Reaction kettle production scheduling method and device, computer equipment and storage medium

Abstract

The invention relates to a reaction kettle production scheduling method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring work order information of production scheduling of a reaction kettle; performing dynamic virtual splitting on the work order information to generate an initial chemical work order population; performing fitness value evaluation according to the initial chemical single population to obtain an evaluation result; performing crossover operation according to the evaluation result to obtain a crossover result; performing mutation operation according to the crossing result to obtain a mutation result; and sorting according to a variation result to generate a production scheduling plan. According to the method, automatic production scheduling of large-scale orders can be achieved without manual intervention, the scheduling production scheduling problem of a multi-dimensional optimization target is solved in the complex production environment of processing large orders, multiple production lines and multiple materials, errors caused by manual operation are reduced through automatic production scheduling, the accuracy and reliability of a production scheduling plan are improved, and the production scheduling efficiency is improved. The method is suitable for connection rules of continuous batch production lines, so that the production process is more efficient and controllable.

Description

Technical Field

[0001] The present application relates to the technical field of production scheduling, and particularly to a reactor production scheduling method, device, computer device, and storage medium. Background Art

[0002] In the manufacturing industry, the optimization of shop floor production scheduling is the key to improving production efficiency and enterprise competitiveness. Traditional manual scheduling methods are often inefficient and error-prone when dealing with a large number of orders and complex production line rules. The fine chemical industry focuses on the deep processing of chemical raw materials and their products, and its products are known for high added value and specialization. Compared with bulk chemicals, fine chemical products have a wide variety of types, complex and variable production processes, and must be customized according to the specific needs of customers. At present, most manufacturing enterprises have promoted systems such as ERP and MES, and have achieved informatization in the production execution aspect, but the pre-production planning stage still relies on manual experience for scheduling, resulting in the disconnection between production planning and production execution. Therefore, how to achieve the rapid transformation of enterprises under the general trend of intelligent manufacturing transformation has become a long-term goal of the manufacturing industry.

[0003] In the production process of fine chemical enterprises, planning and scheduling are at the core. It not only determines the specific time of material requirements but also directly affects the completion time of products. However, the unique production characteristics of the fine chemical industry pose many challenges to traditional scheduling methods: due to diverse and frequently changing customer demands, production plans need to be adjusted frequently; the complexity of production processes requires precise control of reaction conditions, which increases the difficulty of production equipment switching and maintenance; under limited production capacity conditions, how to reasonably allocate resources to maximize output benefits is also a complex optimization problem. Although most current literature and patents mainly focus on traditional job shop scheduling problems (JSP) and flexible job shop scheduling problems (FJSP), these models do not fully consider the special needs of the fine chemical industry and thus cannot effectively solve the scheduling problems in this field. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a reactor production scheduling method, device, computer device, computer-readable storage medium, and computer program product that can perform intelligent scheduling.

[0005] In a first aspect, the present application provides a reactor production scheduling method. The method includes:

[0006] Obtain the work order information for reactor production scheduling;

[0007] Dynamically and virtually split the work order information to generate an initial chemical work order population;

[0008] Evaluate the fitness value based on the initial work order population to obtain an evaluation result;

[0009] Perform a crossover operation based on the evaluation result to obtain a crossover result;

[0010] Perform a mutation operation based on the crossover result to obtain a mutation result;

[0011] Sort according to the mutation result to generate a production scheduling plan.

[0012] In one embodiment, initialize the population of the initial work order to generate a chromosome population;

[0013] Evaluate the fitness value of the chromosomes in the chromosome population to obtain an evaluation result;

[0014] The calculation formula for the fitness value evaluation is as follows:

[0015] f = -w 1 E + w 2 U - w 3 C + w 4 O r + w 5 O n

[0016] w 1 、w 2 、w 3 、w 4 、w 5 are user-defined weights;

[0017] E is the evaluation score for violating the earliest start time rule;

[0018] U is the evaluation score for resource utilization rate;

[0019] C is the evaluation score for the cleaning time between work orders;

[0020] O r is the evaluation score for the order completion rate;

[0021] O n is the evaluation score for the order completion quantity;

[0022] E, U, C, O r 、O n are all normalized.

[0023] In one embodiment, randomly select chromosomes from the evaluation result for fitness value comparison to obtain a tournament population;

[0024] Perform a crossover operation on the chromosomes in the tournament population to generate crossover chromosomes;

[0025] Combine the crossover chromosomes to form a population and obtain the crossover result.

[0026] In one embodiment, perform a mutation operation on the crossover chromosomes to generate mutant chromosomes;

[0027] Combine the mutant chromosomes to form a population and obtain the mutation result.

[0028] In one embodiment, detect whether the sorting of the mutation result satisfies a preset switching rule;

[0029] If the work order sorting of the mutation result satisfies the preset switching rule, then sort multiple work orders to generate a production scheduling plan;

[0030] If the work order sorting of the mutation result does not satisfy the preset switching rule, then add cleaning work orders before and after this work order, and then generate a production scheduling plan.

[0031] In one embodiment, detect whether the crossover rate of the crossover chromosomes is greater than the crossover threshold;

[0032] If the crossover rate of the crossover chromosomes is less than or equal to the crossover threshold, then detect whether the mutation rate of this chromosome is greater than the mutation threshold;

[0033] If the mutation rate of this chromosome is less than or equal to the mutation threshold, then perform fitness value evaluation on this chromosome.

[0034] In a second aspect, the present application also provides a reactor production scheduling device. The device includes:

[0035] An information acquisition module, configured to acquire work order information for reactor production scheduling;

[0036] A virtual splitting module, configured to dynamically and virtually split the work order information to generate an initial work order population;

[0037] An information evaluation module, configured to perform fitness value evaluation according to the initial work order population to obtain an evaluation result;

[0038] A crossover operation module, configured to perform a crossover operation according to the evaluation result to obtain a crossover result;

[0039] A mutation operation module, configured to perform a mutation operation according to the crossover result to obtain a mutation result;

[0040] A production scheduling module, configured to generate a production scheduling plan according to the mutation result.

[0041] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0042] Obtain the work order information for the production scheduling of the reactor;

[0043] Dynamically and virtually split the work order information to generate an initial work order population;

[0044] Evaluate the fitness value based on the initial work order population to obtain an evaluation result;

[0045] Perform a crossover operation based on the evaluation result to obtain a crossover result;

[0046] Perform a mutation operation based on the crossover result to obtain a mutation result;

[0047] Sort according to the mutation result to generate a production scheduling plan.

[0048] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0049] Obtain the work order information for the production scheduling of the reactor;

[0050] Dynamically and virtually split the work order information to generate an initial work order population;

[0051] Evaluate the fitness value based on the initial work order population to obtain an evaluation result;

[0052] Perform a crossover operation based on the evaluation result to obtain a crossover result;

[0053] Perform a mutation operation based on the crossover result to obtain a mutation result;

[0054] Sort according to the mutation result to generate a production scheduling plan.

[0055] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0056] Obtain the work order information for the production scheduling of the reactor;

[0057] Dynamically and virtually split the work order information to generate an initial work order population;

[0058] Evaluate the fitness value based on the initial work order population to obtain an evaluation result;

[0059] Perform a crossover operation based on the evaluation result to obtain a crossover result;

[0060] Perform a mutation operation based on the crossover result to obtain a mutation result;

[0061] Perform sorting based on the mutation result to generate a production scheduling plan.

[0062] The above reactor production scheduling method, device, computer device and storage medium, obtain the work order information of reactor production scheduling; dynamically and virtually split the work order information to generate an initial work order population; perform fitness value evaluation based on the initial work order population to obtain an evaluation result; perform a crossover operation based on the evaluation result to obtain a crossover result; perform a mutation operation based on the crossover result to obtain a mutation result; perform sorting based on the mutation result to generate a production scheduling plan. The present invention can achieve automated production scheduling for large-scale orders without manual intervention, handle the scheduling and production problems of multi-dimensional optimization objectives in a complex production environment with large orders, multiple production lines and multiple materials, reduce the errors caused by manual operations through automated production scheduling, improve the accuracy and reliability of the production scheduling plan, and is applicable to the connection rules of continuous batch production lines, making the production process more efficient and controllable. Brief Description of the Drawings

[0063] Figure 1 It is an application environment diagram of the reactor production scheduling method in an embodiment;

[0064] Figure 2 It is a flow schematic diagram of the reactor production scheduling method in an embodiment;

[0065] Figure 3 It is a dynamic splitting flow chart of the reactor production scheduling method in an embodiment;

[0066] Figure 4 It is a work order sorting schematic diagram of the reactor production scheduling method in an embodiment;

[0067] Figure 5 It is a double-layer coding schematic diagram of the reactor production scheduling method in an embodiment;

[0068] Figure 6 It is a flow schematic diagram of the reactor production scheduling method in another embodiment;

[0069] Figure 7 It is a structural block diagram of the reactor production scheduling device in an embodiment;

[0070] Figure 8 It is an internal structure diagram of a computer device in an embodiment. Detailed Description of the Invention

[0071] To make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0072] The reaction kettle production scheduling method provided by the embodiment of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. Obtain the work order information for the reaction kettle production scheduling; perform dynamic virtual splitting on the work order information to generate an initial work order population; perform fitness value evaluation according to the initial work order population to obtain an evaluation result; perform crossover operation according to the evaluation result to obtain a crossover result; perform mutation operation according to the crossover result to obtain a mutation result; perform sorting according to the mutation result to generate a production scheduling plan. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be instrument meters, sensor devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0073] In one embodiment, as Figure 2 shown, a reaction kettle production scheduling method is provided. Taking the method applied to the Figure 1 server 104 as an example, the method includes the following steps:

[0074] Step 202, obtain the work order information for the reaction kettle production scheduling.

[0075] Step 204, perform dynamic virtual splitting on the work order information to generate an initial work order population.

[0076] Specifically, the work order information is stratified by using dynamic splitting technology to generate an initial work order population suitable for the genetic algorithm, ensuring that the production scheduling plan of each population individual can meet specific production scheduling constraints.

[0077] In one embodiment, as Figure 3 shown, the specific process of the work order splitting process is as follows:

[0078] 1. Requirement sorting.

[0079] Specifically, first sort all requirements.

[0080] 2. There are uncalculated orders.

[0081] Specifically, check whether there are unprocessed demand orders.

[0082] 3. Select the first sorted demand.

[0083] Specifically, if there are uncalculated demand orders, select the demand ranked at the top.

[0084] 4. Calculate the resource group first.

[0085] Specifically, determine whether the demand can be immediately met according to the availability of resources.

[0086] 5. Determine whether there are resources with available time before the delivery date.

[0087] Specifically, if there are resources with available time before the delivery date, enter the first stage; if there are no resources with available time before the delivery date, enter the second stage.

[0088] First stage:

[0089] 6. Sort the resource groups with virtual available time before the delivery date.

[0090] 7. There are resource groups that can be selected in sequence.

[0091] Specifically, if there are no resource groups that can be selected in sequence, determine whether there are resources with available time before the delivery date.

[0092] If there are resource groups that can be selected in sequence, perform sorting within the resource groups.

[0093] 7. Sort within the resource groups.

[0094] Specifically, sort all resource groups. If the virtual earliest available time within the group is the same, perform priority sorting within the group. Otherwise, sort the resource groups in ascending order according to the virtual earliest available time.

[0095] 8. Select the resource with the earliest virtual available time within the group.

[0096] Specifically, if the remaining demand is greater than 0 and the virtual available time within the group is the same, perform batch splitting + assign virtual time + update resource status + demand deduction.

[0097] 9. If the remaining demand is greater than 0 and the virtual available time within the group is different, perform batch splitting + assign virtual time + update resource status + demand deduction, and continue to execute the next step; if the remaining demand is 0, end the process and generate an initial work order population.

[0098] Second stage:

[0099] 9. Sort all resource groups.

[0100] 10. Select the resource with the earliest virtual available time within the resource group.

[0101] 11. Whether the virtual earliest times within the group are consistent.

[0102] Specifically, if the virtual earliest times within the group are consistent, then perform a descending order of the priorities within the group, traverse the resource group in sequence, then split batches + assign virtual time + update the resource status + deduct requirements. If the remaining requirements are greater than 0, then traverse the resource group in sequence and continue to execute the next step; if the remaining requirements are 0, then end the process and generate the initial work order population.

[0103] If the virtual earliest times within the group are not consistent, then sort the resource group in ascending order according to the virtual available time, select the resource with the earliest virtual available time within the resource group, then split batches + assign virtual time + update the resource status + deduct requirements. If the remaining requirements are greater than 0, then select the resource with the earliest virtual available time within the resource group and continue to execute the next step; if the remaining requirements are 0, then end the process and generate the initial work order population.

[0104] Step 206, perform a fitness value evaluation based on the initial work order population to obtain an evaluation result.

[0105] Specifically, initialize the population of the initial work order population to generate a chromosome population; perform a fitness value evaluation on the chromosomes in the chromosome population to obtain an evaluation result.

[0106] More specifically, create a group containing multiple possible solutions, where the solution is a chromosome and the group is a chromosome population.

[0107] The calculation formula for the fitness value evaluation is as follows:

[0108] f = -w 1 E + w 2 U - w 3 C + w 4 O r + w 5 O n

[0109] w 1 、w 2 、w 3 、w 4 、w 5 are user-defined weights;

[0110] E is the evaluation score for violating the earliest start time rule;

[0111] U is the evaluation score for resource utilization;

[0112] C is the evaluation score for the cleaning time between work orders;

[0113] O r is the evaluation score for the order completion rate;

[0114] O n is the evaluation score for the order completion quantity;

[0115] E, U, C, O r , O n are all normalized.

[0116] Step 208, perform a crossover operation according to the evaluation result to obtain a crossover result.

[0117] Specifically, randomly select chromosomes in the evaluation result for fitness value comparison to obtain a tournament population; perform a crossover operation on the chromosomes in the tournament population to generate crossover chromosomes; form a population with the crossover chromosomes to obtain a crossover result.

[0118] Among them, the chromosome consists of two layers of encoding: a resource selection layer and a work order sequence layer.

[0119] Resource selection layer encoding: The first layer of encoding represents resource selection, and A, B, and C respectively represent different resources. For example, as Figure 4 shown, the encoding of the first row is AAABCACCCBAABA.

[0120] Work order sequence layer encoding: The second layer of encoding represents the sorting of work orders, and the numbers represent the work order assignment order. For example, as Figure 4 shown, the second row is 1573241061129, indicating the processing order of work orders.

[0121] More specifically, for each pair of selected chromosome parents, perform a crossover operation once to create two crossover chromosomes. The crossover operation is to exchange some genes of the chromosome parents to create crossover chromosomes. For example, for the resource selection layer, a cut point can be randomly selected and the resource selection of the chromosome parents is crossed here; for the work order sequence layer, the same method can be adopted, a cut point is randomly selected and the work order sequence of the chromosome parents is crossed here.

[0122] Step 210, perform a mutation operation according to the crossover result to obtain a mutation result.

[0123] Specifically, perform a mutation operation on the crossover chromosomes to generate mutant chromosomes; form a population with the mutant chromosomes to obtain a mutation result.

[0124] More specifically, for each crossover chromosome, a mutation operation is performed to change some of its genes. This is usually achieved by flipping a bit in the crossover chromosome. At the resource selection layer, mutation may mean replacing one resource with another; at the work order sequence layer, mutation may mean adjusting the order of work orders.

[0125] Add all the generated mutant chromosomes to the new population, replacing a part of the members of the old population to form a new population.

[0126] Step 212, sort according to the mutation result to generate a production scheduling plan.

[0127] Specifically, detect whether the sorting of the mutation result meets a preset switching rule; if the work order sorting of the mutation result meets the preset switching rule, then sort multiple work orders to generate a production scheduling plan; if the work order sorting of the mutation result does not meet the preset switching rule, then add cleaning work orders before and after this work order, and then generate a production scheduling plan.

[0128] In one embodiment, replace a part of the members of the old population with all the mutant chromosomes to form a new population. As Figure 5 shown, each chromosome of the new population is assigned work orders according to Figure 5 and the blue squares are work order sorting actions. At the same time, follow the switching rule, that is, if the materials before and after do not meet the switching rule table, then add a cleaning work order between the front and back work orders.

[0129] The method further includes: detecting whether the crossover rate of the crossover chromosome is greater than the crossover threshold; if the crossover rate of the crossover chromosome is less than or equal to the crossover threshold, then detect whether the mutation rate of this chromosome is greater than the mutation threshold; if the mutation rate of this chromosome is less than or equal to the mutation threshold, then evaluate the fitness value of this chromosome.

[0130] wherein, the crossover threshold and the mutation threshold

[0131] Specifically, calculate the fitness value of each chromosome in the population, and mark the chromosome with the highest fitness value as the best solution.

[0132] More specifically, after forming the new population, check whether there is a chromosome in the new population with a higher fitness value than the chromosome with the highest fitness value before; if there is a chromosome with a higher fitness value, then update this chromosome as the best solution.

[0133] The method further includes: detecting whether a predefined termination condition has been reached; if the predefined termination condition has been reached, then stop the calculation; if the predefined termination condition has not been reached, then continue the next round of calculation.

[0134] Specifically, the termination condition can be conditions such as reaching the maximum number of iterations or a certain number of chromosome fitness values being greater than a preset value.

[0135] In a specific embodiment, as Figure 6 shown, the specific steps are as follows:

[0136] 1. Start: The program starts.

[0137] 2. Input the data required by the algorithm.

[0138] Specifically, input the parameters and data required by the algorithm, such as the objective function, the initial solution set, etc.

[0139] 3. Parameter initialization.

[0140] Specifically, initialize the parameters in the algorithm, such as the population size, the crossover probability, the mutation probability, etc.

[0141] 4. Select to the resource group in sequence.

[0142] Specifically, select individuals from the current population into a new population according to a certain rule or strategy.

[0143] 5. Judge to end.

[0144] Specifically, detect whether the predefined termination condition has been reached, and then stop the algorithm.

[0145] 6. Population initialization.

[0146] Specifically, create a population (referred to as the "chromosome population") containing multiple possible solutions (referred to as "chromosomes"). Each chromosome consists of two layers of encoding: the resource selection layer and the work order layer.

[0147] 7. Fitness value function evaluation.

[0148] Specifically, for each chromosome, calculate its corresponding fitness value, which usually involves converting the chromosome into a solution to the actual problem and applying the objective function to evaluate its quality.

[0149] 8. Save the optimal chromosome.

[0150] Specifically, mark the chromosome with the highest fitness value as the current best solution.

[0151] 9. Tournament selection.

[0152] Specifically, randomly select a certain number of chromosomes from the current chromosome population and compare their fitness values.

[0153] By randomly selecting a chromosome as the seed chromosome, and then randomly selecting several other chromosomes to compare with the seed chromosome. Compare the fitness values of these chromosomes and select the chromosome with the highest fitness value as the winner. Repeat this process multiple times until enough winners are selected. Add the winners to the population to obtain a new generation of population, preventing local optima and achieving data diversity.

[0154] 10. Crossover operation.

[0155] Specifically, for each pair of selected chromosome parents, perform a crossover operation to create two crossover chromosomes.

[0156] More specifically, detect whether the crossover rate of the crossover chromosome is greater than the crossover threshold; if the crossover rate of the crossover chromosome is less than or equal to the crossover threshold, then detect whether the mutation rate of this crossover chromosome is greater than the mutation threshold.

[0157] 11. Mutation operation.

[0158] Specifically, for each crossover chromosome, perform a mutation operation to change some of its genes to generate a mutant chromosome.

[0159] More specifically, detect whether the mutation rate of the mutant chromosome is greater than the mutation threshold; if the mutation rate of the mutant chromosome is less than or equal to the mutation threshold, then evaluate the fitness value of this mutant chromosome.

[0160] 12. New population formation.

[0161] Specifically, add all the generated mutant chromosomes to the new population, replacing a part of the members of the old population to form a new population.

[0162] 13. Work order assignment sorting.

[0163] Specifically, perform work order assignment sorting on each chromosome in the new population.

[0164] 14. Fitness value function re-evaluation.

[0165] Specifically, recalculate the fitness value of each chromosome in the new population.

[0166] 15. Update the optimal chromosome.

[0167] Specifically, check whether there is a chromosome in the new population with a higher fitness value than the chromosome with the highest fitness value before; if there is a chromosome with a higher fitness value, then update this chromosome as the best solution.

[0168] 16. Determine the termination condition.

[0169] Specifically, detect whether the predefined termination condition has been reached, and then stop the algorithm.

[0170] In the above-mentioned reactor production scheduling method, obtain the work order information for reactor production scheduling; evaluate the fitness value according to the initial work order population to obtain an evaluation result; perform a crossover operation according to the evaluation result to obtain a crossover result; perform a mutation operation according to the crossover result to obtain a mutation result; sort according to the mutation result to generate a production scheduling plan. The present invention can achieve automatic production scheduling of large-scale orders without manual intervention, handle the scheduling and production problems of multi-dimensional optimization objectives in a complex production environment with large orders, multiple production lines, and multiple materials, reduce the errors caused by manual operations through automatic production scheduling, improve the accuracy and reliability of the production scheduling plan, and is applicable to the connection rules of continuous batch production lines, making the production process more efficient and controllable.

[0171] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0172] Based on the same inventive concept, the embodiment of the present application also provides a reactor production scheduling device for implementing the above-mentioned reactor production scheduling method. The implementation solution provided by this device to solve problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the reactor production scheduling device provided below can refer to the limitations on the reactor production scheduling method in the above text, and will not be repeated here.

[0173] In one embodiment, as Figure 7 shown, a reactor production scheduling device is provided, including: an information acquisition module 710, a virtual splitting module 720, an information evaluation module 720, a crossover operation module 730, a mutation operation module 740, and a production scheduling plan module 750, where:

[0174] The information acquisition module 710 is used to acquire the work order information for reactor production scheduling.

[0175] The virtual splitting module 720 is used to dynamically and virtually split the work order information to generate an initial work order population.

[0176] An information evaluation module 730, which is used to evaluate the fitness values according to the initialized work order population and obtain an evaluation result.

[0177] A crossover operation module 740, which is used to perform a crossover operation according to the evaluation result and obtain a crossover result.

[0178] A mutation operation module 750, which is used to perform a mutation operation according to the crossover result and obtain a mutation result.

[0179] A production scheduling plan module 760, which is used to generate a production scheduling plan according to the mutation result.

[0180] The information evaluation module 730 is further used to initialize the population of the initialized work order to generate a chromosome population;

[0181] Evaluate the fitness values of the chromosomes in the chromosome population to obtain an evaluation result;

[0182] The calculation formula for the fitness value evaluation is as follows:

[0183] f = -w 1 E + w 2 U - w 3 C + w 4 O r + w 5 O n

[0184] w 1 、w 2 、w 3 、w 4 、w 5 are user-defined weights;

[0185] E is the evaluation score for violating the earliest start time rule;

[0186] U is the evaluation score for resource utilization rate;

[0187] C is the evaluation score for the cleaning time between work orders;

[0188] O r is the evaluation score for the order completion rate;

[0189] O n is the evaluation score for the order completion quantity;

[0190] E, U, C, O r 、O n are all normalized.

[0191] The crossover operation module 740 is further used to randomly select chromosomes from the evaluation results for fitness value comparison to obtain a tournament population;

[0192] Perform a crossover operation on the chromosomes in the tournament population to generate crossover chromosomes;

[0193] Form a population with the crossover chromosomes to obtain a crossover result.

[0194] The mutation operation module 750 is further configured to perform a mutation operation on the crossover chromosomes to generate mutant chromosomes;

[0195] Form a population with the mutant chromosomes to obtain a mutation result.

[0196] The production scheduling plan module 760 is further configured to detect whether the sorting of the mutation result meets a preset switching rule;

[0197] If the work order sorting of the mutation result meets the preset switching rule, then sort multiple work orders to generate a production scheduling plan;

[0198] If the work order sorting of the mutation result does not meet the preset switching rule, then add cleaning work orders before and after this work order, and then generate a production scheduling plan.

[0199] The mutation operation module 750 is further configured to detect whether the crossover rate of the crossover chromosomes is greater than a crossover threshold;

[0200] If the crossover rate of the crossover chromosomes is less than or equal to the crossover threshold, then detect whether the mutation rate of this chromosome is greater than a mutation threshold;

[0201] If the mutation rate of this chromosome is less than or equal to the mutation threshold, then perform a fitness value evaluation on this chromosome.

[0202] Each module in the above reactor production scheduling device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above respective modules.

[0203] In one embodiment, a computer device is provided. This computer device can be a server, and its internal structure diagram can be as Figure 8As shown. The computer device includes a processor, a memory, and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store production scheduling plan data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a reactor production scheduling method.

[0204] Those skilled in the art can understand that Figure 8 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0205] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements any one of the reactor production scheduling methods in the above embodiments.

[0206] Obtain the work order information for reactor production scheduling;

[0207] Dynamically and virtually split the work order information to generate an initial work order population;

[0208] Evaluate the fitness value according to the initial work order population to obtain an evaluation result;

[0209] Perform a crossover operation according to the evaluation result to obtain a crossover result;

[0210] Perform a mutation operation according to the crossover result to obtain a mutation result;

[0211] Sort according to the mutation result to generate a production scheduling plan.

[0212] In one embodiment, when the processor executes the computer program, it also implements the following steps: Initialize the population of the initial work order population to generate a chromosome population;

[0213] Evaluate the fitness value of the chromosomes in the chromosome population to obtain an evaluation result;

[0214] The calculation formula for the fitness value evaluation is as follows:

[0215] f = -w 1 E + w 2 U - w3 C + w 4 O r + w 5 O n

[0216] w 1 、w 2 、w 3 、w 4 、w 5 are user-defined weights;

[0217] E is the evaluation score for violating the earliest start time rule;

[0218] U is the evaluation score for resource utilization rate;

[0219] C is the evaluation score for the cleaning time between work cells;

[0220] O r is the evaluation score for order completion rate;

[0221] O n is the evaluation score for the number of completed orders;

[0222] E, U, C, O r 、O n are all normalized.

[0223] In one embodiment, when the processor executes the computer program, the following steps are further implemented: randomly select chromosomes in the evaluation results for fitness value comparison to obtain a tournament population;

[0224] Perform crossover operations on the chromosomes in the tournament population to generate crossover chromosomes;

[0225] Form a population with the crossover chromosomes to obtain a crossover result.

[0226] In one embodiment, when the processor executes the computer program, the following steps are further implemented: perform mutation operations on the crossover chromosomes to generate mutant chromosomes;

[0227] Form a population with the mutant chromosomes to obtain a mutation result.

[0228] In one embodiment, when the processor executes the computer program, the following steps are further implemented: detect whether the sorting of the mutation results meets a preset switching rule;

[0229] If the work order sorting of the mutation results meets the preset switching rule, then sort multiple work orders to generate a production plan;

[0230] If the work order sorting of the mutation results does not meet the preset switching rule, then add cleaning work orders before and after this work order, and then generate a production plan.

[0231] In one embodiment, when the processor executes the computer program, the following steps are further implemented: detecting whether the crossover rate of the crossover chromosome is greater than the crossover threshold;

[0232] If the crossover rate of the crossover chromosome is less than or equal to the crossover threshold, detecting whether the mutation rate of the chromosome is greater than the mutation threshold;

[0233] If the mutation rate of the chromosome is less than or equal to the mutation threshold, evaluating the fitness value of the chromosome.

[0234] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the reactor production scheduling methods in the above embodiments is implemented.

[0235] Obtaining the work order information of the reactor production scheduling;

[0236] Dynamically and virtually splitting the work order information to generate an initial work order population;

[0237] Evaluating the fitness value according to the initial work order population to obtain an evaluation result;

[0238] Performing a crossover operation according to the evaluation result to obtain a crossover result;

[0239] Performing a mutation operation according to the crossover result to obtain a mutation result;

[0240] Sorting according to the mutation result to generate a production scheduling plan.

[0241] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: initializing the population of the initial work order population to generate a chromosome population;

[0242] Evaluating the fitness value of the chromosomes in the chromosome population to obtain an evaluation result;

[0243] The calculation formula for the fitness value evaluation is as follows:

[0244] f = -w 1 E + w 2 U - w 3 C + w 4 O r + w 5 O n

[0245] w 1 、w 2 、w 3 、w 4 、w 5 are user-defined weights;

[0246] E is the evaluation score for violating the earliest start time rule;

[0247] U is the evaluation score for resource utilization rate;

[0248] C is the evaluation score for the cleaning time between work cells;

[0249] O r is the evaluation score for the order completion rate;

[0250] O n is the evaluation score for the order completion quantity;

[0251] E, U, C, O r , O n are all normalized.

[0252] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: randomly select chromosomes in the evaluation results for fitness value comparison to obtain a tournament population;

[0253] Perform a crossover operation on the chromosomes in the tournament population to generate crossover chromosomes;

[0254] Form a population with the crossover chromosomes to obtain a crossover result.

[0255] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: perform a mutation operation on the crossover chromosomes to generate mutant chromosomes;

[0256] Form a population with the mutant chromosomes to obtain a mutation result.

[0257] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: detect whether the sorting of the mutation result satisfies a preset switching rule;

[0258] If the work order sorting of the mutation result satisfies the preset switching rule, then sort multiple work orders to generate a production scheduling plan;

[0259] If the work order sorting of the mutation result does not satisfy the preset switching rule, then add cleaning work orders before and after this work order, and then generate a production scheduling plan.

[0260] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: detect whether the crossover rate of the crossover chromosomes is greater than the crossover threshold;

[0261] If the crossover rate of the crossover chromosomes is less than or equal to the crossover threshold, then detect whether the mutation rate of this chromosome is greater than the mutation threshold;

[0262] If the mutation rate of the chromosome is less than or equal to the mutation threshold, the fitness value of the chromosome is evaluated.

[0263] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the following steps:

[0264] Obtain the work order information of the reactor production scheduling;

[0265] Dynamically and virtually split the work order information to generate an initial work order population;

[0266] Evaluate the fitness value according to the initial work order population to obtain an evaluation result;

[0267] Perform a crossover operation according to the evaluation result to obtain a crossover result;

[0268] Perform a mutation operation according to the crossover result to obtain a mutation result;

[0269] Sort according to the mutation result to generate a production scheduling plan.

[0270] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: Initialize the population of the initial work order population to generate a chromosome population;

[0271] Evaluate the fitness value of the chromosomes in the chromosome population to obtain an evaluation result;

[0272] The calculation formula for the fitness value evaluation is as follows:

[0273] f = -w 1 E + w 2 U - w 3 C + w 4 O r + w 5 O n

[0274] w 1 、w 2 、w 3 、w 4 、w 5 are user-defined weights;

[0275] E is the evaluation score for violating the earliest start time rule;

[0276] U is the evaluation score for resource utilization rate;

[0277] C is the evaluation score for the cleaning time between work orders;

[0278] O r is the evaluation score for the order completion rate;

[0279] O n is the evaluation score for the order completion quantity;

[0280] E, U, C, O r , O n All have been normalized.

[0281] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: randomly select chromosomes in the evaluation results for fitness value comparison to obtain a tournament population;

[0282] Perform crossover operations on the chromosomes in the tournament population to generate crossover chromosomes;

[0283] Form a population with the crossover chromosomes to obtain a crossover result.

[0284] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: perform mutation operations on the crossover chromosomes to generate mutant chromosomes;

[0285] Form a population with the mutant chromosomes to obtain a mutation result.

[0286] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: detect whether the sorting of the mutation result satisfies a preset switching rule;

[0287] If the work order sorting of the mutation result satisfies the preset switching rule, then sort multiple work orders to generate a production scheduling plan;

[0288] If the work order sorting of the mutation result does not satisfy the preset switching rule, then add cleaning work orders before and after this work order, and then generate a production scheduling plan.

[0289] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: detect whether the crossover rate of the crossover chromosomes is greater than a crossover threshold;

[0290] If the crossover rate of the crossover chromosomes is less than or equal to the crossover threshold, then detect whether the mutation rate of this chromosome is greater than a mutation threshold;

[0291] If the mutation rate of this chromosome is less than or equal to the mutation threshold, then perform fitness value evaluation on this chromosome.

[0292] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0293] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0294] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0295] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for scheduling production of a reactor, characterized in that: The method comprises: Get the work order information of reactor production scheduling; Dynamically and virtually splitting the work order information to generate an initialization work order population; Perform fitness value evaluation according to the initialized work order population to obtain an evaluation result; Perform a crossover operation according to the evaluation result to obtain a crossover result; Perform a mutation operation according to the crossover result to obtain a mutation result; The variation results are sorted and a production schedule is generated.

2. The method according to claim 1, characterized in that The fitness value evaluation is performed according to the initialized work order population to obtain the evaluation result, which includes: Initializing the initialization work order population to generate a chromosome population; Evaluating the fitness values ​​of chromosomes in the chromosome population to obtain evaluation results; The fitness value evaluation calculation formula is as follows: f=-w1E+w2U-w3C+w4O r +w5O n w1, w2, w3, w4, and w5 are user-defined weights; E is the evaluation score for violating the earliest start time rule; U is the resource utilization evaluation score; C is the cleaning time evaluation score between work orders; O r Provide an evaluation score for order completion rate; O n Evaluate the number of completed orders; E, U, C, O r , O n All have been normalized.

3. The method according to claim 2, characterized in that The performing a crossover operation according to the evaluation result to obtain a crossover result comprises: Randomly selecting chromosomes from the evaluation results to compare fitness values ​​to obtain a championship population; Performing a crossover operation on the chromosomes in the tournament population to generate crossover chromosomes; The crossover chromosomes are organized into a population to obtain the crossover result.

4. The method according to claim 3, characterized in that The performing a mutation operation according to the crossover result to obtain a mutation result comprises: Performing a mutation operation on the crossover chromosome to generate a mutant chromosome; The mutant chromosomes are organized into a population to obtain the mutation results.

5. The method according to claim 1, characterized in that The sorting according to the variation results to generate a production schedule includes: Detecting whether the mutation result sorting satisfies a preset switching rule; If the work order sorting of the variation result meets the preset switching rule, multiple work orders are sorted to generate a production schedule; If the work order sequence of the variation result does not meet the preset switching rule, a cleaning work order is added before and after the work order, and then a production schedule is generated.

6. The method according to claim 4, characterized in that The method further comprises: Detecting whether the crossover rate of the crossover chromosome is greater than a crossover threshold; If the crossover rate of the crossover chromosome is less than or equal to the crossover threshold, then detecting whether the mutation rate of the chromosome is greater than the mutation threshold; If the mutation rate of the chromosome is less than or equal to the mutation threshold, the fitness value of the chromosome is evaluated.

7. A reactor production scheduling device, characterized in that: The device comprises: Information acquisition module, used to obtain work order information of reactor production scheduling; A virtual splitting module, used to dynamically and virtually split the work order information to generate an initialization work order population; An information evaluation module, used to evaluate the fitness value according to the initialized work order population to obtain an evaluation result; A cross operation module, used to perform a cross operation according to the evaluation result to obtain a cross result; A mutation operation module, used for performing a mutation operation according to the crossover result to obtain a mutation result; The production scheduling module is used to generate a production scheduling plan according to the variation results.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images