Material supply method and system

Abstract

The invention discloses a material supply method and system, and the method comprises the steps: obtaining scene parameters, and generating an initial population; calculating a first adaptive value of the initial population; preprocessing the initial population to obtain a first population, and calculating a second adaptive value of the first population; combining the initial population with the first population to obtain a second population, and screening the second population to obtain a third population; performing neighborhood search on the feasible solution of the third population to obtain a fourth population, and calculating a third adaptive value of the fourth population; combining the third population and the fourth population to obtain a fifth population, screening the fifth population to obtain a sixth population, and calculating a fourth adaptive value of the sixth population; obtaining a current iteration frequency, and if the current iteration frequency is smaller than a preset iteration frequency, repeating the above steps until the current iteration frequency is equal to the preset iteration frequency; and selecting a minimum value from all the adaptive values, and obtaining pareto leading edge data corresponding to the minimum value so as to obtain a target supply scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of material supply, and in particular to a material supply method and system. Background Art

[0002] In reality, the logistics system for material transmission includes at least nodes that need materials, vehicles that deliver materials, and material transfer stations. In the existing technology, the material supply plan planning is mostly focused on the shortest path, shortest time, etc. In certain scenarios, the material transfer station in the logistics system may fail. The existing technical solution needs to eliminate the failed material transfer station and then plan the material supply plan focusing on the shortest path, shortest time, etc., that is, re-plan the plan, and then the logistics system shows problems such as slow response, mismatch between supply and demand, and low distribution efficiency. Summary of the invention

[0003] Based on this, it is necessary to propose a material supply method and system to address the technical problems of the existing logistics system such as slow response, mismatch between supply and demand, and low distribution efficiency when the transfer station fails.

[0004] In a first aspect, a material supply method is provided, the method comprising:

[0005] Obtaining scenario parameters of a target material supply scenario, and generating an initial population by genetic coding according to the scenario parameters;

[0006] Calculating a first fitness value of the initial population under preset constraints by using a preset objective function;

[0007] Performing selection, crossover, and mutation processing on individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraint conditions through the preset objective function;

[0008] The initial population and the first population are combined to obtain a second population, and the second population is subjected to a first population screening to obtain a third population;

[0009] Performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition through the preset objective function;

[0010] The third population and the fourth population are combined to obtain a fifth population, and the fifth population is screened for a second time to obtain a sixth population, and a fourth fitness value of the sixth population under the preset constraint condition is calculated by the preset objective function;

[0011] Obtaining the current number of iterations, if the current number of iterations is less than the preset number of iterations, taking the sixth population as the initial population, continuing the steps of selecting, crossovering, and mutating the individuals in the initial population, and recording the fitness value set when the sixth population is used as the initial population, until the current number of iterations is equal to the preset number of iterations;

[0012] A minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and pareto frontier data corresponding to the minimum value is obtained, and a target supply plan is obtained according to the pareto frontier data.

[0013] Optionally, the step of obtaining scene parameters of the target material supply scene and generating an initial population by genetic coding according to the scene parameters includes:

[0014] Obtaining scenario parameters of the target material supply scenario, the scenario parameters including: the matching relationship between demand points and delivery vehicles, the matching relationship between vehicles and transfer stations, the distribution sequence matrix of demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered;

[0015] An initial population is generated by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered.

[0016] Optionally, the step of generating an initial population by means of genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery sequence matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered includes:

[0017] Generate a first individual set in a random generation strategy by means of genetic coding according to the matching relationship between the demand point and the delivery vehicle, the matching relationship between the vehicle and the transfer station, the delivery order matrix of the demand point, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered;

[0018] Generate a second set of individuals in a greedy generation strategy by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered;

[0019] The initial population is generated based on the first individual set and the second individual set.

[0020] Optionally, the step of calculating the first fitness value of the initial population under preset constraints by using a preset objective function includes:

[0021] By the preset objective function:

[0022]

[0023] Calculate the first fitness value of the initial population under the preset constraints, where ω is the failure scenario, P ω is the probability of failure scenario, Cost ω is the total cost after temporary adjustment for failure scenario ω, Rate ω The failure scenario ω is satisfactory after temporary adjustment. The preset constraints include the demand for materials, the vehicle loading capacity, the vehicle departure and return conditions at the same node, the vehicle's trip continuity, the time to reach the node, the transfer station condition where the vehicle is prohibited from driving, and the vehicle loading capacity on the effective path.

[0024] Optionally, the step of performing selection, crossover and mutation processing on individuals in the initial population to obtain a first population includes:

[0025] Selecting parent individuals from the initial population by tournament selection;

[0026] According to a preset crossover probability, a exchange individual is selected from the initial population by uniform crossover, and an intermediate population is constructed based on the parent individual and the exchange individual;

[0027] The intermediate population is mutated according to a preset mutation rule to obtain the first population.

[0028] Optionally, the step of performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population includes:

[0029] According to the first rule in the preset rules, the route that only delivers one node is deleted from the feasible solutions of the third population to obtain a first initial feasible solution;

[0030] According to a second rule in the preset rules, the farthest node on each route in the initial feasible solution is reallocated to obtain a second initial feasible solution;

[0031] According to the third rule in the preset rules, the shortest path is searched for each path in the second initial feasible solution to obtain a fourth population.

[0032] Optionally, the step of performing a first population screening on the second population to obtain a third population comprises:

[0033] The second population is screened for the first time by using the elite retention strategy and the crowding distribution strategy to obtain the third population.

[0034] In a second aspect, the present application provides a material supply device, the device comprising:

[0035] A data acquisition module, used to obtain scenario parameters of a target material supply scenario, and generate an initial population by genetic coding according to the scenario parameters;

[0036] A first calculation module, used for calculating a first fitness value of the initial population under preset constraints through a preset objective function;

[0037] A second calculation module is used to select, crossover and mutate the individuals in the initial population to obtain a first population, and calculate a second fitness value of the first population under the preset constraint conditions through the preset objective function;

[0038] a third calculation module, configured to merge the initial population and the first population to obtain a second population, and perform a first population screening on the second population to obtain a third population;

[0039] a fourth calculation module, configured to perform a neighborhood search on a feasible solution of the third population according to a preset rule to obtain a fourth population, and calculate a third fitness value of the fourth population under the preset constraint condition through the preset objective function;

[0040] a fifth calculation module, configured to merge the third population and the fourth population to obtain a fifth population, perform a second population screening on the fifth population to obtain a sixth population, and calculate a fourth fitness value of the sixth population under the preset constraint conditions through the preset objective function;

[0041] an iteration module, configured to obtain a current number of iterations, and if the current number of iterations is less than the preset number of iterations, use the sixth population as the initial population, continue the steps of selecting, crossover, and mutation processing the individuals in the initial population, and record a fitness value set when the sixth population is used as the initial population, until the current number of iterations is equal to the preset number of iterations;

[0042] A solution output module is used to select a minimum value among the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain the Pareto frontier data corresponding to the minimum value, and obtain a target supply solution according to the Pareto frontier data.

[0043] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned material supply method are implemented.

[0044] The present application obtains scenario parameters of a target material supply scenario, and generates an initial population by means of genetic coding according to the scenario parameters; calculates a first fitness value of the initial population under preset constraints by means of a preset objective function; performs selection, crossover, and mutation processing on individuals in the initial population to obtain a first population, and calculates a second fitness value of the first population under the preset constraints by means of the preset objective function; merges the initial population and the first population to obtain a second population, and performs a first population screening on the second population to obtain a third population; performs a neighborhood search on feasible solutions of the third population according to preset rules to obtain a fourth population, and calculates a third fitness value of the fourth population under the preset constraints by means of the preset objective function; merges the third population and the fourth population to obtain to the fifth population, and perform a second population screening on the fifth population to obtain the sixth population, and calculate the fourth fitness value of the sixth population under the preset constraint conditions through the preset objective function; obtain the current number of iterations, if the current number of iterations is less than the preset number of iterations, then use the sixth population as the initial population, continue the steps of selecting, crossing, and mutating the individuals in the initial population, and record the fitness value set when the sixth population is the initial population, until the current number of iterations is equal to the preset number of iterations; select the minimum value among the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain the Pareto frontier data corresponding to the minimum value, and obtain the target supply plan according to the Pareto frontier data. In the process of formulating the material supply plan, the scenario of transfer station failure is considered, and through overall planning, human transportation capacity is reasonably arranged to reduce costs on the basis of ensuring timeliness. At the same time, when a transfer station fails, there is no need to plan the plan again. You can directly output the material supply plan that takes the transfer station failure into consideration when formulating the material supply plan, thereby avoiding problems such as slow response of the logistics system, mismatch between supply and demand, and low distribution efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] in:

[0047] Figure 1 A flow chart of a material supply method in one embodiment;

[0048] Figure 2 A schematic diagram of an encoding result in a material supply method in one embodiment;

[0049] Figure 3 A flowchart of fitness value calculation in a material supply method in one embodiment;

[0050] Figure 4 It is a structural block diagram of a material supply device in one embodiment;

[0051] Figure 5 is a structural block diagram of a computer device in one embodiment;

[0052] Figure 6 It is a structural block diagram of a computer device in another embodiment. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not 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.

[0054] The present invention is described in detail below through specific embodiments.

[0055] See also Figure 1 As shown, Figure 1 A schematic flow chart of a material supply method provided in an embodiment of the present invention includes the following steps:

[0056] S101, obtaining scenario parameters of a target material supply scenario, and generating an initial population by genetic coding according to the scenario parameters;

[0057] In a possible implementation, the step of obtaining scene parameters of the target material supply scene and generating an initial population by genetic coding according to the scene parameters includes:

[0058] Obtaining scenario parameters of the target material supply scenario, the scenario parameters including: the matching relationship between demand points and delivery vehicles, the matching relationship between vehicles and transfer stations, the distribution sequence matrix of demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered;

[0059] An initial population is generated by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered.

[0060] Exemplarily, the scenario parameters include: the number of warehouses in the secondary supply network, the number of optional transfer stations, the number of demand points to be delivered and the two-dimensional coordinates of each node location; the parameters include the demand volume of each demand point, the current infection rate, the satisfaction time threshold, the capacity, usage cost, transportation cost, average speed of the first and second level distribution vehicles, and the operating cost of the transfer station. The scenario parameters also include: calculating the failure probability of the transfer station through the current infection rate; calculating the distance matrix of the first and second level networks through the two-dimensional coordinates of the nodes, and the distance matrix of the first and second level networks is used to calculate the computational cost.

[0061] For example, a combination of the matching relationship between the demand point and the delivery vehicle and the matching relationship between the vehicle and the transfer station is used, and then the delivery order matrix of the demand point is encoded according to the matching relationship between the demand point and the delivery vehicle and the matching relationship between the vehicle and the transfer station, such as Figure 2 As shown. According to the gene encoding method, N individuals (initial population) are initially generated. The gene decoding is to convert the chromosome represented by the gene into the final overall plan for the emergency warehouse site selection and distribution path. The matching gene of the vehicle and the emergency warehouse is decoded to obtain the selected emergency warehouse node, and then the complete distribution path of each vehicle after departing from the emergency warehouse and the distribution order of the demand points are decoded according to the distribution order gene of the demand points. .

[0062] S102, calculating a first fitness value of the initial population under preset constraints by using a preset objective function;

[0063] In a possible implementation, the step of calculating the first fitness value of the initial population under preset constraints by using a preset objective function includes:

[0064] By the preset objective function:

[0065]

[0066] Calculate the first fitness value of the initial population under the preset constraints, where ω is the failure scenario, P ω is the probability of failure scenario, Cost ω is the total cost after temporary adjustment for failure scenario ω, Rate ωThe failure scenario ω is satisfactory after temporary adjustment. The preset constraints include the demand for materials, the vehicle loading capacity, the vehicle departure and return conditions at the same node, the vehicle's trip continuity, the time to reach the node, the transfer station condition where the vehicle is prohibited from driving, and the vehicle loading capacity on the effective path.

[0067] Exemplarily, the mathematical representation of the preset constraint condition is:

[0068]

[0069]

[0070] Constraints are imposed on the demand for materials, the load capacity of vehicles, the restriction of vehicles' departure and return to the same node, the continuity of vehicles' journeys, the time of arrival at nodes, the transfer stations where vehicle bans are invalid, and the load capacity of vehicles on effective paths.

[0071] S103, performing selection, crossover, and mutation processing on individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraint conditions by using the preset objective function;

[0072] In a possible implementation, the step of performing selection, crossover, and mutation processing on individuals in the initial population to obtain the first population includes:

[0073] Selecting parent individuals from the initial population by tournament selection;

[0074] According to a preset crossover probability, a exchange individual is selected from the initial population by uniform crossover, and an intermediate population is constructed based on the parent individual and the exchange individual;

[0075] The intermediate population is mutated according to a preset mutation rule to obtain the first population.

[0076] For example, the parent individuals are first selected from the population by tournament selection, and then the uniform crossover method is used to select each group of genes with a crossover probability p. s After deciding whether to exchange, a mutation operation is then used to generate a new population (the first population). The mutation operation is to randomly select one operation from the set of candidate operations to execute, and then decide whether to execute other operations with a probability of 50%.

[0077] The set of operations to be selected includes:

[0078] Randomly exchange the demand points and starting transfer stations of the two vehicles.

[0079] Randomly swap the starting transfer stations of the two vehicles.

[0080] Randomly exchange the delivery demand points of the two vehicles.

[0081] Randomly change the delivery vehicle of a demand point.

[0082] After the cross-mutation operation, the feasibility of the solution needs to be repaired, the overloaded and over-threshold demand points need to be reallocated, and then the distribution order of the primary and secondary networks is generated according to the shortest circuit path algorithm.

[0083] S104, merging the initial population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population;

[0084] In a possible implementation, the step of performing a first population screening on the second population to obtain a third population includes:

[0085] The second population is screened for the first time by using the elite retention strategy and the crowding distribution strategy to obtain the third population.

[0086] Exemplarily, the first population screening is non-dominated elite screening. Specifically, the Pareto frontiers of various levels of the population are obtained by using fast non-dominated sorting, and then the top N individuals are screened out by using elite retention strategy and crowding distribution strategy.

[0087] S105, performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition by using the preset objective function;

[0088] In a possible implementation manner, the step of performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population includes:

[0089] According to the first rule in the preset rules, the route that only delivers one node is deleted from the feasible solutions of the third population to obtain a first initial feasible solution;

[0090] According to a second rule in the preset rules, the farthest node on each route in the initial feasible solution is reallocated to obtain a second initial feasible solution;

[0091] According to the third rule in the preset rules, the shortest path is searched for each path in the second initial feasible solution to obtain a fourth population.

[0092] For example, the destruction operation is to delete the route that only delivers one node, and set the state of this demand point to empty; at the same time, delete the farthest node of each path from the route, and set the state to empty. Repair operator: minimum cost insertion. After the destruction operation, the demand point with empty state traverses the paths allowed by capacity for minimum cost insertion to determine the secondary network distribution route. After all the demand points with empty state are reallocated, the primary network distribution route is replanned according to the new transfer station. The exact algorithm for the shortest circuit path is implemented for each route of the secondary network.

[0093] S106, merging the third population and the fourth population to obtain a fifth population, performing a second population screening on the fifth population to obtain a sixth population, and calculating a fourth fitness value of the sixth population under the preset constraint condition by using the preset objective function;

[0094] Exemplarily, the second population screening is non-dominated elite screening. Specifically, the Pareto frontiers of various levels of the population are obtained by using fast non-dominated sorting, and then the top N individuals are screened out by the elite retention strategy and the crowding distribution strategy.

[0095] S107, obtaining the current number of iterations, and if the current number of iterations is less than the preset number of iterations, taking the sixth population as the initial population, continuing the steps of selecting, crossovering, and mutating the individuals in the initial population, and recording the fitness value set when the sixth population is used as the initial population, until the current number of iterations is equal to the preset number of iterations;

[0096] S108. Select a minimum value among the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, obtain Pareto frontier data corresponding to the minimum value, and obtain a target supply plan according to the Pareto frontier data.

[0097] The scenario parameters of the target material supply scenario are obtained, and an initial population is generated by genetic coding according to the scenario parameters; a first fitness value of the initial population under preset constraints is calculated by a preset objective function; individuals in the initial population are selected, crossed, and mutated to obtain a first population, and a second fitness value of the first population under the preset constraints is calculated by the preset objective function; the initial population and the first population are merged to obtain a second population, and the second population is screened for the first time to obtain a third population; a neighborhood search is performed on feasible solutions of the third population according to preset rules to obtain a fourth population, and a third fitness value of the fourth population under the preset constraints is calculated by the preset objective function; the third population and the fourth population are merged to obtain a fourth population. Five populations, and perform a second population screening on the fifth population to obtain the sixth population, and calculate the fourth fitness value of the sixth population under the preset constraint conditions through the preset objective function; obtain the current number of iterations, if the current number of iterations is less than the preset number of iterations, use the sixth population as the initial population, continue the steps of selecting, crossing, and mutating the individuals in the initial population, and record the fitness value set when the sixth population is the initial population until the current number of iterations is equal to the preset number of iterations; select the minimum value among the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain the Pareto frontier data corresponding to the minimum value, and obtain the target supply plan according to the Pareto frontier data. In the process of formulating the material supply plan, the scenario of transfer station failure is considered, and through overall planning, human transportation capacity is reasonably arranged to reduce costs on the basis of ensuring timeliness. At the same time, when a transfer station fails, there is no need to plan the plan again. You can directly output the material supply plan that takes the transfer station failure into consideration when formulating the material supply plan, thereby avoiding problems such as slow response of the logistics system, mismatch between supply and demand, and low distribution efficiency.

[0098] In a possible implementation, the step of generating an initial population by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery sequence matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered includes:

[0099] Generate a first individual set in a random generation strategy by means of genetic coding according to the matching relationship between the demand point and the delivery vehicle, the matching relationship between the vehicle and the transfer station, the delivery order matrix of the demand point, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered;

[0100] Generate a second set of individuals in a greedy generation strategy by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered;

[0101] The initial population is generated based on the first individual set and the second individual set.

[0102] Exemplarily, a greedy strategy is used to generate 30% of the initial individuals in an orderly manner to ensure the effectiveness and quality of the initial population. Secondly, a random generation strategy is used to generate the remaining 70% of the initial individuals to maintain the diversity of the initial population.

[0103] Greedy generation strategy:

[0104] Generate matching genes between demand points and vehicles. Allocate each demand point to a vehicle for delivery without exceeding the vehicle's capacity limit and delivery threshold.

[0105] Select the transfer station and complete the secondary network path planning. Traverse each transfer station for each vehicle's delivery route, use the greedy algorithm to solve the shortest tour route, select the transfer station with the minimum distance cost, and encode the demand point delivery order gene matrix.

[0106] Complete the first-level network path planning. Through the arrangement of the above-mentioned second-level supply network, the demand of each transfer station is obtained, and the shortest tour route is solved by dynamic programming.

[0107] Random generation strategy:

[0108] Generate matching genes for vehicles and transfer stations. Randomly assign transfer stations to each vehicle in the secondary network. (Set a probability limit of no more than 25% for vehicles to be used)

[0109] Generate matching genes between demand points and vehicles. In the above list of used vehicles, each demand point is assigned to a vehicle for delivery without exceeding the vehicle capacity limit and delivery threshold.

[0110] Complete secondary network path planning. Use the greedy algorithm to solve the shortest tour route and encode the genetic matrix of the distribution order of the demand point.

[0111] Complete the first-level network path planning. Through the arrangement of the above-mentioned second-level supply network, the demand of each transfer station is obtained, and the shortest tour route is solved using the dynamic programming method.

[0112] In a possible implementation, in the face of emergency material supply, the cost is controlled on the basis of pursuing the highest possible time efficiency, and the dual-objective optimization of maximizing final demand satisfaction and minimizing total cost is achieved.

[0113] The total cost includes the transportation costs of primary and secondary distribution, the vehicle usage costs of primary and secondary distribution, and the fixed costs of transfer station operations.

[0114]

[0115] The satisfaction of the demand point is obtained through the relationship between the arrival time and the time threshold, and the sum of the satisfaction evaluations of all demand points is taken as the overall satisfaction index.

[0116]

[0117] First, the total cost and satisfaction of each solution after temporary adjustment under various failure scenarios are calculated, and then the expected total cost and satisfaction of the solution are obtained as evaluation indicators based on the failure probability of the failure scenario.

[0118] In one possible implementation, the probability of failure scenario ω occurring is:

[0119]

[0120] Cost ω 、Rate ω : Total cost and satisfaction after temporary adjustment of failure scenario ω.

[0121] In a possible implementation, Figure 3 As shown, a fitness value calculation process includes: judging whether all feasible solutions of the population have completed the fitness value calculation, and if so, outputting the fitness values ​​of all solutions; if not, reading a solution in the population, judging whether the selected solution has completed all failure scenarios, and if the selected solution has completed all failure scenarios, calculating the total cost expectation and satisfaction expectation of the selected solution; if the selected solution has not completed all failure scenarios, selecting the failure scenarios that the selected solution has not completed, making temporary adjustments to the unfinished failure scenarios, and calculating the total cost and satisfaction of the unfinished failure scenarios, until the selected solution completes all failure scenarios.

[0122] Second, as Figure 4 As shown, the present application provides a material supply device, the device comprising:

[0123] The data acquisition module 201 is used to obtain the scene parameters of the target material supply scene, and generate the initial population through genetic coding according to the scene parameters;

[0124] A first calculation module 202, used to calculate a first fitness value of the initial population under preset constraints through a preset objective function;

[0125] The second calculation module 203 is used to select, crossover and mutate the individuals in the initial population to obtain a first population, and calculate the second fitness value of the first population under the preset constraint conditions through the preset objective function;

[0126] A third calculation module 204 is used to merge the initial population and the first population to obtain a second population, and perform a first population screening on the second population to obtain a third population;

[0127] A fourth calculation module 205 is used to perform a neighborhood search on a feasible solution of the third population according to a preset rule to obtain a fourth population, and calculate a third fitness value of the fourth population under the preset constraint condition through the preset objective function;

[0128] a fifth calculation module 206, configured to merge the third population and the fourth population to obtain a fifth population, perform a second population screening on the fifth population to obtain a sixth population, and calculate a fourth fitness value of the sixth population under the preset constraint condition by using the preset objective function;

[0129] Iteration module 207, used to obtain the current iteration number, if the current iteration number is less than the preset iteration number, take the sixth population as the initial population, continue the steps of selecting, crossover and mutation processing the individuals in the initial population, and record the fitness value set when the sixth population is used as the initial population, until the current iteration number is equal to the preset iteration number;

[0130] The solution output module 208 is used to select a minimum value among the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain the Pareto frontier data corresponding to the minimum value, and obtain a target supply solution according to the Pareto frontier data.

[0131] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements a function or step on the service side of a material supply method.

[0132] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of the client side of a material supply method.

[0133] In one embodiment, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: calculating a first fitness value of the initial population under preset constraints by using a preset objective function; performing selection, crossover, and mutation processing on individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraints by using the preset objective function; merging the initial population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population; performing a neighborhood search on feasible solutions of the third population according to preset rules to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraints by using the preset objective function; The three populations are merged with the fourth population to obtain a fifth population, and the fifth population is screened for a second time to obtain a sixth population, and the fourth fitness value of the sixth population under the preset constraints is calculated through the preset objective function; the current number of iterations is obtained, and if the current number of iterations is less than the preset number of iterations, the sixth population is used as the initial population, and the steps of selecting, crossovering, and mutating the individuals in the initial population are continued, and the fitness value set when the sixth population is used as the initial population is recorded until the current number of iterations is equal to the preset number of iterations; the minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and the Pareto frontier data corresponding to the minimum value is obtained, and the target supply plan is obtained according to the Pareto frontier data.

[0134] In one embodiment, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented: calculating a first fitness value of the initial population under preset constraints by using a preset objective function; performing selection, crossover, and mutation processing on individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraints by using the preset objective function; merging the initial population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population; performing a neighborhood search on feasible solutions of the third population according to preset rules to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraints by using the preset objective function; combining the third population and the first population to obtain a second population, and performing a first population screening on the second population to obtain a third population; performing a neighborhood search on feasible solutions of the third population according to preset rules to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraints by using the preset objective function; combining the third population and the first population Four populations are merged to obtain a fifth population, and the fifth population is screened for a second time to obtain a sixth population, and the fourth fitness value of the sixth population under the preset constraints is calculated through the preset objective function; the current number of iterations is obtained, and if the current number of iterations is less than the preset number of iterations, the sixth population is used as the initial population, and the steps of selecting, crossovering, and mutating the individuals in the initial population are continued, and the fitness value set when the sixth population is used as the initial population is recorded until the current number of iterations is equal to the preset number of iterations; the minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and the Pareto frontier data corresponding to the minimum value is obtained, and the target supply plan is obtained according to the Pareto frontier data.

[0135] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0136] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0137] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0138] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A material supply method, characterized in that: The method comprises: Obtaining scenario parameters of a target material supply scenario, and generating an initial population by genetic coding according to the scenario parameters; Calculating a first fitness value of the initial population under preset constraints by using a preset objective function; Performing selection, crossover, and mutation processing on individuals in the initial population to obtain a first population, and calculating a second fitness value of the first population under the preset constraint conditions through the preset objective function; The initial population and the first population are combined to obtain a second population, and the second population is subjected to a first population screening to obtain a third population; Performing a neighborhood search on feasible solutions of the third population according to a preset rule to obtain a fourth population, and calculating a third fitness value of the fourth population under the preset constraint condition through the preset objective function; The third population and the fourth population are combined to obtain a fifth population, and the fifth population is screened for a second time to obtain a sixth population, and a fourth fitness value of the sixth population under the preset constraint condition is calculated by the preset objective function; Obtaining the current number of iterations, if the current number of iterations is less than the preset number of iterations, taking the sixth population as the initial population, continuing the steps of selecting, crossovering, and mutating the individuals in the initial population, and recording the fitness value set when the sixth population is used as the initial population, until the current number of iterations is equal to the preset number of iterations; A minimum value is selected from the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and pareto frontier data corresponding to the minimum value is obtained, and a target supply plan is obtained according to the pareto frontier data.

2. The material supply method according to claim 1, characterized in that: The step of obtaining the scene parameters of the target material supply scene and generating the initial population by genetic coding according to the scene parameters includes: Obtaining scenario parameters of the target material supply scenario, the scenario parameters including: the matching relationship between demand points and delivery vehicles, the matching relationship between vehicles and transfer stations, the distribution sequence matrix of demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered; An initial population is generated by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered.

3. The material supply method according to claim 2, characterized in that: The step of generating an initial population by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery sequence matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered includes: Generate a first individual set in a random generation strategy by means of genetic coding according to the matching relationship between the demand point and the delivery vehicle, the matching relationship between the vehicle and the transfer station, the delivery order matrix of the demand point, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered; Generate a second set of individuals in a greedy generation strategy by genetic coding according to the matching relationship between the demand points and the delivery vehicles, the matching relationship between the vehicles and the transfer stations, the delivery order matrix of the demand points, the number of warehouses in the secondary supply network, the number of optional transfer stations, and the number of demand points to be delivered; The initial population is generated based on the first individual set and the second individual set.

4. The material supply method according to claim 1, characterized in that: The step of calculating the first fitness value of the initial population under preset constraints by using a preset objective function comprises: By the preset objective function: Calculate the first fitness value of the initial population under the preset constraints, where ω is the failure scenario, P ω is the probability of failure scenario, Cost ω is the total cost after temporary adjustment for failure scenario ω, Rate ω The failure scenario ω is satisfactory after temporary adjustment. The preset constraints include the demand for materials, the vehicle loading capacity, the vehicle departure and return conditions at the same node, the vehicle's trip continuity, the time to reach the node, the transfer station condition where the vehicle is prohibited from driving, and the vehicle loading capacity on the effective path.

5. The material supply method according to claim 1, characterized in that: The step of performing selection, crossover and mutation processing on the individuals in the initial population to obtain the first population includes: Selecting parent individuals from the initial population by tournament selection; According to a preset crossover probability, a exchange individual is selected from the initial population by uniform crossover, and an intermediate population is constructed based on the parent individual and the exchange individual; The intermediate population is mutated according to a preset mutation rule to obtain the first population.

6. The material supply method according to claim 1, characterized in that: The step of performing neighborhood search on feasible solutions of the third population according to preset rules to obtain a fourth population includes: According to the first rule in the preset rules, the route that only delivers one node is deleted from the feasible solutions of the third population to obtain a first initial feasible solution; According to a second rule in the preset rules, the farthest node on each route in the initial feasible solution is reallocated to obtain a second initial feasible solution; According to the third rule in the preset rules, the shortest path is searched for each path in the second initial feasible solution to obtain a fourth population.

7. The material supply method according to claim 1, characterized in that: The step of performing a first population screening on the second population to obtain a third population comprises: The second population is screened for the first time by using the elite retention strategy and the crowding distribution strategy to obtain the third population.

8. A material supply device, characterized in that: The device comprises: A data acquisition module, used to obtain scenario parameters of a target material supply scenario, and generate an initial population by genetic coding according to the scenario parameters; A first calculation module, used for calculating a first fitness value of the initial population under preset constraints through a preset objective function; A second calculation module is used to select, crossover and mutate the individuals in the initial population to obtain a first population, and calculate a second fitness value of the first population under the preset constraint conditions through the preset objective function; a third calculation module, configured to merge the initial population and the first population to obtain a second population, and perform a first population screening on the second population to obtain a third population; a fourth calculation module, configured to perform a neighborhood search on a feasible solution of the third population according to a preset rule to obtain a fourth population, and calculate a third fitness value of the fourth population under the preset constraint condition through the preset objective function; a fifth calculation module, configured to merge the third population and the fourth population to obtain a fifth population, perform a second population screening on the fifth population to obtain a sixth population, and calculate a fourth fitness value of the sixth population under the preset constraint conditions through the preset objective function; an iteration module, configured to obtain a current number of iterations, and if the current number of iterations is less than the preset number of iterations, use the sixth population as the initial population, continue the steps of selecting, crossover, and mutation processing the individuals in the initial population, and record a fitness value set when the sixth population is used as the initial population, until the current number of iterations is equal to the preset number of iterations; A solution output module is used to select a minimum value among the first fitness value, the second fitness value, the third fitness value, the fourth fitness value and the fitness value set, and obtain the Pareto frontier data corresponding to the minimum value, and obtain a target supply solution according to the Pareto frontier data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the material supply method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the material supply method according to any one of claims 1 to 7 are implemented.

Images