Production scheduling method and device, electronic equipment and storage medium
The production sequence of workshop production indicators is determined through the multi-objective particle swarm algorithm, which solves the problem of long calculation time in the existing technology, improves production scheduling efficiency, and is suitable for intelligent and flexible workshops.
Patent Information
- Application Number
- CN202310636658.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art has a long calculation time when determining the production scheduling sequence that meets the workshop production indicators, which is difficult to meet the production scheduling efficiency, especially in the case of large amount of data and complex processes in intelligent and flexible workshops.
The multi-target particle swarm algorithm is used to predict the production index value by determining the production scheduling sequence of the workpiece to be processed and the equipment attributes of the processing equipment, and to determine the target particles that meet the production scheduling conditions from the particles to be processed, so as to quickly determine the production scheduling sequence.
It improves production scheduling efficiency, can quickly determine the production scheduling sequence that meets various production indicators, shortens the calculation time, and is suitable for production scheduling in intelligent and flexible workshops.
Smart Images

Figure CN119067331A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a production scheduling method, device, electronic device and storage medium. Background Art
[0002] With the advancement of intelligent and flexible workshops, the amount of workshop data (for example, the number of products, processing equipment, etc.) is becoming larger and larger, the production process (for example, the processing procedures of the workpieces to be processed, etc.) is becoming more and more complicated, and the workshop production indicators (for example, the total processing time to complete the processing of each product in the workshop, production efficiency, equipment capacity and equipment utilization, etc.) are increasing. When using different production scheduling sequences for production scheduling, it will affect various production indicators.
[0003] In the related art, it takes a long time to calculate to determine the production order that meets several production indicators. The calculation speed is very slow, and it is difficult to determine the production order that meets each production indicator at the same time, and it is difficult to meet the production scheduling efficiency. Therefore, how to quickly determine the production order that meets various production indicators has become a technical problem that needs to be solved in this field. Summary of the invention
[0004] The embodiment of the present application provides a production scheduling method to solve the problem in the related art that it is difficult to determine a production scheduling sequence that satisfies each production indicator at the same time.
[0005] Correspondingly, an embodiment of the present application also provides a production scheduling device, an electronic device and a storage medium to ensure the implementation and application of the above method.
[0006] On the one hand, an embodiment of the present application provides a production scheduling method, the method comprising:
[0007] Determine the production order of at least two workpieces to be processed;
[0008] Taking the production scheduling sequence as the particles to be processed, and determining the prediction index values corresponding to the particles to be processed under at least two production indexes according to the equipment attributes of the processing equipment;
[0009] The predicted index values are calculated according to a multi-objective particle swarm algorithm, and target particles that meet production scheduling conditions are determined from the particles to be processed according to the calculation results; wherein the production scheduling conditions include target index values for each production index.
[0010] On the other hand, an embodiment of the present application provides a production scheduling device, including:
[0011] A production scheduling sequence determination module, used to determine the production scheduling sequence of at least two workpieces to be processed;
[0012] An index value prediction module, used to use the production scheduling sequence as the particles to be processed, and determine the predicted index values corresponding to the particles to be processed under at least two production indicators according to the equipment attributes of the processing equipment;
[0013] The target particle determination module is used to calculate the above-mentioned prediction index value according to the multi-objective particle swarm algorithm, and determine the target particles that meet the production scheduling conditions from the above-mentioned particles to be processed according to the calculation results; wherein the production scheduling conditions include the target index value of each production index.
[0014] On the other hand, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein the processor and the memory are connected to each other;
[0015] The memory is used to store computer programs;
[0016] The above-mentioned processor is configured to execute the production scheduling method provided in the embodiment of the present application when calling the above-mentioned computer program.
[0017] On the other hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the production scheduling method provided by the embodiment of the present application.
[0018] In an embodiment of the present application, by determining the production scheduling order of at least two workpieces to be processed and the production scheduling conditions including the target indicator value of each production indicator, the determined production scheduling order is used as the particles to be processed, and according to the equipment properties of the processing equipment, the predicted indicator values corresponding to the particles to be processed under at least two production indicators are determined; and the above-mentioned predicted indicator values are calculated according to the multi-objective particle swarm algorithm, and the target particles that meet the production scheduling conditions are determined from the particles to be processed according to the calculation results. The production scheduling order that meets various production indicators can be quickly determined, thereby improving the production scheduling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0020] Figure 1 One of the flow diagrams of the production scheduling method provided in the embodiment of the present application is shown;
[0021] Figure 2 One of the scenario schematic diagrams of the production scheduling method provided in the embodiment of the present application is shown;
[0022] Figure 3 The second flowchart of the production scheduling method provided in the embodiment of the present application is shown;
[0023] Figure 4a A schematic diagram of a system architecture for implementing a production scheduling method provided in an embodiment of the present application is shown;
[0024] Figure 4b A second schematic diagram of a scenario of the production scheduling method provided in an embodiment of the present application is shown;
[0025] Figure 4c The third schematic diagram of the scenario of the production scheduling method provided in the embodiment of the present application is shown;
[0026] Figure 4d A fourth schematic diagram of a scenario of the production scheduling method provided in an embodiment of the present application is shown;
[0027] Figure 4e A fifth scenario schematic diagram of the production scheduling method provided in an embodiment of the present application is shown;
[0028] Figure 5 A schematic diagram of the structure of a production scheduling device provided in an embodiment of the present application is shown;
[0029] Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0031] In view of the problem that it takes a long time to determine the production order that meets various production indicators in the related art, and it is difficult to meet the production scheduling efficiency, the embodiment of the present application provides a production scheduling method, which can be implemented by any electronic device. Among them, the electronic device can be a server device or a terminal device, or a device or chip integrated on these devices, and the embodiment of the present application does not limit this.
[0032] See also Figure 1 The production scheduling method provided in the embodiment of the present application may include the following steps:
[0033] Step S101: Determine the production order of at least two workpieces to be processed.
[0034] The workpiece to be processed may include but is not limited to the raw material or semi-finished product that can be obtained by processing, etc., again without limitation. In the embodiment of the present application, the specific number of the workpiece to be processed is not specifically limited and can be determined according to actual conditions.
[0035] When a workpiece to be processed is processed to obtain a workpiece (in order to distinguish it from the workpiece to be processed, the workpiece that has completed all processing operations may be referred to as a finished workpiece, that is, the product corresponding to the workpiece to be processed), the processing procedures of the workpiece to be processed may be set according to the specific processing stage. Each processing stage is a processing procedure, and the processing time required for each processing procedure may be determined based on experience or experimental values, and is generally a fixed value.
[0036] Combination Figure 2 The specific scene embodiment shown is used to more clearly illustrate the processing process in the workshop. Figure 2 As shown in the figure, when processing workpieces in a workshop, the workshop may include n workpieces to be processed, and continuous processing is required in c (c ≥ 2) processing stages to obtain the finished workpieces corresponding to each workpiece to be processed, and at least one processing stage is equipped with at least two processing equipment. Assume that processing stage i is equipped with m i processing equipment, you can i A processing device is selected from the processing devices to perform the processing operation of the processing stage i on the workpiece to be processed.
[0037] In this scenario embodiment, when performing processing operations on each workpiece, at least the following processing conditions exist:
[0038] Condition 1: For each processing stage, the processing operations corresponding to the processing stage can only be performed on the designated processing equipment; and for each workpiece, the processing operations corresponding to the processing stage can only be started on the workpiece after the processing operations corresponding to the previous processing stage of the processing stage have been completed on the workpiece.
[0039] Condition 2: At a certain moment, only one operation (i.e., the processing operation corresponding to one processing stage of a workpiece) can be performed by one processing device.
[0040] Condition 3: Each job can only be processed once on one processing equipment.
[0041] Condition 4: The various processing stages required to complete each workpiece and the processing time required to perform the processing operations corresponding to each processing stage are known. And for a workpiece, the processing procedures corresponding to its various processing stages will not change.
[0042] Condition 5: When using the same processing equipment to switch between different types of workpieces to be processed (i.e., processing another workpiece to be processed after processing the first workpiece to be processed), time costs are required, and frequent switching will affect the yield of the finished workpieces.
[0043] Condition 6: During each production schedule, there may be semi-finished products in the workshop that have entered or are in the buffer zone;
[0044] Condition 7: Processing equipment that is under maintenance will be temporarily unavailable for scheduling;
[0045] Condition 8: Different types of finished workpieces have different delivery dates and the delivery dates are dispersed; different types of finished workpieces will be delivered in different quantities at different delivery dates and delivered in batches.
[0046] It should be noted that, for each workpiece to be processed, the workpiece to be processed may correspond to one processing stage or multiple processing stages, which is not limited in the embodiments of the present application. Wherein, when the workpiece to be processed corresponds to multiple processing stages, there are corresponding processing steps between each processing stage.
[0047] For example, when a workpiece is an iron block and a screw is obtained by a processing step consisting of turning, forging and cold heading the iron block, turning can be regarded as the processing operation corresponding to the first processing stage of the workpiece, forging can be regarded as the processing operation corresponding to the second processing stage of the workpiece, and cold heading can be regarded as the processing operation corresponding to the third processing stage of the workpiece.
[0048] Specifically, during processing, the iron block (i.e., the original material) is regarded as the workpiece to be processed in the first processing stage, and the workpiece to be processed in the second processing stage is obtained by performing the processing operation corresponding to the first processing stage (turning processing) on the sub-workpiece to be processed in the first stage; the workpiece to be processed in the third processing stage is obtained by performing the processing operation corresponding to the second processing stage (forging processing) on the workpiece to be processed in the second processing stage; and the finished workpiece, i.e., the product corresponding to the iron block, i.e., the screw, is obtained by performing the processing operation corresponding to the third processing stage (cold heading) on the workpiece to be processed in the third processing stage.
[0049] The production scheduling order of at least two workpieces to be processed is the processing order obtained after random initialization based on the workpiece identifications of the workpieces to be processed, which is not limited in the embodiment of the present application.
[0050] As an example, there are 5 workpieces in the workpiece group, namely: Workpiece 1, Workpiece 2, Workpiece 3, Workpiece 4, and Workpiece 5. The corresponding initialization production scheduling order can be: Workpiece 1→Workpiece 2→Workpiece 3→Workpiece 4→Workpiece 5, or it can be: Workpiece 4→Workpiece 3→Workpiece 2→Workpiece 5→Workpiece 1, etc.
[0051] In order to obtain a more accurate production scheduling sequence, shorten the search time and converge quickly, improve the speed of determining the final production scheduling sequence, and meet the development needs of intelligent and flexible workshops, in the embodiment of the present application, the actual production mode can also be combined, for example, the number of workpieces to be processed, the processing procedures, the delivery time, etc., at least one item, to initialize the production scheduling sequence and obtain the production scheduling sequence. The production scheduling sequence initialization method can specifically include the following methods:
[0052] Method 1: Taking the production scheduling initialization based on the workpiece type to be processed, the correct sequence of the processing procedures of the workpiece to be processed and the number of workpieces to be processed as an example, the production scheduling order of all workpieces to be processed can be randomly set while ensuring the sequence of the processing procedures (i.e., random initialization of part of the production scheduling order is performed).
[0053] As an example, there are 5 workpieces in the workpiece group, namely: workpiece 1, workpiece 2, workpiece 3, workpiece 4, workpiece 5, and except for workpiece 2 which is realized through three processing stages a, b, c with a processing sequence (that is, the workpiece to be processed of workpiece 2 can be expressed as workpiece 2a→workpiece 2b→workpiece 2c), the remaining workpieces can be realized through one processing stage, and the production scheduling sequence can be obtained: workpiece 4→workpiece 2a→workpiece 3→workpiece 2b→workpiece 5→workpiece 2c→workpiece 1. Among them, in this production scheduling sequence, the processing sequence of workpiece 2 has not changed.
[0054] Method 2: Taking the production scheduling initialization based on the workpiece type to be processed, the correct sequence of processing procedures for the workpiece to be processed, the number of workpieces to be processed, and the batch continuity of the same product as an example, the production scheduling order of all workpieces to be processed can be randomly set (i.e., continuous initialization of some particles) while ensuring the batch continuity and processing sequence of the same product.
[0055] As an example, there are 5 workpieces in the workpiece group, namely: workpiece 1, workpiece 2, workpiece 3, workpiece 4, workpiece 5, and except for workpiece 2 which is realized through three processing stages a, b, c with sub-processing sequences (i.e., the workpiece to be processed of workpiece 2 can be expressed as workpiece 2a→workpiece 2b→workpiece 2c), the remaining workpieces can be realized through one processing stage, and the initial production scheduling sequence can be obtained: workpiece 4→workpiece 3→workpiece 2a→workpiece 2b→workpiece 2c→workpiece 5→workpiece 1. Among them, in this production scheduling sequence, the processing sequence of workpiece 2 has not changed, and each processing stage is continuous.
[0056] Method 3: Taking the initialization of the production scheduling sequence based on the workpiece type to be processed, the correct sequence of processing procedures for the workpiece to be processed, the number of workpieces to be processed, the batch continuity of the same product and the delivery time as an example, the production scheduling sequence can be set on the premise of ensuring the sequence of delivery time, the number of each delivery, the batch continuity of the same product and the sequence of procedures (i.e., initializing the delivery sequence of some particles).
[0057] As an example, there are 5 workpieces in the workpiece group, namely: workpiece 1, workpiece 2, workpiece 3, workpiece 4, workpiece 5. Among them, except for workpiece 2, which is realized through three processing stages a, b, and c with sub-processing sequences (that is, the workpiece to be processed of workpiece 2 can be expressed as workpiece 2a→workpiece 2b→workpiece 2c), the remaining workpieces can be realized through one processing stage, and the order of the delivery time of each workpiece is: workpiece 2→workpiece 3→workpiece 1→workpiece 5→workpiece 4, then the initial production scheduling sequence can be obtained: workpiece 2a→workpiece 2b→workpiece 2c→workpiece 3→workpiece 1→workpiece 5→workpiece 4. Among them, in this production scheduling sequence, the processing order of workpiece 2 has not changed, the processing stages of workpiece 2 are continuous, and it can be guaranteed that the delivery time is in the order of the delivery time.
[0058] Optionally, different methods of initializing the production scheduling sequence may be combined to determine the production scheduling sequence. For example, according to the total number of workpieces of each workpiece type in the workshop, the production scheduling sequence number corresponding to method 1: the production scheduling sequence number corresponding to method 2: the production scheduling sequence number corresponding to method 3 = 3:3:4 may be adopted, and the production scheduling sequence may be determined by method 1, method 2, and method 3 respectively.
[0059] It should be noted that in order to improve the production efficiency of the workshop, the workpieces in the workshop can also be divided based on the number of workpieces that can be processed simultaneously by the processing equipment in the workshop and the number of workpieces of each type processed, so as to realize batch processing operations of the same processing stage for each workpiece in the same workpiece group.
[0060] As an example, take workpieces of five different workpiece types, A, B, C, D, and E, which can be produced in the same workshop as an example. If the total number of workpieces to be processed in the workshop is 80, among which the processing numbers of workpieces corresponding to workpiece type A, workpiece type B, workpiece type C, workpiece type D, and workpiece type E are 10, 15, 10, 20, and 15, respectively, then: based on the number of workpieces that can be processed simultaneously by the processing equipment in the workshop each time (for example, 5) and the processing number of workpieces of each workpiece type, the workpieces in the workshop can be divided into 14 workpiece groups (i.e., 14 batches), that is: the workpieces of workpiece type A are divided into two workpiece groups A1 and A2, the workpieces of workpiece type B are divided into three workpiece groups B1, B2, and B3, the workpieces of workpiece type C are divided into two workpiece groups C1 and C2, the workpieces of workpiece type D are divided into four workpiece groups D1, D2, D3, and D4, and the workpieces of workpiece type E are divided into three sub-workpiece groups E1, E2, and E3.
[0061] Step S102: taking the production scheduling sequence as particles to be processed, and determining the prediction index values corresponding to the particles to be processed under at least two production indexes according to the equipment attributes of the processing equipment.
[0062] In an embodiment of the present application, after determining the particles to be processed (i.e., the production sequence), the position information, speed information, and weight information of each particle to be processed can also be initialized, wherein the position information represents the particle to be processed itself (for example, the initial position of each particle to be processed can be determined based on the order of determining the production sequence), the speed information is the movement speed in the multi-particle space, the weight information is consistent with the position information, and the weight information with the forward position information is also larger.
[0063] The equipment attributes of the processing equipment may include the number of processing equipment of different processing types, the working status of the processing equipment (for example, can be scheduled, cannot be scheduled, temporarily cannot be scheduled), the processing operations that the processing equipment can perform, etc.
[0064] Production indicators may include but are not limited to the total completion time of all workpieces, the processing continuity of the equipment (i.e., minimizing the frequent switching of the types of workpieces processed by the same equipment), delivery time, etc.
[0065] When determining the predicted index values corresponding to the above-mentioned particles to be processed under at least two production indicators respectively according to the equipment properties of the processing equipment, the predicted index value of the corresponding particles to be processed under each production indicator can be determined respectively based on each production indicator when each processing equipment is used to process each workpiece to be processed in the particles to be processed.
[0066] Among them, when determining the corresponding time period for selecting the corresponding processing equipment for each process (an operation) of a workpiece, the optional processing equipment corresponding to each process of each workpiece can be first determined based on the processing operations that can be performed by the processing equipment; and combined with the completion time of the previous process of the workpiece, the processing time of the current process, and the tangent time between the previous operation and the current operation of the optional processing equipment, the processing equipment corresponding to the workpiece and the available time period of the processing equipment are determined from the optional processing equipment, and then the cycle is repeated until the selection of processing equipment is completed for all operations.
[0067] Optionally, if it can be determined that multiple processing equipment can perform a processing operation on a certain workpiece, the earliest available processing equipment can be selected from the processing equipment.
[0068] Step S103: Calculate the predicted index values according to the multi-objective particle swarm algorithm, and determine the target particles that meet the production scheduling conditions from the particles to be processed according to the calculation results; wherein the production scheduling conditions include the target index value of each production index.
[0069] It is understandable that the target indicator value may be a specific numerical value, a numerical range or a relative value, and the embodiments of the present application are not limited thereto.
[0070] Optionally, corresponding to the production indicator of completion time, the production scheduling conditions may include: minimum maximum completion time, that is, after determining the maximum completion time of each particle to be processed, the minimum value of the maximum completion time of each particle to be processed is determined as the minimum maximum completion time, and the corresponding particles to be processed are particles that meet the production scheduling conditions.
[0071] Among them, for each particle to be processed, when determining the maximum completion time of the particle to be processed, the processing equipment and available time period for executing the particle to be processed can be first determined, and then the sum of the estimated execution time of each operation in the particle to be processed and the switching time of each processing equipment can be determined as the maximum completion time of the particle to be processed.
[0072] Optionally, corresponding to the production indicator of delivery time, the production scheduling conditions may include: meeting the delivery time of each workpiece to be processed.
[0073] Optionally, corresponding to the production index of switching continuity, the production scheduling conditions may include: the sum of switching time is shortest and the switching continuity is best. That is, when processing each process in the particles to be processed, the sum of the switching time of each processing equipment is shortest, and the product switching amount corresponding to each processing equipment is the least (that is, the same processing equipment processes the processing operations of the same product as much as possible).
[0074] Optionally, after determining the values of the prediction indicators of each particle to be processed, the indicators can be normalized, and the particle to be processed that is closest to the production scheduling condition among the particles to be processed can be determined as the target particle. If there are multiple particles to be processed that are closest to the production scheduling condition, any particle to be processed among the particles to be processed that are closest to the production scheduling condition can be randomly determined as the target particle.
[0075] In an embodiment of the present application, by determining the production scheduling order of at least two workpieces to be processed and the production scheduling conditions including the target indicator value of each production indicator, the determined production scheduling order is used as the particles to be processed, and according to the equipment properties of the processing equipment, the predicted indicator values corresponding to the particles to be processed under at least two production indicators are determined; and the above-mentioned predicted indicator values are calculated according to the multi-objective particle swarm algorithm, and the target particles that meet the production scheduling conditions are determined from the particles to be processed according to the calculation results. The production scheduling order that meets various production indicators can be quickly determined, thereby improving the production scheduling efficiency.
[0076] Optionally, the calculation of the prediction index value according to the multi-objective particle swarm algorithm and determining the target particles satisfying the production scheduling conditions from the particles to be processed according to the calculation result may include:
[0077] According to the above-mentioned prediction index value, the initial position information of the above-mentioned particle to be processed in the production index space is determined; the dimension of the production index space is used to represent the production index;
[0078] Determining the particle crowding degree of the to-be-processed particles in the production index space according to the initial position information;
[0079] According to the particle crowding degree, the target particles are determined.
[0080] In this implementation, each production indicator can be used as a dimension to construct a production indicator space, and the initial position information of the particle to be processed in the production indicator space can be determined according to the predicted indicator value of the particle to be processed corresponding to each production indicator.
[0081] It is understandable that the position information of the particle to be processed in the production index space can also be determined based on the initialized position information of the particle to be processed; and after the predicted index value of the particle to be processed is determined, the position information of the particle to be processed in the production index space is adjusted to the initial position information.
[0082] After determining the initial position information of each particle to be processed, the spatial range formed by the initial position information of each particle to be processed can be divided into different grid spaces according to the initial position information of each particle to be processed, and the particle crowding degree of the particle to be processed can be determined according to the number of particles in the grid space to which the initial position information of each particle to be processed belongs.
[0083] Specifically, assuming that the total number of particles to be processed is 100, numbered 1, ..., 100, the spatial range formed by the initial position information of each particle to be processed can be divided into 10 grid spaces, and the particle crowding degree of the particle to be processed can be respectively the number of particles x in the grid space where the particle to be processed is located 1 ,x 2 ,…x 100 .
[0084] Optionally, after the particle crowding degree of each to-be-processed particle is determined, the to-be-processed particle with the lowest particle crowding degree may be determined as the target particle in consideration of the difficulty of screening each to-be-processed particle.
[0085] Optionally, the target particles may be determined based on the following particle crowding selection function:
[0086]
[0087]
[0088] Wherein, r represents the total number of particles to be processed, and 10 is a constant, and the specific value can be determined according to the actual situation. i is the probability that the particle to be processed is determined as the target particle, n i is the middle value.
[0089] In determining the m i After that, the accumulated value of the crowding selection function of the current particle to be processed can be calculated And randomly generate a random number between 0 and 1. If the random number is less than or equal to sp i , then the particle i to be processed is the target particle.
[0090] Based on the particle crowding degree of the particles to be processed in the production index space, the target particles that meet the production scheduling conditions can be quickly determined.
[0091] Optionally, the step of determining the particle crowding degree of the to-be-processed particles in the production index space according to the initial position information may include:
[0092] Determine the target velocity information of the particles to be processed;
[0093] According to the target speed information, the initial position information is updated to obtain updated position information;
[0094] The particle crowding degree is re-determined according to the updated position information.
[0095] Optionally, the above-mentioned determination of the target speed information of the particles to be processed may include:
[0096] Determining first position information of the particle to be processed according to a comparison result of the current position information and the historical position information of the particle to be processed;
[0097] Determine the second position information according to the comparison result of the current position information of all the particles to be processed and the target position information; the target position information is the position information of the target index value in the production index space;
[0098] The target speed information is updated according to the current position information, the first position information and the second position information by using a preset speed information updating method.
[0099] Optionally, when performing the second round of iterations, the current position information of the particle to be processed is the same as the historical position information, that is, the initial position information. Then, based on the speed information, the moving time and the current position information of the particle to be processed, the product of the speed information of the particle to be processed and the moving time can be added to the current position information of the particle to be processed to obtain the position information to be processed, and the position information that meets the production scheduling conditions (that is, the position information that is closer to the target position information) between the current position information of the particle to be processed and the position information to be processed is determined as the first position information.
[0100] When the third round of iteration is performed, the target speed information can be determined according to the above target speed information determination method, and the current position information can be updated.
[0101] When determining the second position information, the position information closest to the target position information in the current position information of each particle to be processed can be determined as the second position information, that is, the position information of the target particle in the previous iteration process.
[0102] Optionally, the following preset speed information updating method may be used to determine the target speed information:
[0103] V i =×v i + 1 r 1 (pbest-p i )+ 2 r 2 (hbest-p i)
[0104] Among them, v i is the current speed information, p i is the current position information of the particle to be processed, pbest is the first position information, gbest is the second position information, ω is the inertia coefficient (non-negative constant), c 1 、c 2 is the acceleration constant, used to adjust the learning step size, r 1 , r 2 is a random constant. Among them, ω, c 1 、c 2 、r 1 and r 2 The specific value can be determined according to actual conditions.
[0105] After determining the target velocity information of the particle to be processed, the current position information of the particle to be processed can be updated according to the following method to obtain the updated position information:
[0106] P i = i + i
[0107] After the position information (ie, the prediction index value) of each particle to be processed is updated, the above method can be used to iterate the particle crowding degree, and the target particle can be determined again based on the updated particle crowding degree.
[0108] In this implementation, the position information of each particle to be processed can be updated, the particle crowding degree can be iterated, and after the particle crowding degree is determined, the target particle can be re-determined based on the updated particle crowding degree, so that the target particle that meets the production scheduling conditions can be determined through multiple rounds of iterative calculations, thereby improving the accuracy of the determined target particles.
[0109] Optionally, the calculation of the prediction index value according to the multi-objective particle swarm algorithm and determining the target particles satisfying the production scheduling conditions from the particles to be processed according to the calculation result may include:
[0110] According to the priorities of the at least two production indicators, determine the target production indicator with the highest priority;
[0111] Determining a sampling ratio of the particles to be processed according to the predicted index value of the particles to be processed under the target production index;
[0112] According to the sampling ratio, the target particles are sampled from the particles to be processed.
[0113] Optionally, the determining of the sampling ratio of the particles to be processed according to the predicted index value of the particles to be processed under the target production index may include:
[0114] Determine the minimum value among the predicted index values of each particle to be processed under the above target production index;
[0115] The sampling ratio of the particles to be processed is determined according to the minimum value and the predicted index value of the particles to be processed under the target production index.
[0116] In this implementation, the priority of each production indicator can be determined according to actual conditions. For example, according to the priority of each production indicator, it can be determined that the target production indicator with the highest priority is the completion time.
[0117] If there is a production index with the highest priority, after determining the minimum value of the predicted index values of each particle to be processed under the production index, the production index can be determined as the target production index, and subsequent operations can be performed according to the determined minimum value. If there are multiple production indexes with the highest priority, after determining the minimum value of the predicted index values of each particle to be processed under the above-mentioned production indexes with the highest priority, the maximum value among the minimum values can be used, and the production index corresponding to the maximum value can be determined as the target production index, and subsequent operations can be performed.
[0118] When determining the sampling ratio of the particles to be processed, the sum k of the predicted index values of each particle to be processed under the target production index can be determined, a first ratio of the predicted index value of the particle to be processed under the target production index to the sum of the predicted index values can be determined, and the sampling ratio of the particles to be processed can be determined as the ratio of the first ratio corresponding to the particle to be processed to k.
[0119] As an example, assuming that there are two particles a and b to be processed, the production scheduling conditions may include the total completion time of all workpieces (i.e., target x), the processing continuity of the equipment (i.e., target y), and the delivery time (i.e., target z), and the production indicators with the highest priority are target y and target z. After normalizing the predicted index values of the particles to be processed under each production indicator, the normalized predicted index values of the two particles to be processed can be obtained as follows: a[1, 0.5, 0.8], b[2, 0.6, 0.6].
[0120] Then we can traverse the predicted index values of the two to-be-processed particles a and b under target y and target z respectively, and determine the minimum values under target y and target z, i.e. y_min=0.5 (from particle a), z_min=0.6 (from particle b). And determine the maximum value of y_min and z_min, i.e. z_min=0.6, and we can determine that target z is the target that needs to be focused on in this round, i.e. the target production index. Then, according to the values of 0.8 and 0.6 of the to-be-processed particles a and b under target z respectively, we can extract in proportion. Among them, k is sum(a, b)=0.8+0.6=1.4, l[a]=1.4 / 0.8, l[b]=1.4 / 0.6, then the sampling ratio corresponding to the to-be-processed particle a is l[a] / k, and the sampling ratio corresponding to the to-be-processed particle b is l[b] / k. And according to the sampling ratios corresponding to the particles a to be processed and the particles b to be processed, sampling is performed on the particles a to be processed and the particles b to be processed, and the particles obtained by sampling are determined as target particles.
[0121] It is understandable that the position information of each particle to be processed may also be updated according to the above method, and the updated position information may be normalized, and iteration may be performed based on the normalized prediction index value until the target particle is determined.
[0122] Optionally, before calculating the prediction index value according to the multi-objective particle swarm algorithm, the method may further include:
[0123] Determining candidate particles among the particles to be processed according to a comparison result of the prediction index values of at least two of the particles to be processed;
[0124] Among the particles to be processed, the prediction index value of the candidate particles is greater than the prediction index value of the non-candidate particles.
[0125] Optionally, the determining of candidate particles among the particles to be processed according to the comparison result of the prediction index values of at least two of the particles to be processed may include:
[0126] When the number of the candidate particles is greater than a preset threshold, particles whose number is the preset threshold are screened from the candidate particles based on the particle crowding degree of the candidate particles.
[0127] In this implementation, the Pareto method can be used to determine candidate particles based on the Pareto dominance relationship. In the Parto dominance relationship (i.e., the dominance relationship of the decision vector and the dominance relationship of the target vector), if and only if X1 is not worse than X2 in all targets, and is strictly better than X2 in at least one target, that is, one decision vector X1 dominates another decision vector X2, and X1 can be regarded as a non-inferior solution, that is, a dominant solution, and X2 can be regarded as a dominated solution.
[0128] In the embodiment of the present application, the prediction index values of two particles to be processed can be compared to determine the dominant solution and the dominated solution in the two particles to be processed, and the dominated solution is deleted and the dominant solution is retained to obtain a preset number of candidate particles.
[0129] After determining the dominant solution, the number of dominant solutions can also be determined. When the number of dominant solutions is less than or equal to a preset threshold, the determined dominant solution can be used as a candidate particle. When the number of dominant solutions is less than the preset threshold, the dominant solution can be re-determined from the dominated solutions until the total number of dominant solutions determined reaches the preset threshold.
[0130] When the number of dominant solutions is greater than a preset threshold, some dominant solutions may be removed based on the particle crowding of the to-be-processed particles corresponding to each dominant solution until a total number of dominant solutions reaching the preset threshold is determined. For example, the to-be-processed particles with a high particle crowding may be removed.
[0131] Specifically, the selection probability pp of each particle to be processed is calculated according to the particle crowding degree of the particle to be processed corresponding to the dominant solution. i = i 2 , and determine the cumulative value of the selected probability of the particle to be processed And randomly generate a random number a between 0 and the sum of the selected probabilities. If the random number a is less than or equal to spp i , the particles to be processed are cleared.
[0132] It is understandable that, in the above iterative process, all the particles to be processed can be merged again after each iteration, and the candidate particles and the target particles can be re-determined to avoid errors in a single iteration process and affect the accuracy of the target particles finally determined.
[0133] By determining candidate particles in the above manner and removing redundant candidate particles, the amount of data required in the process of determining target particles can be reduced, thereby increasing the probability of determining target particles.
[0134] In summary, if Figure 3 As shown, in the production scheduling method, the following steps may be included:
[0135] Step 301: Initialize the position, velocity, and weight of particles (i.e., particles to be processed);
[0136] Step 302: Calculate the initialization fitness (i.e., the prediction index value) according to the machine selection result (i.e., the algorithm calculation process);
[0137] Step 303: Initializing the individual optimum (i.e. determining the initial position information and determining the first position information);
[0138] Step 304: Particle archiving (i.e. determining candidate particles);
[0139] Step 305: Calculate and initialize the global optimum (determine the second position information);
[0140] Step 306: Update particle position, velocity, and weight;
[0141] Step 307: Calculate the updated fitness according to the machine selection result;
[0142] Step 308: Update individual optimum;
[0143] Step 309: Update particle archive;
[0144] Step 310: Update the global optimum and determine whether the number of iterations is reached or the convergence condition is met. If so, the process ends; if not, the process returns to step 306.
[0145] It should be noted that step 303, step 305, and step 307 may also be replaced by determining a sampling ratio, which will not be elaborated here.
[0146] In order to facilitate a better understanding of the production scheduling method provided in the embodiment of the present application, the production scheduling method is better explained below with reference to specific examples.
[0147] Step 1: Figure 4a The production scheduling style configuration 301 and constraint conditions 302 shown in the figure can be used to construct a production scheduling style (i.e., production scheduling conditions and goals) according to the actual production needs of different factories in the actual production scheduling process.
[0148] Step 2: If Figure 4a As shown in 303, the configured scheduling style and constraints are input into the scheduling optimization algorithm (for example, a heuristic algorithm or a mathematical programming algorithm), and the above-mentioned production scheduling method is used for calculation, and the style configuration (i.e., production scheduling conditions and goals) of each scheduling scheme (i.e., scheduling sequence) is evaluated, such as completion time evaluation, equipment utilization evaluation, and WIP (work in progress, workshop production management) indicator evaluation.
[0149] Step 3: If Figure 4a 304 shown, the best production scheduling scheme can be selected according to the evaluation index and output to the user, including the daily plan (such as Figure 4b or Figure 4c As shown), minute-level plans (such as Figure 4d or Figure 4eshown).
[0150] in, Figure 4d or Figure 4e It is represented by a Gantt chart, where Figure 4d or Figure 4e In the Gantt chart, the horizontal axis is time (Time, unit: day), the vertical axis is the equipment name (Machine), each color represents a product, each long bar represents each process of the product, the left side of the long bar is the start processing time, and the right side is the end processing time.
[0151] Figure 4b The product demand table shown is based on days, i.e., a daily schedule. Figure 4b As shown, the products to be produced include product B1A013Z15V601, product B1A014YW5V801, product B1A015B75E501, ..., product B1A150X05T403. As an example, the quantity of product B1A015QQ5T401 to be produced (i.e., processed) on February 7, 2022 is 400, the quantity of product B1A020QV5T405 is 1600, and the total quantity of each product to be produced on February 7, 2022 is 2000; the quantity of product B1A014YW5V801 to be produced on February 10, 2022 is 100, the quantity of product B1A015QQ5T401 is 2000, and the total quantity of each product to be produced on February 10, 2022 is 2100.
[0152] Figure 4c The production process indicator table shown indicates the demand list, process route, machine information (i.e., information of processing equipment), production scheduling style (i.e., production scheduling style), actual production line dashboard, daily capacity curve chart, daily inventory curve chart, daily output curve chart, etc. of different products. Among them, the demand list includes delivery time, total number of products, delivery time satisfaction (i.e., the ratio of the number of products actually produced during the delivery time to the total number of products), predicted delivery time, production (i.e., the number of products being produced), and completed (i.e., the number of products that have been completed). The process route is the site order determined based on the production stage (i.e., process) of each product. The machine information includes different sites and the available machine identifiers corresponding to each site. The production scheduling style includes the maximum demand satisfaction, the maximum capacity, the minimum number of line changes, the lowest inventory, and the balanced output. The real-time production line dashboard is the indicator value of each production indicator determined according to the actual production situation, specifically including the WIP value, the capacity indicator value of the current machine, the input of the current product, and the output of the current product.
[0153] like Figure 4cAs shown, the product currently being produced is product A, the delivery date of product A is October 11, 2022, the required production quantity is 30,000, the predicted delivery date is October 11, 2022, 4,000 units have been put into production, and 2,000 units have been completed. The process route of product A is M→L→K→S. The indicator values of each production indicator, product A is currently being produced at site M, and the machines that can produce the current process of product A at site M include M1, M2, M3, and L2. The WIP value of product A is 2000, the capacity indicator value of the currently used machine M1 is 3000, the input of product A is 2000, and the output of product A is 2000.
[0154] It should be noted that in the actual production process, different products may be in demand at different time periods. Figure 4c As shown, the delivery date of Product A includes October 11, 2022 and December 1, 2022.
[0155] like Figure 4d As shown in the figure, when the final target production order is determined according to different production orders and the optional machines at each site for each production order, the actual processing machine can be selected from the optional machines according to the production end time of the machine. The vertical axis is the different machine identifiers, and the horizontal axis is the production end time corresponding to each machine. When the vertical axis is fixed, each square represents the production start time to production end time of the current process of the machine corresponding to the vertical axis. Figure 4d As shown in the partial enlarged view 401, when the first process (process 1) of product A is produced by machine M2, the production start time is 10:30 on October 11, 2022, and the production end time is 10:35 on October 11, 2022. By analogy, the final production end time of each machine can be determined, and then based on the length of the production end time of each machine, it is selected whether to use the machine to process the process of the current product.
[0156] like Figure 4e As shown, when the product is processed by each machine, the current time (i.e. Figure 4e The timestamp shown in 402 in the figure is used to identify the completed processes on each machine, the locked processes (i.e., the preparatory work for the process to be processed has been set on the machine, and the process to be processed will be processed on the machine soon), and the adjustable processes (i.e., the preparatory work for the process to be processed has not been set on the machine, and the machine that can process the process to be processed can be reselected).
[0157] Of course, other methods can also be used to express it. For example, after the production scheduling plan is completed, the expected delivery date of each product and the number of products put into production as of the current date can be calculated, and a real-time capacity dashboard (real-time inventory, input, and output) and various graphs showing the factory's production status (daily capacity graph of production lines, daily inventory graph, and daily output graph, etc.) can be generated.
[0158] The method of determining the production schedule can also be visualized by entering a new demand list (including product name, delivery date, required quantity), process route, machine information, production schedule style, equipment maintenance plan, and semi-finished product inventory data, and clicking the rearrangement control (such as Figure 4c As shown), a new production schedule can be obtained again.
[0159] Experiments have shown that by applying this production scheduling method, the calculation time for a two-month minute-level production plan at the output factory is only 8 minutes, which is much lower than the time for manual scheduling.
[0160] Based on the same principle as the production scheduling method provided in the embodiment of the present application, the embodiment of the present application also provides a production scheduling device. Figure 5 As shown, the device 50 comprises:
[0161] A production scheduling module 501 is used to determine the production scheduling of at least two workpieces to be processed;
[0162] The index value prediction module 502 is used to use the production scheduling sequence as the particles to be processed, and determine the predicted index values corresponding to the particles to be processed under at least two production indicators according to the equipment attributes of the processing equipment;
[0163] The target particle determination module 503 is used to calculate the above-mentioned prediction index value according to the multi-objective particle swarm algorithm, and determine the target particles that meet the production scheduling conditions from the above-mentioned particles to be processed according to the calculation results; wherein the production scheduling conditions include the target index value of each production index.
[0164] Optionally, the target particle determination module 503 calculates the prediction index value according to a multi-objective particle swarm algorithm, and determines the target particles that meet the production scheduling conditions from the particles to be processed according to the calculation result, which may include:
[0165] According to the above-mentioned prediction index value, the initial position information of the above-mentioned particle to be processed in the production index space is determined; the dimension of the production index space is used to represent the production index;
[0166] Determining the particle crowding degree of the to-be-processed particles in the production index space according to the initial position information;
[0167] According to the particle crowding degree, the target particles are determined.
[0168] Optionally, the target particle determination module 503 determines the particle crowding degree of the to-be-processed particle in the production index space according to the initial position information, which may include:
[0169] Determine the target velocity information of the particles to be processed;
[0170] According to the target speed information, the initial position information is updated to obtain updated position information;
[0171] The particle crowding degree is re-determined according to the updated position information.
[0172] Optionally, the target particle determination module 503 determines the target velocity information of the particle to be processed, which may include:
[0173] Determining first position information of the particle to be processed according to a comparison result of the current position information and the historical position information of the particle to be processed;
[0174] Determine the second position information according to the comparison result of the current position information of all the particles to be processed and the target position information; the target position information is the position information of the target index value in the production index space;
[0175] The target speed information is updated according to the current position information, the first position information and the second position information by using a preset speed information updating method.
[0176] Optionally, the target particle determination module 503 calculates the prediction index value according to a multi-objective particle swarm algorithm, and determines the target particles that meet the production scheduling conditions from the particles to be processed according to the calculation result, which may include:
[0177] According to the priorities of the at least two production indicators, determine the target production indicator with the highest priority;
[0178] Determining a sampling ratio of the particles to be processed according to the predicted index value of the particles to be processed under the target production index;
[0179] According to the sampling ratio, the target particles are sampled from the particles to be processed.
[0180] Optionally, the target particle determination module 503 determines the sampling ratio of the particles to be processed according to the predicted index value of the particles to be processed under the target production index, which may include:
[0181] Determine the minimum value among the predicted index values of each particle to be processed under the above target production index;
[0182] The sampling ratio of the particles to be processed is determined according to the minimum value and the predicted index value of the particles to be processed under the target production index.
[0183] Optionally, the above device may further include a candidate particle determination module, which is used to:
[0184] Before calculating the prediction index value according to the multi-objective particle swarm algorithm, determining candidate particles among the particles to be processed according to a comparison result of the prediction index values of at least two of the particles to be processed;
[0185] Among the particles to be processed, the prediction index value of the candidate particles is greater than the prediction index value of the non-candidate particles.
[0186] Optionally, the candidate particle determination module determines the candidate particles among the particles to be processed according to the comparison result of the prediction index values of at least two of the particles to be processed, which may include:
[0187] When the number of the candidate particles is greater than a preset threshold, particles whose number is the preset threshold are screened from the candidate particles based on the particle crowding degree of the candidate particles.
[0188] In an embodiment of the present application, by determining the production scheduling order of at least two workpieces to be processed and the production scheduling conditions including the target indicator value of each production indicator, the determined production scheduling order is used as the particles to be processed, and according to the equipment properties of the processing equipment, the predicted indicator values corresponding to the particles to be processed under at least two production indicators are determined; and the above-mentioned predicted indicator values are calculated according to the multi-objective particle swarm algorithm, and the target particles that meet the production scheduling conditions are determined from the particles to be processed according to the calculation results. The production scheduling order that meets various production indicators can be quickly determined, thereby improving the production scheduling efficiency.
[0189] The device of the embodiments of the present application can execute the method provided by the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.
[0190] Based on the same principle as the production scheduling method and device provided in the embodiment of the present application, an electronic device (such as a server) is also provided in the embodiment of the present application. The electronic device may include a memory, a processor, and a computer program stored in the memory. The processor executes:
[0191] Determine the production order of at least two workpieces to be processed;
[0192] Taking the production scheduling sequence as the particles to be processed, and determining the prediction index values corresponding to the particles to be processed under at least two production indexes according to the equipment attributes of the processing equipment;
[0193] The predicted index values are calculated according to a multi-objective particle swarm algorithm, and target particles that meet production scheduling conditions are determined from the particles to be processed according to the calculation results; wherein the production scheduling conditions include target index values for each production index.
[0194] In an embodiment of the present application, by determining the production scheduling order of at least two workpieces to be processed and the production scheduling conditions including the target indicator value of each production indicator, the determined production scheduling order is used as the particles to be processed, and according to the equipment properties of the processing equipment, the predicted indicator values corresponding to the particles to be processed under at least two production indicators are determined; and the above-mentioned predicted indicator values are calculated according to the multi-objective particle swarm algorithm, and the target particles that meet the production scheduling conditions are determined from the particles to be processed according to the calculation results. The production scheduling order that meets various production indicators can be quickly determined, thereby improving the production scheduling efficiency.
[0195] See also Figure 5 , Figure 5 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present application. Figure 5 As shown, the electronic device 600 in this embodiment may include: a processor 601, a network interface 604 and a memory 605. In addition, the above-mentioned electronic device 600 may also include: an object interface 603, and at least one communication bus 602. Among them, the communication bus 602 is used to realize the connection and communication between these components. Among them, the object interface 603 may include a display screen (Display), a keyboard (Keyboard), and the object interface 603 may optionally include a standard wired interface and a wireless interface. The network interface 604 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 605 may be a high-speed RAM memory, or it may be a non-volatile memory (NVM), such as at least one disk storage. The memory 605 may optionally also be at least one storage device located away from the aforementioned processor 601. As Figure 5 As shown, the memory 605 as a computer-readable storage medium may include an operating system, a network communication module, an object interface module, and a device control application program.
[0196] exist Figure 5 In the electronic device 600 shown, the network interface 604 can provide a network communication function; the object interface 603 is mainly used to provide an input interface for the object; and the processor 601 can be used to call the device control application stored in the memory 605 to achieve:
[0197] In some feasible implementations, the processor 601 is configured to:
[0198] It should be understood that in some feasible implementations, the processor 601 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.
[0199] In a specific implementation, the electronic device 600 can execute the above-mentioned functions through its built-in functional modules. Figure 1 For the implementation methods provided in each step, please refer to the implementation methods provided in the above steps for details, which will not be repeated here.
[0200] The present application also provides a computer-readable storage medium, which stores a computer program and is executed by a processor to implement Figure 1 For the methods provided in each step, please refer to the implementation methods provided in the above steps for details, which will not be repeated here.
[0201] The above-mentioned computer-readable storage medium may be an internal storage unit of the production scheduling device or electronic device provided in any of the above-mentioned embodiments, such as a hard disk or memory of an electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the electronic device. The above-mentioned computer-readable storage medium may also include a disk, an optical disk, a read-only memory (read-only memory, ROM) or a random access memory (random access memory, RAM), etc. Further, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
[0202] The present invention provides a computer program product, which includes a computer program. The computer program is executed by a processor. Figure 1 The methods provided in each step.
[0203] The terms "first", "second" and the like in the claims, the specification and the drawings of the present application are used to distinguish different objects rather than to describe a specific order.
[0204] In addition, those skilled in the art will understand that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or electronic device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or electronic devices.
[0205] Mentioning "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. Displaying the phrase at various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments. The term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.
[0206] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0207] The above disclosure is only the preferred embodiment of the present application, which cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.
Claims
1. A production scheduling method, characterized in that: include: Determine the production order of at least two workpieces to be processed; Taking the production scheduling sequence as the particles to be processed, and determining the prediction index values corresponding to the particles to be processed under at least two production indexes according to the equipment attributes of the processing equipment; The predicted index value is calculated according to a multi-objective particle swarm algorithm, and target particles that meet production scheduling conditions are determined from the particles to be processed according to the calculation results; wherein the production scheduling conditions include the target index value of each of the production indicators.
2. The method according to claim 1, characterized in that The step of calculating the predicted index value according to the multi-objective particle swarm algorithm and determining target particles that meet the production scheduling conditions from the particles to be processed according to the calculation result includes: According to the predicted index value, determining the initial position information of the to-be-processed particle in the production index space; the dimension of the production index space is used to represent the production index; Determining the particle crowding degree of the to-be-processed particle in the production index space according to the initial position information; The target particles are determined according to the particle crowding degree.
3. The method according to claim 2, characterized in that Determining the particle crowding degree of the to-be-processed particle in the production index space according to the initial position information includes: Determining target velocity information of the particles to be processed; updating the initial position information according to the target speed information to obtain updated position information; The particle crowding degree is re-determined according to the updated position information.
4. The method according to claim 3, characterized in that The step of determining target velocity information of the particles to be processed comprises: Determining first position information of the particle to be processed according to a comparison result of the current position information and the historical position information of the particle to be processed; Determine the second position information according to the comparison result of the current position information of all the particles to be processed and the target position information; the target position information is the position information of the target index value in the production index space; The target speed information is updated according to the current position information, the first position information and the second position information by using a preset speed information updating method.
5. The method according to claim 1, characterized in that The step of calculating the predicted index value according to the multi-objective particle swarm algorithm and determining target particles that meet the production scheduling conditions from the particles to be processed according to the calculation result includes: Determining a target production indicator with the highest priority according to the priorities of the at least two production indicators; Determining a sampling ratio of the particles to be processed according to a predicted index value of the particles to be processed under the target production index; The target particles are obtained by sampling the particles to be processed according to the sampling ratio.
6. The method according to claim 5, characterized in that The step of determining the sampling ratio of the particles to be processed according to the predicted index value of the particles to be processed under the target production index comprises: Determine the minimum value among the predicted index values of the particles to be processed under the target production index; The sampling ratio of the particles to be processed is determined according to the ratio information of the minimum value to the predicted index value of the particles to be processed under the target production index.
7. The method according to any one of claims 1 to 6, characterized in that Before calculating the prediction index value according to the multi-objective particle swarm algorithm, the method further includes: Determining candidate particles among the particles to be processed according to a comparison result of the prediction index values of at least two of the particles to be processed; Among the particles to be processed, the prediction index value of the candidate particles is greater than the prediction index value of the non-candidate particles.
8. The method according to claim 6, characterized in that The step of determining candidate particles among the particles to be processed according to the comparison result of the prediction index values of at least two particles to be processed comprises: When the number of the candidate particles is greater than a preset threshold, particles whose number is the preset threshold are screened from the candidate particles based on the particle crowding degree of the candidate particles.
9. A production scheduling device, characterized in that: include: A production scheduling sequence determination module, used to determine the production scheduling sequence of at least two workpieces to be processed; An index value prediction module, used to use the production scheduling sequence as the particles to be processed, and determine the predicted index values corresponding to the particles to be processed under at least two production indicators according to the equipment attributes of the processing equipment; The target particle determination module is used to calculate the predicted index value according to the multi-objective particle swarm algorithm, and determine the target particles that meet the production scheduling conditions from the particles to be processed according to the calculation results; wherein the production scheduling conditions include the target index value of each of the production indicators.
10. An electronic device, characterized in that: comprising a processor and a memory, wherein the processor and the memory are connected to each other; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 8 when calling the computer program.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.
Citation Information
Cited By
Production scheduling method and system, and electronic device and storage medium
EP4600877A1
Production scheduling method and system, and electronic device and storage medium
WO2024244196A1
