Production main plan scheduling optimization method and device, equipment and medium

Abstract

The invention provides a production main plan scheduling optimization method and device, equipment and a medium, and belongs to the technical field of scheduling systems. The method comprises the following steps: constructing a production resource utilization rate objective function by taking a plurality of production requirements and the production speed of production equipment as input and taking maximum production resource utilization rate as output, and determining constraint conditions of the production resource utilization rate objective function; performing optimization solution on the production resource utilization rate objective function by utilizing a genetic algorithm, and determining a plurality of optimal production requirements meeting constraint conditions of the production resource utilization rate objective function and the production speed of the production equipment; and issuing the plurality of optimal production requirements and the production speed of the production equipment to a production workshop so as to control the production workshop to perform production according to the plurality of optimal production requirements and the production speed of the corresponding production equipment. Through multi-factor optimization and the genetic algorithm, the production resource utilization rate and the quality searching quality are improved, the cost is reduced, and the production efficiency is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of scheduling systems, and in particular to a production master plan scheduling optimization method, a production master plan scheduling optimization device, an electronic device and a computer-readable storage medium. Background Art

[0002] With the rapid development of industrialization, the high quality of products will face new challenges, so new requirements are put forward for the production capacity resource allocation of product manufacturers. In recent years, data-driven models are gradually improving the traditional resource management model of the manufacturing industry. Due to the relatively concentrated maintenance period of power plants, the demand orders for products have increased significantly. In addition, the preparation cycle of some products is long and is subject to resource constraints, resulting in manual production scheduling that is time-consuming and of low quality, seriously affecting the delivery time of products and even affecting the startup time of power plants.

[0003] At present, the production scheduling of products still adopts manual scheduling. In order to meet the goal of on-time delivery, this method needs to reserve ample buffer time. When there are insert orders or urgent orders, the flexibility of manual adjustment is low, and it is difficult to ensure on-time delivery. In addition, the production master plan scheduling for the preparation of denitrification catalysts mainly considers a single factor. Generally speaking, companies will choose a mathematical model to optimize the relationship between supply, demand and production in a linear programming manner by minimizing delay time, cycle time and lead time.

[0004] However, the existing production master plan scheduling method causes a mismatch between overall production demand and equipment capacity due to manual scheduling and local optimization, resulting in insufficient overall production resource utilization. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a production master plan scheduling optimization method, device, equipment and medium to solve the above problems.

[0006] In order to achieve the above object, an embodiment of the present invention provides a production master plan scheduling optimization method, comprising: Taking multiple production demands and the production speed of the corresponding production equipment as input and the maximum production resource utilization as output, a production resource utilization objective function is constructed, and the constraints of the production resource utilization objective function are determined; Using genetic algorithms, the objective function of production resource utilization is optimized and solved to determine the optimal multiple production demands and the production speeds of the corresponding production equipment that meet the constraints of the objective function of production resource utilization; The optimal multiple production requirements and the production speeds of the corresponding production equipment are sent to the production workshop to control the production workshop to produce according to the optimal multiple production requirements and the production speeds of the corresponding production equipment.

[0007] Optionally, the production resource utilization objective function is: ;in, represents the maximum production resource utilization, represents the i-th production demand, represents the i-th production speed, Indicates the preset production plan deadline. Indicates the preset production plan start time.

[0008] Optionally, the constraints of the production resource utilization objective function are: ;in, Represents the total production demand.

[0009] Optionally, a genetic algorithm is used to optimize and solve the production resource utilization objective function to determine the optimal multiple production demands and the production speeds of the corresponding production equipment that meet the constraint conditions of the production resource utilization objective function, including: Step 1: Initialize the number of chromosomes, the maximum number of iterations, and the preset fitness threshold; wherein the chromosomes include master chromosomes and slave chromosomes; Step 2: Real number encoding is performed on multiple production requirements and the production speeds of the corresponding production equipment respectively, and the multiple production requirements after real number encoding are mapped to multiple initial master chromosomes, and the production speeds of the multiple production equipment after real number encoding are mapped to multiple initial slave chromosomes; Step 3: Based on the multiple production demands corresponding to each initial master chromosome and the production speeds of the multiple production equipment corresponding to each initial slave chromosome, the production resource utilization rate of each initial chromosome is obtained, and the production resource utilization rate of each initial chromosome is used as the fitness value of each initial chromosome; Step 4: based on the fitness value of each initial chromosome, a preset number of parent chromosomes are selected from the multiple initial chromosomes, and the initial chromosomes other than the preset number of parent chromosomes are determined as non-parent chromosomes; Step 5: Based on a preset crossover probability and a preset number of crossover points, a synchronous crossover operation is performed on a preset number of parent chromosomes to obtain a preset number of offspring chromosomes; Step 6: Based on the preset mutation probability, perform synchronous mutation operations on a preset number of offspring chromosomes to obtain a preset number of target offspring chromosomes; Step 7: Based on the multiple production requirements corresponding to the preset number of target offspring chromosomes and the production speed of the corresponding production equipment, the production resource utilization rate of each target offspring chromosome is obtained, and the production resource utilization rate of each target offspring chromosome is used as the fitness value of each target offspring chromosome; Step 8: Determine whether the current number of iterations is greater than the maximum number of iterations or whether the fitness value of any target offspring chromosome is greater than a preset fitness threshold; Step 9: If yes, then the multiple production demands and the production speeds of the corresponding production equipment corresponding to the target offspring chromosome with the largest fitness value are taken as the multiple optimal production demands and the production speeds of the corresponding production equipment; If not, the multiple initial chromosomes are updated to a preset number of target offspring chromosomes and non-parent chromosomes, and the process returns to step 3.

[0010] Optionally, based on a plurality of production requirements corresponding to each initial master chromosome and a production speed of a plurality of production equipment corresponding to each initial slave chromosome, a production resource utilization rate of each initial chromosome is obtained, including: The following formula is used to calculate the multiple production demands corresponding to each initial master chromosome and the production speeds of multiple production equipment corresponding to each initial slave chromosome to obtain the production resource utilization rate of each initial chromosome; ;in, represents the production resource utilization rate of each initial chromosome, represents the i-th production demand of the initial chromosome, represents the production speed of the i-th production equipment of the initial chromosome, Indicates the preset production plan deadline. Indicates the preset production plan start time.

[0011] Optionally, before the step of updating the multiple initial chromosomes to a preset number of target offspring chromosomes and non-parent chromosomes, the method further comprises: Calculate the standard deviation of the fitness values ​​of multiple target offspring chromosomes; Determine whether the standard deviation of the fitness values ​​of multiple target offspring chromosomes is greater than a preset standard deviation threshold; If yes, then increase the preset crossover probability or the preset number of crossover points or the preset mutation probability; If not, the preset crossover probability or the preset number of crossover points or the preset mutation probability is reduced.

[0012] Optionally, before the step of updating the multiple initial chromosomes to a preset number of target offspring chromosomes and non-parent chromosomes, the method further comprises: Calculate the standard deviation of the fitness values ​​of multiple target offspring chromosomes; Determine whether the standard deviation of the fitness values ​​of multiple target offspring chromosomes is greater than a preset standard deviation threshold; If so, reduce the preset amount; If not, increase the preset amount.

[0013] In a second aspect of the embodiments of the present invention, a production master plan scheduling optimization device is provided, comprising: A function building module is used to take multiple production demands and the production speed of corresponding production equipment as input, take the maximum production resource utilization as output, build a production resource utilization objective function, and determine the constraint conditions of the production resource utilization objective function; The function solving module is used to use a genetic algorithm to optimize and solve the production resource utilization objective function, and determine the optimal multiple production demands and the production speed of the corresponding production equipment that meet the constraint conditions of the production resource utilization objective function; The scheduling optimization module is used to send the optimal multiple production requirements and the production speeds of the corresponding production equipment to the production workshop to control the production workshop to produce according to the optimal multiple production requirements and the production speeds of the corresponding production equipment.

[0014] In a third aspect of the embodiments of the present invention, there is provided an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the above-mentioned production master plan scheduling optimization method is executed.

[0015] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, storing computer instructions, which, when executed on a computer, enable the computer to execute the above-mentioned production master plan scheduling optimization method.

[0016] Beneficial effects of the present invention: (1) Multi-factor optimization: The present invention comprehensively considers multiple production demands and the production speed of the corresponding production equipment, more comprehensively evaluates the utilization of production resources, and avoids the limitations brought by single-factor optimization.

[0017] (2) Improving the utilization rate of production resources: The present invention constructs a production resource utilization objective function and uses a genetic algorithm to find the optimal solution. This optimization method can effectively improve the utilization rate of production resources, reduce production costs, and improve production efficiency.

[0018] (3) Improving the quality of searching for the best solution: The genetic algorithm of the present invention dynamically adjusts the parameters of the genetic algorithm, so that it has a strong global search capability, can effectively handle complex problems, avoid falling into local optimal solutions, and improve the quality of searching for the best solution.

[0019] (4) Improving scheduling flexibility: The present invention can automatically generate the optimal production scheduling plan and can adjust it according to actual conditions, thereby improving scheduling flexibility and ensuring on-time delivery.

[0020] (5) High degree of automation: The present invention can automatically schedule the production master plan, reduce manual intervention, and improve the efficiency of production management.

[0021] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flowchart of a production master plan scheduling optimization method provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a production master plan scheduling optimization device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0025] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0026] Embodiment 1 Please refer to Figure 1 , Figure 1 : is a flow chart of a production master plan scheduling optimization method provided by an embodiment of the present invention, the method comprising the following steps: S100, taking multiple production demands and the production speeds of corresponding production equipment as inputs and taking the maximum production resource utilization as output, constructing a production resource utilization objective function, and determining the constraint conditions of the production resource utilization objective function; Production demand refers to the quantity of various products that an enterprise needs to produce within a certain period of time. The unit can be cubic meters, kilograms, units, parts, etc.

[0027] The production speed of production equipment refers to the number of products that the production equipment can produce within a certain period of time. The unit can be cubic meters / hour, kilograms / hour, units / hour, or parts / hour.

[0028] In one embodiment, the production demand consists of the net demand for raw materials and the net demand for finished products. The system distinguishes the material attributes according to the material master data, calculates the actual demand according to the following formula, and stores the calculation result in the scheduling system memory.

[0029] Production demand = net demand for raw materials + net demand for finished products.

[0030] Net raw material demand = raw material demand - raw material inventory.

[0031] Net demand for finished products = finished product demand + production work order - planned work order + manual adjustment.

[0032] It should be noted that the production demand calculation results are sliced ​​to divide the production demand into small batches of production work orders to obtain multiple sub-production demands, that is, multiple production demands in this application.

[0033] It should be noted that the production speed of each production equipment is different. In order to know which production equipment corresponds to each production demand, the production speed of the production equipment is selected as the optimization parameter of the production resource utilization objective function.

[0034] S200, using an improved genetic algorithm to optimize and solve the production resource utilization objective function, and determine the optimal multiple production demands and corresponding production speeds of production equipment that meet the constraint conditions of the production resource utilization objective function; In one embodiment, the production resource utilization objective function is: ;in, represents the maximum production resource utilization, represents the i-th production demand, represents the i-th production speed, Indicates the preset production plan deadline. Indicates the preset production plan start time.

[0035] In one embodiment, ;in, Represents the total production demand.

[0036] It should be noted that the purpose of constraining the sum of multiple production demands to be the total production demand is to prevent the sum of multiple production demands found out from exceeding the total production demand, thus avoiding waste of resources.

[0037] Further, in order to better understand how the present invention uses the improved genetic algorithm to optimize and solve the production resource utilization objective function, and determine the optimal multiple production demands and the production speed of the corresponding production equipment that meet the constraint conditions of the production resource utilization objective function, the following is a detailed description: Step 1: Initialize the number of chromosomes, the maximum number of iterations, and the preset fitness threshold; wherein the chromosomes include master chromosomes and slave chromosomes; For example, assume that the number of initialized chromosomes is 10, the maximum number of iterations is set to 100, and the preset fitness threshold is set to 60.

[0038] Initial chromosome 1: {[100, 20], [110, 30], [90, 40], [200, 20], [150, 30], [130, 40]}.

[0039] Initial chromosome 2: {[120, 20], [180, 30], [100, 40], [220, 20], [150, 30], [90, 40]}.

[0040] Initial chromosome 3: {[140, 20], [160, 30], [120, 40], [210, 20], [170, 30], [110, 40]}.

[0041] Initial chromosome 4: {[130, 20], [170, 30], [110, 40], [230, 20], [160, 30], [100, 40]}.

[0042] Initial chromosome 5: {[150, 20], [190, 30], [90, 40], [240, 20], [140, 30], [130, 40]}.

[0043] Initial chromosome 6: {[160, 20], [200, 30], [80, 40], [250, 20], [130, 30], [120, 40]}.

[0044] Initial chromosome 7: {[170, 20], [210, 30], [70, 40], [260, 20], [120, 30], [110, 40]}.

[0045] Initial chromosome 8: {[180, 20], [220, 30], [60, 40], [270, 20], [110, 30], [100, 40]}.

[0046] Initial chromosome 9: {[190, 20], [230, 30], [50, 40], [280, 20], [100, 30], [90, 40]}.

[0047] Initial chromosome 10: {[200, 20], [240, 30], [40, 40], [290, 20], [90, 30], [80, 40]}.

[0048] Step 2: Real number encoding is performed on multiple production requirements and the production speeds of the corresponding production equipment respectively, and the multiple production requirements after real number encoding are mapped to multiple initial master chromosomes, and the production speeds of the multiple production equipment after real number encoding are mapped to multiple initial slave chromosomes; It is understandable that since the data is already in real number form, we can directly use this data as the encoding of the chromosome.

[0049] Step 3: Based on the multiple production demands corresponding to each initial master chromosome and the production speeds of the multiple production equipment corresponding to each initial slave chromosome, the production resource utilization rate of each initial chromosome is obtained, and the production resource utilization rate of each initial chromosome is used as the fitness value of each initial chromosome; In one embodiment, step 3 specifically includes: The following formula is used to calculate the multiple production demands corresponding to each initial master chromosome and the production speeds of multiple production equipment corresponding to each initial slave chromosome to obtain the production resource utilization rate of each initial chromosome; ;in, represents the production resource utilization rate of each initial chromosome, represents the i-th production demand of the initial chromosome, represents the production speed of the i-th production equipment of the initial chromosome, Indicates the preset production plan deadline. Indicates the preset production plan start time.

[0050] The fitness value of the initial chromosome 1 is: =58.33 The initial fitness value of chromosome 2: =65.5 The initial fitness value of chromosome 3: =68.5 The fitness value of the initial chromosome 4 is: =68.5 The initial fitness value of chromosome 5: =72 The initial fitness value of chromosome 6: =73 The initial fitness value of chromosome 7: =74 The initial fitness value of chromosome 8: =75 The initial fitness value of chromosome 9: =76 The fitness value of the initial chromosome 10 is: =77 Step 4: based on the fitness value of each initial chromosome, a preset number of parent chromosomes are selected from the multiple initial chromosomes, and the initial chromosomes other than the preset number of parent chromosomes are determined as non-parent chromosomes; In one embodiment, methods for selecting parent chromosomes include but are not limited to roulette wheel selection, tournament selection, random selection, sorting selection, linear ranking selection, and elite retention strategy, etc.

[0051] 1. Roulette Wheel Selection: This is a selection method based on fitness ratio. The probability of each individual being selected is proportional to its fitness.

[0052] Calculate the sum of fitness of all individuals.

[0053] Each individual is assigned a selection interval whose length is proportional to the individual's fitness.

[0054] Randomly generate a number between 0 and the total, and select the individual that falls within the selection interval of the individual.

[0055] 2. Tournament Selection: A certain number of individuals (called the tournament size) is randomly selected from the population.

[0056] Among these individuals, the one with the highest fitness is selected as the parent.

[0057] This approach can increase the diversity of the population and avoid premature convergence.

[0058] 3. Stochastic Universal Sampling (SUS): Similar to roulette wheel selection, but fairer and avoids the bias that may occur when the number of individuals in roulette wheel selection is small.

[0059] Place pointers of the same size as the population evenly on a line and distribute the line segments in proportion to the fitness of the individuals.

[0060] Randomly select a starting point and select other points at equal distances according to the population size, and select the individual on which the line segment falls.

[0061] 4. Rank Selection: Sort the population according to the fitness of the individuals.

[0062] Assign selection probabilities based on ranking rather than using fitness values ​​directly. For example, the first-ranked individual has the highest selection probability, and the last-ranked individual has the lowest selection probability.

[0063] This approach can reduce the impact of changes in the scale of fitness values.

[0064] 5. Linear Ranking Selection: Similar to ranked selection, but the selection probabilities are distributed through a linear function, so that individuals with higher rankings have a higher probability of selection, but not absolute.

[0065] 6. Elitism A certain number of the best individuals are retained in the new generation and enter the next generation directly without participating in crossover and mutation.

[0066] This can ensure the convergence of the algorithm and ensure that the optimal solution will not be destroyed.

[0067] For better understanding, the following selection sort selection method selects a preset number of parent chromosomes from multiple initial chromosomes for explanation: Assuming that the preset number is 5, the 10 chromosomes, initial chromosome 1 (58.33), initial chromosome 2 (65.5), initial chromosome 3 (68.5), initial chromosome 4 (68.5), initial chromosome 5 (72), initial chromosome 6 (73), initial chromosome 7 (74), initial chromosome 8 (75), initial chromosome 9 (76) and initial chromosome 10 (77), are sorted according to their fitness values.

[0068] The results after sorting are initial chromosome 10 (77), initial chromosome 9 (76), initial chromosome 8 (75), initial chromosome 7 (74), initial chromosome 6 (73), initial chromosome 5 (72), initial chromosome 4 (68.5), initial chromosome 3 (68.5), initial chromosome 2 (65.5) and initial chromosome 1 (58.33), and then the first 5 are selected as parent chromosomes (initial chromosome 10, initial chromosome 9, initial chromosome 8, initial chromosome 7 and initial chromosome 6), and the remaining chromosomes are non-parent chromosomes (initial chromosome 5, initial chromosome 4, initial chromosome 3, initial chromosome 2 and initial chromosome 1).

[0069] Step 5: Based on a preset crossover probability and a preset number of crossover points, a synchronous crossover operation is performed on a preset number of parent chromosomes to obtain a preset number of offspring chromosomes; In one embodiment, the crossover operation method includes but is not limited to single-point crossover, two-point crossover, multi-point crossover, uniform crossover, cyclic crossover, partial mapping crossover, sequential crossover, position-based crossover, and the like.

[0070] 1. Single-Point Crossover: A crossover point is randomly selected on the chromosome of an individual. The part before the crossover point is retained from one parent, and the part after the crossover point is from the other parent.

[0071] 2. Two-Point Crossover: Randomly select two crossover points on the chromosome of an individual. The part between the two crossover points is exchanged, and the rest remains unchanged.

[0072] 3. Multi-Point Crossover: Similar to two-point crossover, but multiple crossover points are selected on the chromosome. The crossover points divide the chromosome into multiple fragments, which are exchanged between parents.

[0073] 4. Uniform Crossover: For each gene on a chromosome, a random decision is made whether to exchange. Each gene has the same chance of being exchanged, independent of other genes.

[0074] 5. Cycle Crossover (CXP): Create offspring by tracking matches between two parent chromosomes. The matching genes form one or more cycles, and the cycles in the offspring chromosomes come from different parents.

[0075] 6. Partial Mapped Crossover (PMX): Similar to cyclic crossover, but uses mapping relationships to ensure that each gene appears only once in the offspring. Select a crossover region in the two parents and create a mapping relationship to exchange genes in the non-crossover region.

[0076] 7. Order Crossover (OX): Select a portion of the sequence of one parent and insert it into the other parent, keeping the relative position unchanged. The remaining genes are filled in according to the order of the other parent.

[0077] 8. Position-Based Crossover (PBX): Genes in the parent generation are selected according to a predefined position vector and inserted into the offspring.

[0078] It should be noted that since the number of parent chromosomes to be crossed needs to be determined based on the crossover probability, in order to ensure that the number of chromosomes in subsequent iterations remains consistent with the number of initial chromosomes, we directly use the parent chromosomes that have not performed the crossover operation as the daughter chromosomes.

[0079] For better understanding, the following selects multi-point crossover to perform synchronous crossover operations on a preset number of parent chromosomes to explain: Step 1: Determine the parent chromosome: Initial chromosome 6: {[160, 20], [200, 30], [80, 40], [250, 20], [130, 30], [120, 40]}.

[0080] Initial chromosome 7: {[170, 20], [210, 30], [70, 40], [260, 20], [120, 30], [110, 40]}.

[0081] Initial chromosome 8: {[180, 20], [220, 30], [60, 40], [270, 20], [110, 30], [100, 40]}.

[0082] Initial chromosome 9: {[190, 20], [230, 30], [50, 40], [280, 20], [100, 30], [90, 40]}.

[0083] Initial chromosome 10: {[200, 20], [240, 30], [40, 40], [290, 20], [90, 30], [80, 40]}.

[0084] Step 2: Determine the crossover probability to be 0.8 and the number of crossover points to be 2 There are 5 parent chromosomes in total, 5*0.8=4, that is, 4 parent chromosomes are randomly selected from the 5 parent chromosomes, and then the 4 parent chromosomes are crossover operated in pairs.

[0085] Assume that initial chromosome 6, initial chromosome 7, initial chromosome 8 and initial chromosome 10 are selected, and then initial chromosome 6 performs a crossover operation with initial chromosome 8, initial chromosome 7 performs a crossover operation with initial chromosome 10, and the number of crossovers is 2.

[0086] Step 3: Perform crossover operation: The result after the crossover operation: Daughter chromosome 6: {[160, 20], [220, 30], [80, 40], [250, 20], [110, 30], [120, 40]}.

[0087] Daughter chromosome 8: {[180, 20], [200, 30], [60, 40], [270, 20], [130, 30], [100, 40]}.

[0088] Daughter chromosome 7: {[200, 20], [210, 30], [70, 40], [260, 20], [120, 30], [80, 40]}.

[0089] Daughter chromosome 10: {[170, 20], [240, 30], [40, 40], [290, 20], [90, 30], [110, 40]}.

[0090] Step 6: Based on the preset mutation probability, perform synchronous mutation operations on a preset number of offspring chromosomes to obtain a preset number of target offspring chromosomes; In one embodiment, the mutation operation method includes but is not limited to 1. Bit Flip Mutation: For binary-coded chromosomes, bit flip mutation refers to randomly selecting one or more bits on the chromosome and flipping them (0 becomes 1, 1 becomes 0).

[0091] 2. Uniform Mutation: In this method, each gene has an equal chance of being randomly chosen a new value, which is usually chosen uniformly within the domain of the gene.

[0092] 3. Boundary Mutation: Similar to uniform mutation, but the new value is randomly selected on the boundary of the variable's domain instead of uniformly selected across the entire domain.

[0093] 4. Non-Uniform Mutation: This mutation method tends to produce larger mutation steps in the early stages of the algorithm. As the iterations proceed, the step size gradually decreases, which helps to quickly explore the solution space in the early stages of the search and fine-tune the solution in the later stages.

[0094] 5. Gaussian mutation: For real-number-coded chromosomes, Gaussian mutation refers to adding a random number that obeys the Gaussian (normal) distribution near the gene value to generate a new gene value.

[0095] 6. Polynomial Mutation: This method is usually used in real-coded genetic algorithms. It generates new gene values ​​through polynomial distribution and is usually used in some advanced evolutionary algorithms, such as differential evolution algorithms.

[0096] 7. Swap Mutation: For arrangement-coded chromosomes, swap mutation refers to randomly selecting two positions on the chromosome and exchanging the genes at these two positions.

[0097] 8. Insertion Mutation: In the sequenced chromosomes, insertion mutation refers to the random selection of a gene and its insertion into another random position.

[0098] 9. Inversion Mutation: For arrangement-coded chromosomes, inversion mutation refers to randomly selecting a subsequence on the chromosome and reversing it.

[0099] It should be noted that the probability of mutation is usually used to determine whether a single gene position mutates, while the number of mutations is used to determine how many mutations will occur in the population in total.

[0100] For better understanding, the following uniform mutation is used to perform synchronous mutation operations on a preset number of offspring chromosomes: Step 1: Determine the mutation probability to be 0.01 Step 2: Determine the offspring chromosomes: According to step 6, the offspring chromosomes are: Daughter chromosome 6: {[160, 20], [220, 30], [80, 40], [250, 20], [110, 30], [120, 40]}.

[0101] Daughter chromosome 8: {[180, 20], [200, 30], [60, 40], [270, 20], [130, 30], [100, 40]}.

[0102] Daughter chromosome 7: {[200, 20], [210, 30], [70, 40], [260, 20], [120, 30], [80, 40]}.

[0103] Daughter chromosome 10: {[170, 20], [240, 30], [40, 40], [290, 20], [90, 30], [110, 40]}.

[0104] Daughter chromosome 9: {[190, 20], [230, 30], [50, 40], [280, 20], [100, 30], [90, 40]}.

[0105] Step 3: Perform mutation operation Based on a mutation probability of 0.01, randomly select a gene value for a small change. Assume that only the first value of the gene may mutate, and the mutation operation is to increase or decrease the value by a fixed amount (for example, 1), that is, the first value of each gene has a 1% probability of increasing or decreasing by 1. The following are the chromosome values ​​after mutation: Daughter chromosome 6: {[160, 20], [220, 30], [80, 40], [250, 20], [110, 30], [120, 40]} Assume that the first value of the third gene mutates and decreases by 1. The target offspring chromosome 6 after mutation is: {[160, 20], [220, 30], [79, 40], [250, 20], [110, 30], [120, 40]} Daughter chromosome 8: {[180, 20], [200, 30], [60, 40], [270, 20], [130, 30], [100, 40]} Assume that the first value of the second gene mutates and decreases by 1. The target offspring chromosome 8 after mutation is: {[180, 20], [201, 30], [60, 40], [270, 20], [130, 30], [100, 40]} Daughter chromosome 7: {[200, 20], [210, 30], [70, 40], [260, 20], [120, 30], [80, 40]} Assume that the first value of the first gene mutates and increases by 1. The target offspring chromosome 7 after mutation is: {[201, 20], [210, 30], [70, 40], [260, 20], [120, 30], [80, 40]} Daughter chromosome 10: {[170, 20], [240, 30], [40, 40], [290, 20], [90, 30], [110, 40]} Assume that the first value of the 4th gene mutates and decreases by 1. The target offspring chromosome 10 after mutation is: {[170, 20], [240, 30], [40, 40], [289, 20], [90, 30], [110, 40]} Daughter chromosome 9: {[190, 20], [230, 30], [50, 40], [280, 20], [100, 30], [90, 40]} Assume that the first value of the second and fifth genes mutates, increasing by 1 and decreasing by 1 respectively. The target offspring chromosome 9 after mutation is: {[190, 20], [231, 30], [50, 40], [280, 20], [101, 30], [90, 40]} Step 7: Based on the multiple production requirements corresponding to the preset number of target offspring chromosomes and the production speed of the corresponding production equipment, the production resource utilization rate of each target offspring chromosome is obtained, and the production resource utilization rate of each target offspring chromosome is used as the fitness value of each target offspring chromosome; According to step 6, we can know that: target offspring chromosome 6: {[160, 20], [220, 30], [79, 40], [250, 20], [110, 30], [120, 40]}; target offspring chromosome 8: {[180, 20], [201, 30], [60, 40], [270, 20], [130, 30], [100, 40]}; target offspring chromosome 7: {[201, 20], [210, 30] , [70, 40], [260, 20], [120, 30], [80, 40]}; target offspring chromosome 10: {[170, 20], [240, 30], [40, 40], [289, 20], [90, 30], [110, 40]}; target offspring chromosome 9: {[190, 20], [231, 30], [50, 40], [280, 20], [101, 30], [90, 40]}.

[0106] Target progeny chromosome 6: =72.95 Target progeny chromosome 8: =75.06 Target progeny chromosome 7: =75.6 Target offspring chromosome 10: =75.4 Target offspring chromosome 9: =76.13 Step 8: Determine whether the current number of iterations is greater than the maximum number of iterations or whether the fitness value of any target offspring chromosome is greater than a preset fitness threshold; Step 9: If yes, then the multiple production demands and the production speeds of the corresponding production equipment corresponding to the target offspring chromosome with the largest fitness value are taken as the multiple optimal production demands and the production speeds of the corresponding production equipment; Specifically, assuming that the preset fitness threshold is 60, and the fitness values ​​of the target offspring chromosome 6, the target offspring chromosome 8, the target offspring chromosome 7, the target offspring chromosome 10, and the target offspring chromosome 9 are all greater than 60, the multiple optimal production demands corresponding to the maximum fitness value (target offspring chromosome 9) and the production speeds of the corresponding production equipment ({[190, 20], [231, 30], [50, 40], [280, 20], [101, 30], [90, 40]}) are taken as the multiple optimal production demands and the production speeds of the corresponding production equipment.

[0107] If not, the multiple initial chromosomes are updated to a preset number of target offspring chromosomes and non-parent chromosomes, and the process returns to step 3.

[0108] Specifically, assuming that the preset fitness threshold is 80, and none of the fitness values ​​of the target offspring chromosome 6, the target offspring chromosome 8, the target offspring chromosome 7, the target offspring chromosome 10, and the target offspring chromosome 9 is greater than 80, all the previous non-parent chromosomes (initial chromosome 1, initial chromosome 2, initial chromosome 3, initial chromosome 4, initial chromosome 5) are used as initial chromosomes, and then return to step 3 for loop iteration.

[0109] In one embodiment, before the step of updating the multiple initial chromosomes to a preset number of target offspring chromosomes and non-parent chromosomes, the method further includes: Calculate the standard deviation of the fitness values ​​of multiple target offspring chromosomes; The fitness value of the target offspring chromosome 6 is: =72.95 The fitness value of the target offspring chromosome 8 is: =75.06 The fitness value of the target offspring chromosome 7 is: =75.6 The fitness value of the target offspring chromosome 10 is: =75.4 The fitness value of the target offspring chromosome 9 is: =76.13 Standard Deviation: Calculate the average: 72.95+75.06+75.6+75.4+76.13=75.116 Compute the square of the difference between each value and the mean: (72.95−75.116) 2 =7.4284 (75.06−75.116) 2 =0.0126 (75.6−75.116) 2 =0.3604 (75.4−75.116) 2 =0.2364 (76.13−75.116) 2 =1.6424 Sum: 7.4284+0.0126+0.3604+0.2364+1.6424=9.669 Variance = 9.669 / 5 = 1.9338 Standard Deviation = ≈1.3959 Determine whether the standard deviation of the fitness values ​​of multiple target offspring chromosomes is greater than a preset standard deviation threshold; If yes, then increase the preset crossover probability or the preset number of crossover points or the preset mutation probability; If not, the preset crossover probability or the preset number of crossover points or the preset mutation probability is reduced.

[0110] Specifically, the population diversity is determined by calculating the standard deviation of the target offspring chromosome fitness value. If the standard deviation is greater than the preset threshold, it means that the population diversity is low and it is easy to fall into the local optimal solution. At this time, it is necessary to increase the crossover probability and mutation probability to increase the population diversity; conversely, if the standard deviation is less than the preset threshold, it means that the population diversity is high. At this time, the crossover probability and mutation probability can be reduced to improve the search efficiency.

[0111] In this embodiment, this adaptive parameter adjustment mechanism can effectively balance the search range and search efficiency of the algorithm, and improve the probability of the algorithm finding the global optimal solution.

[0112] In one embodiment, before the step of updating the multiple initial chromosomes to a preset number of target offspring chromosomes and non-parent chromosomes, the method further includes: Calculate the standard deviation of the fitness values ​​of multiple target offspring chromosomes; Specifically, refer to the process of calculating the variance, which will not be repeated here.

[0113] Determine whether the standard deviation of the fitness values ​​of multiple target offspring chromosomes is greater than a preset standard deviation threshold; If so, reduce the preset amount; If not, increase the preset amount.

[0114] Specifically, the population diversity is also determined by calculating the standard deviation of the target offspring chromosome fitness value. If the standard deviation is greater than the preset threshold, it means that the population diversity is low, and the population size needs to be reduced to improve the search efficiency; conversely, if the standard deviation is less than the preset threshold, it means that the population diversity is high, and the population size can be increased to expand the search range.

[0115] In this embodiment, this population size adjustment mechanism can effectively balance the search range and search efficiency of the algorithm, and improve the probability of the algorithm finding the global optimal solution.

[0116] S300, sending the optimal multiple production requirements and the production speeds of the corresponding production equipment to the production workshop to control the production workshop to produce according to the optimal multiple production requirements and the production speeds of the corresponding production equipment.

[0117] The production workshop refers to the actual place where products are produced, including production lines, equipment, workers, etc.

[0118] In one embodiment, the production scheduling results can be sent to the production workshop through electronic spreadsheets, production management systems, production scheduling software, etc. The production scheduling results can also be communicated to relevant personnel through production scheduling meetings, etc.

[0119] Specifically, each production equipment has its own corresponding production speed. Therefore, after obtaining the optimal multiple production demands and the production speeds of the corresponding production equipment, we can know which production equipment is needed to produce different production demands. Therefore, the production workshop arranges the corresponding production equipment to produce the corresponding production demands of the products, thereby ensuring that the utilization rate of the entire production resources can be maximized.

[0120] In one or more of the above embodiments, in addition to using genetic algorithms to optimize and solve the production resource utilization objective function, the present invention can also use other optimization algorithms to solve it. Among them, other optimization algorithms include but are not limited to: gradient descent method, Newton method, conjugate gradient method, quasi-Newton method, simplex method, interior point method, simulated annealing, particle swarm optimization, ant colony algorithm, differential evolution and artificial fish swarm algorithm.

[0121] Gradient Descent: It finds the minimum by iteratively reducing the gradient of the objective function.

[0122] Newton's Method: Use the first and second order derivatives of the objective function to find the root of the function, which can be used for optimization.

[0123] Conjugate Gradient Method: A modified gradient descent method that uses conjugate directions for search.

[0124] Quasi-Newton Method: Similar to Newton's method, but does not require the calculation of the second-order derivative matrix, but instead constructs an approximate matrix.

[0125] Simplex Method: Mainly used for linear programming problems, it finds the optimal solution by iteratively searching the vertices of the feasible domain.

[0126] Interior Point Method: An algorithm for solving linear programming and convex optimization problems by iteratively moving inside the feasible region to find the optimal solution.

[0127] Simulated Annealing: A probabilistic search algorithm inspired by the annealing process of solid materials.

[0128] Particle Swarm Optimization (PSO): simulates the social behavior of bird flocks or fish schools, and finds the optimal solution through the mutual cooperation of individuals in the group.

[0129] Ant Colony Optimization (ACO): Find the optimal solution to the problem by simulating the foraging behavior of ants.

[0130] Differential Evolution: An efficient global optimization algorithm that seeks the optimal solution by iteratively improving candidate solutions.

[0131] Artificial Fish Swarm Algorithm: Finds the optimal solution by simulating the foraging, grouping and chasing behaviors of fish schools.

[0132] Beneficial effects of the present invention: (1) Multi-factor optimization: The present invention comprehensively considers multiple production demands and the production speed of the corresponding production equipment, more comprehensively evaluates the utilization of production resources, and avoids the limitations brought by single-factor optimization.

[0133] (2) Improving the utilization rate of production resources: The present invention constructs a production resource utilization objective function and uses a genetic algorithm to find the optimal solution. This optimization method can effectively improve the utilization rate of production resources, reduce production costs, and improve production efficiency.

[0134] (3) Improving the quality of searching for the best solution: The genetic algorithm of the present invention dynamically adjusts the parameters of the genetic algorithm, so that it has a strong global search capability, can effectively handle complex problems, avoid falling into local optimal solutions, and improve the quality of searching for the best solution.

[0135] (4) Improving scheduling flexibility: The present invention can automatically generate the optimal production scheduling plan and can adjust it according to actual conditions, thereby improving scheduling flexibility and ensuring on-time delivery.

[0136] (5) High degree of automation: The present invention can automatically schedule the production master plan, reduce manual intervention, and improve the efficiency of production management.

[0137] Embodiment 2 Based on the same inventive concept, Figure 2 As shown, the embodiment of the present invention further provides a production master plan scheduling optimization device 200, comprising: The function construction module 210 is used to construct a production resource utilization objective function with multiple production requirements and corresponding production speeds of production equipment as inputs and the maximum production resource utilization as output, and to determine the constraint conditions of the production resource utilization objective function; The function solving module 220 is used to use an improved genetic algorithm to optimize and solve the production resource utilization objective function, and determine the optimal multiple production demands and the production speeds of the corresponding production equipment that meet the constraint conditions of the production resource utilization objective function; The scheduling optimization module 230 is used to send the optimal multiple production requirements and the production speeds of the corresponding production equipment to the production workshop to control the production workshop to produce according to the optimal multiple production requirements and the production speeds of the corresponding production equipment.

[0138] It should be understood that the device corresponds to the above-mentioned production master schedule optimization method embodiment and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the above description. To avoid repetition, the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0139] Embodiment 3 Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, including: a processor and a memory, the memory storing machine-readable instructions executable by the processor, and the machine-readable instructions executing the above-mentioned production master plan scheduling optimization method when executed by the processor.

[0140] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0141] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0142] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0143] Embodiment 4 Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the above-mentioned production master plan scheduling optimization method.

[0144] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0145] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0146] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0148] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0149] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0150] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0151] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A production master plan scheduling optimization method, characterized in that: include: Taking multiple production demands and the production speed of the corresponding production equipment as input and the maximum production resource utilization as output, a production resource utilization objective function is constructed, and the constraints of the production resource utilization objective function are determined; Using genetic algorithms, the objective function of production resource utilization is optimized and solved to determine the optimal multiple production demands and the corresponding production speeds of production equipment that meet the constraints of the objective function of production resource utilization; The optimal multiple production requirements and the production speeds of the corresponding production equipment are sent to the production workshop to control the production workshop to produce according to the optimal multiple production requirements and the production speeds of the corresponding production equipment.

2. The production master plan scheduling optimization method according to claim 1, characterized in that: The objective function of production resource utilization is: ;in, represents the maximum production resource utilization, represents the i-th production demand, represents the i-th production speed, Indicates the preset production plan deadline. Indicates the preset production plan start time.

3. The production master plan scheduling optimization method according to claim 2 is characterized in that: The constraints of the production resource utilization objective function are: ;in, Represents the total production demand.

4. The production master plan scheduling optimization method according to claim 1, characterized in that: Using genetic algorithms, the objective function of production resource utilization is optimized and solved to determine the optimal multiple production demands and the corresponding production speeds of production equipment that meet the constraints of the objective function of production resource utilization, including: Step 1: Initialize the number of chromosomes, the maximum number of iterations, and the preset fitness threshold; wherein the chromosomes include master chromosomes and slave chromosomes; Step 2: Real number encoding is performed on multiple production requirements and the production speeds of the corresponding production equipment respectively, and the multiple production requirements after real number encoding are mapped to multiple initial master chromosomes, and the production speeds of the multiple production equipment after real number encoding are mapped to multiple initial slave chromosomes; Step 3: Based on the multiple production demands corresponding to each initial master chromosome and the production speeds of the multiple production equipment corresponding to each initial slave chromosome, the production resource utilization rate of each initial chromosome is obtained, and the production resource utilization rate of each initial chromosome is used as the fitness value of each initial chromosome; Step 4: Based on the fitness value of each initial chromosome, a preset number of parent chromosomes are selected from multiple initial chromosomes, and the initial chromosomes other than the preset number of parent chromosomes are determined as non-parent chromosomes; Step 5: Based on a preset crossover probability and a preset number of crossover points, a synchronous crossover operation is performed on a preset number of parent chromosomes to obtain a preset number of offspring chromosomes; Step 6: Based on the preset mutation probability, perform synchronous mutation operations on a preset number of offspring chromosomes to obtain a preset number of target offspring chromosomes; Step 7: Based on the multiple production requirements corresponding to the preset number of target offspring chromosomes and the production speed of the corresponding production equipment, the production resource utilization rate of each target offspring chromosome is obtained, and the production resource utilization rate of each target offspring chromosome is used as the fitness value of each target offspring chromosome; Step 8: Determine whether the current number of iterations is greater than the maximum number of iterations or the fitness value of any target offspring chromosome is greater than a preset fitness threshold; Step 9: If yes, then the multiple production demands and the production speeds of the corresponding production equipment corresponding to the target offspring chromosome with the largest fitness value are taken as the multiple optimal production demands and the production speeds of the corresponding production equipment; If not, the multiple initial chromosomes are updated to a preset number of target offspring chromosomes and non-parent chromosomes, and the process returns to step 3.

5. The production master plan scheduling optimization method according to claim 4 is characterized in that: Based on the multiple production demands corresponding to each initial master chromosome and the production speeds of multiple production equipment corresponding to each initial slave chromosome, the production resource utilization rate of each initial chromosome is obtained, including: The following formula is used to calculate the multiple production demands corresponding to each initial master chromosome and the production speeds of multiple production equipment corresponding to each initial slave chromosome to obtain the production resource utilization rate of each initial chromosome; ;in, represents the production resource utilization rate of each initial chromosome, represents the i-th production demand of the initial chromosome, represents the production speed of the i-th production equipment of the initial chromosome, Indicates the preset production plan deadline. Indicates the preset production plan start time.

6. The production master plan scheduling optimization method according to claim 4, characterized in that: Before the step of updating the multiple initial chromosomes to a preset number of target offspring chromosomes and non-parent chromosomes, the method further includes: Calculate the standard deviation of the fitness values ​​of multiple target offspring chromosomes; Determine whether the standard deviation of the fitness values ​​of multiple target offspring chromosomes is greater than a preset standard deviation threshold; If yes, then increase the preset crossover probability or the preset number of crossover points or the preset mutation probability; If not, the preset crossover probability or the preset number of crossover points or the preset mutation probability is reduced.

7. The production master plan scheduling optimization method according to claim 4 is characterized in that: Before the step of updating the multiple initial chromosomes to a preset number of target offspring chromosomes and non-parent chromosomes, the method further includes: Calculate the standard deviation of the fitness values ​​of multiple target offspring chromosomes; Determine whether the standard deviation of the fitness values ​​of multiple target offspring chromosomes is greater than a preset standard deviation threshold; If so, reduce the preset amount; If not, increase the preset amount.

8. A production master plan scheduling optimization device, characterized in that: include: A function building module is used to take multiple production demands and the production speed of corresponding production equipment as input, take the maximum production resource utilization as output, build a production resource utilization objective function, and determine the constraint conditions of the production resource utilization objective function; The function solving module is used to use a genetic algorithm to optimize and solve the production resource utilization objective function, and determine the optimal multiple production demands and the production speed of the corresponding production equipment that meet the constraint conditions of the production resource utilization objective function; The scheduling optimization module is used to send the optimal multiple production requirements and the production speeds of the corresponding production equipment to the production workshop to control the production workshop to produce according to the optimal multiple production requirements and the production speeds of the corresponding production equipment.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the production master plan scheduling optimization method described in any one of claims 1-7 is executed.

10. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a computer, the computer is enabled to execute the production master plan scheduling optimization method described in any one of claims 1 to 7.

Images