Manufacturing resource optimization method and device, storage medium and electronic equipment

Abstract

The embodiment of the application discloses an optimization method and device of manufacturing resources, a storage medium and an electronic device, and belongs to the computer field. Order demand information is decomposed into multiple manufacturing tasks, and a chromosome is constructed. The number of gene groups included in the chromosome is equal to the number of manufacturing tasks, each gene group in the chromosome contains a manufacturing task serial number, an atomic manufacturing task serial number and an atomic manufacturing service serial number, and a primary population of individuals containing the above chromosome structure is iteratively processed by using a genetic algorithm to obtain an optimal solution for processing multiple manufacturing tasks. In this way, when a manufacturing enterprise produces and sells in the market, the manufacturing resources are optimized in combination with supplier raw materials, production base capacity, warehouse storage and transportation tool constraints, so that the total cost and total time are minimized, and the market competitiveness of the manufacturing enterprise is improved.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly to a method, apparatus, storage medium, and electronic device for optimizing manufacturing resources. Background Technology

[0002] With globalization, international trade is becoming increasingly frequent. When receiving and processing order requests, companies strive to minimize service costs and delivery times to achieve higher profits and better customer satisfaction. However, the entire upstream and downstream chain of order requests is lengthy, and many factors influence the cost and time of order requests. Therefore, finding the optimal solution based on these factors is a pressing issue that needs to be addressed. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides a method, apparatus, storage medium, and electronic device for optimizing manufacturing resources, thereby resolving the optimization problems of manufacturing resources in the prior art.

[0004] In a first aspect, this application provides a method for optimizing manufacturing resources, comprising:

[0005] Decompose the order demand information into I manufacturing tasks; where I ≥ 1 and I is an integer;

[0006] An initial population is randomly generated; wherein the initial population contains multiple individuals, and each individual's chromosome includes I genomes, and each genome contains: manufacturing task number i, atom manufacturing task number j, and atom manufacturing service number k. ij ; 1≤i≤I, and are integers; the atomic manufacturing task set contains A atomic manufacturing tasks, 1≤j≤A, and j is an integer; the atomic manufacturing service set includes: procurement tasks, production tasks, warehousing tasks, and transportation tasks; the number of atomic manufacturing service sets for atomic manufacturing task number j is B. ij ; 1≤k ij ≤B ij And k ij It is an integer;

[0007] Determine the fitness function; wherein the fitness function is used to constrain the total cost and total time of the I manufacturing tasks to be minimized;

[0008] A genetic algorithm is used to iteratively process individual selection and chromosome evolution in the first generation population;

[0009] After the preset conditions are met, the iteration stops, and the individual with the highest fitness in the current population is obtained;

[0010] The optimal solution for the I manufacturing tasks is determined based on the chromosome of the individual with the highest fitness.

[0011] In one possible design, the fitness function is expressed using the following formula:

[0012] minF = ω1*C + ω2*T; where minF represents the evaluation value, C represents the total cost, T represents the total time, ω1 + ω2 = 1, ω1 and ω2 represent the weights of the total cost and the total time, respectively. The total cost includes material procurement cost, transportation cost and warehouse storage cost, and the total time includes production response time.

[0013] In one possible design, the means of transportation is a ship;

[0014] The formula for calculating the material procurement cost is as follows: The formula for calculating the warehouse storage cost is as follows: The formula for calculating transportation costs

[0015] Where I represents the number of manufacturing tasks, i represents the atomic manufacturing task number, and j represents the atomic manufacturing service number. Let N be the decision variable, representing the selection of the k-th atomic manufacturing service from the corresponding atomic manufacturing service set for the j-th atomic manufacturing task i; M P represents the quantity of materials purchased. S S represents the warehousing cost per unit of material or finished product. S P is the storage space required for materials and finished products. V N represents the price of a ship's cargo space. V T represents the number of ships. W T is the waiting time required for production. S The service time required for production, i.e., the ship's service time.

[0016] In one possible design, the evolution of the chromosome includes:

[0017] Pair individuals in the population into twos;

[0018] For two paired individuals, one or more atomic manufacturing service serial numbers at the same position are randomly selected and swapped to obtain two new individuals.

[0019] In one possible design, the variations in the chromosome include:

[0020] The individual's atomic manufacturing service serial number changes randomly within a specified range of values.

[0021] In one possible design, the individual selection includes:

[0022] The fitness of each individual in the population is calculated based on the fitness function;

[0023] Individuals in the population are sorted in descending order based on their fitness.

[0024] Select the top M individuals; where M is an integer greater than 1.

[0025] In one possible design, the preset conditions include: reaching a preset number of iterations or the maximum fitness of multiple consecutive populations fluctuating within a specified range.

[0026] Secondly, this application provides a manufacturing resource optimization apparatus, comprising:

[0027] The decomposition unit is used to decompose order demand information into I manufacturing tasks;

[0028] A generation unit is used to randomly generate an initial population; wherein the initial population contains multiple individuals, and each individual's chromosome includes I genomes, and each genome contains: manufacturing task number i, atom manufacturing task number j, and atom manufacturing service number k. ij ; 1≤i≤I, and are integers; the atomic manufacturing task set contains A atomic manufacturing tasks, 1≤j≤A, and j is an integer; the atomic manufacturing service set includes: procurement tasks, production tasks, warehousing tasks, and transportation tasks; the number of atomic manufacturing service sets for atomic manufacturing task number j is B. ij ; 1≤k ij ≤B ij And k ij It is an integer;

[0029] A determining unit is used to determine a fitness function; wherein the fitness function is used to constrain the total cost and total time of the I manufacturing tasks to be minimized;

[0030] An iterative unit is used to perform iterative processing of individual selection and chromosome evolution on the first-generation population using a genetic algorithm;

[0031] The acquisition unit is used to stop the iteration after the preset conditions are met and to acquire the individual with the highest fitness in the current population.

[0032] The determining unit is further configured to determine the optimal solution for the I manufacturing tasks based on the chromosome of the individual with the highest fitness.

[0033] In one possible design, the fitness function is expressed using the following formula:

[0034] minF = ω1*C + ω2*T; where minF represents the evaluation value, C represents the total cost, T represents the total time, ω1 + ω2 = 1, ω1 and ω2 represent the weights of the total cost and the total time, respectively. The total cost includes material procurement cost, transportation cost and warehouse storage cost, and the total time includes production response time.

[0035] In one possible design, the means of transportation is a ship;

[0036] The formula for calculating the material procurement cost is as follows: The formula for calculating the warehouse storage cost is as follows: The formula for calculating transportation costs

[0037] Where I represents the number of manufacturing tasks, i represents the atomic manufacturing task number, and j represents the atomic manufacturing service number. Let N be the decision variable, representing the selection of the k-th atomic manufacturing service from the corresponding atomic manufacturing service set for the j-th atomic manufacturing task i; M P represents the quantity of materials purchased. S S represents the warehousing cost per unit of material or finished product. S P is the storage space required for materials and finished products. V N represents the price of a ship's cargo space. V T represents the number of ships. W T is the waiting time required for production. S The service time required for production, i.e., the ship's service time.

[0038] In one possible design, the evolution of the chromosome includes:

[0039] Pair individuals in the population into twos;

[0040] For two paired individuals, one or more atomic manufacturing service serial numbers at the same position are randomly selected and swapped to obtain two new individuals.

[0041] In one possible design, the variations in the chromosome include:

[0042] The individual's atomic manufacturing service serial number changes randomly within a specified range of values.

[0043] In one possible design, the individual selection includes:

[0044] The fitness of each individual in the population is calculated based on the fitness function;

[0045] Individuals in the population are sorted in descending order based on their fitness.

[0046] Select the top M individuals; where M is an integer greater than 1.

[0047] In one possible design, the preset conditions include: reaching a preset number of iterations or the maximum fitness of multiple consecutive populations fluctuating within a specified range.

[0048] This application also provides an apparatus for implementing the manufacturing resource optimization method described in the first or second aspect. For example, the apparatus may be a chip or a server. The above method can be implemented through software, hardware, or hardware executing corresponding software.

[0049] In one possible implementation, the device includes a processor and a memory; the processor is configured to support the device in performing the corresponding functions described in the above methods. The memory is coupled to the processor and stores necessary programs (instructions) and / or data for the device. Optionally, the device may also include a communication interface to support communication between the device and other devices or network elements.

[0050] In another possible implementation, the apparatus may include unit modules that perform the corresponding actions in the above method.

[0051] In another possible implementation, a processor and a transceiver device are included, the processor being coupled to the transceiver device, the processor being configured to execute a computer program or instructions to control the transceiver device to receive and send information; when the processor executes the computer program or instructions, the processor is also configured to implement the above method.

[0052] This application also provides an apparatus comprising: a memory and a processor; wherein the memory stores a set of program code, and the processor is configured to invoke the program code stored in the memory to execute the methods described in various aspects.

[0053] Another aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0054] Another aspect of this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the above aspects.

[0055] According to the above embodiments, order demand information is decomposed into multiple manufacturing tasks, and a chromosome is constructed: the number of genomes included in the chromosome is equal to the number of manufacturing tasks. Each genome in the chromosome contains a manufacturing task sequence number, an atomic manufacturing task sequence number, and an atomic manufacturing service sequence number. The set of atomic manufacturing tasks includes procurement tasks, production tasks, warehousing tasks, and transportation tasks. An initial population is generated, and then a genetic algorithm is used to iteratively process the initial population to obtain the optimal solution for handling multiple manufacturing tasks. This application optimizes manufacturing resources by combining the constraints of supplier raw materials, production base capacity, warehouse storage, and transportation tools when manufacturing enterprises produce and sell to the market, so as to minimize the total cost and total time and improve the market competitiveness of manufacturing enterprises. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating the method for optimizing manufacturing resources provided in an embodiment of this application;

[0058] Figure 2 This is a schematic diagram of the chromosome structure of an individual provided in the embodiments of this application;

[0059] Figure 3 This is the iterative processing procedure provided in the embodiments of this application;

[0060] Figure 4 This is a schematic diagram illustrating the principle of chromosome crossing over provided in the embodiments of this application;

[0061] Figure 5 This is a schematic diagram illustrating the principle of chromosome variation provided in the embodiments of this application;

[0062] Figure 6 This is a schematic diagram of the structure of a device provided in an embodiment of this application;

[0063] Figure 7 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0064] To optimize the total cost and time of an order, this application provides a method, apparatus, storage medium, and electronic device for optimizing manufacturing resources. To better understand the technical solution provided in this application, the basic principles of the solution are briefly explained below:

[0065] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0066] Manufacturing enterprises face long supply chains and increasingly complex cost and delivery time factors when processing orders. Optimizing these factors to minimize costs and delivery time is a pressing issue. To address this, this application provides a method, apparatus, electronic device, and storage medium for optimizing manufacturing resources. The method decomposes order demand information into multiple manufacturing tasks, constructing a chromosome: the number of genomes in the chromosome equals the number of manufacturing tasks. Each genome in the chromosome contains a manufacturing task sequence number, an atomic manufacturing task sequence number, and an atomic manufacturing service sequence number. The atomic manufacturing task set includes procurement tasks, production tasks, warehousing tasks, and transportation tasks. An initial population is generated, and a genetic algorithm iteratively processes this initial population to obtain the optimal solution for handling multiple manufacturing tasks. This application optimizes manufacturing resources by considering constraints such as supplier raw materials, production base capacity, warehousing, and transportation tools when manufacturing enterprises produce and sell to the market, minimizing total costs and time and improving the market competitiveness of manufacturing enterprises.

[0067] Among them, the Genetic Algorithm (GA) is a computational model that simulates the biological evolutionary process based on natural selection and genetic mechanisms in Darwin's theory of evolution. It is a method for searching for optimal solutions by simulating the natural evolutionary process. Its main characteristics are: direct operation on structural objects, without the constraints of differentiation and function continuity; inherent implicit parallelism and better global optimization capabilities; and the use of probabilistic optimization methods, which can automatically acquire and guide the optimization search space without the need for deterministic rules, and adaptively adjust the search direction.

[0068] Genetic algorithms start with a population representing the set of possible solutions to a problem. A population consists of a certain number of individuals encoded by genes. Each individual is actually a chromosome-based entity with specific characteristics.

[0069] Chromosomes, as the primary carriers of genetic material—collections of multiple genes—determine an individual's outward appearance through a specific gene combination that defines their internal phenotype (genotype). For example, the characteristic of black hair is determined by a specific gene combination on the chromosome that controls this trait. Therefore, initially, a mapping from phenotype to genotype—that is, encoding—is required. Since mimicking gene encoding is complex, we often simplify it, using methods such as binary encoding.

[0070] After the initial population is generated, it evolves generation by generation according to the principles of survival of the fittest and natural selection, producing increasingly better approximate solutions. In each generation, individuals are selected based on their fitness in the problem domain, and genetic operators from natural genetics are used for crossover and mutation to generate a population representing a new set of solutions. This application uses a genetic algorithm to optimize multiple procurement, manufacturing, warehousing, and transportation tasks related to order requirements, resulting in reduced service costs and shorter delivery times when processing order demands.

[0071] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features described in the embodiments of this application can be combined with each other without conflict.

[0072] The information recommendation method provided in the embodiments of this application will be further explained below. For example... Figure 1 As shown, it includes the following steps:

[0073] S101. Decompose the order demand information into I manufacturing tasks.

[0074] The order demand information represents information about the goods that the customer needs to purchase, such as quantity, model, price, and delivery date. This application can obtain the order demand information from the contract information signed with the customer, and decompose the goods required by the order demand information into I manufacturing tasks, where I is an integer greater than 1. Each manufacturing task is used to manufacture multiple parts of the same type, and different manufacturing tasks are used to manufacture different types of parts. After completing multiple manufacturing tasks, the goods required by the customer's order demand information can be obtained.

[0075] For example: Based on the customer's order requirements, two manufacturing tasks are generated, namely Manufacturing Task 1 and Manufacturing Task 2. Manufacturing Task 1 is used to manufacture 10 parts 1, and Manufacturing Task 2 is used to manufacture 20 parts 2.

[0076] S102, Randomly generate the first generation population.

[0077] The initial population contains multiple individuals. Each individual's chromosome includes: manufacturing task number i, atomic manufacturing task number j, and atomic manufacturing service number k. In the initial population, the atomic service corresponding to the atomic manufacturing service number k is randomly selected from the corresponding atomic manufacturing service set; i≤1≤I and is an integer, i.e. i=1,2,…,I.

[0078] The atomic manufacturing task set contains A atomic manufacturing tasks, where 1 ≤ j ≤ A and j is an integer, i.e., j = 1, 2, ..., A. Different manufacturing tasks are associated with the same atomic manufacturing task set, meaning that different parts all undergo the same processing steps. The atomic manufacturing task set includes procurement tasks, manufacturing tasks, warehousing tasks, and transportation tasks. In addition to the above four atomic manufacturing tasks, the atomic manufacturing task set can also consider other atomic manufacturing tasks according to actual needs. That is, different parts must go through the four stages of procurement, manufacturing, warehousing, and transportation before they can be delivered to the customer.

[0079] The atomic manufacturing service set corresponding to manufacturing task i and atomic manufacturing task number j contains B ij Atom manufacturing service, 1≤k ij ≤B ij And k ij The set of atomic manufacturing services may be the same or different for different manufacturing tasks under the same atomic manufacturing task. For example: the suppliers that can be selected for part 1 under the procurement task are: supplier 1, supplier 2 and supplier 3; the suppliers that can be selected for part 2 under the procurement task are: supplier 4, supplier 5 and supplier 6.

[0080] For example, the serial numbers start from 1 and increment by 1, i.e., 1, 2, ... Based on the customer's order requirements, two manufacturing tasks are generated, manufacturing 10 parts 1 and 20 parts 2 respectively. The atomic manufacturing task set includes four atomic manufacturing tasks: procurement, production, warehousing, and transportation. The atomic manufacturing service set corresponding to the procurement task of part 1 is: supplier 1, supplier 2, and supplier 3, totaling three atomic manufacturing services. The atomic manufacturing service set under the procurement task of part 2 is: supplier 4, supplier 5, and supplier 6, totaling four atomic manufacturing services. The atomic manufacturing service set corresponding to the production task of part 1 is: production base 1, production base 2, and production base 3, totaling three atomic manufacturing services. The atomic manufacturing service set corresponding to the production task of part 2 is: production base 4, production base 5, and production base 6, totaling three atomic manufacturing services. The atomic manufacturing service set corresponding to the warehousing task of part 1 is: warehouse 1, warehouse 2, and warehouse 3. The atomic manufacturing service set corresponding to the warehousing task of part 2 is: warehouse 1, warehouse 2, and warehouse 3, the same as that of part 1. The set of atomic manufacturing services corresponding to the transportation task of part 1 is: transportation vehicle 1, transportation vehicle 2 and transportation vehicle 3. The set of atomic manufacturing services corresponding to the transportation task of part 2 is: transportation vehicle 1, transportation vehicle 2 and transportation vehicle 3, for a total of 3 atomic manufacturing services.

[0081] Assume the randomly generated initial population contains 10 individuals, each individual's chromosomes are divided into 2 genomes, and the number of genomes equals the number of creation tasks. See also Figure 2 The diagram shows the structure of a chromosome. Genome 1 is 113-122-132-141, and Genome 2 is 211-222-232-243. Each genome contains four genes. The first value of each gene represents the manufacturing task number, ranging from 1 to 2; the second value represents the atomic manufacturing task number, ranging from 1 to 4; and the third value represents the atomic manufacturing service number, ranging from 1 to 3. 113 indicates that the procurement task for part 1 uses the third supplier (i.e., supplier 3), and 211 indicates that the procurement task for part 2 uses the first supplier (i.e., supplier 1).

[0082] S103. Determine the adaptive function.

[0083] The fitness function is used to constrain the total cost and total time of I manufacturing tasks to be minimized. The fitness function is the objective function, and its evaluation value can be obtained by weighted averaging of total cost and total time. For example, the fitness function can be expressed as: minF = ω1*C + ω2*T, where minF represents the evaluation value, C represents the total cost, T represents the total time, and ω1 + ω2 = 1, where ω1 and ω2 represent the weights of total cost and total time, respectively. The values ​​of the weights can be determined according to actual needs, and this application does not impose any restrictions. For example, ω1 = ω2 = 0.5. This application uses the fitness function to calculate the fitness of an individual. Fitness is negatively correlated with the above evaluation value; that is, the smaller the evaluation value, the higher the fitness, and vice versa. For example, fitness and the above evaluation value are inversely proportional.

[0084] In this embodiment, the total cost includes material procurement costs, transportation costs, and warehousing costs, and the total time includes production response time. The formula for calculating material procurement costs is: The formula for calculating warehouse storage costs is: When the means of transportation is a ship, the formula for calculating transportation costs is:

[0085] Where I represents the number of manufacturing tasks, i represents the atomic manufacturing task number, and j represents the atomic manufacturing service number. Let N be the decision variable, representing the selection of the k-th atomic manufacturing service from the corresponding atomic manufacturing service set for the j-th atomic manufacturing task i; M P represents the quantity of materials purchased. S S represents the warehousing cost per unit of material or finished product. S P is the storage space required for materials and finished products. V N represents the price of a ship's cargo space. V T represents the number of ships. W T is the waiting time required for production. S The service time required for production, i.e., the ship's service time.

[0086] S104. Use a genetic algorithm to perform iterative processing of individual selection and chromosome evolution on the first generation population.

[0087] The process involves using a fitness function as a constraint, employing a genetic algorithm to iterate through the initial population. The fitness function is then used to calculate the fitness of each individual, and a predetermined number of individuals are selected from the population according to a predefined selection rule, eliminating those that do not meet the requirements. For example, the selection rule might be: sort the individuals in the population in descending order of fitness, select the top predetermined number of individuals, and eliminate the rest. Then, the selected predetermined number of individuals undergo chromosome crossover and mutation to generate the next generation population. This process is repeated until the predetermined conditions are met, at which point iteration ceases.

[0088] For example: see Figure 3 The flowchart shown is a diagram of the iterative processing. The iterative processing process includes:

[0089] S1. Randomly generate the initial population.

[0090] S2. Calculate the fitness of each individual in the population using the fitness function.

[0091] The fitness function in S103 is used to calculate the fitness of each individual in the population. Higher fitness means lower cost and less time, while lower fitness means higher cost and more time.

[0092] S3. Select a preset number of individuals based on fitness.

[0093] The selection rules can be implemented using the following methods:

[0094] Roulette wheel selection is a replay-based random sampling method. The probability of each individual entering the next generation of the population is equal to the ratio of its fitness value to the sum of the fitness values ​​of all individuals in the entire population.

[0095] Stochastic Tournament: Each time, a pair of individuals is selected by roulette, and then these two individuals compete for the selection. The one with higher fitness is selected. This process is repeated until all individuals are selected.

[0096] Optimal retention selection: First, perform the selection operation of the genetic algorithm according to the roulette wheel selection method, and then completely copy the individual with the highest fitness in the current population to the next generation population.

[0097] Unrepeatable random selection (also called expected value selection): This method involves randomly selecting individuals based on their expected survival in the next generation. The method is as follows:

[0098] (1) Calculate the number of individuals in the next generation of the population, N, where N > 0.

[0099] (2) If an individual is selected to participate in the crossover operation, its expected number of survivals in the next generation is reduced by 0.5. If an individual is not selected to participate in the crossover operation, its expected number of survivals in the next generation is reduced by 1.0.

[0100] (3) As the selection process proceeds, if the number of individuals with a survival expectation is less than 0, then that individual will no longer have the opportunity to be selected.

[0101] Deterministic selection: This involves selecting according to a specific, predetermined method. The specific process is as follows:

[0102] (1) Calculate the expected number N of each individual in the group in the next generation of the group.

[0103] (2) Use the integer part of N to determine the number of each corresponding individual surviving in the next generation population.

[0104] (3) Sort the individuals in descending order using the fractional part of N, and add the first M individuals to the next generation population. This completely determines the M individuals in the next generation population. M is an integer greater than 1.

[0105] Random selection without replay: This ensures that multiple individuals with fitness greater than the average fitness can be passed on to the next generation, resulting in a smaller selection error.

[0106] Uniform sorting: Sort all individuals in the population according to their fitness, and assign the probability of each individual being selected based on this sort.

[0107] The optimal preservation strategy is to replace the individual with the highest fitness in the current population with the lowest fitness generated after crossover and mutation operations.

[0108] Random league selection: Each time, the individual with the highest fitness among several individuals is selected and passed on to the next generation of the population.

[0109] Exclusionary selection: Newly generated offspring will replace or exclude similar older parent individuals, increasing the diversity of the population.

[0110] In this embodiment, a deterministic selection method can be used to select individuals in the population. Specifically, individuals in the population are sorted in descending order according to their fitness, and then a preset number of individuals at the top are selected. The preset number can be determined according to actual needs, and this application does not impose any restrictions.

[0111] S4. Perform chromosome crossover and mutation on a preset number of individuals to generate the next generation population.

[0112] In this embodiment, chromosome crossing means that two paired chromosomes exchange some of their genes in some way, thereby forming two new individuals.

[0113] The methods of intersection include:

[0114] One-point crossover: refers to randomly setting only one crossover point in the individual's encoding string, and then exchanging parts of the chromosomes of the two paired individuals at that point.

[0115] Two-point intersection and multi-point intersection:

[0116] (1) Two-point crossover: Two crossover points are randomly set in the individual coding string, and then some genes are exchanged.

[0117] (2) Multi-point Crossover:

[0118] Uniform crossover: Genes at each locus of two paired individuals are exchanged with the same crossover probability, thus forming two new individuals.

[0119] Arithmetic Crossover: This operation generates two new individuals through a linear combination of two existing individuals. The objects of this operation are typically individuals represented using floating-point numbers.

[0120] For example, see Figure 4 The diagram shown illustrates the principle of chromosome crossing over. Gene 232 on the second genome of individual 1 and gene 233 on the second genome of individual 2 are exchanged, as are gene 243 on the second genome of individual 1 and gene 241 on the second genome of individual 2. After the exchange, two new individuals are obtained.

[0121] In this embodiment, chromosomal variation means that genes at certain locations on a chromosome are replaced by other alleles, thereby forming a new individual.

[0122] The methods of mutation include:

[0123] Simple Mutation: Mutating one or more bits in an individual encoded string by means of a random number of bits with a mutation probability, based solely on the value at the bit position.

[0124] Uniform Mutation: Replacing the original gene values ​​at each locus in an individual's coding string with random numbers that conform to a uniform distribution within a certain range, with a small probability.

[0125] Boundary mutation: Randomly selecting one of two corresponding boundary gene values ​​at a gene locus to replace the original gene value. It is particularly suitable for problems where the optimal point is located at or near the boundary of a feasible solution.

[0126] Non-uniform mutation: The original gene values ​​are randomly perturbed, and the result of the perturbation is used as the new gene values ​​after mutation. After performing mutation operations on each locus with the same probability, it is equivalent to making a slight change to the entire solution vector in the solution space.

[0127] Gaussian approximate mutation: When performing the mutation operation, the mean of P is used as the average value and the variance is P. 2 A random number from a normal distribution is used to replace the original gene value.

[0128] For example, see Figure 5 The diagram illustrates the principle of chromosome variation. When the second gene on the first chromosome of an individual mutates from 122 to 121, a new individual is generated.

[0129] S5. Determine whether the preset conditions are met. If yes, continue to execute S2; if no, execute S6.

[0130] Among them, the preset conditions can represent the conditions for stopping the iteration process. For example, the preset conditions are: the number of iterations reaches a threshold, or the maximum fitness of individuals in multiple consecutive groups fluctuates within a specified range, that is, when the maximum fitness of the group does not change significantly, the iteration process stops.

[0131] S6. Identify the individual with the highest fitness in the current population.

[0132] S7. Generate the optimal solution for chromosomes based on this individual.

[0133] The solution specifies the atomic manufacturing services to be selected under each atomic manufacturing task in order to minimize the cost and time of the manufacturing task.

[0134] S105. When the preset conditions are met, stop the iteration and obtain the individual with the highest fitness in the current population.

[0135] The specific process of S105 can be referred to the description of S5, and will not be repeated here.

[0136] S106. Determine the optimal solution for manufacturing task I based on the chromosome of the individual with the highest fitness.

[0137] For example, a manufacturing task is used to manufacture 10 parts 1 and 20 parts 2. Assume that when the iteration stops, the chromosome of the individual with the highest fitness in the current population is: 112-121-131-143--213-223-233-241, which means the optimal solution is: for part 1, select supplier number 2 in the procurement task, select production base number 1 in the production task, select warehouse number 1 in the warehousing task, and select transportation vehicle number 3 in the transportation task; for part 2, select supplier number 3 in the procurement task, select production base number 3 in the production task, select warehouse number 3 in the warehousing task, and select transportation vehicle number 1 in the transportation task.

[0138] In this embodiment, order demand information is decomposed into multiple manufacturing tasks, and a chromosome is constructed: the number of genomes in the chromosome is equal to the number of manufacturing tasks. Each genome in the chromosome contains a manufacturing task sequence number, an atomic manufacturing task sequence number, and an atomic manufacturing service sequence number. The set of atomic manufacturing tasks includes procurement tasks, production tasks, warehousing tasks, and transportation tasks. An initial population is generated, and then a genetic algorithm is used to iteratively process the initial population to obtain the optimal solution for handling multiple manufacturing tasks. When a manufacturing enterprise produces and sells to the market, this application optimizes manufacturing resources by combining constraints on supplier raw materials, production base capacity, warehouse storage, and transportation tools, so as to minimize its total cost and total time and improve the market competitiveness of the manufacturing enterprise.

[0139] The above Figure 1 The optimization methods for manufacturing resources are described in detail. Based on the same technical concept, a schematic diagram of the structure of an apparatus according to an embodiment of this application is provided.

[0140] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a device 6 provided in an embodiment of this application. The device 6 may include a decomposition unit 601, a generation unit 602, a determination unit 603, an iteration unit 604, and an acquisition unit 605.

[0141] Decomposition unit 601 is used to decompose order demand information into I manufacturing tasks;

[0142] Generation unit 602 is used to randomly generate an initial population; wherein, the initial population contains multiple individuals, and each individual's chromosome includes I genomes, and each genome contains: manufacturing task number i, atom manufacturing task number j, and atom manufacturing service number k. ij; 1≤i≤I, and are integers; the atomic manufacturing task set contains A atomic manufacturing tasks, 1≤j≤A, and j is an integer; the atomic manufacturing service set includes: procurement tasks, production tasks, warehousing tasks, and transportation tasks; the number of atomic manufacturing service sets for atomic manufacturing task number j is B. ij ; 1≤k ij ≤B ij And k ij It is an integer;

[0143] The determining unit 603 is used to determine the fitness function; wherein the fitness function is used to constrain the total cost and total time of the I manufacturing tasks to be minimized;

[0144] The iteration unit 604 is used to perform iterative processing of individual selection and chromosome evolution on the first generation population using a genetic algorithm;

[0145] The acquisition unit 605 is used to stop the iteration after the preset conditions are met and to acquire the individual with the highest fitness in the current population.

[0146] The determining unit 603 is further configured to determine the optimal solution for the I manufacturing task based on the chromosome of the individual with the highest fitness.

[0147] In one possible design, the fitness function is expressed using the following formula:

[0148] minF = ω1*C + ω2*T; where minF represents the evaluation value, C represents the total cost, T represents the total time, ω1 + ω2 = 1, ω1 and ω2 represent the weights of the total cost and the total time, respectively. The total cost includes material procurement cost, transportation cost and warehouse storage cost, and the total time includes production response time.

[0149] In one possible design, the means of transportation is a ship;

[0150] The formula for calculating the material procurement cost is as follows: The formula for calculating the warehouse storage cost is as follows: The formula for calculating the transportation cost is as follows:

[0151] Where I represents the number of manufacturing tasks, i represents the atomic manufacturing task number, and j represents the atomic manufacturing service number. Let N be the decision variable, representing the selection of the k-th atomic manufacturing service from the corresponding atomic manufacturing service set for the j-th atomic manufacturing task i; M P represents the quantity of materials purchased. S S represents the warehousing cost per unit of material or finished product. SP is the storage space required for materials and finished products. V N represents the price of a ship's cargo hold. V T represents the number of ships. W T is the waiting time required for production. S The service time required for production, i.e., the ship's service time.

[0152] In one possible design, the evolution of the chromosome includes:

[0153] Pair individuals in the population together;

[0154] For two paired individuals, one or more atomic manufacturing service serial numbers at the same position are randomly selected and swapped to obtain two new individuals.

[0155] In one possible design, the variations in the chromosome include:

[0156] The individual's atomic manufacturing service serial number changes randomly within a specified range of values.

[0157] In one possible design, the individual selection includes:

[0158] The fitness of each individual in the population is calculated based on the fitness function;

[0159] Individuals in the population are sorted in descending order based on their fitness.

[0160] Select the top M individuals; where M is an integer greater than 1.

[0161] In one possible design, the preset conditions include: reaching a preset number of iterations or the maximum fitness of multiple consecutive populations fluctuating within a specified range.

[0162] This application's embodiments and Figure 1 The method implementations are based on the same concept and bring about the same technical effects. The specific process can be referred to Figure 1 The method embodiments described herein will not be repeated here.

[0163] The device 6 can be a field-programmable gate array (FPGA), a dedicated integrated chip, a system on chip (SoC), a central processing unit (CPU), a network processor (NP), a digital signal processing circuit, a micro controller unit (MCU), or a programmable logic device (PLD) or other integrated chip to implement the relevant functions.

[0164] Figure 7 This is a schematic diagram of an electronic device structure provided in an embodiment of the present application. The electronic device 7 includes: a memory 702, a processor 701, and a transceiver 703.

[0165] The memory 702 can be a separate physical unit, which can be connected to the processor 701 and transceiver 703 via a bus. The memory 702, processor 701, and transceiver 703 can also be integrated together, implemented in hardware, etc.

[0166] The memory 702 is used to store programs that implement the above method embodiments or the various modules of the device embodiments. The processor 701 calls the program to execute the operations of the above method embodiments.

[0167] Optionally, the electronic device 7 also includes input devices and output devices, including but not limited to a keyboard, mouse, touch panel, camera and microphone; and output devices including but not limited to a display screen.

[0168] Communication interfaces are used to send and receive various types of messages. Communication interfaces include, but are not limited to, wireless interfaces or wired interfaces.

[0169] Optionally, when some or all of the manufacturing resource optimization methods in the above embodiments are implemented by software, the apparatus may also include only a processor. A memory for storing programs is located outside the apparatus, and the processor is connected to the memory via circuitry / wires to read and execute the programs stored in the memory.

[0170] The processor can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0171] The processor may further include hardware chips. These hardware chips may be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The PLDs may be complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), generic array logic (GALs), or any combination thereof.

[0172] Memory may include volatile memory, such as random-access memory (RAM); memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD), or solid-state drive (SSD); memory may also include combinations of the above types of memory.

[0173] This application also provides a computer storage medium storing a computer program for executing the manufacturing resource optimization method provided in the above embodiments.

[0174] This application also provides a computer program product containing instructions that, when run on a computer, causes the computer to execute the manufacturing resource optimization method provided in the above embodiments.

[0175] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0176] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0177] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0178] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

Claims

1. A method for optimizing manufacturing resources, characterized in that, The method includes: Decompose the order demand information into I manufacturing tasks; where I ≥ 1 and I is an integer; An initial population is randomly generated; wherein the initial population contains multiple individuals, and each individual's chromosome includes I genomes, and each genome contains: manufacturing task number i, atom manufacturing task number j, and atom manufacturing service number k. ij ; 1≤i≤I, and are integers; the atomic manufacturing task set contains A atomic manufacturing tasks, 1≤j≤A, and j is an integer; the atomic manufacturing service set includes: procurement tasks, production tasks, warehousing tasks, and transportation tasks; the number of atomic manufacturing service sets for atomic manufacturing task number j is B. ij ; 1≤k ij ≤B ij And k ij It is an integer; Determine the fitness function; wherein the fitness function is used to constrain the total cost and total time of the I manufacturing tasks to be minimized; the total cost includes material procurement cost, transportation cost and warehouse storage cost, and the total time includes production response time; the fitness function is expressed by the following formula: minF=ω1*C+ω2*T; where minF represents the evaluation value, C represents the total cost, T represents the total time, ω1+ω2=1, and ω1 and ω2 represent the weights of the total cost and the total time, respectively; A genetic algorithm is used to iteratively process individual selection and chromosome evolution in the first generation population; After the preset conditions are met, the iteration stops, and the individual with the highest fitness in the current population is obtained; The optimal solution for the I manufacturing tasks is determined based on the chromosome of the individual with the highest fitness.

2. The method according to claim 1, characterized in that, The means of transport was a ship; The formula for calculating the material procurement cost is as follows: ; The formula for calculating the warehouse storage cost is as follows: ; The formula for calculating the transportation cost is as follows: ; Where I represents the number of manufacturing tasks, i represents the atomic manufacturing task number, and j represents the atomic manufacturing service number. Let N be the decision variable, representing the selection of the k-th atomic manufacturing service from the corresponding atomic manufacturing service set for the j-th atomic manufacturing task i; M P represents the quantity of materials purchased. S S represents the warehousing cost per unit of material or finished product. S P is the storage space required for materials and finished products. V N represents the price of a ship's cargo space. V This refers to the number of ships.

3. The method according to claim 1 or 2, characterized in that, The evolution of the chromosomes includes: Pair individuals in the population together; For two paired individuals, one or more atomic manufacturing service serial numbers at the same position are randomly selected and swapped to obtain two new individuals.

4. The method according to claim 3, characterized in that, The chromosomal variations include: The individual's atomic manufacturing service serial number changes randomly within a specified range of values.

5. The method according to claim 1, 2, or 4, characterized in that, The individual selection includes: The fitness of each individual in the population is calculated based on the fitness function; Individuals in the population are sorted in descending order based on their fitness. Select the top M individuals; where M is an integer greater than 1.

6. The method according to claim 5, characterized in that, The preset conditions include: reaching a preset number of iterations or the maximum fitness of multiple consecutive populations fluctuating within a specified range.

7. A device for optimizing manufacturing resources, characterized in that, The device includes: The decomposition unit is used to decompose order demand information into I manufacturing tasks; A generation unit is used to randomly generate an initial population; wherein the initial population contains multiple individuals, and each individual's chromosome includes I genomes, and each genome contains: manufacturing task number i, atom manufacturing task number j, and atom manufacturing service number k. ij ; 1≤i≤I, and are integers; the atomic manufacturing task set contains A atomic manufacturing tasks, 1≤j≤A, and j is an integer; the atomic manufacturing service set includes: procurement tasks, production tasks, warehousing tasks, and transportation tasks; the number of atomic manufacturing service sets for atomic manufacturing task number j is B. ij ; 1≤k ij ≤B ij And k ij It is an integer; A determination unit is used to determine the fitness function; wherein the fitness function is used to constrain the total cost and total time of the I manufacturing tasks to be minimized; the total cost includes material procurement cost, transportation cost and warehouse storage cost, and the total time includes production response time; the fitness function is expressed by the following formula: minF=ω1*C+ω2*T; where minF represents the evaluation value, C represents the total cost, T represents the total time, ω1+ω2=1, and ω1 and ω2 represent the weights of the total cost and the total time, respectively; An iterative unit is used to perform iterative processing of individual selection and chromosome evolution on the first-generation population using a genetic algorithm; The acquisition unit is used to stop the iteration after the preset conditions are met and to acquire the individual with the highest fitness in the current population. The determining unit is further configured to determine the optimal solution for the I manufacturing tasks based on the chromosome of the individual with the highest fitness.

8. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps of any one of the methods of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It includes program code that, when the program product is run on an electronic device, causes the electronic device to perform the steps of the method of any one of claims 1 to 6.

Images