Production task scheduling method and device, electronic equipment and computer storage medium

Abstract

The invention relates to a production task scheduling method and device, electronic equipment and a computer storage medium, and belongs to the technical field of intelligent production.The production task scheduling method comprises the steps that production demand task information and factory production resource information are obtained, determining an initial scheduling scheme and an initial batching scheme of the workpieces to be produced based on the production demand task information and the factory production resource information; a preset batching scheme prediction model is adopted to predict the initial scheduling scheme and an initial batching scheme corresponding to the initial scheduling scheme, and an optimal batching scheme of the workpieces to be produced is obtained; and calculating a target function value of a candidate scheduling scheme corresponding to the optimal batching scheme based on a preset target function, and determining an optimal scheduling scheme of the to-be-produced workpiece based on the target function value. According to the method, the production efficiency can be effectively improved, and the factory capacity is maximized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent production technology, and in particular to a production task scheduling method, device, electronic equipment and computer storage medium. Background Art

[0002] In recent years, with the increasing complexity and scale of manufacturing systems, many companies have gradually shifted from traditional centralized production environments to more flexible distributed production environments. This shift can, on the one hand, adapt to the large-scale production needs of multiple varieties, and on the other hand, increase production capacity and reduce costs. As a result, the scheduling problem of distributed heterogeneous replacement assembly lines has also arisen.

[0003] In the existing related technologies, batch flow technology is usually used to solve the workshop scheduling problem. Batch flow technology allows a large number of workpieces to be divided into multiple sub-batches for processing. The workpieces can be transferred to downstream machines before all workpieces are processed, and overlapping processing is allowed on different machines. Batch flow technology not only optimizes the production rhythm, but also can significantly reduce the idle time of factory equipment and improve the utilization rate of equipment, thereby achieving efficient allocation of resources. In batch flow technology, the determination of the batching scheme for the workpieces to be produced and the scheduling scheme for the workpieces to be produced will directly affect the production efficiency of the workpieces to be produced. In the existing batching scheme, due to the uncertainty of the number of batches and the number of sub-batch workpieces, the difficulty of solving the batching scheme is relatively high, and the allocation scheme and scheduling scheme of the workpieces to be produced are solved as separate problems, resulting in low synergy between the batching scheme and the scheduling scheme, which ultimately leads to low production efficiency.

[0004] It can be seen that the existing technology for the batching scheme and scheduling scheme of the workpieces to be produced cannot meet the production needs. Summary of the invention

[0005] In view of this, it is necessary to provide a production task scheduling method, device, electronic device and computer storage medium to solve the problem that the existing technology for the batching scheme and scheduling scheme of the workpieces to be produced cannot meet the production needs.

[0006] In order to solve the above problems, in a first aspect, the present invention provides a production task scheduling method, comprising: Obtaining production demand task information and factory production resource information, and determining an initial scheduling plan and an initial batching plan for the workpieces to be produced based on the production demand task information and the factory production resource information; The preset batch plan prediction model is used to predict the initial scheduling plan and the initial batch plan corresponding to the initial scheduling plan to obtain the optimal batch plan for the workpieces to be produced; Calculate the objective function value of the candidate scheduling plan corresponding to the optimal batching plan based on the preset objective function, and determine the optimal scheduling plan for the workpieces to be produced based on the objective function value.

[0007] In a possible implementation manner, determining an initial scheduling plan and an initial batching plan for the workpieces to be produced based on the production demand task information and the factory production resource information includes: Determine an initial scheduling plan for the workpieces to be produced based on the production demand task information and the factory production resource information; Generate a plurality of initial batching plans corresponding to the initial scheduling plan based on the initial scheduling plan and the preset constraint conditions.

[0008] In a possible implementation manner, the preset constraint conditions include:

[0009]

[0010]

[0011]

[0012]

[0013]

[0014]

[0015]

[0016]

[0017]

[0018]

[0019] Among them, n represents the total number of workpieces, j represents the workpiece number; m represents the total number of machines; i represents the machine number; f represents the total number of factories, k represents the factory number; g represents the sub-batch number, represents the workpiece j the quantity that needs to be processed, represents belonging to the workpiece j the sub-batch g of the batch, represents belonging to the workpiece j the number of sub-batches, represents the maximum number of sub - batches; represents the i processing time of the k th machine in the factory represents the i processing time of the th machine; j represents the processing time of workpiece k in the i th machine of the factory; represents the processing time of the j th sub - batch belonging to workpiece g in the k th machine of the factory; i represents the processing time of the th sub - batch belonging to workpiece j in the g th machine of the factory; k represents the start time of the i th machine for the th sub - batch belonging to workpiece j in the g th machine of the factory; k represents the completion time of the i th machine for the th sub - batch of the workpiece in the k factory from the i th machine to the i +1 th machine; indicates that if the j th sub - batch belonging to workpiece g is processed on the k th machine of the factory, then i = 1, otherwise = 0. = 0.

[0020] In a possible implementation manner, the determination process of the candidate scheduling scheme corresponding to the optimal batching scheme includes: Determining multiple primary candidate scheduling schemes based on the optimal batching scheme, production demand task information, and factory production resource information; Optimizing the multiple primary candidate scheduling schemes using a self - learning algorithm and a co - evolutionary algorithm to obtain multiple candidate scheduling schemes.

[0021] In a possible implementation manner, optimizing the multiple primary candidate scheduling schemes using a self - learning algorithm and a co - evolutionary algorithm to obtain multiple candidate scheduling schemes includes: Calculating the objective function values of each primary candidate scheduling scheme using a preset objective function; Optimize the first primary candidate scheduling plan using a self - learning algorithm to obtain the first candidate scheduling plan, where the objective function value of the first primary candidate scheduling plan is greater than or equal to a preset objective function threshold; Optimize the second primary candidate scheduling plan using an insight learning algorithm to obtain the second candidate scheduling method, where the objective function value of the second primary candidate scheduling plan is less than the preset objective function threshold.

[0022] In a possible implementation manner, the optimization process of multiple primary candidate scheduling plans further includes: Optimize the first candidate scheduling plan and the second candidate scheduling method respectively using a neighborhood search operation to obtain the target candidate scheduling plan.

[0023] In a possible implementation manner, the objective function is:

[0024]

[0025] Wherein, is the objective function, indicating that the maximum completion time of the workpiece to be produced is minimized, n represents the total number of workpieces, j represents the workpiece serial number; m represents the total number of machines; i represents the machine serial number; f represents the total number of factories, k represents the factory serial number; represents the factory j the number of workpieces that the factory g represents the sub - batch serial number, belongs to the workpiece j of the g th k in the i completion time of the th machine in the factory.

[0026] In a second aspect, the present invention further provides a production task scheduling device, including: An initial plan generation module, configured to obtain production demand task information and factory production resource information, and determine an initial scheduling plan and an initial batching plan for the workpiece to be produced based on the production demand task information and the factory production resource information; An optimal batching plan determination module, configured to predict the initial scheduling plan and the initial batching plan corresponding to the initial scheduling plan using a preset batching plan prediction model to obtain the optimal batching plan for the workpiece to be produced; An optimal scheduling plan determination module, configured to calculate the objective function value of the candidate scheduling plan corresponding to the optimal batching plan based on a preset objective function, and determine the optimal scheduling plan for the workpiece to be produced based on the objective function value.

[0027] In a third aspect, the present invention further provides an electronic device, including a memory and a processor, wherein, the memory is used for storing programs; the processor is coupled to the memory and is used for executing the programs stored in the memory to implement the steps in the production task scheduling method of any of the above embodiments.

[0028] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing computer-readable programs or instructions, and when the programs or instructions are executed by a processor, the steps in the production task scheduling method of any of the above embodiments can be implemented.

[0029] The beneficial effects of the present invention are as follows: The production task scheduling method provided by the present invention determines the initial scheduling plan and the initial batching plan of the workpiece to be produced according to the production demand task information and the factory production resource information, and then uses a preset batching plan prediction model to predict the initial scheduling plan and the initial batching plan corresponding to the initial scheduling plan, so as to obtain the optimal batching plan of the workpiece to be produced. Based on the prediction model, the optimal batching plan of the workpiece to be produced is determined, which improves the efficiency and accuracy of determining the optimal batching plan. Based on this, the objective function value of the candidate scheduling plan corresponding to the optimal batching plan is calculated based on a preset objective function, and the optimal scheduling plan of the workpiece to be produced is determined based on the objective function value. The optimal scheduling plan corresponding to the optimal batching plan is determined through the optimal batching plan and the preset objective function, which ensures the coordination between the optimal batching plan and the optimal scheduling plan, can effectively improve the production efficiency, and realize the maximization of the factory production capacity. Description of the Drawings

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a schematic flowchart of a production task scheduling method provided by an embodiment of the present invention; Figure 2 It is a schematic flowchart of a method for generating a batching plan and a scheduling plan provided by an embodiment of the present invention; Figure 3 It is a schematic flowchart of a method for determining a candidate scheduling plan provided by an embodiment of the present invention; Figure 4 It is a schematic flowchart of an implementation method of S402 provided by an embodiment of the present invention; Figure 5Schematic diagram of a partial cross - mapping operation provided by an embodiment of the present invention; Figure 6 Schematic diagram of a uniform cross - mapping operation provided by an embodiment of the present invention; Figure 7 Schematic diagram of a single - point insertion operator in a key factory provided by an embodiment of the present invention; Figure 8 Schematic diagram of a two - point swap operator in a key factory provided by an embodiment of the present invention; Figure 9 Schematic diagram of a single - point insertion operator between key factories provided by an embodiment of the present invention; Figure 10 Schematic diagram of a two - point swap operator between key factories provided by an embodiment of the present invention; Figure 11 Schematic diagram of the structure of a production task scheduling device provided by an embodiment of the present invention; Figure 12 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0032] The following will specifically describe the preferred embodiments of the present invention with reference to the accompanying drawings. The accompanying drawings form a part of the present invention and are used together with the embodiments of the present invention to explain the principle of the present invention, rather than to limit the scope of the present invention.

[0033] In the embodiments of the present invention, the descriptions such as "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0034] Referring to "embodiment" herein means that the specific features, structures, or characteristics described in connection with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0035] A specific embodiment of the present invention, as Figure 1 shown, discloses a production task scheduling method, including: S101, obtaining production demand task information and factory production resource information, and determining an initial scheduling plan and an initial batching plan for the workpieces to be produced based on the production demand task information and the factory production resource information.

[0036] In the embodiments of the present invention, the production demand task information includes, but is not limited to, the product category of the workpieces to be produced, the quantity of each workpiece to be produced, the technological processes of each workpiece to be produced, etc. The factory production resource information includes, but is not limited to, the number of factories, the types and quantities of factory processing machines, the production capacity of each processing machine, the cost of factory processing machines, etc. The scheduling plan includes the allocation plan for allocating the workpieces to be produced to factories and the processing sequence plan for each factory for various workpieces to be produced. The batching plan includes a plan for dividing each workpiece to be produced into multiple sub-batches for processing, where the number of sub-batches into which the workpiece to be produced is divided is uncertain, and the quantity of the workpieces to be produced in each sub-batch is also uncertain.

[0037] In the embodiments of the present invention, based on the production demand task information and the factory production resource information, the batching plan and the scheduling plan for the workpieces to be produced can be initialized. Specifically, an initial scheduling plan and an initial batching plan for the workpieces to be produced can be randomly generated without considering production efficiency, and the initial scheduling plan and the initial batching plan are optimized through subsequent optimization plans.

[0038] S102, use a preset batching plan prediction model to predict the initial scheduling plan and the initial batching plan corresponding to the initial scheduling plan, and obtain the optimal batching plan for the workpieces to be produced.

[0039] In the embodiments of the present invention, the preset batching plan prediction model can be a neural network model, such as a Transformer prediction model. This batching plan prediction model takes the combination of the batching plan and the scheduling plan as the input and can output the feasibility of the batching plan. Specifically, when training the batching plan prediction model, various batching plans including consistent batching and equal quantity batching can be generated according to the processing requirements of similar workpieces, the number of sub-batches, and the maximum and minimum batch sizes of the sub-batches. At the same time, a large number of scheduling plans corresponding to the various batching plans are generated, and a batching plan - a scheduling plan - the feasibility of this batching plan and this scheduling plan are used as a set of data to construct a data set. Then, the data in the data set is divided into a training set (80%), a validation set (10%), and a test set (10%) according to a ratio to train the Transformer prediction model, and a trained batching plan prediction model is obtained.

[0040] In an embodiment of the present invention, the input of the batch scheme prediction model is a scheduling scheme and a batch scheme corresponding to the scheduling scheme. When generating an initial scheduling scheme according to the production demand task information and the factory production resource information, multiple initial scheduling schemes can be generated, and each initial scheduling scheme includes multiple initial batch schemes. When using the batch scheme prediction model for prediction, each initial scheduling scheme and each initial batch scheme need to be used as inputs for prediction to obtain the scores of each initial scheduling scheme and initial batch scheme. Specifically, this score is also calculated according to the objective function.

[0041] Specifically, when calculating the scores of the initial scheduling scheme and the initial batch scheme, first determine the processing order of the workpieces to be produced in the initial scheduling scheme and the factory allocation scheme of the workpieces to be produced, determine the production tasks of each factory, then determine the corresponding batch scheme according to the production tasks of each factory, and then use the batch scheme prediction model to calculate the scores of the scheduling scheme and the batch scheme.

[0042] Furthermore, take the initial batch scheme in the combination of the initial scheduling scheme and the initial batch scheme with the highest score as the optimal batch scheme, and based on this optimal batch scheme in the subsequent optimization process, determine the corresponding optimal scheduling scheme.

[0043] S103, calculate the objective function value of the candidate scheduling scheme corresponding to the optimal batch scheme based on a preset objective function, and determine the optimal scheduling scheme of the workpieces to be produced based on the objective function value.

[0044] In an embodiment of the present invention, after determining the optimal batch scheme, the corresponding optimal scheduling scheme can be determined according to the optimal batch scheme. The preset objective function refers to the condition for constraining the optimal batch scheme and the optimal scheduling scheme, generally the minimum maximum completion time of the workpieces to be produced. Before that, assumptions need to be made: (1) all machines and workpieces are available at time zero; (2) the processing time of each workpiece on each machine in each factory is known; (3) the buffer between machines is infinite; (4) the sum of the quantities of each sub-batch of each type of workpiece should be equal to the total quantity of the workpiece; (5) the number of sub-batches of the workpiece cannot exceed the set maximum number of batches; (6) at any time, a sub-batch can only be processed by one machine, and one machine can only process one sub-batch; (7) when the sub-batches belonging to a workpiece are being processed on a machine, it is not allowed for the sub-batches belonging to other workpieces to be mixed and processed on this machine; (8) after a workpiece is assigned to a certain factory, it cannot be processed by other factories; (9) the setup time of the machine is included in the transportation time; (10) during the entire production and scheduling process, the machine is always available. Based on the above assumptions, a distributed heterogeneous permutation flow shop batch flow optimization model can be constructed, and based on this distributed heterogeneous permutation flow shop batch flow optimization model, the optimization solution of the batch scheme and the scheduling scheme can be realized.

[0045] In the embodiments of the present invention, the objective function is:

[0046]

[0047] where is the objective function, indicating that the maximum completion time of the workpiece to be produced is minimized, n represents the total number of workpieces, j represents the workpiece serial number; m represents the total number of machines; i represents the machine serial number; f represents the total number of factories, k represents the factory serial number; represents the factory j the number of workpieces that need to be produced, g represents the sub - batch serial number, belongs to the workpiece j of the g th k sub - batch in the i th

[0048] The production task scheduling method provided by the present invention determines the initial scheduling plan and initial batching plan of the workpiece to be produced according to the production demand task information and factory production resource information, then uses a preset batching plan prediction model to predict the initial scheduling plan and the corresponding initial batching plan of the initial scheduling plan, obtains the optimal batching plan of the workpiece to be produced, determines the optimal batching plan of the workpiece to be produced based on the prediction model, improves the efficiency and accuracy of determining the optimal batching plan. Based on this, the objective function value of the candidate scheduling plan corresponding to the optimal batching plan is calculated based on the preset objective function, and the optimal scheduling plan of the workpiece to be produced is determined based on the objective function value. The optimal scheduling plan corresponding to the optimal batching plan is determined through the optimal batching plan and the preset objective function, ensuring the coordination between the optimal batching plan and the optimal scheduling plan, which can effectively improve production efficiency and maximize the factory production capacity.

[0049] In some embodiments of the present invention, as Figure 2 shown, determining the initial scheduling plan and initial batching plan of the workpiece to be produced based on the production demand task information and factory production resource information includes: S201, determining the initial scheduling plan of the workpiece to be produced based on the production demand task information and factory production resource information.

[0050] In the embodiments of the present invention, as in the foregoing embodiments, the initial scheduling plan should include the factory allocation plan for the initial workpieces to be produced and the processing sequence plan for each workpiece to be produced. For example, if the workpieces to be produced include six types, namely A, B, C, D, E, and F, and the factories that can process these workpieces to be produced include Factory a and Factory b, then the initial scheduling plan can be that workpieces A, B, and C to be produced are processed by Factory a, and workpieces D, E, and F to be produced are processed by Factory b. Moreover, the processing sequence of each workpiece in Factory a is B - C - A, and the processing sequence in Factory b is D - F - E. This initial scheduling plan is randomly generated. Of course, the above embodiments are only simple embodiments for easy expression, and the determination of the specific initial scheduling plan needs to be formulated according to the actual production situation.

[0051] S202, generate a plurality of initial batching plans corresponding to the initial scheduling plan based on the initial scheduling plan and the preset constraint conditions.

[0052] In the embodiments of the present invention, the preset constraint conditions include: Constraint condition 1: Ensure that any sub - batch of each workpiece can only be processed by one machine in one factory.

[0053]

[0054] Constraint condition 2: Limits the maximum number of sub - batches of each workpiece.

[0055]

[0056] Constraint condition 3: Represents the relationship between the total number of batches and the number of sub - batches of the workpiece.

[0057]

[0058] Constraint condition 4: Represents the method for calculating the processing time of the g - th batch of workpiece j on the i - th machine in Factory k.

[0059]

[0060] Constraint condition 5: Represents the processing time of the machine when the current workpiece sub - batch finishes processing on machine i.

[0061]

[0062] Constraint condition 6: Represents the completion time of the g - th batch of workpiece j on the i - th machine in the first factory.

[0063]

[0064] Constraint condition 7: Represents the completion time of the g - th batch of workpiece j on the i - th machine in Factory k.

[0065]

[0066] Constraint 8: Represents the start time of the g-th batch of workpiece j on the i-th machine in the first factory.

[0067]

[0068] Constraint 9: Represents the start time of the g-th batch of workpiece j on the i-th machine in factory k.

[0069]

[0070] Constraint 10: Defines the transportation time from machine i to machine i + 1. It is defined as the average processing time of all workpieces on machines i and i + 1.

[0071]

[0072] Among them, , n represents the total number of workpieces, j represents the workpiece number; m represents the total number of machines; i represents the machine number; f represents the total number of factories, k represents the factory number; g represents the sub-batch number, represents the workpiece j the required processing quantity, represents belonging to workpiece j of sub-batch g batch quantity, represents belonging to workpiece j the number of sub-batches, represents the maximum number of sub-batches; represents the i th machine in factory k processing time, represents the i th machine processing time, represents workpiece j in k factory's i th machine processing time, represents belonging to workpiece j of the g th sub-batch in k factory's i th machine processing time, represents belonging to workpiece j of the g th sub-batch in k factory's iThe start time of the machine, belongs to the workpiece j of the g th sub - batch at k the completion time of the i th machine in the factory, the sub - batch of the workpiece at k the factory from the i th machine to the i th + 1 machine's transportation time; denotes that if the sub - batch j belongs to the workpiece g is processed on the k th machine in the factory, then i = 1, otherwise = 0. = 0.

[0073] In the embodiments of the present invention, for each scheduling scheme, a corresponding plurality of batching schemes can be generated. The subsequent embodiments of the present invention will describe in detail the determination of the batching scheme.

[0074] In some embodiments of the present invention, as Figure 3 shown, the determination process of the candidate scheduling scheme corresponding to the optimal batching scheme includes: S301, determining a plurality of primary candidate scheduling schemes based on the optimal batching scheme, production demand task information, and factory production resource information.

[0075] In the embodiments of the present invention, after determining the optimal batching scheme, a corresponding plurality of primary candidate scheduling schemes can be determined according to the optimal batching scheme. Specifically, the optimal batching scheme includes the batches into which each workpiece to be produced is divided and the number of workpieces to be produced in each sub - batch. Based on this, combined with the production capacity of the factory, it can be determined which factory each workpiece to be produced is assigned to, and the processing order of the workpieces to be produced in each factory, thereby determining a plurality of primary candidate scheduling schemes.

[0076] S302, optimizing the plurality of primary candidate scheduling schemes by using a self - learning algorithm and a co - evolutionary algorithm to obtain a plurality of candidate scheduling schemes.

[0077] In the embodiments of the present invention, after determining the plurality of primary candidate scheduling schemes, based on the complexity of the scheduling problem, the primary candidate scheduling schemes can be optimized to obtain a plurality of candidate scheduling schemes. Optional optimization schemes can be a self - learning algorithm and a co - evolutionary algorithm. The specific optimization process will be described in detail later in the present invention.

[0078] In some embodiments of the present invention, as Figure 4 shown, S302 includes: S401. Calculate the objective function values of each primary candidate scheduling plan using a preset objective function; S402. Optimize the first primary candidate scheduling plan using a self-learning algorithm to obtain a first candidate scheduling plan, where the objective function value of the first primary candidate scheduling plan is greater than or equal to a preset objective function threshold; S403. Optimize the second primary candidate scheduling plan using an insight learning algorithm to obtain a second candidate scheduling method, where the objective function value of the second primary candidate scheduling plan is less than the preset objective function threshold.

[0079] In the embodiment of the present invention, for the primary candidate scheduling plans determined based on the optimal batching plan, the objective function values of each primary candidate scheduling plan can be calculated using the objective function in the foregoing embodiment, and each primary candidate scheduling plan can be classified according to the objective function values of each primary candidate scheduling plan into a first primary candidate scheduling plan and a second primary candidate scheduling plan, where the objective function value of the first primary candidate scheduling plan is greater than or equal to the preset objective function threshold, and the objective function value of the second primary candidate scheduling plan is less than the preset objective function threshold. Further, for the first primary candidate scheduling plan, a self-learning algorithm can be used to optimize it to further improve the quality of the candidate scheduling plan. Specifically, two first primary candidate scheduling plans are randomly selected from the set of first primary candidate scheduling plans, and partial cross-mapping operations and uniform cross-mapping operations are respectively performed to obtain new first primary candidate scheduling plans, and then the new primary candidate scheduling plans are added to the set of first primary candidate scheduling plans, and random mutations are performed on each first primary candidate scheduling plan in the set of first primary candidate scheduling plans to obtain a first candidate scheduling plan to increase the diversity of the first candidate scheduling plan. For the second primary candidate scheduling plan, an insight learning algorithm can be used for optimization. Specifically, for each second primary candidate scheduling plan in the set of second primary candidate scheduling plans, a first primary candidate scheduling plan is randomly selected from the set of first primary candidate scheduling plans, and partial cross-mapping operations and uniform cross-mapping operations are performed on the second primary candidate scheduling plan and the first primary candidate scheduling plan to obtain a new second primary candidate scheduling plan, and the new second primary candidate scheduling plan is added to the set of second primary candidate scheduling plans, and random mutations are performed on the second primary candidate scheduling plans in the new set of second primary candidate scheduling plans to obtain a second candidate scheduling plan. Specifically, as Figure 5As shown in the figure, it is a schematic diagram of the partial crossover mapping operation. In two parent individuals (Parent1 and Parent2), two crossover points are randomly selected to determine the segments to be exchanged. The segments between the crossover points of Parent1 and Parent2 are swapped to generate a temporary offspring. Since the direct exchange of segments may result in duplicate elements and missing elements, a repair operation is required to finally obtain the offspring. As Figure 6 shown in the figure, it is a schematic diagram of the uniform crossover mapping operation. A mask with the same length as the individual is randomly generated, and each locus is represented by 0 or 1 to indicate whether to exchange. According to the mask, the genes at the positions where the mask value is 1 are exchanged, and the genes at the positions where the mask value is 0 are inherited, finally obtaining the offspring.

[0080] In the embodiments of the present invention, different algorithms are used to optimize the primary candidate scheduling schemes of different qualities to obtain candidate scheduling schemes, ensuring the quality and diversity of the candidate scheduling schemes.

[0081] In some embodiments of the present invention, the optimization process of multiple primary candidate scheduling schemes further includes: Using the neighborhood search operation to optimize the first candidate scheduling scheme and the second candidate scheduling method respectively to obtain the target candidate scheduling scheme.

[0082] In the embodiments of the present invention, for the first candidate scheduling scheme and the second candidate scheduling obtained in the foregoing embodiments, the neighborhood search operation can be used for optimization. Specifically, the neighborhood search operation includes four key operations: single-point insertion within a key factory, two-point exchange within a key factory, single-point insertion between key factories, and two-point exchange between key factories. Among them, as Figure 7 shown in the figure, it is a schematic diagram of the single-point insertion operator within a key factory. Select a key factory from the current solution; if there are multiple key factories, randomly select one; within this factory, randomly delete a workpiece at any position and insert it into another position in this factory to generate a new solution. As Figure 8 shown in the figure, it is a schematic diagram of the two-point exchange operator within a key factory. Select a key factory from the current solution; if there are multiple key factories, randomly select one; in the workpiece sequence of this factory, randomly select two non-adjacent workpieces and exchange their positions to obtain a new solution. As Figure 9 shown in the figure, it is a schematic diagram of the single-point insertion operator between key factories. Randomly select two key factories from the current solution; if there is only one key factory in the current solution, randomly select another factory from the non-key factories; subsequently, randomly delete a workpiece from one key factory and insert it into any position in another factory to generate a new solution. As Figure 10As shown in the figure, it is a schematic diagram of the two-point exchange operator between key factories. Two key factories are randomly selected from the current solution; if there is only one key factory in the current solution, another factory is randomly selected from non-key factories; among these two factories, workpieces at any two positions are randomly exchanged to ensure obtaining a legal coding vector and generating a new solution. Based on the above operations, multiple new candidate scheduling plans can be obtained. The objective function values of each new candidate scheduling plan are calculated using the objective function, and the candidate scheduling plans with objective function values greater than the preset objective function threshold are determined as target candidate scheduling plans.

[0083] In the embodiments of the present invention, when determining the final optimal scheduling plan, it is necessary to select from the candidate scheduling plans obtained from all the above embodiments. Specifically, the optimal batching plan and each candidate scheduling plan can be used as the input of the preset objective function, calculate the corresponding objective function values, and determine the candidate scheduling plan with the largest objective function value as the optimal scheduling plan.

[0084] Furthermore, after the scheduling is completed, the data and process information generated during the entire scheduling process are completely stored in the cloud database. These data will provide important references and guidance for future scheduling work, promote the improvement of the plan and the optimization of the algorithm, and lay a foundation for the continuous production optimization of the enterprise.

[0085] The present invention fully considers two key issues of the distributed heterogeneous permutation flow shop batch flow problem, effectively solves the sub-batch division and scale optimization problems; at the same time, with the help of the efficient iterative optimization ability of the co-evolution algorithm, it solves the workpiece allocation and processing sequence optimization problems, and conducts targeted optimization on complex production scheduling problems, providing theoretical support and practical basis for realizing efficient production management.

[0086] To better implement the production task scheduling method in the embodiments of the present invention, correspondingly, based on the production task scheduling method, as Figure 11 shown, the embodiments of the present invention also provide a production task scheduling device. The production task scheduling device 1100 includes: An initial plan generation module 1101, configured to obtain production demand task information and factory production resource information, and determine an initial scheduling plan and an initial batching plan for workpieces to be produced based on the production demand task information and the factory production resource information; An optimal batching plan determination module 1102, configured to use a preset batching plan prediction model to predict the initial scheduling plan and the initial batching plan corresponding to the initial scheduling plan, and obtain the optimal batching plan for workpieces to be produced; An optimal scheduling plan determination module 1103, configured to calculate the objective function values of candidate scheduling plans corresponding to the optimal batching plan based on a preset objective function, and determine the optimal scheduling plan for workpieces to be produced based on the objective function values.

[0087] The production task scheduling device 1100 provided in the above embodiments can implement the technical solutions described in the above embodiments of the production task scheduling method. For the specific implementation principles of the above modules or units, reference can be made to the corresponding content in the above embodiments of the production task scheduling method, which will not be elaborated here.

[0088] The production task scheduling device provided by the present invention determines an initial scheduling plan and an initial batching plan for workpieces to be produced according to production demand task information and factory production resource information, and then uses a preset batching plan prediction model to predict the initial scheduling plan and the initial batching plan corresponding to the initial scheduling plan, so as to obtain an optimal batching plan for the workpieces to be produced. Based on the prediction model, the optimal batching plan for the workpieces to be produced is determined, which improves the efficiency and accuracy of determining the optimal batching plan. Based on this, the objective function value of the candidate scheduling plan corresponding to the optimal batching plan is calculated based on a preset objective function, and the optimal scheduling plan for the workpieces to be produced is determined based on the objective function value. By determining the optimal scheduling plan corresponding to the optimal batching plan through the optimal batching plan and the preset objective function, the coordination between the optimal batching plan and the optimal scheduling plan is ensured, which can effectively improve production efficiency and maximize the factory production capacity.

[0089] As Figure 12 shown, the present invention also correspondingly provides an electronic device 1200. The electronic device 1200 includes a processor 1201, a memory 1202, and a display 1203. Figure 12 Only some components of the electronic device 1200 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0090] In some embodiments, the processor 1201 may be a central processing unit (CPU), a microprocessor, or other data processing chips, and is used to run the program code stored in the memory 1202 or process data, such as the production task scheduling method in the present invention.

[0091] In some embodiments, the processor 1201 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 1201 may be local or remote. In some embodiments, the processor 1201 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0092] The memory 1202 can be an internal storage unit of the electronic device 1200 in some embodiments, such as the hard disk or memory of the electronic device 1200. The memory 1202 can also be an external storage device of the electronic device 1200 in some other embodiments, such as a plug-in hard disk equipped on the electronic device 1200, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0093] Furthermore, the memory 1202 can also include both the internal storage unit of the electronic device 1200 and the external storage device. The memory 1202 is used to store the application software installed on the electronic device 1200 and various types of data.

[0094] The display 1203 can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. in some embodiments. The display 1203 is used to display the information of the electronic device 1200 and to display a visual user interface. The components 1201 - 1203 of the electronic device 1200 communicate with each other through the system bus.

[0095] In some embodiments, when the processor 1201 executes the production task scheduling program in the memory 1202, the following steps can be implemented: Obtain the production demand task information and the factory production resource information, and determine the initial scheduling plan and the initial batching plan of the workpieces to be produced based on the production demand task information and the factory production resource information; Use a preset batching plan prediction model to predict the initial scheduling plan and the initial batching plan corresponding to the initial scheduling plan, and obtain the optimal batching plan of the workpieces to be produced; Calculate the objective function value of the candidate scheduling plan corresponding to the optimal batching plan based on a preset objective function, and determine the optimal scheduling plan of the workpieces to be produced based on the objective function value.

[0096] It should be understood that when the processor 1201 executes the production task scheduling program in the memory 1202, in addition to the above functions, other functions can also be implemented. For specific details, please refer to the description of the corresponding method embodiments above.

[0097] Further, the embodiments of the present invention do not specifically limit the type of the mentioned electronic device 1200. The electronic device 1200 may be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop, or other portable electronic devices. Exemplary embodiments of the portable electronic device include, but are not limited to, portable electronic devices equipped with IOS, android, microsoft, or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop with a touch-sensitive surface (such as a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1200 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0098] Correspondingly, the embodiments of the present invention also provide a computer-readable storage medium. The computer-readable storage medium is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the production task scheduling methods provided by the above-mentioned method embodiments can be implemented.

[0099] Those skilled in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0100] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention.

Claims

1. A production task scheduling method, characterized in that: include: Acquire production demand task information and factory production resource information, and determine an initial scheduling plan and an initial batching plan for workpieces to be produced based on the production demand task information and the factory production resource information; Using a preset batch plan prediction model to predict the initial scheduling plan and the initial batch plan corresponding to the initial scheduling plan, to obtain the optimal batch plan for the workpieces to be produced; The objective function value of the candidate scheduling scheme corresponding to the optimal batching scheme is calculated based on a preset objective function, and the optimal scheduling scheme for the workpiece to be produced is determined based on the objective function value.

2. The production task scheduling method according to claim 1, characterized in that: The determining of the initial scheduling scheme and the initial batching scheme of the workpieces to be produced based on the production demand task information and the factory production resource information includes: Determine an initial scheduling plan for the workpieces to be produced based on the production demand task information and the factory production resource information; A plurality of initial batching plans corresponding to the initial scheduling plan are generated based on the initial scheduling plan and preset constraints.

3. The production task scheduling method according to claim 2, characterized in that: The preset constraints include: in, n Represents the total number of workpieces, j Represents the workpiece serial number; m Represents the total number of machines; i Represents the machine serial number; f Represents the total number of factories, k Represents the factory serial number; g Represents the sub-batch number, Representative workpiece j The quantity required for processing, Represents artifacts j Sub-batch g The batch size, Represents artifacts j The number of sub-batches, Represents the maximum number of sub-batches; Representative i Machines in the factory k The processing time, Representative i The processing time of each machine, Representative workpiece j exist k The factory's i The processing time of each machine, Represents artifacts j No. g The number of sub-batch k The factory's i The processing time of each machine, Represents artifacts j No. g The number of sub-batch k The factory's i The start time of the machine, Workpiece j No. g The number of sub-batch k The factory's i The completion time of each machine, The sub-batch of workpieces is k Factory from i Machine to i +1 machine shipping time; Indicates that it belongs to the workpiece j Sub-batch g exist k The factory's i If the machine is used for processing, =1, otherwise =0.

4. The production task scheduling method according to claim 1, characterized in that: The process of determining the candidate scheduling scheme corresponding to the optimal batching scheme includes: Determine a plurality of primary candidate scheduling solutions based on the optimal batching solution, the production demand task information and the factory production resource information; The multiple primary candidate scheduling schemes are optimized by using a self-learning algorithm and a co-evolutionary algorithm to obtain multiple candidate scheduling schemes.

5. The production task scheduling method according to claim 4, characterized in that: The self-learning algorithm and the co-evolutionary algorithm are used to optimize the multiple primary candidate scheduling schemes to obtain multiple candidate scheduling schemes, including: Calculating the objective function value of each of the primary candidate scheduling solutions using a preset objective function; Optimizing the first primary candidate scheduling scheme by using a self-learning algorithm to obtain a first candidate scheduling scheme, wherein the objective function value of the first primary candidate scheduling scheme is greater than or equal to a preset objective function threshold; The second primary candidate scheduling scheme is optimized by using an insight learning algorithm to obtain a second candidate scheduling method, wherein the objective function value of the second primary candidate scheduling scheme is less than a preset objective function threshold.

6. The production task scheduling method according to claim 5, characterized in that: The optimization process of the plurality of primary candidate scheduling solutions further includes: The first candidate scheduling scheme and the second candidate scheduling scheme are optimized respectively by using a neighborhood search operation to obtain a target candidate scheduling scheme.

7. The production task scheduling method according to claim 1, characterized in that: The objective function is: in, is the objective function, indicating that the maximum completion time of the workpiece to be produced is minimized. n Represents the total number of workpieces, j Represents the workpiece serial number; m Represents the total number of machines; i Represents the machine serial number; f Represents the total number of factories, k Represents the factory serial number; Representative Factory j The number of workpieces to be produced, g Represents the sub-batch number, Workpiece j No. g The number of sub-batch k The factory's i The completion time of each machine.

8. A production task scheduling device, characterized in that: include: An initial plan generation module is used to obtain production demand task information and factory production resource information, and determine an initial scheduling plan and an initial batching plan for the workpieces to be produced based on the production demand task information and the factory production resource information; An optimal batching scheme determination module is used to use a preset batching scheme prediction model to predict the initial scheduling scheme and the initial batching scheme corresponding to the initial scheduling scheme to obtain the optimal batching scheme for the workpieces to be produced; The optimal scheduling scheme determination module is used to calculate the objective function value of the candidate scheduling scheme corresponding to the optimal batching scheme based on a preset objective function, and determine the optimal scheduling scheme for the workpiece to be produced based on the objective function value.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the production task scheduling method described in any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the production task scheduling method described in any one of claims 1 to 7 above.

Images