine vehicle dispatching method according to claim 1, characterized in that: Also includes: Based on the third constraint, randomly generate a first dispatch path sequence for the first truck; Determine, based on the first dispatch path sequence of the first truck, a second dispatch path sequence for a second truck other than the first truck, wherein the second dispatch path sequence is the same as the first dispatch path sequence; generating an initial population based on the first dispatching route sequence of the first truck and the second dispatching route sequence of the second truck; The third constraint condition includes: After the current truck leaves the loading point corresponding to the current excavator, it goes to the unloading point that is not currently occupied by other trucks; After the current truck leaves the current unloading point, it goes to the loading point corresponding to the excavator that is not currently occupied by other trucks, or goes to the loading point corresponding to the excavator that meets the preset loading waiting time.

7. A mine vehicle dispatching device, characterized in that: include: a code acquisition module, configured to acquire scheduling information of a loading point, an excavator, and a truck, and to perform symbol coding on the loading point, the excavator, and the truck according to the scheduling information, to obtain a first symbol code corresponding to the loading point, a second symbol code corresponding to the excavator, and a third symbol code corresponding to the truck; a population generation module, configured to generate an initial population based on the first symbol code, the second symbol code, and the third symbol code, wherein individuals in the initial population represent a scheduling solution consisting of a scheduling path sequence corresponding to all third symbol codes, wherein the scheduling path sequence corresponding to each third symbol code includes at least one scheduling path consisting of a pair of the first symbol code and the second symbol code; a function construction module, configured to construct an objective function under a first constraint condition with minimizing the total transportation cost of the scheduling solution as an optimization goal, where the first constraint condition is a constraint condition of the scheduling solution; a scheme acquisition module, configured to iteratively evolve the initial population using a genetic algorithm based on the objective function until a preset termination condition is reached to obtain an optimal scheduling scheme; and A scheduling module, configured to output the optimal scheduling plan in a preset output manner, so as to schedule the trucks according to the optimal scheduling plan; The optimization goal is to minimize the total transportation cost of the scheduling scheme, and to construct an objective function under the first constraint condition, including: Determining a total transportation cost of the scheduling solution based on the heavy-load transportation cost and the empty-load transportation cost of the truck corresponding to each of the third symbol codes, and the heavy-load transportation cost and the empty-load transportation cost of the excavator corresponding to each of the second symbol codes in the scheduling path sequence corresponding to each of the third symbol codes; Taking minimizing the total transportation cost of the scheduling plan as the optimization goal, constructing an objective function under the first constraint condition; Among them, the first constraint condition includes at least one of path uniqueness constraint, vehicle load constraint, transportation demand constraint, vehicle quantity constraint, unloading point selection constraint, time allocation constraint, operation area constraint, vehicle type quantity constraint, loading point compatibility constraint, area allocation constraint, excavator allocation uniqueness constraint and pit compatibility constraint, and the objective function is used to determine the fitness of each individual in the initial population.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the mine vehicle dispatching method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the mine vehicle dispatching method according to any one of claims 1 to 6 is implemented.

Images