Resource configuration method for distributed manufacturing multi-production tasks, service platform and medium

Abstract

This application relates to a resource allocation method, service platform, and medium for distributed manufacturing with multiple production tasks. The method includes: determining the task completion degree of the manufacturing task associated with each manufacturing unit when an interrupt command is received; determining the current manufacturing task from all manufacturing tasks corresponding to the manufacturing configuration information based on the task completion degree, determining the candidate manufacturing unit associated with each current manufacturing task, and the candidate manufacturing unit being associated with at least one manufacturing device; performing hybrid coding based on the current manufacturing task, task completion degree, and manufacturing device to generate multiple hybrid coding bodies; after determining the fitness of the hybrid coding bodies according to a preset fitness function, performing corresponding genetic evolution operation iterations and simulated annealing search iterations using a genetic simulated annealing algorithm based on the multiple hybrid coding bodies and their corresponding fitness, until a preset number of iterations are performed, and selecting the target hybrid coding body from the multiple candidate hybrid coding bodies to obtain the resource allocation result.

Description

Technical Field

[0001] This application relates to the field of smart logistics and warehouse management technology, and in particular to resource allocation methods, service platforms and media for distributed manufacturing with multiple production tasks. Background Technology

[0002] In distributed manufacturing, when faced with complex tasks and long implementation cycles, the actual production process is often accompanied by various resource-level uncertainties. Under the influence of such uncertainties, resource allocation schemes must possess extremely strong robustness, meaning they can maintain efficient operation even under dynamically changing conditions.

[0003] In related technologies, under complex production environments, uncertainties in personnel, materials, and equipment severely restrict resource allocation and planning. In related technologies, to meet diverse production needs, equipment may need to operate at high loads for extended periods, accelerating facility depreciation. If equipment maintenance time and fault response plans are not reserved in the scheduling, production plans will fall into chaos, significantly increasing production costs.

[0004] In related technologies, under uncertain environments, the absence of skilled workers or the lack of operational expertise of new or temporarily assigned personnel can easily lead to production errors, resulting in a large number of defective products and increased raw material loss costs.

[0005] Furthermore, in an uncertain environment, uncertainties are difficult to withstand risks such as market supply and demand fluctuations and supplier delays in delivery. Small-batch production requires scattered materials, and once the supply is interrupted, the production line will stop, resulting in energy waste. Unstable material quality or non-compliance with specifications will lead to defective products in the production process, causing waste of raw materials. If an emergency procurement and quality monitoring mechanism is not established, it will seriously affect the continuity of production and cost control.

[0006] There is still no effective solution to the problem of low availability, applicability, reliability and robustness of resource allocation schemes for distributed manufacturing with multiple production tasks in related technologies. Summary of the Invention

[0007] This application provides a resource allocation method for distributed manufacturing with multiple production tasks, which at least solves the problems of low availability, applicability, reliability and robustness of resource allocation schemes for distributed manufacturing with multiple production tasks in related technologies.

[0008] In a first aspect, embodiments of this application provide a resource allocation method for distributed manufacturing with multiple production tasks, comprising: during the execution of production-operation-storage collaborative operations based on generated manufacturing configuration information, determining the task completion degree of the manufacturing task associated with each manufacturing unit when an interruption command is received, wherein the manufacturing configuration information includes at least the manufacturing task corresponding to the manufacturing unit, and the manufacturing configuration information is generated based on received historical production order information and pre-configured resource information, using a genetic simulated annealing algorithm for production-operation-storage collaborative planning and configuration; based on the task completion degree, determining the current manufacturing task from all the manufacturing tasks corresponding to the manufacturing configuration information, and determining the candidate manufacturing unit associated with each current manufacturing task, wherein the current manufacturing task is used to characterize the manufacturing task that needs to be reconfigured, and the candidate manufacturing unit is associated with at least one manufacturing device; based on the current manufacturing task, the corresponding task completion degree, and the corresponding production-operation-storage collaborative operation, determining the current manufacturing task, determining the corresponding production-operation-storage collaborative operation ... The manufacturing equipment is hybrid-coded to generate multiple hybrid codes. Each hybrid code includes multiple code elements, which represent configuration schemes of the manufacturing equipment corresponding to a current manufacturing task. Each code element is also associated with transportation and storage decision information determined according to a preset production-transportation-storage collaborative decision model. After determining the fitness of the hybrid codes according to a preset fitness function, the genetic simulated annealing algorithm is used to perform corresponding genetic evolution iterations and simulated annealing search iterations based on the multiple hybrid codes and their corresponding fitness values ​​until a preset number of iterations are completed. A target hybrid code is selected from the generated candidate hybrid codes. The resource configuration result includes all configuration schemes corresponding to the target hybrid code and the transportation and storage decision information corresponding to each configuration scheme. The fitness is used to determine the optimal configuration cost of the production, transportation, and storage three-stage system corresponding to the corresponding code element.

[0009] Secondly, embodiments of this application provide a service platform, including a memory and a processor, characterized in that the memory stores a computer program, and the processor is configured to run the computer program to perform the steps of the resource allocation method for distributed manufacturing with multiple production tasks described in the first aspect.

[0010] Thirdly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the resource allocation method for distributed manufacturing with multiple production tasks as described in the first aspect above.

[0011] Compared to related technologies, the resource allocation method, service platform, and medium for distributed manufacturing with multiple production tasks provided in this application embodiment determine the task completion degree of each manufacturing task associated with a manufacturing unit when an interruption command is received during the production-operation-storage collaborative operation based on the generated manufacturing configuration information. The manufacturing configuration information includes at least the manufacturing task corresponding to the manufacturing unit, and is generated based on received historical production order information and pre-configured resource information, using a genetic simulated annealing algorithm for production-operation-storage collaborative planning and configuration. Based on the task completion degree, the current manufacturing task is determined from all manufacturing tasks corresponding to the manufacturing configuration information, and candidate manufacturing units associated with each current manufacturing task are determined. The current manufacturing task represents the manufacturing task requiring reconfiguration, and each candidate manufacturing unit is associated with at least one manufacturing device. Multiple hybrid encoding bodies are generated based on the current manufacturing task, the corresponding task completion degree, and the corresponding manufacturing device. Each hybrid encoding body includes multiple code elements, each code element representing a configuration scheme for configuring the corresponding manufacturing device for a current manufacturing task. The code is also associated with transportation and warehousing decision information determined according to a preset production-transportation-storage collaborative decision-making model. After determining the fitness corresponding to the hybrid code body according to a preset fitness function, based on multiple hybrid codes body and their corresponding fitness, the genetic simulated annealing algorithm is used to perform corresponding genetic evolution operation iterations and simulated annealing search iterations until a preset number of iterations are completed. A target hybrid code body is selected from the multiple candidate hybrid code bodies generated. The resource configuration result includes all configuration schemes corresponding to the target hybrid code body and the transportation and warehousing decision information corresponding to each configuration scheme. The fitness is used to determine the optimal configuration cost of the production-transportation-storage three-stage system corresponding to the corresponding code body. It takes into account uncertainties such as equipment production interruption, defect rate, and fluctuations in unit personnel cost caused by staff absence. It configures the resource configuration model with uncertain resources based on a hybrid improved genetic algorithm to achieve reasonable allocation of available equipment resources. It makes adjustments to the existing resource configuration scheme to adapt to dynamic disturbances under uncertain environments, completes customer requirements within the delivery period, and solves the problems of low availability, applicability, reliability, and robustness of resource configuration schemes for distributed manufacturing with multiple production tasks in related technologies. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1This is a hardware structure block diagram of the terminal of the resource allocation method for distributed manufacturing with multiple production tasks according to an embodiment of this application; Figure 2 This is a flowchart of a resource allocation method for distributed manufacturing with multiple production tasks, according to an embodiment of this application. Figure 3 This is a schematic diagram illustrating a partial matching and cross operation in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the uniform mutation operation performed in an embodiment of this application; Figure 5 This is a schematic diagram illustrating sequential crossover operations in an embodiment of this application. Figure 6 This is a structural block diagram of a resource allocation device for distributed manufacturing with multiple production tasks, according to an embodiment of this application. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application. Furthermore, it is understood that although the efforts made in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, modifications to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0014] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0015] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "a," "an," "an," "the," and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms "comprising," "including," "having," and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. "Multiple stages" used in this application refers to two or more stages. "And / or" describes the relationship between related objects, indicating that three relationships may exist; for example, "A and / or B" can represent: A alone, A and B simultaneously, and B alone. The terms "first," "second," "third," etc., used in this application are merely to distinguish similar objects and do not represent a specific ordering of objects.

[0016] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. Taking running on a terminal as an example, Figure 1 This is a hardware structure block diagram of the terminal for a resource allocation method for distributed manufacturing with multiple production tasks, according to an embodiment of this application. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0017] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the resource allocation method for distributed manufacturing with multiple production tasks in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0018] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0019] This embodiment provides a resource allocation method for distributed manufacturing with multiple production tasks, running on the aforementioned terminal. Figure 2 This is a flowchart of a resource allocation method for distributed manufacturing with multiple production tasks according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0020] Step S201: During the production-operation-storage collaborative operation based on the generated manufacturing configuration information, determine the task completion degree of the manufacturing task associated with each manufacturing unit when the interruption command is received. The manufacturing configuration information includes at least the manufacturing task corresponding to the manufacturing unit. The manufacturing configuration information is generated by using the genetic simulated annealing algorithm to perform production-operation-storage collaborative planning and configuration based on the received historical production order information and pre-configured resource information.

[0021] In this embodiment, the executing entity of this application embodiment includes, but is not limited to, a control system that manages the three stages of production, transportation and warehousing of a distributed manufacturing system, and performs resource allocation for coordinated optimization of production, transportation and warehousing.

[0022] In this embodiment, the resource allocation method is based on distributed manufacturing resource optimization under uncertain environments. These uncertain environments include uncertainties in the following dimensions: first, equipment dimensions, including equipment failure, performance degradation, and facility depreciation; second, personnel dimensions, including employee leave, skill gaps and attrition, improper operation, unreasonable equipment usage frequency, and insufficient personnel; and third, material dimensions, including market supply and demand fluctuations and delayed delivery by suppliers. To address production fluctuations caused by these uncertainties, a resource allocation scheme that considers uncertainty needs to be constructed, i.e., the resource allocation method of this embodiment is implemented to improve the availability, applicability, and reliability of the resource allocation strategy in executing complex tasks as expected (corresponding to the generated manufacturing configuration information). Robustness; In this embodiment, when uncertainties exist and cause resource status uncertainty, the current manufacturing task may be interrupted. For example, if a manufacturing device (corresponding to a resource) experiences a production interruption, it is necessary to re-plan the manufacturing configuration for manufacturing tasks that have not yet been produced or completed. That is, the manufacturing configuration will be re-planned based on the currently executed and generated manufacturing configuration information. In this embodiment, the re-planning of manufacturing configuration for manufacturing tasks that have not yet been produced or completed takes into account the task completion degree of the corresponding manufacturing task, and classifies the current manufacturing task into: completed manufacturing task, unexecuted manufacturing task, and incomplete manufacturing task according to the task completion degree. It should be noted that completed manufacturing tasks are not included in the re-planning of manufacturing configuration.

[0023] Step S202: Based on the task completion rate, determine the current manufacturing task from all manufacturing tasks corresponding to the manufacturing configuration information, and determine the alternative manufacturing unit associated with each current manufacturing task. The current manufacturing task is used to represent the manufacturing task that needs to be reconfigured, and the alternative manufacturing unit is associated with at least one manufacturing device.

[0024] In this embodiment, based on the corresponding task completion level, the current manufacturing tasks that require manufacturing configuration replanning are determined. These current manufacturing tasks include unexecuted manufacturing tasks and incomplete manufacturing tasks. During the manufacturing configuration replanning process, the reconfigured manufacturing resources differ for current manufacturing tasks with different completion levels. For incomplete manufacturing tasks, only the corresponding manufacturing equipment can be replaced. That is, manufacturing equipment that meets the production requirements of the incomplete manufacturing task is configured among the manufacturing equipment currently available in the manufacturing unit. For example, previously, a manufacturing task with a completion level of 0.2 was manufactured on manufacturing equipment 2 in manufacturing unit 1, but the manufacturing equipment... If a production interruption occurs corresponding to Backup 2, then for the current manufacturing task, it can only be selected from other manufacturing equipment associated with manufacturing unit 1 (e.g., manufacturing equipment 3, 4, 5). Thus, for an incomplete manufacturing task, the candidate manufacturing unit is constrained to be the manufacturing unit already configured in the manufacturing configuration information of the already produced unit, and it is constrained to be selected from the manufacturing equipment associated with that manufacturing unit during subsequent optimization configuration. For a manufacturing task that has not been executed, the manufacturing unit that has not executed the corresponding manufacturing task can be used as the corresponding candidate manufacturing unit, and one of the candidate manufacturing units can be selected as the order unit that has not executed the manufacturing task. The configured manufacturing equipment can be any manufacturing equipment associated with that manufacturing unit.

[0025] Understandably, for manufacturing tasks that have not been performed, a new manufacturing unit can be configured, which means replacing the manufacturing unit and simultaneously replacing the manufacturing equipment. For manufacturing tasks that have not been completed, the replacement of the manufacturing unit is not allowed, and the replacement manufacturing equipment must be the same as the original manufacturing unit. However, the replacement of the manufacturing equipment is allowed. When selecting the replacement manufacturing equipment, priority is given to the idle manufacturing equipment in the current manufacturing unit. If there is no idle manufacturing equipment, it is allowed to take over the unfinished manufacturing task after other manufacturing equipment has completed the corresponding manufacturing task. Alternatively, the currently configured manufacturing equipment can be repaired. The goal is to achieve rapid production and timely delivery, thereby minimizing production costs and maximizing the total benefits of the three stages of production, transportation, and warehousing.

[0026] Step S203: Based on the current manufacturing task, the corresponding task completion degree and the corresponding manufacturing equipment, perform hybrid coding to generate multiple hybrid coding bodies. The hybrid coding body includes multiple code sub-codes. The code sub-codes are used to represent the configuration scheme of the corresponding manufacturing equipment for a current manufacturing task. Each code sub-code is also associated with a transportation and warehousing decision information determined according to a preset production, transportation and storage collaborative decision model.

[0027] In this embodiment, the current manufacturing task, task completion degree, and configured manufacturing equipment are encoded into a single code. This code includes a task code, a task completion degree code, and a device code. The device code of the manufacturing equipment is variable. This embodiment configures the corresponding manufacturing equipment for the current manufacturing task, using the device code as a genetic value to perform multiple configuration planning decisions. This aims to generate the optimal decision scheme that adapts to all current manufacturing tasks and minimizes the total cost. In this embodiment, a task completion degree code is set to determine the type of current manufacturing task corresponding to the task code. Based on this type, the range of device codes for the manufacturing equipment configured for the current manufacturing task is constrained. For example, when encoding the device corresponding to an incomplete manufacturing task, the corresponding manufacturing equipment needs to be selected from the manufacturing equipment associated with the original manufacturing unit (as the corresponding alternative manufacturing unit). Priority is given to selecting idle manufacturing equipment from other manufacturing equipment besides those currently interrupted. If no idle manufacturing equipment is available, the manufacturing equipment that can start production first can be selected, including manufacturing equipment that became idle after completing other manufacturing tasks earliest and manufacturing equipment that has recovered from an interrupted state to a usable state.

[0028] It is important to understand that production and transportation are independent processes. Resource allocation is based solely on production costs. Although initial resource allocation is based on production costs, all products produced by branch plants ultimately need to be transported to the central warehouse. Therefore, transportation costs are still considered when calculating total costs. Furthermore, the transportation distance from each branch plant (manufacturing unit) to the central warehouse is used as the basis for calculating transportation costs when solving for the total cost across the three stages. In this embodiment, whether it is the initial coding or the subsequent solution process, each change in coding or equipment coding represents a configuration decision process. After the decision is completed, the transportation and warehousing decision information corresponding to a coding is determined. That is, after all codings are coded in a single decision, the location, timing (the specific time is obtained by dividing the task volume by the production efficiency of the manufacturing equipment), storage time in the manufacturing unit, transportation start time, arrival time in the central warehouse, storage time in the central warehouse, delivery start time, and delivery completion time of all corresponding manufacturing tasks are determined. In other words, the transportation and warehousing decision information corresponding to all codings is determined. These associated configurations are resource allocations that have already been completed in the planning stage.

[0029] It should be noted that by integrating multiple uncertainties in the production system, the probability of equipment failure and production changeover during the manufacturing equipment planning stage is fully considered. Maintenance costs are incorporated into the planned cost accounting system, and by reserving maintenance time, plan delays and cost spikes caused by equipment downtime are avoided. Regarding material planning, resource allocation plans are developed not only based on standard usage but also with an additional safety stock buffer matching the expected losses from non-conforming products. This ensures that material supply is closely synchronized with the production plan, effectively reducing material waste costs and the risk of plan interruptions caused by non-conforming products. In terms of human resource planning, factors such as differences in personnel skills and unexpected leave are transformed into dynamic variables of unit labor costs.

[0030] Step S204: After determining the fitness of the hybrid code body according to the preset fitness function, based on multiple hybrid code bodies and their corresponding fitness, the genetic simulated annealing algorithm is used to perform corresponding genetic evolution operation iterations and simulated annealing search iterations until the preset number of iterations is reached. The target hybrid code body is selected from the multiple candidate hybrid code bodies generated. The resource allocation result includes all configuration schemes corresponding to the target hybrid code body and the transportation and storage decision information corresponding to each configuration scheme. The fitness is used to determine the optimal configuration cost of the production, transportation and storage three stages corresponding to the corresponding code body.

[0031] In this embodiment, after initial encoding and population initialization, the fitness of each hybrid code is determined based on the fitness function constructed by associating multi-dimensional costs, and the total cost obtained by adding the multi-dimensional costs is used as the fitness value. The smaller the fitness value, the better the corresponding resource allocation scheme.

[0032] In this embodiment, in determining the corresponding hybrid coding body, selection, crossover, and mutation operations corresponding to the genetic evolution operation are performed based on fitness and the hybrid coding body. Simulated annealing search iteration is performed on the new hybrid coding body after completing one genetic evolution operation to generate the current optimized hybrid coding body. After optimizing for a preset number of times, the target hybrid coding body is selected from the multiple candidate hybrid coding bodies generated.

[0033] Through steps S201 to S204 above, during the production-operation-storage collaborative operation based on the generated manufacturing configuration information, the task completion degree of the manufacturing task associated with each manufacturing unit is determined when an interrupt command is received; based on the task completion degree, the current manufacturing task is determined from all manufacturing tasks corresponding to the manufacturing configuration information, and a candidate manufacturing unit associated with each current manufacturing task is determined, with each candidate manufacturing unit associated with at least one manufacturing device; based on the current manufacturing task, the corresponding task completion degree, and the corresponding manufacturing device, hybrid coding is performed to generate multiple hybrid coding bodies, each hybrid coding body including multiple code elements, each code element representing a configuration scheme for configuring the corresponding manufacturing device for a current manufacturing task; after determining the fitness corresponding to the hybrid coding body according to a preset fitness function, based on the multiple hybrid coding bodies and their corresponding fitness values... This paper utilizes a genetic simulated annealing algorithm to perform corresponding genetic evolution operations and simulated annealing search iterations until a preset number of iterations are reached. A target hybrid code is selected from multiple candidate hybrid code bodies generated. The resource allocation results include all configuration schemes corresponding to the target hybrid code body and transportation and warehousing decision information for each configuration scheme. It considers uncertainties such as equipment production interruptions, defect rates, and fluctuations in unit personnel costs caused by staff absences. By configuring the resource allocation model with uncertain resources based on a hybrid improved genetic algorithm, it achieves reasonable allocation of available equipment resources. It adjusts existing resource allocation schemes to adapt to dynamic disturbances under uncertain environments, fulfilling customer requirements within the delivery period. This solves the problems of low availability, applicability, reliability, and robustness of resource allocation schemes for distributed manufacturing with multiple production tasks in related technologies.

[0034] In some embodiments, the current manufacturing task is determined from all manufacturing tasks corresponding to the manufacturing configuration information based on the task completion rate, which is achieved through the following steps:

[0035] Step 21: Based on the task completion rate, delete the completed manufacturing tasks from all manufacturing tasks corresponding to the manufacturing configuration information to obtain the first manufacturing task set. The manufacturing tasks in the first manufacturing task set include unexecuted manufacturing tasks and incomplete manufacturing tasks.

[0036] In this embodiment, completed manufacturing tasks are not included in the replanning of manufacturing configuration. Therefore, before determining the manufacturing tasks that need to be configured, completed manufacturing tasks need to be excluded to obtain alternative tasks for the current manufacturing task. In this embodiment, the task completion rate is calculated based on the ratio of the number of completed products to the number of products required for a manufacturing task.

[0037] Step 22: Select unexecuted manufacturing tasks from the first manufacturing task set to obtain the first manufacturing task.

[0038] Step 23: Determine the remaining task level corresponding to all unfinished manufacturing tasks in the first manufacturing task set, and take the task quantity corresponding to the remaining task level as the new task quantity of the corresponding unfinished manufacturing task to obtain the corresponding second manufacturing task.

[0039] In this embodiment, for unfinished manufacturing tasks, some of them have already been manufactured. Therefore, when reconfiguring, it is only necessary to configure the corresponding resource configuration for the unfinished parts of the products. The task quantity corresponding to the remaining task quantity is used as the task quantity of the current manufacturing task to match the configuration of the corresponding manufacturing equipment.

[0040] Step 24: Combine all first manufacturing tasks and all second manufacturing tasks into the current manufacturing task.

[0041] Through steps 21 to 24 above, the corresponding current manufacturing tasks are selected and classified, and the corresponding candidate manufacturing units are matched according to the classification of the current manufacturing tasks, thereby determining the manufacturing equipment that can be configured for the current manufacturing tasks.

[0042] In some embodiments, determining the alternative manufacturing unit associated with each current manufacturing task includes the following steps:

[0043] Step 31: Determine the manufacturing cells and manufacturing equipment associated with the unfinished manufacturing tasks corresponding to the second manufacturing task, and obtain the limited selection of manufacturing cells and limited selection of manufacturing equipment.

[0044] Step 32: After designating the limited manufacturing unit as the candidate manufacturing unit associated with the corresponding second manufacturing task, select manufacturing equipment other than the limited manufacturing equipment from all manufacturing equipment associated with the limited manufacturing unit to obtain the candidate manufacturing equipment.

[0045] Step 33: Select the alternative manufacturing equipment as the manufacturing equipment associated with the alternative manufacturing unit associated with the second manufacturing task.

[0046] In this embodiment, after determining the current manufacturing task of the classification, for the second manufacturing task corresponding to the incomplete manufacturing task, the corresponding alternative manufacturing unit is determined and unique, that is, the manufacturing unit corresponding to the incomplete task in the generated manufacturing configuration information, which is the corresponding limited manufacturing unit. At the same time, the manufacturing equipment that can be configured for the second manufacturing task in the future is the manufacturing equipment associated with the corresponding manufacturing unit, which is the limited manufacturing equipment. The limited manufacturing equipment is preferentially selected from all the manufacturing equipment associated with the limited manufacturing unit except for the manufacturing equipment currently corresponding to the second manufacturing task. When there is no free manufacturing equipment, the manufacturing equipment that first completed other manufacturing tasks can be preferentially selected, that is, the manufacturing equipment that first became free. At the same time, if the manufacturing equipment currently corresponding to the second manufacturing task recovers to the manufacturing state earlier than other manufacturing equipment that first became free, then the corresponding manufacturing equipment can be used as the corresponding limited manufacturing equipment.

[0047] Understandably, when allocating corresponding manufacturing equipment to unfinished manufacturing tasks, the constraints include that the manufacturing unit cannot be changed for the unfinished task, and the replacement manufacturing equipment must not interrupt the production of other manufacturing tasks. In other words, it can be an idle manufacturing equipment within the corresponding manufacturing unit, a manufacturing equipment waiting to become idle, or a manufacturing equipment that is currently restored to a production-ready state, and must be restored earlier than an idle manufacturing equipment. Specifically, the goal is to reduce the storage time within the manufacturing unit. By configuring the manufacturing equipment that can complete the manufacturing task earliest, the corresponding storage costs can be reduced.

[0048] In some embodiments, determining the alternative manufacturing unit associated with each current manufacturing task includes the following steps:

[0049] Step 41: Obtain all manufacturing units corresponding to the manufacturing configuration information, select all manufacturing units except for the limited selection manufacturing units, and obtain candidate manufacturing units. The candidate manufacturing units include one of the manufacturing units associated with completed manufacturing tasks and one of the manufacturing units associated with unexecuted manufacturing tasks.

[0050] Step 42: The candidate manufacturing unit is designated as the alternative manufacturing unit associated with the corresponding first manufacturing task, and the manufacturing equipment associated with the candidate manufacturing unit is designated as the manufacturing equipment associated with the alternative manufacturing unit associated with the first manufacturing task.

[0051] In this embodiment, after determining the current manufacturing task of the classification, for the first manufacturing task corresponding to the unexecuted manufacturing task, the corresponding alternative manufacturing unit is a manufacturing unit that cannot interrupt the production of other manufacturing tasks. That is, any manufacturing unit other than the limited selection manufacturing unit among all manufacturing units corresponding to the generated manufacturing configuration information. It should be understood that for the manufacturing unit corresponding to the completed manufacturing task, because the corresponding manufacturing task has been completed, the corresponding manufacturing equipment will be idle. When the manufacturing equipment can complete the production of at least one product corresponding to the unexecuted manufacturing task, the manufacturing unit can be configured to the alternative manufacturing unit associated with the corresponding first manufacturing task. It should be noted that for the manufacturing unit corresponding to the completed manufacturing task, when only the corresponding manufacturing equipment is idle, the alternative manufacturing unit associated with the first manufacturing task uses the idle manufacturing equipment as the corresponding alternative manufacturing equipment. During configuration, the alternative manufacturing equipment is selected, and other manufacturing equipment of other executing manufacturing tasks is not used as alternative manufacturing equipment.

[0052] Through steps 41 to 42 above, the candidate manufacturing unit and the corresponding manufacturing equipment corresponding to the first manufacturing task are determined.

[0053] In some embodiments, multiple hybrid coded bodies are generated by hybrid coding based on the current manufacturing task, the corresponding task completion rate, and the corresponding manufacturing equipment, through the following steps:

[0054] Step 51: Based on the task completion rate corresponding to the current manufacturing task, determine the intended manufacturing equipment corresponding to the current manufacturing task. The intended manufacturing equipment includes one of the alternative manufacturing equipment and the manufacturing equipment associated with the candidate manufacturing unit.

[0055] In this embodiment, the corresponding manufacturing task is classified according to the task completion degree, and a first manufacturing task and a second manufacturing task are classified. Then, the intended manufacturing equipment is selected from the manufacturing equipment associated with the candidate manufacturing units corresponding to the first manufacturing task and the second manufacturing task, respectively.

[0056] Step 52: Encode the current manufacturing task, the intended manufacturing equipment corresponding to the current manufacturing task, and the corresponding task completion degree into a code sub-code, and combine multiple code sub-codes corresponding to the current manufacturing task into an initial code body. The code sub-code includes a task code, a task degree code, and an equipment code arranged in order from top to bottom. The task degree code is used to constrain the manufacturing equipment configured for the corresponding current manufacturing task.

[0057] In this embodiment, when the resource status is uncertain, the current production task may be interrupted. If a manufacturing device experiences a production interruption, resources need to be reconfigured for tasks that have not yet been produced. This embodiment adds task completion status to the deterministic encoding method, including completed tasks, incomplete tasks, and partially completed tasks. In this embodiment, for simplicity, a real number encoding form is used. Assuming there are 6 production tasks and each manufacturing unit has a certain number of manufacturing devices, the corresponding encoding for the resource allocation scheme at a certain moment is shown in Table 1 below. Table 1 Task completion rate 1 0 0.2 1 0 1 Device Code 1 4 5 3 2 1 Table 1 shows that Task 1 is configured with Equipment 1 for production, and the task is 50% complete. Task 2 is configured with Equipment 4 for production, and the task has not yet started production. Task 3 is configured with Equipment 5 for production, and the current task completion rate is 20%, and so on. It should be noted that when making new resource configurations, tasks with a completion rate of 1 are not considered current manufacturing tasks. That is, the relevant codes for tasks with a completion rate of 1 are invalid by default and do not participate in the corresponding algorithm calculations. However, the corresponding manufacturing equipment can participate in the equipment allocation for manufacturing tasks that have not yet started production. In other words, the corresponding manufacturing equipment can participate in the manufacturing of manufacturing tasks that have not yet started production.

[0058] In this embodiment, for a task code, its corresponding task completion code is determined and constant, while the device code configured for it is randomly assigned, that is, randomly assigned from the allowed configuration device codes. For example, for the second manufacturing task, the corresponding task code is 1, the task completion degree is 0.5, and the manufacturing equipment associated with its original manufacturing unit 1 includes: manufacturing equipment 1, manufacturing equipment 2, manufacturing equipment 3, and manufacturing equipment 4. The originally configured manufacturing equipment is manufacturing equipment 2. Therefore, the device code corresponding to the current code's code can be manufacturing equipment 1, manufacturing equipment 3, or manufacturing equipment 4, and the corresponding code is... .

[0059] Step 53: Based on the initial coding body, perform population initialization to generate multiple hybrid coding bodies. During the population initialization process, select the corresponding intended manufacturing equipment from all intended manufacturing equipment corresponding to each current manufacturing task and generate the corresponding equipment code.

[0060] Through steps 51 to 53 above, hybrid coding based on task completion is achieved.

[0061] In some embodiments, the genetic simulated annealing algorithm is used to perform corresponding genetic evolution operations and simulated annealing search iterations, which is achieved through the following steps:

[0062] Step 61: After determining the multiple current coding bodies that participate in the current genetic evolution operation and simulated annealing search iteration, calculate the fitness of the current coding body according to the fitness function. The current hybrid coding body includes one of the following: hybrid coding body, historical coding body that has completed the previous genetic evolution operation and simulated annealing search iteration.

[0063] In this embodiment, after generating the corresponding hybrid coding body and determining the current coding body participating in the current solution, the transportation and warehousing decision information planned in the initial planning stage will be determined. During the initial planning process, the following mathematical model parameters will be set: 1. At the initial moment, all products and resources (at least including manufacturing equipment) are in a state of waiting to be matched, and sub-tasks (corresponding to manufacturing tasks) cannot be split during transportation; 2. Processed workpieces must immediately enter the storage area, and the storage area has unlimited capacity, without considering storage limitations; 3. Delivery vehicles do not consider mileage constraints, only need to meet the maximum vehicle capacity limit, and the running speed is constant; 4. Goods contained in any sub-task must be transported in the same batch and all of them must be transported.

[0064] In this embodiment, by constructing a mathematical model that incorporates uncertainties in dimensions such as equipment, materials, and manpower when formulating production plans, various risk factors are transformed into quantifiable cost indicators. A mathematical model with the goal of minimizing costs is established, providing a scientific decision-making basis for the full-cycle planning management of the production system. Based on the deterministic resource allocation model, considering the additional costs required to hinder the execution of the original planned resource scheme due to uncertainties in equipment, materials, and personnel, the corresponding fitness function mathematical model is determined as: minC unce =C zc +C uma +C ume +C upe C zc =minC prod +minC tra +C s ; ; ; ; ; ; The corresponding constraints are as follows: ; Among them, C zc Determine the total cost under the environment for resources; C prod For production costs; C tra For path cost; C sC1 is warehousing cost; C2 is raw material cost; C3 is facility depreciation cost; C4 is labor cost; C5 is energy consumption cost. minC tra =C dis ; ; ; The corresponding constraints are: ; Among them, C dis C represents the path cost; it also represents the path cost from the manufacturing unit to the central warehouse and the path cost from the central warehouse to customer delivery. s Indicates inventory cost; d j c is the transportation distance from manufacturing unit j to the main warehouse. t The unit transportation cost from the manufacturing unit to the central warehouse; The unit transportation cost from the central warehouse to the customer; d i This refers to the transportation distance from the central warehouse to customer i. The earliest start time for vehicle c of manufacturing unit j to begin transportation; For manufacturing tasks The completion time, which is also the warehousing time; For the vth manufacturing task of order i Customer demand (product quantity), c s For the unit storage cost of each manufacturing unit, c zs The unit inventory cost of the central warehouse; T i The latest time that customer i's manufacturing task will arrive at the central warehouse; Manufacturing tasks for customer i The time it takes for the products to arrive at the central warehouse; This represents a unique constraint on a manufacturing cell, a manufacturing task. Only one manufacturing unit can be selected; Indicates manufacturing task The processing time expression, Let k be the unit capacity of the manufacturing equipment. For the vth manufacturing task of order i Customer demand (product quantity); This indicates a supply and demand balance constraint, where production volume equals task demand, ensuring that all tasks are processed; Q represents the maximum capacity constraint for vehicles. c The maximum load capacity of vehicle c; This indicates that the departure time of vehicle c in the manufacturing unit is the latest production time for this batch of manufacturing tasks. Indicates manufacturing task The completion time, The start time (departure time) of transportation for vehicle c in manufacturing unit j. An expression representing the start time of shipment for customer i; Indicates manufacturing task The time expression for the arrival time from the manufacturing unit to the main warehouse. Let C be the arrival time of vehicle C in manufacturing unit j; To represent the manufacturing task of customer i Arrival time at the main warehouse; The expression representing the shipping time from the central warehouse to the customer, t i d represents the time required for a delivery vehicle to travel from the central warehouse to customer i. i The distance from the customer to the central warehouse; This indicates a delivery time constraint, meaning the total time cannot exceed the customer's delivery date; ; ; ; In this embodiment, the following decision variables are set. , x jc , y r ; Indicates manufacturing task Is there a manufacturing unit j to be configured? Indicates manufacturing task Is it configured by the kth manufacturing equipment in manufacturing unit j? jc Indicates whether vehicle c of manufacturing unit j participates in transportation; Indicates whether vehicle c in manufacturing unit j is responsible for the manufacturing task. ;y r Indicates whether vehicle r in the main warehouse is in use; Among them, C uma The additional costs incurred due to various obstacles to the execution of the original planned resource scheme (corresponding to the generated manufacturing configuration information) caused by equipment status uncertainty include equipment failure repair costs, additional equipment depreciation costs caused by non-conforming products, and additional energy consumption costs caused by non-conforming products; C ume C is the additional material cost incurred due to the number of defective finished products. upe This includes the cost of production efficiency fluctuations caused by employee skill proficiency and the additional temporary labor costs incurred due to employee absences; this cost is reflected in the cost change per unit quantity. M is the set of manufacturing cells, M = {m1, m2, m...} j ,…,m J}; D is the customer set, D={1,2,…,i,…i}, where i represents the i-th customer; the set of manufacturing tasks for customer i is , Let v be the v-th manufacturing task for customer i, and let v be the v-th production requirement for customer i; Manufacturing task The candidate resource set for manufacturing unit j is K is the v-th manufacturing task. In manufacturing unit j, the total number of candidate resources is N, the total number of customers is c, the vehicle identifier of each manufacturing unit is u, the total number of transport vehicles in each manufacturing unit is r, and the total number of warehouse vehicles is r. For manufacturing tasks The unit cost of raw materials; For manufacturing tasks Demand; This represents the unit depreciation cost for a single resource k (corresponding to manufacturing equipment k); The unit labor cost for manufacturing unit j; The average power of this manufacturing resource (corresponding to manufacturing equipment); The unit energy cost of manufacturing unit j; This refers to the unit capacity of the resource. For manufacturing tasks Demand; For subtasks The candidate resource set in manufacturing unit j; Indicates task Arrival time at the main factory; Indicates manufacturing task Demand; This represents the unit raw material cost of the manufacturing task in manufacturing unit j; n represents the repair cost per unit time. jk Number of equipment downtimes. Let K be the defect rate of resource k (corresponding to the kth manufacturing equipment) in manufacturing unit j. The power of this resource (the corresponding manufacturing equipment). For unit raw material cost, △ C This is due to the increased unit labor cost caused by personnel fluctuations; Represents the earliest shipping time for customer i; J represents the total number of manufacturing units; j represents the j-th manufacturing unit; D i Delivery time for customer i; Q c Q represents the maximum capacity of the vehicle. i The total demand of customer i; t i The time required to reach customer i (from the central warehouse to the customer).

[0065] It is important to understand that the equipment experiences occasional downtime for most of its operating time, and the downtime intervals approximately follow an exponential distribution: , Let be the probability that the equipment will stop at time t. Let be the downtime probability of resource k (corresponding to the k-th manufacturing equipment) in manufacturing unit j. The reliability function based on the exponential distribution represents the probability that a device can operate continuously for a time t without downtime. ,when When approaching infinity, the Taylor function of the exponential function... Downtime probability As n approaches infinity, the time segment approaches infinitesimal. Within a single time segment, there are only two outcomes: machine stoppage and no stoppage. The number of stoppages follows a binomial distribution. The number of equipment stoppages is caused by equipment failure and production changeover. The probability of production interruption can be obtained from historical production data. Therefore, the number of production stoppages for equipment k (corresponding to the k-th manufacturing equipment) in manufacturing unit j is... It can be represented as: , Let T be the downtime probability of the k-th manufacturing equipment in manufacturing unit j. jk Let $\frac{k}{k}$ be the running time of the k-th manufacturing equipment. The corresponding constraints are: , Let t be the state of the k-th manufacturing equipment in manufacturing unit j, when =1 indicates that the kth manufacturing equipment is shut down.

[0066] Step 62: Select a preset number of candidate codecs from multiple current codecs based on the corresponding fitness and preset selection operations. The selection operations include individual selection based on tournament selection and elite retention strategies.

[0067] Step 63: For multiple candidate codes, perform crossover and mutation operations corresponding to the genetic simulated annealing algorithm in sequence to generate the first code corresponding to the current genetic evolution iteration. In the crossover and mutation operations, select the intended manufacturing equipment configured for crossover and mutation from all intended manufacturing equipment corresponding to the current manufacturing task corresponding to each code. The crossover operation includes partial matching crossover, and the mutation operation includes uniform mutation.

[0068] In some of these alternative implementations, refer to Figure 3 For multiple candidate codebases, a partially matched crossover (PMX) operation is performed, which involves randomly selecting a crossover point between the candidate codebases of two parent codebases (see reference). Figure 3The vertical lines in the diagram are used to swap the device codes after the intersection (corresponding to the device codes of the three tasks to the right of the vertical lines).

[0069] In some of these alternative implementations, refer to Figure 4 A uniform mutation operation is performed on the new hybrid coding variant that has completed cross-matching. Also, randomly selected devices within the new hybrid coding variant are encoded (corresponding to partial gene values, see reference). Figure 4 The dashed box in the image is randomly perturbed, resulting in a new hybrid coding body. (Refer to...) Figure 4 The hybrid encoding corresponding to the offspring in the middle.

[0070] Step 64: Perform simulated annealing local search corresponding to the genetic simulated annealing algorithm on multiple first coding bodies to locally optimize the first coding bodies and generate second coding bodies corresponding to the current simulated annealing search iteration. Based on the fitness of the second coding bodies and the second coding bodies, and according to the preset acceptance criteria, perform unacceptance and unupdate processing on the second coding bodies to generate candidate hybrid coding bodies corresponding to one genetic evolution operation iteration and simulated annealing search iteration.

[0071] In this embodiment, each first encoded body is treated as the original individual, and the following steps are performed:

[0072] Step 1: Generate neighborhood solutions: Randomly fine-tune the resource configuration scheme of manufacturing equipment corresponding to 1-2 manufacturing tasks in the first coding body, that is, fine-tune the equipment codes in 1-2 coding sub-codes of the first coding body to generate corresponding new individuals.

[0073] Step 2: Calculate the fitness difference ΔE between the original individual and the new individual, and determine whether it is less than 0. If ΔE < 0, accept the new individual directly; if ΔE > 0, accept it with a probability P = exp(−ΔE / T), that is, generate a 0-1 random number. If the result is less than P, accept the new solution so that the probability of existence can escape the local optimum.

[0074] Step 3, Cooling: Cool down according to the formula: T(k+1)=αT(k) (α is the cooling rate) until T is lower than the termination temperature, gradually reducing the probability of accepting a poor solution.

[0075] Step 4: Check if the temperature has dropped to the termination temperature or reached the upper limit of the number of iterations. If not, return to the step of generating neighborhood solutions and continue. If so, end the local search and output the current approximate optimal solution, which is to obtain the candidate hybrid coding body corresponding to the first coding body.

[0076] In some alternative implementations, after generating the corresponding candidate hybrid code, the following steps are also performed:

[0077] Step 1: Determine the fitness of each candidate hybrid codec, and based on the fitness, select candidate hybrid codecs with a fitness less than a first set value from all candidate hybrid codecs to obtain elite hybrid codecs;

[0078] Step 2: Select the intended hybrid codecs with a fitness greater than the second set value from all candidate hybrid codecs to obtain a preset number of hybrid codecs to be replaced;

[0079] Step 3: Select a preset number of elite hybrid codes from the elite hybrid codes and replace all the hybrid codes to be replaced with the corresponding elite hybrid codes to obtain candidate hybrid codes generated based on the elite retention strategy.

[0080] In some embodiments, selecting a target hybrid codebase from a plurality of generated candidate hybrid codebases includes the following steps:

[0081] Step 71: Obtain candidate hybrid code bodies that have completed a preset number of iterations, and determine the fitness of each candidate hybrid code body.

[0082] Step 72: Select the candidate hybrid code with the lowest fitness from the candidate hybrid code that has completed a preset number of iterations, in order of increasing fitness, to obtain the target hybrid code.

[0083] In some embodiments, generating manufacturing configuration information includes the following steps:

[0084] Step 81: Obtain multiple historical order information, determine multiple historical manufacturing tasks based on the historical order information, determine the manufacturing equipment corresponding to each preset manufacturing unit based on the pre-configured resource information, encode the historical manufacturing tasks and corresponding manufacturing equipment and initialize the population, and generate a historical mixed coding population including multiple historical mixed coding bodies.

[0085] Step 82: Based on the corresponding fitness and preset selection operation, select a preset number of historical hybrid coding bodies from the historical hybrid coding body population, and perform crossover and mutation operations corresponding to the genetic simulated annealing algorithm on the selected historical hybrid coding bodies in sequence to generate the first hybrid coding body corresponding to the current genetic evolution iteration. The selection operation includes individual selection based on tournament selection and elite retention strategies, the crossover operation includes sequential crossover, and the mutation operation includes random mutation.

[0086] In this embodiment, the total operating cost C is calculated. zc As the corresponding fitness, C zc The calculation can be referred to the description of the relevant mathematical model above.

[0087] In some of these alternative implementations, refer to Figure 5 For multiple historical mixed coding bodies, a sequential crossover operation is performed. This involves randomly selecting the start and end positions from two parent historical mixed coding bodies, and starting from the crossover point, performing a device coding sequence for one parent individual (see reference). Figure 5 The corresponding dashed box in the middle is exchanged with the device encoding sequence of another parent individual, but the device encoding sequence before and after the crossover point remains unchanged; in this embodiment, a random mutation operation is used on the new encoding body that has completed the crossover matching.

[0088] Step 83: Perform simulated annealing local search corresponding to the genetic simulated annealing algorithm on multiple first hybrid coding bodies to locally optimize the first hybrid coding bodies and generate a second hybrid coding body corresponding to the current simulated annealing search iteration;

[0089] Step 84: Based on the fitness of the second hybrid code and the second hybrid code, the second hybrid code is de-accepted and de-updated according to the preset acceptance criteria to generate the intention hybrid code corresponding to one genetic evolution operation iteration and simulated annealing search iteration. After a preset number of iterations, the manufacturing configuration information is generated based on the decoded intention hybrid code.

[0090] In this embodiment, the simulated annealing local search and deacceptance and update of the first hybrid coding body can refer to the simulated annealing local search and the update based on the elite retention strategy for the first coding body described above, and will not be repeated here.

[0091] Through steps 81 to 84 above, the manufacturing configuration information for the initial configuration plan is generated.

[0092] This embodiment also provides a resource allocation device for distributed manufacturing with multiple production tasks. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0093] Figure 6 This is a structural block diagram of a resource allocation device for distributed manufacturing with multiple production tasks, according to an embodiment of this application. Figure 6 As shown, the device includes a determining module 61, a selecting module 62, an encoding module 63, and a processing module 64, wherein...

[0094] The determination module 61 is used to determine the task completion degree of the manufacturing task associated with each manufacturing unit when receiving an interruption command during the production-operation-storage collaborative operation based on the generated manufacturing configuration information. The manufacturing configuration information includes at least the manufacturing task corresponding to the manufacturing unit. The manufacturing configuration information is generated by using the genetic simulated annealing algorithm to perform production-operation-storage collaborative planning and configuration based on the received historical production order information and pre-configured resource information.

[0095] Select module 62, coupled to determine module 61, is used to determine the current manufacturing task from all manufacturing tasks corresponding to the manufacturing configuration information based on the task completion degree, and to determine the candidate manufacturing unit associated with each current manufacturing task. The current manufacturing task is used to characterize the manufacturing task that needs to be reconfigured, and the candidate manufacturing unit is associated with at least one manufacturing device.

[0096] The encoding module 63, coupled to the selection module 62, is used to perform hybrid encoding based on the current manufacturing task, the corresponding task completion degree and the corresponding manufacturing equipment to generate multiple hybrid encoding bodies. The hybrid encoding body includes multiple code sub-codes. The code sub-codes are used to represent the configuration scheme of the corresponding manufacturing equipment for a current manufacturing task. Each code sub-code is also associated with a transportation and storage decision information determined according to a preset production, transportation and storage collaborative decision model.

[0097] The processing module 64, coupled to the encoding module 63, is used to determine the fitness of the hybrid encoding body according to the preset fitness function, and then, based on multiple hybrid encoding bodies and their corresponding fitness, use the genetic simulated annealing algorithm to perform corresponding genetic evolution operation iterations and simulated annealing search iterations until the preset number of iterations is reached. The target hybrid encoding body is selected from the multiple candidate hybrid encoding bodies generated. The resource configuration result includes all configuration schemes corresponding to the target hybrid encoding body and the transportation and storage decision information corresponding to each configuration scheme. The fitness is used to determine the optimal configuration cost of the production, transportation and storage three stages corresponding to the corresponding encoding body.

[0098] This embodiment also provides a service platform, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0099] Optionally, the service platform may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0100] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0101] S1, during the production, operation and storage collaborative operation based on the generated manufacturing configuration information, determine the task completion degree of the manufacturing task associated with each manufacturing unit when the interruption command is received. The manufacturing configuration information includes at least the manufacturing task corresponding to the manufacturing unit. The manufacturing configuration information is generated by using the genetic simulated annealing algorithm for production, operation and storage collaborative planning and configuration based on the received historical production order information and pre-configured resource information.

[0102] S2, based on the task completion rate, determine the current manufacturing task from all manufacturing tasks corresponding to the manufacturing configuration information, and determine the alternative manufacturing unit associated with each current manufacturing task. The current manufacturing task is used to represent the manufacturing task that needs to be reconfigured, and the alternative manufacturing unit is associated with at least one manufacturing device.

[0103] S3. Based on the current manufacturing task, the corresponding task completion rate, and the corresponding manufacturing equipment, perform hybrid coding to generate multiple hybrid coding bodies. Each hybrid coding body includes multiple code sub-codes. The code sub-codes are used to represent the configuration scheme of the corresponding manufacturing equipment for a current manufacturing task. Each code sub-code is also associated with transportation and warehousing decision information determined according to a preset production, transportation, and storage collaborative decision model.

[0104] S4. After determining the fitness of the hybrid code body according to the preset fitness function, based on multiple hybrid codes body and their corresponding fitness, the genetic simulated annealing algorithm is used to perform corresponding genetic evolution operation iteration and simulated annealing search iteration until the preset number of iterations is reached. The target hybrid code body is selected from the multiple candidate hybrid codes body generated. The resource allocation result includes all configuration schemes corresponding to the target hybrid code body and the transportation and storage decision information corresponding to each configuration scheme. The fitness is used to determine the optimal configuration cost of the production, transportation and storage three stages corresponding to the corresponding code body.

[0105] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0106] Furthermore, in conjunction with the resource allocation method for distributed manufacturing with multiple production tasks described in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the resource allocation methods for distributed manufacturing with multiple production tasks described in the above embodiments.

[0107] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A resource allocation method for distributed manufacturing with multiple production tasks, characterized in that, include: During the production, operation, and storage collaborative operation based on the generated manufacturing configuration information, the task completion degree of the manufacturing task associated with each manufacturing unit is determined when an interruption command is received. The manufacturing configuration information includes at least the manufacturing task corresponding to the manufacturing unit. The manufacturing configuration information is generated based on the received historical production order information and pre-configured resource information, and is generated by using the genetic simulated annealing algorithm for production, operation, and storage collaborative planning and configuration. Based on the task completion rate, the current manufacturing task is determined from all the manufacturing tasks corresponding to the manufacturing configuration information, and the alternative manufacturing unit associated with each current manufacturing task is determined. The current manufacturing task is used to characterize the manufacturing task that needs to be reconfigured, and the alternative manufacturing unit is associated with at least one manufacturing device. Based on the current manufacturing task, the corresponding task completion degree, and the corresponding manufacturing equipment, a hybrid coding is performed to generate multiple hybrid coding bodies. Each hybrid coding body includes multiple code sub-codes. Each code sub-code is used to represent the configuration scheme of the manufacturing equipment corresponding to the current manufacturing task. Each code sub-code is also associated with transportation and warehousing decision information determined according to a preset production, transportation, and storage collaborative decision model. After determining the fitness of the hybrid codec according to the preset fitness function, based on multiple hybrid codescs and their corresponding fitness, the genetic simulated annealing algorithm is used to perform corresponding genetic evolution operation iterations and simulated annealing search iterations until the preset number of iterations is reached. Then, a target hybrid codec is selected from the multiple candidate hybrid codescs generated. The resource configuration result includes all configuration schemes corresponding to the target hybrid codec and the transportation and warehousing decision information corresponding to each configuration scheme. The fitness is used to determine the optimal configuration cost of the production, transportation, and storage three stages corresponding to the corresponding codec.

2. The method according to claim 1, characterized in that, Based on the task completion rate, the current manufacturing task is determined from all the manufacturing tasks corresponding to the manufacturing configuration information, including: Based on the task completion rate, delete the completed manufacturing tasks from all the manufacturing tasks corresponding to the manufacturing configuration information to obtain a first manufacturing task set, wherein the manufacturing tasks in the first manufacturing task set include unexecuted manufacturing tasks and incomplete manufacturing tasks. From the first manufacturing task set, select the unexecuted manufacturing task to obtain the first manufacturing task; Determine the remaining task degree corresponding to all the unfinished manufacturing tasks in the first manufacturing task set, and take the task quantity corresponding to the remaining task degree as the new task quantity of the corresponding unfinished manufacturing task to obtain the corresponding second manufacturing task; Combine all the first manufacturing tasks and all the second manufacturing tasks into the current manufacturing task.

3. The method according to claim 2, characterized in that, Determining the alternative manufacturing units associated with each of the current manufacturing tasks, including: The manufacturing unit and the manufacturing equipment associated with the unfinished manufacturing task corresponding to the second manufacturing task are determined to obtain a limited selection of manufacturing units and limited selection of manufacturing equipment; After designating the limited manufacturing unit as the candidate manufacturing unit associated with the corresponding second manufacturing task, select the manufacturing equipment other than the limited manufacturing equipment from all the manufacturing equipment associated with the limited manufacturing unit to obtain the candidate manufacturing equipment; The alternative manufacturing equipment is the manufacturing equipment associated with the alternative manufacturing unit associated with the second manufacturing task.

4. The method according to claim 3, characterized in that, Determining the alternative manufacturing units associated with each of the current manufacturing tasks, including: Obtain all manufacturing units corresponding to the manufacturing configuration information, select all manufacturing units except the limited selection manufacturing units, and obtain candidate manufacturing units, wherein the candidate manufacturing units include one of the manufacturing units associated with the completed manufacturing tasks and the manufacturing units associated with the unexecuted manufacturing tasks; The candidate manufacturing unit is designated as the alternative manufacturing unit associated with the corresponding first manufacturing task, and the manufacturing equipment associated with the candidate manufacturing unit is designated as the manufacturing equipment associated with the alternative manufacturing unit associated with the first manufacturing task.

5. The method according to claim 4, characterized in that, Based on the current manufacturing task, the corresponding task completion rate, and the corresponding manufacturing equipment, a hybrid coding is performed to generate multiple hybrid coding bodies, including: Based on the task completion rate corresponding to the current manufacturing task, a target manufacturing equipment corresponding to the current manufacturing task is determined, wherein the target manufacturing equipment includes one of the alternative manufacturing equipment and the manufacturing equipment associated with the candidate manufacturing unit; The current manufacturing task, the intended manufacturing equipment corresponding to the current manufacturing task, and the corresponding task completion degree are encoded into a code sub-code, and multiple code sub-codes corresponding to the current manufacturing task are combined into an initial code body. The code sub-code includes a task code, a task degree code, and a equipment code arranged in a vertical order. The task degree code is used to constrain the manufacturing equipment configured for the corresponding current manufacturing task. Based on the initial code body, population initialization is performed to generate multiple hybrid code bodies. During the population initialization process, the corresponding intended manufacturing equipment is selected from all the intended manufacturing equipment corresponding to each current manufacturing task, and the corresponding equipment code is generated.

6. The method according to claim 5, characterized in that, The genetic simulated annealing algorithm is used to perform corresponding genetic evolution operation iterations and simulated annealing search iterations, including: After determining the multiple current coding bodies that participate in the current genetic evolution operation and simulated annealing search iteration, the fitness corresponding to the current coding body is calculated according to the fitness function, wherein the current coding body includes one of the following: the hybrid coding body, or a historical coding body that has completed the previous genetic evolution operation and simulated annealing search iteration; Based on the corresponding fitness and preset selection operation, a preset number of candidate codecs are selected from multiple current codecs, wherein the selection operation includes individual selection based on tournament selection and elite retention strategies; For multiple candidate codes, crossover and mutation operations corresponding to the genetic simulated annealing algorithm are performed sequentially to generate the first code corresponding to the current genetic evolution iteration. In the crossover and mutation operations, the intended manufacturing equipment configured for crossover and mutation is selected from all the intended manufacturing equipment corresponding to the current manufacturing task corresponding to each code. The crossover operation includes partial matching crossover, and the mutation operation includes uniform mutation. Simulated annealing local search corresponding to the genetic simulated annealing algorithm is performed on multiple first codes to locally optimize the first codes and generate a second code corresponding to the current simulated annealing search iteration. Based on the second code and the fitness corresponding to the second code, the second code is de-accepted and de-updated according to a preset acceptance criterion to generate the candidate hybrid code corresponding to one iteration of genetic evolution operation and simulated annealing search.

7. The method according to claim 6, characterized in that, Select the target hybrid codename from the generated candidate hybrid codenames, including: Obtain the candidate hybrid code that has completed a preset number of iterations, and determine the fitness corresponding to each candidate hybrid code; According to the fitness order from small to large, the candidate hybrid codec with the smallest fitness is selected from the candidate hybrid codecs that have completed a preset number of iterations to obtain the target hybrid codec.

8. The method according to claim 1, characterized in that, Generating the manufacturing configuration information includes: Obtain the corresponding historical production order information, determine the historical manufacturing tasks based on the historical production order information, determine the manufacturing equipment corresponding to each preset manufacturing unit based on the pre-configured resource information, and encode and initialize the historical manufacturing tasks and the corresponding manufacturing equipment to generate a historical hybrid coding population including multiple historical hybrid coding bodies. Based on the corresponding fitness and preset selection operation, a preset number of historical hybrid coding bodies are selected from the historical hybrid coding body population. The selected historical hybrid coding bodies are then subjected to crossover and mutation operations corresponding to the genetic simulated annealing algorithm in sequence to generate the first hybrid coding body corresponding to the current genetic evolution iteration. The selection operation includes individual selection based on tournament selection and elite retention strategies, the crossover operation includes sequential crossover, and the mutation operation includes random mutation. Perform simulated annealing local search corresponding to the genetic simulated annealing algorithm on multiple first hybrid coding bodies to locally optimize the first hybrid coding bodies and generate a second hybrid coding body corresponding to the current simulated annealing search iteration; Based on the second hybrid code and the fitness corresponding to the second hybrid code, the second hybrid code is subjected to deacceptance and de-update processing according to a preset acceptance criterion to generate an intention hybrid code corresponding to one genetic evolution operation iteration and simulated annealing search iteration. After a preset number of iterations, the manufacturing configuration information is generated based on the decoded intention hybrid code.

9. A service platform, comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the steps of the resource allocation method for distributed manufacturing multi-production tasks as described in any one of claims 1 to 8.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the resource allocation method for distributed manufacturing with multiple production tasks as described in any one of claims 1 to 8.

Images