A method and apparatus for executing a design of a hybrid production

Abstract

The application discloses a kind of hybrid production execution design method and device.The application includes: generating event set, event set includes production subject identification, online time, production constraint and process set;Arrange event set, get initial particle, when initial particle reaches preset quantity, get initial particle group, wherein each event set corresponds to an initial particle, initial particle includes at least one planned event, planned event includes at least one process set, process set includes at least one process;Step S103, optimize initial particle, get initial optimized particle;Step S104, evaluate initial optimized particle, get initial optimal particle;Repeat the execution step S103-step S104 to preset number of times, obtain final optimal particle.Through the application, the problem that cannot be dynamically adjusted in production process in related art is solved.

Description

Technical Field

[0001] This invention relates to the field of production scheduling technology, and more particularly to a method and apparatus for designing the execution of mixed production. Background Technology

[0002] Current automotive final assembly is a linear, takt-cycle production workshop where multiple branch lines converge into a main line. However, production lines under construction are beginning to exhibit a hybrid model combining discrete unit (DMU) and line assembly. Specifically, some highly automated assembly units, where the production takt-cycle is difficult to adjust, or where the process is not suitable for movement, utilize the DMU assembly mode, while other semi-automated or less automated assembly processes still employ the takt-cycle production line mode. Currently, mature automotive production execution systems are primarily based on line takt-cycle production, which is incompatible with the flexible DMU production execution model.

[0003] Flexible manufacturing needs to meet three types of flexibility: production flexibility, process flexibility, and equipment flexibility.

[0004] Production flexibility refers to the system's ability to dynamically schedule production based on the current production status during the manufacturing process. For example, if an assembly unit experiences a breakdown and shutdown, the system can reroute vehicles originally scheduled to enter that assembly unit to another assembly unit of the same type. When an assembly unit is overloaded, the system can reroute subsequent vehicles to similar assembly units based on the actual operating load, or pre-install other assembly work within the permissible range according to process presets.

[0005] Process flexibility refers to the dynamic adjustment of the production process and suitable assembly units for a particular vehicle model based on different vehicle types, site conditions, equipment requirements, and process cycles. For example, in the current market environment, many vehicle models support various personalized configurations for customers. Under these diverse configuration requirements, the system needs to meet the diverse process configurations of different vehicle models. Furthermore, in conjunction with equipment flexibility, when the equipment and site layouts for the same vehicle model change, the system needs to support readjustments to the production process to maximize the efficiency of the adjusted equipment layout. In addition, due to the increased autonomy of the scheduling system, a higher degree of freedom is required in the process design process to realize the potential of the scheduling system; for example, the process sequence can be interchanged, and certain processes can be skipped.

[0006] Equipment flexibility refers to the ability of a workshop to add or remove production equipment based on current production conditions. Because current assembly unit designs support modifications to these units, different assembly functions can be achieved by replacing equipment. This necessitates adjustments to the assembly layout that require production scheduling, processes, production monitoring, and digital twin platforms to be able to visually switch and adjust these adjustments.

[0007] Flexible manufacturing demands a data-driven production process. Under the current cycle-driven model, data only guides the production line to perform brute-force actions such as alarms and line stoppages, failing to meet the flexibility requirements of discrete unit manufacturing. Furthermore, while current manufacturing execution systems can adjust the sequence of processes to some extent, they cannot dynamically adjust them during production, nor can they handle large-scale mixed-line production or adjust certain processes to a parallel sequence. Due to the characteristics of cycle-driven manufacturing, past systems did not require planning for large-scale production events, but current flexible manufacturing creates space for planning. For example, panoramic sunroofs, typically required only for high-end vehicles, do not account for a large proportion of daily production; therefore, we do not need to produce them in bulk, thus avoiding congestion in the sunroof assembly unit.

[0008] There is currently no effective solution to the aforementioned problems in the relevant technologies. Summary of the Invention

[0009] The main objective of this application is to provide a hybrid production execution design method and apparatus to at least solve the problem in related technologies that cannot be dynamically adjusted during the production process.

[0010] To achieve the above objectives, according to one aspect of this application, an execution design method for hybrid production is provided. The method includes: generating an event set, the event set including a production entity identifier, a launch time, production constraints, and a process set; arranging the event set to obtain initial particles; when the initial particles reach a preset number, obtaining an initial particle swarm, wherein each event set corresponds to one initial particle, the initial particle including at least one planned item, the planned item including at least one process set, and the process set including at least one process; step S103, optimizing the initial particles to obtain initial optimized particles; step S104, evaluating the initial optimized particles to obtain initial optimal particles; and repeating steps S103-S104 for a preset number of times to obtain the final optimal particles.

[0011] Optionally, a planned event is randomly selected from the event set, and all first processes of the planned event are obtained, wherein the first process is the process corresponding to the starting point of each process set in the planned event; the execution process of the first process is selected within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; based on the production preceding process of the process, the execution process that can be executed after the production preceding process of the process is randomly selected, wherein the production preceding process is the process before the main production process; the start time and end time of the execution process are determined, and the time occupancy of the assembly unit corresponding to the execution process is marked, and the completion time of the process is updated; when all process sets in the planned event of the event set are arranged, the first generation particle is obtained.

[0012] Optionally, in step S301, the optimization vector length, particle optimization rounds, and particle optimization target percentage are set. The optimization vector length represents the time difference between two processes in the same assembly unit and the distance between two processes in different assembly units. The optimization target percentage represents the percentage of the time consumed by the initial optimization particles relative to the total time consumed by the initial particles. The position refers to a production entity within a specific assembly unit. In step S302, based on the set vector length, two processes to be exchanged or moved are selected from the optimization stage particles. The optimization stage particles include the initial particles and the particles obtained from each optimization. The processes to be exchanged are any two processes in two assembly units of the same type, or any two processes in one assembly unit. In step S303, the exchanged optimization stage particles are re-integrated to obtain the final completion time of each process. In step S304, the integrated optimization stage particles are detected, including: when the integration... When the optimized particles meet the production constraints, optimized particles are obtained; when the integrated optimized particles do not meet the production constraints, steps S301-S304 are repeated; in step S305, it is determined whether to retain the optimized particles, including: when the total consumption time of the optimized particles is less than that of the optimized particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than that of the optimized particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed to be the first-generation optimized particles.

[0013] Optionally, when two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

[0014] Optionally, step S501 involves scheduling the time of each process starting from the first process, where the first process is the process corresponding to the starting point of each process set in the planned items. This includes: updating the start time and end time of the process when there is no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned items corresponding to the pre-assembly process, where the pre-assembly process is the process preceding the process on the assembly unit; repeating step S501 until all processes are scheduled to obtain the final completion time of each process.

[0015] Optionally, the retention probability is calculated using the following formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0016] Optionally, calculate the fitness of all initial optimized particles, and select the initial optimized particle with the highest fitness as the initial optimal particle. The calculation formula is as follows: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0017] Optionally, based on the set vector length, two processes to be swapped or moved are selected, including: arbitrarily selecting two processes and comparing their positions with the positions of the processes swapped during the initial optimal particle optimization; if the positions of the two processes are the same as those of the processes swapped during the initial optimal particle optimization, two processes are reselected; if the positions of the two processes after swapping are the same as those of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0018] According to another aspect of this application, an execution design apparatus for hybrid production is provided. The apparatus includes: a generation unit for generating event sets, the event sets including production entity identifiers, online times, production constraints, and process sets; an arrangement unit for arranging the event sets to obtain initial particles, and obtaining an initial particle swarm when the initial particles reach a preset number, wherein each event set corresponds to one initial particle, the initial particle includes at least one planned item, the planned item includes at least one process set, and the process set includes at least one process; an optimization unit for executing step S103 to optimize the initial particles to obtain initial optimized particles; an evaluation unit for executing step S104 to evaluate the initial optimized particles to obtain initial optimal particles; and an execution unit for repeatedly executing steps S103-S104 up to a preset number of times to obtain the final optimal particles.

[0019] To achieve the above objectives, according to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes a hybrid production execution design method of any of the above.

[0020] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a hybrid production execution design method for executing any one of them.

[0021] This application employs the following steps: generating an event set, which includes a production entity identifier, online time, production constraints, and a process set; arranging the event set to obtain initial particles; when the initial particles reach a preset number, an initial particle swarm is obtained, wherein each event set corresponds to one initial particle, and the initial particle includes at least one planned item, which includes at least one process set, and the process set includes at least one process; step S103, optimizing the initial particles to obtain initial optimized particles; step S104, evaluating the initial optimized particles to obtain initial optimal particles; repeating steps S103-S104 up to a preset number of times to obtain the final optimal particles. This solves the problem in related technologies where dynamic adjustments during the production process are impossible, thereby achieving the effect of responding to changes in assembly unit planning and the diversification of assembly paths at any time during the production process. Attached Figure Description

[0022] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an execution design method for hybrid production provided according to an embodiment of this application;

[0024] Figure 2 This is a structural block diagram of a hybrid production execution design apparatus provided according to an embodiment of this application. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] As described in the background section, production adjustments in the existing flexible production line process are not automated. To address the problem that existing technologies cannot dynamically adjust production processes, embodiments of this application provide a hybrid production execution design method and apparatus.

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] This embodiment provides a hybrid production execution design method that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 1 This is a flowchart illustrating a hybrid production execution design method according to an embodiment of this application. For example... Figure 1 As shown, the method includes the following steps:

[0032] Step S101: Generate an event set, which includes the production entity identifier, online time, production constraints, and process set;

[0033] Specifically, each particle (event set) is defined as representing an executable production plan for a given day, i.e., an outcome, regardless of whether the outcome is actually executable. The core content of this outcome is the entry and exit time of each vehicle to be assembled in each assembly unit, the production time, and the transportation time between assembly units. It can also be described as the production sequence of each assembly unit for the day, along with the corresponding specific times and materials used.

[0034] The data involved in the automobile assembly process is encapsulated into four categories: event data, resource data, result data, and constraints.

[0035] Event data describes all the events that the plan will execute. An event is a decomposition of the smallest complete event for this plan. For example, in the car manufacturing process, the entire process of "assembling a car" is defined as an event. Correspondingly, each particle is the calculation result of completing a set of events.

[0036] Due to the complexity of events, the event model needs to be decomposed into a data model. An event consists of vehicle identifier, online time, latest completion requirement, vehicle-following resource set, and process set. The vehicle-following resource set is a type of resource set.

[0037] Process set: A process set is a decomposition of events, describing all the processes required to produce a car. The data model for a process includes main components, process sets, and subsequent processes. In traditional automotive production, in a mainline-branchline collaborative production model, the mainline is driven by the body structure as the primary component, while branchlines are driven by their respective assembled main components, such as doors, seats, center consoles, and chassis. The main component records the unique resource defining this mainline or branchline, and also connects a mainline or branchline production line.

[0038] Process Technology: In flexible manufacturing, processes are determined by different process paths, the sequence of processes can be changed, and different production line stations can be used depending on the production method. Therefore, the process set is actually a tree-structured collection, with each process having a subsequent process set, representing the subsequent optional branches corresponding to the current process. Each process can be achieved through different processes. For example, tire assembly can be completed by different tire assembly units, and the assembly equipment and consumables of different assembly units may also differ. Therefore, the process data structure needs a "process set" to describe the selectable process methods for the current process. The process data structure includes the construction station of the current process, the process time, and the resource set required by the current process. The resource set data structure describes the quantity of current resources required by the process.

[0039] Resource set: The resource set describes all the resources needed in this event. Note that this includes not only consumable resources such as materials, but also main components such as the car body, doors, and central control, as well as production lines, workstations, other production tools used in the manufacturing process, and even the working hours of production line workers.

[0040] In the resource data modeling of this project, we divided resources into three categories: workshop consumable public resources, workshop tool-type public resources, and vehicle-related resources.

[0041] Typically, main components such as the car body, doors, and central control are packaged as vehicle-mounted resources, while assembly units, AGVs, and buffer parking spaces are considered as workshop tool-type public resources, and line-side materials are considered as workshop consumable public resources.

[0042] Result Set: The result set is what we described in the first section as a particle. Each particle represents a result set. Based on the content of the result set, we can describe the sequence and time of assembly units that each component of each vehicle needs to go through, and also describe the production sequence of each assembly unit and the vehicles produced from another perspective. We designed the result set as follows:

[0043] Each result in the result set is the finest-grained element that can describe the result, i.e., a collection of each process. However, unlike the process data structure described above, the result set necessarily has the selected process, the start time of the process, and the duration of the process determined. Therefore, the result set is the collection of processes with determined processes, start times, and execution times, after the event determines the process and the process determines the process.

[0044] Constraint Set: As the name suggests, a constraint set is a collection of data constraints applied to various aspects of the production process due to the characteristics of automobile manufacturing. For example, our constraint set includes the following:

[0045] 1. Constraints on the quantity of consumable resources consumed;

[0046] 2. Regarding the constraints on the use of shared resources, it should be noted that some assembly units support simultaneous production of multiple vehicles. Therefore, there may be multiple vehicles working at the same time in an assembly unit. The constraints here require special handling for the number of vehicles produced at the same time.

[0047] 3. For vehicles with production end time constraints, limit the final production completion time;

[0048] 4. The production sequence of vehicles must not violate the process rules;

[0049] 5. Production intervals must not be less than the planned AGV transport time between workstations;

[0050] Regarding the generation of event sets:

[0051] Project{

[0052] Vin code: "xxxxx",

[0053] Production line entry time: "hh:mi:ss"

[0054] Latest completion time: "hh:mi:ss"

[0055] Process set: [Process 1:{

[0056] Preceding process name: "jobxx"

[0057] Optional processes (array): ["Assembly unit number", "Time taken", "Required resources"]

[0058] }; Process 2: {

[0059] Preceding process name: "jobxx"

[0060] Optional processes (array): ["Assembly unit number", "Time taken", "Required resources"]

[0061] }]

[0062] }

[0063] This data model is described using a JSON-formatted data structure. This data structure is used to describe a specific planned event, such as a vehicle to be produced with a specific code model in automobile production.

[0064] This plan includes the vehicle's VIN code, entry time into the production line, latest completion time, and process set. All times are accurate to the second and expressed in "hh:mi:ss" format.

[0065] The process set element is a JSON array that stores all available processes for executing the event (producing the car) in order. Note that a model of a vehicle may have multiple production paths. This is a tree structure that links processes together through "preceding processes".

[0066] The process set is also described in JSON format, encapsulating the current process name, the previous process name, and the set of optional processes for the current process. The optional execution processes are an array describing all feasible production methods for this process.

[0067] Each execution process includes the assembly unit number (production equipment), assembly time, required materials and quantities. Materials include installation materials and consumables.

[0068] Step S102: Arrange event sets to obtain first-generation particles. When the number of first-generation particles reaches a preset number, a group of first-generation particles is obtained. Each event set corresponds to one first-generation particle. Each first-generation particle includes at least one planned item. Each planned item includes at least one process set. Each process set includes at least one process.

[0069] Specifically, because it is a multi-line production line, there will be multiple process starting points in the process concentration.

[0070] There are also special scenarios that may arise when orchestrating event sets. The solutions are as follows:

[0071] 1) Ordered arrangement: In some cases, due to workshop conditions, it is impossible to adjust the current final assembly entry order, so the entry order will be locked. In this scenario, we can perform the optimization method for individual particles described in point 3 above for arrangement.

[0072] 2) Temporary insertion tasks: For temporary insertion tasks, considering that the vehicle sequence in the current production process cannot be rearranged, the initial particles can be generated at random positions of the inserted vehicles. Considering the feasibility of insertion, the insertion can be carried out in a concentrated manner with random order between the inserted vehicles. The subsequent particle swarm selection and optimization of individual particles are consistent with the original method.

[0073] Step S103: Optimize the first-generation particles to obtain the first-generation optimized particles;

[0074] Specifically, optimization begins with the initial particles, each optimized independently without interference. Since each particle corresponds to a different planned vehicle entry order, the possibility of convergence in optimization results for each particle is avoided.

[0075] Step S104: Evaluate the first-generation optimized particles to obtain the first-generation optimal particles;

[0076] Specifically, after all the first-generation particles have been optimized, the optimized first-generation particles are evaluated to obtain the best first-generation particle after the previous generation optimization.

[0077] Step S105: Repeat steps S103-S104 for a preset number of times to obtain the final optimal particle.

[0078] Specifically, starting with the second generation of optimization, there are slight differences from the first generation. In this generation, when selecting a process step, two processes are chosen for exchange. The position of this process is found to correspond to the selected process of the first-generation optimal particle. If the process's position is already consistent with the first-generation optimal particle, two processes to be replaced are randomly selected again. If the optimized process's position is consistent with the corresponding process position in the first-generation optimal particle, the optimization is retained with random probability, or the process is restored to its original position. Random probability can be understood as the program generating a random number between 0 and 1; if the result is less than 0.5, the process is executed; if it is greater, it is restored. The new generation of particles is evaluated to obtain a new first-generation optimal particle. It is then verified whether the first-generation optimal particle meets the production requirements or reaches the upper limit of the optimization generation. If it does, the calculation exits directly.

[0079] Due to the flexibility required by the equipment, the assembly function of each assembly unit in the grid is not static, and the production line design can be adjusted and modified according to the company's assembly strategy. Accordingly, the execution system needs to be able to support changes in the assembly process of the assembly units. In the flexible production line design method, our core task is to design a production line design scheme that maximizes the efficiency of the current automobile factory in producing the expected models, making the production routes of most vehicles relatively optimal. This invention, based on the implemented production line design layout, calculates the optimal production path planning under the current production plan according to different vehicle models.

[0080] First, by combining the current multi-line production model, data modeling of the production process can be carried out, which can concisely and efficiently express the specific scheme and detailed requirements of the designed process at the data level.

[0081] 1. A clear process sequence and order are required.

[0082] 2. It needs to be able to show which processes can be produced out of order and which processes have one or more prerequisite dependencies.

[0083] 3. It is necessary to reflect the relationship between the process and the equipment, such as the production differences of the same process in different assembly units.

[0084] 4. It is necessary to clearly indicate the production material requirements for each process, such as required man-hours, required materials, and if it is a branch line, it is necessary to identify the main body of production and processing.

[0085] 5. Since the process path is dynamic and multiple options are available, it is necessary to be able to clearly define the transportation time, material preparation time, etc. under different path selections for different processing paths.

[0086] 6. After the daily plan is determined, a specific and unique production plan for each vehicle can be derived based on the process path data model and further constraints. (That is, the process is a data representation that allows for the selection of multiple production methods, while the production plan is generated based on the process path, specifying what to assemble first and what to assemble next for a particular vehicle, and which assembly unit to produce it in.)

[0087] Based on the above plan and requirements, there is usually a 3-hour preparation time from the time all materials are ready and transported to the final execution. Considering extreme cases, it is necessary to generate and repeatedly demonstrate the production process of all main and branch line components planned for daily production within three hours.

[0088] Based on the characteristics of the current assembly workshop, the production sequence of each main component is randomly generated, and combined with the assembly process between components, an overall production plan is integrated as one of the options for the daily production plan; a certain number of production plan result sets are generated in this way as the initial particle swarm.

[0089] In the aforementioned first-generation particle swarm, each particle represents a production plan that can be executed on a certain day. Each particle represents a set, and the format of each element in the set is: AA assembly unit assembles X component using process X at time SS.

[0090] The particles in the above particle group are obtained in a loop. The production time in the assembly unit is recalculated according to the sequence of processes, and particles that do not conform to the production relationship are filtered out. For example, vehicle A requires process a to be performed first and then process b. However, vehicle A performs process a in assembly unit A1 before vehicle B, and vehicle B performs process b in assembly unit B1 before vehicle A. Through integration, executable final particles are obtained in the form of (A1, A)->(A1, B)->(B1, B)->(B1, A).

[0091] This method is suitable for flexible production line planning that relies on assembly units and AGVs. The planning and scheduling tasks can be refined to the workstation level up to 3 hours before production. This method supports situations where the preceding assembly sequence is already set, and also supports the temporary insertion of unplanned vehicles. This method remains usable after production line relocation or changes to assembly unit functions; only the process methods of the corresponding steps in the above-mentioned planning items need to be adjusted before recalculation.

[0092] In an optional embodiment, a planned event is randomly selected from the event set, and all first processes of the planned event are obtained, wherein the first process is the process corresponding to the starting point of each process set in the planned event; the execution process of the first process is selected within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; based on the production pre-process of the process, the execution process that can be executed after the production pre-process is randomly selected for the process, wherein the production pre-process is the process before the process of the main production body; the start time and end time of the execution process are determined, and the time occupancy of the assembly unit corresponding to the execution process is marked, and the completion time of the process is updated; when all process sets in the planned event of the event set are arranged, the first generation particle is obtained.

[0093] Specifically, due to multi-line production, there will be multiple process start points in the planning. Initially, a preliminary particle swarm is defined, corresponding to a preset quantity. The start points of all process sets are obtained. From the processes executable at each start point, one process is randomly selected for execution. Then, executable processes are selected for subsequent processes, based on the preceding processes. After selecting the processes, the start and end times are determined, and the time occupancy of the executing assembly units is marked. This completes the arrangement of one preliminary particle swarm. The preliminary particle swarm is generated once the preset quantity of particles is reached.

[0094] In an optional embodiment, step S301 involves setting the optimization vector length, the number of particle optimization rounds, and the particle optimization target percentage. The optimization vector length represents the time difference between two processes on the same assembly unit and the distance between two processes on different assembly units. The optimization target percentage represents the percentage of the time consumed by the initial optimization particles relative to the total time consumed by the initial particles. The position refers to a production entity within a specific assembly unit. Step S302 involves selecting two processes to be exchanged or moved from the optimization stage particles based on the set vector length. The optimization stage particles include the initial particles and the particles obtained from each optimization. The processes to be exchanged are any two processes on two assembly units of the same type, or any two processes on one assembly unit. Step S303 involves re-integrating the exchanged optimization stage particles to obtain the final completion time of each process. Step S304 involves detecting the integrated optimization stage particles, including: When the integrated optimized stage particles meet the production constraints, optimized particles are obtained; when the integrated optimized stage particles do not meet the production constraints, steps S301-S304 are repeated; in step S305, it is determined whether the optimized particles should be retained, including: when the total consumption time of the optimized particles is less than that of the optimized stage particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized stage particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than that of the optimized stage particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized stage particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized stage particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed as the first-generation optimized particles.

[0095] Specifically, swaps must be performed within a range based on vector length. Failure to meet constraints results in an outcome that does not meet production process requirements. Random swaps may lead to unproducible scenarios. For example, the production process for car p requires it to go to assembly unit A before assembly unit B, while car q requires it to go to assembly unit B before assembly unit A. If the current result set shows assembly unit A planning for q before p and assembly unit B planning for p before q, then the plan contradicts the production process. In such cases, execution restarts from S301. When judging based on the retention probability, a final Boolean value can be generated based on probability P. If the value is true, optimization t2 is retained, even though t2's total time is inferior to t1; if the value is false, this optimization is ignored.

[0096] In an alternative embodiment, when two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

[0097] Specifically, it could be an exchange between the mth vehicle assembly unit and the nth vehicle assembly unit of assembly unit A, or an exchange between the pth vehicle assembly unit of assembly unit A and the qth vehicle assembly unit of assembly unit B, or a migration of the pth vehicle assembly unit of assembly unit A to the qth vehicle assembly unit of assembly unit B for production.

[0098] In an optional embodiment, step S501 involves scheduling the time of each process starting from the first process, wherein the first process is the process corresponding to the starting point of each process set in the planned items, including: updating the start time and end time of the process when there is no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned items corresponding to the pre-assembly process, wherein the pre-assembly process is the process preceding the process on the assembly unit; repeating step S501 until all processes are scheduled to obtain the final completion time of each process.

[0099] Specifically, since each assembly unit continuously assembles many workpieces, and the first workpiece to be assembled is not necessarily the first workpiece assembled in each assembly unit, the scheduling needs to start from the first workpiece to be executed. For example, when workpiece 1 reaches assembly unit B, it is found that workpiece 1 is not the first workpiece in assembly unit B, but workpiece 2 is. Therefore, the scheduling starts from the first operation of workpiece 2. After the operation scheduling of workpiece 2 in assembly unit B is completed, the scheduling of workpiece 1 continues.

[0100] In an optional embodiment, the retention probability is calculated using the formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0101] Specifically, if the total time consumed is greater than that of the original particle, in order to prevent the current particle's optimization path from getting stuck in a local optimum, we calculate the probability that the current particle retains the latest value according to a probability formula. This probability is related to the number of loops that have been executed.

[0102] In one optional embodiment, the fitness of all initial optimized particles is calculated, and the initial optimized particle with the highest fitness is selected as the initial optimal particle. The calculation formula is as follows: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0103] Specifically, the earlier the algebra is listed, the higher the weight of completion time; the later the algebra is listed, the higher the weight of machine load balancing. A higher fitness level is better.

[0104] In an optional embodiment, two processes to be swapped or moved are selected according to the set vector length, including: arbitrarily selecting two processes and comparing the positions of the two processes with the positions of the processes swapped during the initial optimal particle optimization; if the positions of the two processes are the same as the positions of the processes swapped during the initial optimal particle optimization, two processes are reselected; if the positions of the two processes after the swap are the same as the positions of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0105] Specifically, starting from the second generation of optimization, since there is already an initial generation of optimization particles, in order to prevent getting trapped in local optima and wasting resources, it is necessary to compare with the previous generation of initial optimization particles when selecting process exchange and movement, so as to avoid the convergence of the two optimization results.

[0106] This application also provides a hybrid production execution design apparatus. It should be noted that this hybrid production execution design apparatus can be used to execute the hybrid production execution design method provided in this application. This apparatus is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0107] The following describes an execution design apparatus for hybrid production provided in an embodiment of this application.

[0108] Figure 2 This is a structural block diagram of a hybrid production execution design apparatus according to an embodiment of this application. Figure 2As shown, the device includes: a generation unit 201 for generating event sets, the event sets including production entity identifiers, online time, production constraints, and process sets; an arrangement unit 202 for arranging event sets to obtain initial particles, and obtaining an initial particle swarm when the initial particles reach a preset number, wherein each event set corresponds to one initial particle, the initial particle includes at least one planned item, the planned item includes at least one process set, and the process set includes at least one process; an optimization unit 203 for executing step S103 to optimize the initial particles to obtain initial optimized particles; an evaluation unit 204 for executing step S104 to evaluate the initial optimized particles to obtain initial optimal particles; and an execution unit 205 for repeatedly executing steps S103-S104 up to a preset number of times to obtain the final optimal particles.

[0109] In an optional embodiment, the orchestration unit 202 includes: an acquisition subunit, configured to randomly select a planned event from the event set and acquire all first processes of the planned event, wherein the first process is the process corresponding to the starting point of each process set in the planned event; a first selection subunit, configured to select the execution process of the first process within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; a second selection subunit, configured to randomly select an execution process that can be executed after the production preprocess of the process, wherein the production preprocess is the process before the process of the main production body; a determination subunit, configured to determine the start time and end time of the execution process, mark the time occupancy of the assembly unit corresponding to the execution process, and update the completion time of the process; and an orchestration subunit, configured to obtain the initial particles after all process sets in the planned event in the event set have been orchestrated.

[0110] In an optional embodiment, the optimization unit 203 includes: a setting subunit, used to execute step S301, setting the optimization vector length, the number of particle optimization rounds, and the particle optimization target percentage, wherein the optimization vector length is the time difference between two processes on the same assembly unit and the distance between the positions of two processes on different assembly units, and the optimization target percentage is the percentage of the consumption time of the first-generation optimization particles to the consumption time of the first-generation particles, wherein the position is a certain production entity in a certain assembly unit; an exchange subunit, used to execute step S302, selecting two processes to be exchanged or moved in the optimization stage particles according to the set vector length, wherein the optimization stage particles include the first-generation particles and the particles obtained in each optimization, and the processes to be exchanged are any two processes on two assembly units of the same type, or any two processes on one assembly unit; an integration subunit, used to execute step S303, re-integrating the exchanged optimization stage particles to obtain the final completion time of each process; and a detection subunit, used to execute step S304. The detection of integrated optimized stage particles includes: when the integrated optimized stage particles meet production constraints, an optimized particle is obtained; when the integrated optimized stage particles do not meet production constraints, steps S301-S304 are repeated; a judgment subunit is used to execute step S305 to determine whether the optimized particle should be retained, including: when the total consumption time of the optimized particle is less than that of the optimized stage particle obtained in the previous optimization, the optimized particle is recorded as the latest value, and the optimized stage particle obtained in the previous optimization is retained as a historical record; when the total consumption time of the optimized particle is greater than that of the optimized stage particle obtained in the previous optimization, it is determined whether to retain the optimized particle as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particle is not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized stage particle obtained in the previous optimization is the initial particle; a confirmation subunit is used to execute steps S302-S305 repeatedly until the optimized stage particle reaches the particle optimization round number or reaches the particle optimization target percentage, and confirm that the latest value is the initial optimized particle.

[0111] In an alternative embodiment, the exchange subunit includes a moving unit for moving one of the exchanged processes in front of the other when two processes to be exchanged are moved.

[0112] In an optional embodiment, the integration subunit includes: a scheduling module, used in step S501 to schedule the time of processes starting from the first process, wherein the first process is the process corresponding to the starting point of each process set in the planned item, including: updating the start time and end time of the process when the process has no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned item corresponding to the pre-assembly process, wherein the pre-assembly process is the process preceding the process on the assembly unit; and an acquisition module, used to repeat step S501 until all processes are scheduled to obtain the final completion time of each process.

[0113] In one optional embodiment, the determination subunit includes: a calculation module for calculating the retention probability, using the formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0114] In an optional embodiment, the evaluation unit 204 includes: a calculation subunit, used to calculate the fitness of all initial-generation optimized particles, and select the initial-generation optimized particle with the highest fitness as the initial-generation optimal particle, the calculation formula being: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0115] In an optional embodiment, the execution unit 205 includes: a first selection subunit, configured to select two processes to be swapped or moved according to a set vector length; and a second selection subunit, configured to arbitrarily select two processes and compare the positions of the two processes with the positions of the processes swapped during the initial optimal particle optimization. If the positions of the two processes are the same as the positions of the processes swapped during the initial optimal particle optimization, the two processes are reselected. If the positions of the two processes after the swap are the same as the positions of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0116] The hybrid production execution design apparatus includes a processor and a memory. The aforementioned generation units 201, etc., are all stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0117] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and C technical problems can be solved by adjusting kernel parameters.

[0118] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0119] This invention provides a computer-readable storage medium including a stored program, wherein the program, when running, controls the device where the computer-readable storage medium is located to execute the hybrid production execution design method.

[0120] Specifically, a hybrid production execution design approach includes:

[0121] Step S101: Generate an event set, which includes the production entity identifier, online time, production constraints, and process set;

[0122] Specifically, each particle (event set) is defined as representing an executable production plan for a given day, i.e., an outcome, regardless of whether the outcome is actually executable. The core content of this outcome is the entry and exit time of each vehicle to be assembled in each assembly unit, the production time, and the transportation time between assembly units. It can also be described as the production sequence of each assembly unit for the day, along with the corresponding specific times and materials used.

[0123] The data involved in the automobile assembly process is encapsulated into four categories: event data, resource data, result data, and constraints.

[0124] Event data describes all the events that the plan will execute. An event is a decomposition of the smallest complete event for this plan. For example, in the car manufacturing process, the entire process of "assembling a car" is defined as an event. Correspondingly, each particle is the calculation result of completing a set of events.

[0125] Due to the complexity of events, the event model needs to be decomposed into a data model. An event consists of vehicle identifier, online time, latest completion requirement, vehicle-following resource set, and process set. The vehicle-following resource set is a type of resource set.

[0126] Process set: A process set is a decomposition of events, describing all the processes required to produce a car. The data model for a process includes main components, process sets, and subsequent processes. In traditional automotive production, in a mainline-branchline collaborative production model, the mainline is driven by the body structure as the primary component, while branchlines are driven by their respective assembled main components, such as doors, seats, center consoles, and chassis. The main component records the unique resource defining this mainline or branchline, and also connects a mainline or branchline production line.

[0127] Process Technology: In flexible manufacturing, processes are determined by different process paths, the sequence of processes can be changed, and different production line stations can be used depending on the production method. Therefore, the process set is actually a tree-structured collection, with each process having a subsequent process set, representing the subsequent optional branches corresponding to the current process. Each process can be achieved through different processes. For example, tire assembly can be completed by different tire assembly units, and the assembly equipment and consumables of different assembly units may also differ. Therefore, the process data structure needs a "process set" to describe the selectable process methods for the current process. The process data structure includes the construction station of the current process, the process time, and the resource set required by the current process. The resource set data structure describes the quantity of current resources required by the process.

[0128] Resource set: The resource set describes all the resources needed in this event. Note that this includes not only consumable resources such as materials, but also main components such as the car body, doors, and central control, as well as production lines, workstations, other production tools used in the manufacturing process, and even the working hours of production line workers.

[0129] In the resource data modeling of this project, we divided resources into three categories: workshop consumable public resources, workshop tool-type public resources, and vehicle-related resources.

[0130] Typically, main components such as the car body, doors, and central control are packaged as vehicle-mounted resources, while assembly units, AGVs, and buffer parking spaces are considered as workshop tool-type public resources, and line-side materials are considered as workshop consumable public resources.

[0131] Result Set: The result set is what we described as the particles in the first section. Each particle represents a result set. Based on the content of the result set, we can describe the assembly unit sequence and time required for each component of each vehicle, and also describe the production sequence of each assembly unit and the vehicles produced from another perspective. We designed the result set as follows:

[0132] Each result in the result set is the finest-grained element that can describe the result, i.e., a collection of each process. However, unlike the process data structure described above, the result set necessarily has the selected process, the start time of the process, and the duration of the process determined. Therefore, the result set is the collection of processes with determined processes, start times, and execution times, after the event determines the process and the process determines the process.

[0133] Constraint Set: As the name suggests, a constraint set is a collection of data constraints applied to various aspects of the production process due to the characteristics of automobile manufacturing. For example, our constraint set includes the following:

[0134] 1. Constraints on the quantity of consumable resources consumed;

[0135] 2. Regarding the constraints on the use of shared resources, it should be noted that some assembly units support simultaneous production of multiple vehicles. Therefore, there may be multiple vehicles working at the same time in an assembly unit. The constraints here require special handling for the number of vehicles produced at the same time.

[0136] 3. For vehicles with production end time constraints, limit the final production completion time;

[0137] 4. The production sequence of vehicles must not violate the process rules;

[0138] 5. Production intervals must not be less than the planned AGV transport time between workstations;

[0139] Regarding the generation of event sets:

[0140] Project{

[0141] Vin code: "xxxxx",

[0142] Production line entry time: "hh:mi:ss"

[0143] Latest completion time: "hh:mi:ss"

[0144] Process set: [Process 1:{

[0145] Preceding process name: "jobxx"

[0146] Optional processes (array): ["Assembly unit number", "Time taken", "Required resources"]

[0147] }; Process 2: {

[0148] Preceding process name: "jobxx"

[0149] Optional processes (array): ["Assembly unit number", "Time taken", "Required resources"]

[0150] }]

[0151] }

[0152] This data model is described using a JSON-formatted data structure. This data structure is used to describe a specific planned event, such as a vehicle to be produced with a specific code model in automobile production.

[0153] This plan includes the vehicle's VIN code, entry time into the production line, latest completion time, and process set. All times are accurate to the second and expressed in "hh:mi:ss" format.

[0154] The process set element is a JSON array that stores all available processes for executing the event (producing the car) in order. Note that a model of a vehicle may have multiple production paths. This is a tree structure that links processes together through "preceding processes".

[0155] The process set is also described in JSON format, encapsulating the current process name, the previous process name, and the set of optional processes for the current process. The optional execution processes are an array describing all feasible production methods for this process.

[0156] Each execution process includes the assembly unit number (production equipment), assembly time, required materials and quantities. Materials include installation materials and consumables.

[0157] Step S102: Arrange event sets to obtain first-generation particles. When the number of first-generation particles reaches a preset number, a group of first-generation particles is obtained. Each event set corresponds to one first-generation particle. Each first-generation particle includes at least one planned item. Each planned item includes at least one process set. Each process set includes at least one process.

[0158] Specifically, because it is a multi-line production line, there will be multiple process starting points in the process concentration.

[0159] There are also special scenarios that may arise when orchestrating event sets. The solutions are as follows:

[0160] 1) Ordered arrangement: In some cases, due to workshop conditions, it is impossible to adjust the current final assembly entry order, so the entry order will be locked. In this scenario, we can perform the optimization method for individual particles described in point 3 above for arrangement.

[0161] 2) Temporary insertion tasks: For temporary insertion tasks, considering that the vehicle sequence in the current production process cannot be rearranged, the initial particles can be generated at random positions of the inserted vehicles. Considering the feasibility of insertion, the insertion can be carried out in a concentrated manner with random order between the inserted vehicles. The subsequent particle swarm selection and optimization of individual particles are consistent with the original method.

[0162] Step S103: Optimize the first-generation particles to obtain the first-generation optimized particles;

[0163] Specifically, optimization begins with the initial particles, each optimized independently without interference. Since each particle corresponds to a different planned vehicle entry order, the possibility of convergence in optimization results for each particle is avoided.

[0164] Step S104: Evaluate the first-generation optimized particles to obtain the first-generation optimal particles;

[0165] Specifically, after all the first-generation particles have been optimized, the optimized first-generation particles are evaluated to obtain the best first-generation particle after the previous generation optimization.

[0166] Step S105: Repeat steps S103-S104 for a preset number of times to obtain the final optimal particle.

[0167] Specifically, starting with the second generation of optimization, there are slight differences from the first generation. In this generation, when selecting a process step, two processes are chosen for exchange. The position of this process is found to correspond to the selected process of the first-generation optimal particle. If the process's position is already consistent with the first-generation optimal particle, two processes to be replaced are randomly selected again. If the optimized process's position is consistent with the corresponding process position in the first-generation optimal particle, the optimization is retained with random probability, or the process is restored to its original position. Random probability can be understood as the program generating a random number between 0 and 1; if the result is less than 0.5, the process is executed; if it is greater, it is restored. The new generation of particles is evaluated to obtain a new first-generation optimal particle. It is then verified whether the first-generation optimal particle meets the production requirements or reaches the upper limit of the optimization generation. If it does, the calculation exits directly.

[0168] Optionally, a planned event is randomly selected from the event set, and all first processes of the planned event are obtained, wherein the first process is the process corresponding to the starting point of each process set in the planned event; the execution process of the first process is selected within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; based on the production preceding process of the process, the execution process that can be executed after the production preceding process of the process is randomly selected, wherein the production preceding process is the process before the main production process; the start time and end time of the execution process are determined, and the time occupancy of the assembly unit corresponding to the execution process is marked, and the completion time of the process is updated; when all process sets in the planned event of the event set are arranged, the first generation particle is obtained.

[0169] Optionally, in step S301, the optimization vector length, particle optimization rounds, and particle optimization target percentage are set. The optimization vector length represents the time difference between two processes in the same assembly unit and the distance between two processes in different assembly units. The optimization target percentage represents the percentage of the time consumed by the initial optimization particles relative to the total time consumed by the initial particles. The position refers to a production entity within a specific assembly unit. In step S302, based on the set vector length, two processes to be exchanged or moved are selected from the optimization stage particles. The optimization stage particles include the initial particles and the particles obtained from each optimization. The processes to be exchanged are any two processes in two assembly units of the same type, or any two processes in one assembly unit. In step S303, the exchanged optimization stage particles are re-integrated to obtain the final completion time of each process. In step S304, the integrated optimization stage particles are detected, including: when the integration... When the optimized particles meet the production constraints, optimized particles are obtained; when the integrated optimized particles do not meet the production constraints, steps S301-S304 are repeated; in step S305, it is determined whether to retain the optimized particles, including: when the total consumption time of the optimized particles is less than that of the optimized particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than that of the optimized particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed to be the first-generation optimized particles.

[0170] Optionally, when two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

[0171] Optionally, step S501 involves scheduling the time of each process starting from the first process, where the first process is the process corresponding to the starting point of each process set in the planned items. This includes: updating the start time and end time of the process when there is no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned items corresponding to the pre-assembly process, where the pre-assembly process is the process preceding the process on the assembly unit; repeating step S501 until all processes are scheduled to obtain the final completion time of each process.

[0172] Optionally, the retention probability is calculated using the following formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0173] Optionally, calculate the fitness of all initial optimized particles, and select the initial optimized particle with the highest fitness as the initial optimal particle. The calculation formula is as follows: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0174] Optionally, based on the set vector length, two processes to be swapped or moved are selected, including: arbitrarily selecting two processes and comparing their positions with the positions of the processes swapped during the initial optimal particle optimization; if the positions of the two processes are the same as those of the processes swapped during the initial optimal particle optimization, two processes are reselected; if the positions of the two processes after swapping are the same as those of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0175] This invention provides a processor for running a program, wherein the program executes the hybrid production execution design method during runtime.

[0176] Specifically, a hybrid production execution design approach includes:

[0177] Step S101: Generate an event set, which includes the production entity identifier, online time, production constraints, and process set;

[0178] Specifically, each particle (event set) is defined as representing an executable production plan for a given day, i.e., an outcome, regardless of whether the outcome is actually executable. The core content of this outcome is the entry and exit time of each vehicle to be assembled in each assembly unit, the production time, and the transportation time between assembly units. It can also be described as the production sequence of each assembly unit for the day, along with the corresponding specific times and materials used.

[0179] The data involved in the automobile assembly process is encapsulated into four categories: event data, resource data, result data, and constraints.

[0180] Event data describes all the events that the plan will execute. An event is a decomposition of the smallest complete event for this plan. For example, in the car manufacturing process, the entire process of "assembling a car" is defined as an event. Correspondingly, each particle is the calculation result of completing a set of events.

[0181] Due to the complexity of events, the event model needs to be decomposed into a data model. An event consists of vehicle identifier, online time, latest completion requirement, vehicle-following resource set, and process set. The vehicle-following resource set is a type of resource set.

[0182] Process set: A process set is a decomposition of events, describing all the processes required to produce a car. The data model for a process includes main components, process sets, and subsequent processes. In traditional automotive production, in a mainline-branchline collaborative production model, the mainline is driven by the body structure as the primary component, while branchlines are driven by their respective assembled main components, such as doors, seats, center consoles, and chassis. The main component records the unique resource defining this mainline or branchline, and also connects a mainline or branchline production line.

[0183] Process Technology: In flexible manufacturing, processes are determined by different process paths, the sequence of processes can be changed, and different production line stations can be used depending on the production method. Therefore, the process set is actually a tree-structured collection, with each process having a subsequent process set, representing the subsequent optional branches corresponding to the current process. Each process can be achieved through different processes. For example, tire assembly can be completed by different tire assembly units, and the assembly equipment and consumables of different assembly units may also differ. Therefore, the process data structure needs a "process set" to describe the selectable process methods for the current process. The process data structure includes the construction station of the current process, the process time, and the resource set required by the current process. The resource set data structure describes the quantity of current resources required by the process.

[0184] Resource set: The resource set describes all the resources needed in this event. Note that this includes not only consumable resources such as materials, but also main components such as the car body, doors, and central control, as well as production lines, workstations, other production tools used in the manufacturing process, and even the working hours of production line workers.

[0185] In the resource data modeling of this project, we divided resources into three categories: workshop consumable public resources, workshop tool-type public resources, and vehicle-related resources.

[0186] Typically, main components such as the car body, doors, and central control are packaged as vehicle-mounted resources, while assembly units, AGVs, and buffer parking spaces are considered as workshop tool-type public resources, and line-side materials are considered as workshop consumable public resources.

[0187] Result Set: The result set is what we described as the particles in the first section. Each particle represents a result set. Based on the content of the result set, we can describe the assembly unit sequence and time required for each component of each vehicle, and also describe the production sequence of each assembly unit and the vehicles produced from another perspective. We designed the result set as follows:

[0188] Each result in the result set is the finest-grained element that can describe the result, i.e., a collection of each process. However, unlike the process data structure described above, the result set necessarily has the selected process, the start time of the process, and the duration of the process determined. Therefore, the result set is the collection of processes with determined processes, start times, and execution times, after the event determines the process and the process determines the process.

[0189] Constraint Set: As the name suggests, a constraint set is a collection of data constraints applied to various aspects of the production process due to the characteristics of automobile manufacturing. For example, our constraint set includes the following:

[0190] 1. Constraints on the quantity of consumable resources consumed;

[0191] 2. Regarding the constraints on the use of shared resources, it should be noted that some assembly units support simultaneous production of multiple vehicles. Therefore, there may be multiple vehicles working at the same time in an assembly unit. The constraints here require special handling for the number of vehicles produced at the same time.

[0192] 3. For vehicles with production end time constraints, limit the final production completion time;

[0193] 4. The production sequence of vehicles must not violate the process rules;

[0194] 5. Production intervals must not be less than the planned AGV transport time between workstations;

[0195] Regarding the generation of event sets:

[0196] Project{

[0197] Vin code: "xxxxx",

[0198] Production line entry time: "hh:mi:ss"

[0199] Latest completion time: "hh:mi:ss"

[0200] Process set: [Process 1:{

[0201] Preceding process name: "jobxx"

[0202] Optional processes (array): ["Assembly unit number", "Time taken", "Required resources"]

[0203] }; Process 2: {

[0204] Preceding process name: "jobxx"

[0205] Optional processes (array): ["Assembly unit number", "Time taken", "Required resources"]

[0206] }]

[0207] }

[0208] This data model is described using a JSON-formatted data structure. This data structure is used to describe a specific planned event, such as a vehicle to be produced with a specific code model in automobile production.

[0209] This plan includes the vehicle's VIN code, entry time into the production line, latest completion time, and process set. All times are accurate to the second and expressed in "hh:mi:ss" format.

[0210] The process set element is a JSON array that stores all available processes for executing the event (producing the car) in order. Note that a model of a vehicle may have multiple production paths. This is a tree structure that links processes together through "preceding processes".

[0211] The process set is also described in JSON format, encapsulating the current process name, the previous process name, and the set of optional processes for the current process. The optional execution processes are an array describing all feasible production methods for this process.

[0212] Each execution process includes the assembly unit number (production equipment), assembly time, required materials and quantities. Materials include installation materials and consumables.

[0213] Step S102: Arrange event sets to obtain first-generation particles. When the number of first-generation particles reaches a preset number, a group of first-generation particles is obtained. Each event set corresponds to one first-generation particle. Each first-generation particle includes at least one planned item. Each planned item includes at least one process set. Each process set includes at least one process.

[0214] Specifically, because it is a multi-line production line, there will be multiple process starting points in the process concentration.

[0215] There are also special scenarios that may arise when orchestrating event sets. The solutions are as follows:

[0216] 1) Ordered arrangement: In some cases, due to workshop conditions, it is impossible to adjust the current final assembly entry order, so the entry order will be locked. In this scenario, we can perform the optimization method for individual particles described in point 3 above for arrangement.

[0217] 2) Temporary insertion tasks: For temporary insertion tasks, considering that the vehicle sequence in the current production process cannot be rearranged, the initial particles can be generated at random positions of the inserted vehicles. Considering the feasibility of insertion, the insertion can be carried out in a concentrated manner with random order between the inserted vehicles. The subsequent particle swarm selection and optimization of individual particles are consistent with the original method.

[0218] Step S103: Optimize the first-generation particles to obtain the first-generation optimized particles;

[0219] Specifically, optimization begins with the initial particles, each optimized independently without interference. Since each particle corresponds to a different planned vehicle entry order, the possibility of convergence in optimization results for each particle is avoided.

[0220] Step S104: Evaluate the first-generation optimized particles to obtain the first-generation optimal particles;

[0221] Specifically, after all the first-generation particles have been optimized, the optimized first-generation particles are evaluated to obtain the best first-generation particle after the previous generation optimization.

[0222] Step S105: Repeat steps S103-S104 for a preset number of times to obtain the final optimal particle.

[0223] Specifically, starting with the second generation of optimization, there are slight differences from the first generation. In this generation, when selecting a process step, two processes are chosen for exchange. The position of this process is found to correspond to the selected process of the first-generation optimal particle. If the process's position is already consistent with the first-generation optimal particle, two processes to be replaced are randomly selected again. If the optimized process's position is consistent with the corresponding process position in the first-generation optimal particle, the optimization is retained with random probability, or the process is restored to its original position. Random probability can be understood as the program generating a random number between 0 and 1; if the result is less than 0.5, the process is executed; if it is greater, it is restored. The new generation of particles is evaluated to obtain a new first-generation optimal particle. It is then verified whether the first-generation optimal particle meets the production requirements or reaches the upper limit of the optimization generation. If it does, the calculation exits directly.

[0224] Optionally, a planned event is randomly selected from the event set, and all first processes of the planned event are obtained, wherein the first process is the process corresponding to the starting point of each process set in the planned event; the execution process of the first process is selected within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; based on the production preceding process of the process, the execution process that can be executed after the production preceding process of the process is randomly selected, wherein the production preceding process is the process before the main production process; the start time and end time of the execution process are determined, and the time occupancy of the assembly unit corresponding to the execution process is marked, and the completion time of the process is updated; when all process sets in the planned event of the event set are arranged, the first generation particle is obtained.

[0225] Optionally, in step S301, the optimization vector length, particle optimization rounds, and particle optimization target percentage are set. The optimization vector length represents the time difference between two processes in the same assembly unit and the distance between two processes in different assembly units. The optimization target percentage represents the percentage of the time consumed by the initial optimization particles relative to the total time consumed by the initial particles. The position refers to a production entity within a specific assembly unit. In step S302, based on the set vector length, two processes to be exchanged or moved are selected from the optimization stage particles. The optimization stage particles include the initial particles and the particles obtained from each optimization. The processes to be exchanged are any two processes in two assembly units of the same type, or any two processes in one assembly unit. In step S303, the exchanged optimization stage particles are re-integrated to obtain the final completion time of each process. In step S304, the integrated optimization stage particles are detected, including: when the integration... When the optimized particles meet the production constraints, optimized particles are obtained; when the integrated optimized particles do not meet the production constraints, steps S301-S304 are repeated; in step S305, it is determined whether to retain the optimized particles, including: when the total consumption time of the optimized particles is less than that of the optimized particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than that of the optimized particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed to be the first-generation optimized particles.

[0226] Optionally, when two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

[0227] Optionally, step S501 involves scheduling the time of each process starting from the first process, where the first process is the process corresponding to the starting point of each process set in the planned items. This includes: updating the start time and end time of the process when there is no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned items corresponding to the pre-assembly process, where the pre-assembly process is the process preceding the process on the assembly unit; repeating step S501 until all processes are scheduled to obtain the final completion time of each process.

[0228] Optionally, the retention probability is calculated using the following formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0229] Optionally, calculate the fitness of all initial optimized particles, and select the initial optimized particle with the highest fitness as the initial optimal particle. The calculation formula is as follows: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0230] Optionally, based on the set vector length, two processes to be swapped or moved are selected, including: arbitrarily selecting two processes and comparing their positions with the positions of the processes swapped during the initial optimal particle optimization; if the positions of the two processes are the same as those of the processes swapped during the initial optimal particle optimization, two processes are reselected; if the positions of the two processes after swapping are the same as those of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0231] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: generating an event set, the event set including a production entity identifier, a launch time, production constraints, and a process set; arranging the event set to obtain initial particles; when the initial particles reach a preset number, an initial particle swarm is obtained, wherein each event set corresponds to one initial particle, and the initial particle includes at least one planned item, the planned item includes at least one process set, and the process set includes at least one process; step S103, optimizing the initial particles to obtain initial optimized particles; step S104, evaluating the initial optimized particles to obtain initial optimal particles; repeating steps S103-S104 up to a preset number of times to obtain the final optimal particles.

[0232] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0233] Optionally, a planned event is randomly selected from the event set, and all first processes of the planned event are obtained, wherein the first process is the process corresponding to the starting point of each process set in the planned event; the execution process of the first process is selected within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; based on the production preceding process of the process, the execution process that can be executed after the production preceding process of the process is randomly selected, wherein the production preceding process is the process before the main production process; the start time and end time of the execution process are determined, and the time occupancy of the assembly unit corresponding to the execution process is marked, and the completion time of the process is updated; when all process sets in the planned event of the event set are arranged, the first generation particle is obtained.

[0234] Optionally, in step S301, the optimization vector length, particle optimization rounds, and particle optimization target percentage are set. The optimization vector length represents the time difference between two processes in the same assembly unit and the distance between two processes in different assembly units. The optimization target percentage represents the percentage of the time consumed by the initial optimization particles relative to the total time consumed by the initial particles. The position refers to a production entity within a specific assembly unit. In step S302, based on the set vector length, two processes to be exchanged or moved are selected from the optimization stage particles. The optimization stage particles include the initial particles and the particles obtained from each optimization. The processes to be exchanged are any two processes in two assembly units of the same type, or any two processes in one assembly unit. In step S303, the exchanged optimization stage particles are re-integrated to obtain the final completion time of each process. In step S304, the integrated optimization stage particles are detected, including: when the integration... When the optimized particles meet the production constraints, optimized particles are obtained; when the integrated optimized particles do not meet the production constraints, steps S301-S304 are repeated; in step S305, it is determined whether to retain the optimized particles, including: when the total consumption time of the optimized particles is less than that of the optimized particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than that of the optimized particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed to be the first-generation optimized particles.

[0235] Optionally, when two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

[0236] Optionally, step S501 involves scheduling the time of each process starting from the first process, where the first process is the process corresponding to the starting point of each process set in the planned items. This includes: updating the start time and end time of the process when there is no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned items corresponding to the pre-assembly process, where the pre-assembly process is the process preceding the process on the assembly unit; repeating step S501 until all processes are scheduled to obtain the final completion time of each process.

[0237] Optionally, the retention probability is calculated using the following formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0238] Optionally, calculate the fitness of all initial optimized particles, and select the initial optimized particle with the highest fitness as the initial optimal particle. The calculation formula is as follows: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0239] Optionally, based on the set vector length, two processes to be swapped or moved are selected, including: arbitrarily selecting two processes and comparing their positions with the positions of the processes swapped during the initial optimal particle optimization; if the positions of the two processes are the same as those of the processes swapped during the initial optimal particle optimization, two processes are reselected; if the positions of the two processes after swapping are the same as those of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0240] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: generating an event set, the event set including a production entity identifier, online time, production constraints, and a process set; arranging the event set to obtain initial particles, and obtaining an initial particle swarm when the initial particles reach a preset number, wherein each event set corresponds to one initial particle, the initial particle includes at least one planned item, the planned item includes at least one process set, and the process set includes at least one process; step S103, optimizing the initial particles to obtain initial optimized particles; step S104, evaluating the initial optimized particles to obtain initial optimal particles; repeating steps S103-S104 up to a preset number of times to obtain the final optimal particles.

[0241] Optionally, a planned event is randomly selected from the event set, and all first processes of the planned event are obtained, wherein the first process is the process corresponding to the starting point of each process set in the planned event; the execution process of the first process is selected within the starting process group, wherein the starting process group contains all execution processes that can be executed at the starting point of the process set; based on the production preceding process of the process, the execution process that can be executed after the production preceding process of the process is randomly selected, wherein the production preceding process is the process before the main production process; the start time and end time of the execution process are determined, and the time occupancy of the assembly unit corresponding to the execution process is marked, and the completion time of the process is updated; when all process sets in the planned event of the event set are arranged, the first generation particle is obtained.

[0242] Optionally, in step S301, the optimization vector length, particle optimization rounds, and particle optimization target percentage are set. The optimization vector length represents the time difference between two processes in the same assembly unit and the distance between two processes in different assembly units. The optimization target percentage represents the percentage of the time consumed by the initial optimization particles relative to the total time consumed by the initial particles. The position refers to a production entity within a specific assembly unit. In step S302, based on the set vector length, two processes to be exchanged or moved are selected from the optimization stage particles. The optimization stage particles include the initial particles and the particles obtained from each optimization. The processes to be exchanged are any two processes in two assembly units of the same type, or any two processes in one assembly unit. In step S303, the exchanged optimization stage particles are re-integrated to obtain the final completion time of each process. In step S304, the integrated optimization stage particles are detected, including: when the integration... When the optimized particles meet the production constraints, optimized particles are obtained; when the integrated optimized particles do not meet the production constraints, steps S301-S304 are repeated; in step S305, it is determined whether to retain the optimized particles, including: when the total consumption time of the optimized particles is less than that of the optimized particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than that of the optimized particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed to be the first-generation optimized particles.

[0243] Optionally, when two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

[0244] Optionally, step S501 involves scheduling the time of each process starting from the first process, where the first process is the process corresponding to the starting point of each process set in the planned items. This includes: updating the start time and end time of the process when there is no pre-assembly process or the pre-assembly process has been scheduled; when the pre-assembly process of the process has not been scheduled, obtaining the first process of the planned items corresponding to the pre-assembly process, where the pre-assembly process is the process preceding the process on the assembly unit; repeating step S501 until all processes are scheduled to obtain the final completion time of each process.

[0245] Optionally, the retention probability is calculated using the following formula: ,in, To preserve probability, To optimize particle execution time, The execution time of the first-generation particles. The initial execution time.

[0246] Optionally, calculate the fitness of all initial optimized particles, and select the initial optimized particle with the highest fitness as the initial optimal particle. The calculation formula is as follows: ,in, For fitness, To optimize the final completion time of the first-generation particles, To optimize the weight of the final completion time of the first-generation particles in the final evaluation, The imbalance of machine load. The initial optimization of particle loading imbalance weights, = (Current algebra / optimized algebra upper limit), .

[0247] Optionally, based on the set vector length, two processes to be swapped or moved are selected, including: arbitrarily selecting two processes and comparing their positions with the positions of the processes swapped during the initial optimal particle optimization; if the positions of the two processes are the same as those of the processes swapped during the initial optimal particle optimization, two processes are reselected; if the positions of the two processes after swapping are the same as those of the processes swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

[0248] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0249] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0250] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0251] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0252] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0253] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0254] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0255] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0256] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0257] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A hybrid production execution design method, characterized in that, include: Generate an event set, which includes the production entity identifier, online time, production constraints, and process set; Arrange the event set to obtain the first generation particle. When the first generation particle reaches a preset number, the first generation particle group is obtained. Each event set corresponds to one first generation particle. The first generation particle includes at least one planned item. The planned item includes at least one process set. The process set includes at least one process. Step S103: Optimize the first-generation particles to obtain the first-generation optimized particles; Step S103 includes: Step S301, setting the optimization vector length, particle optimization rounds, and particle optimization target percentage, wherein the optimization vector length is the distance between two processes on different assembly units, and the optimization target percentage is the percentage of the consumption time of the first-generation optimization particles relative to the consumption time of the first-generation particles, wherein the position is a certain assembly unit where a certain production entity is located; Step S302, selecting two processes to be exchanged or moved in the optimization stage particles according to the set optimization vector length, wherein the optimization stage particles include the first-generation particles and the particles obtained in each optimization, and the processes to be exchanged are any two processes on two assembly units of the same type, or any two processes on one assembly unit; Step S303, re-integrating the exchanged optimization stage particles to obtain the final completion time of each process; Step S304, detecting the integrated optimization stage particles, including: when the integrated optimization stage particles meet the production requirements... When production constraints are met, the optimized particles are obtained. When the integrated optimized stage particles do not meet production constraints, steps S301-S304 are repeated. Step S305 determines whether the optimized particles should be retained, including: when the total consumption time of the optimized particles is less than the optimized stage particles obtained in the previous optimization, the optimized particles are recorded as the latest value, and the optimized stage particles obtained in the previous optimization are retained as historical records; when the total consumption time of the optimized particles is greater than the optimized stage particles obtained in the previous optimization, it is determined whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, this optimization is ignored; wherein, when the first optimization is performed, the optimized stage particles obtained in the previous optimization are the first-generation particles; steps S302-S305 are repeated until the optimized stage particles reach the number of particle optimization rounds or reach the particle optimization target percentage, and the latest value is confirmed to be the first-generation optimized particles. Step S104: Evaluate the first-generation optimized particles to obtain the first-generation optimal particles; Repeat steps S103-S104 for a preset number of times to obtain the final optimal particle.

2. The method according to claim 1, characterized in that, Arrange the event set to obtain the first-generation particles. When the number of first-generation particles reaches a preset number, a first-generation particle swarm is obtained, including: Randomly select a planned event from the event set and obtain all the first steps of the planned event, wherein the first step is the step corresponding to the starting point of each set of steps in the planned event; Select the execution process of the first operation within the starting process group, wherein the starting process group consists of all the execution processes that can be executed at the starting point of the operation set; Based on the preceding production process of the process, the execution process that can be executed after the preceding production process is randomly selected for the process, wherein the preceding production process is the process before the process of the main production body; Determine the start and end times of the execution process, mark the time occupancy of the assembly unit corresponding to the execution process, and update the completion time of the process. The first-generation particle is obtained after all the process sets in the planned events of the event set have been arranged.

3. The method according to claim 1, characterized in that, Step S302 includes: When two processes to be exchanged are moved, one of the processes to be exchanged moves in front of the other process to be exchanged.

4. The method according to claim 1, characterized in that, Step S303 includes: Step S501: Starting from the first process, schedule the time of the process, wherein the first process is the process corresponding to the starting point of each process set in the planned item, including: when the process has no pre-assembly process or the pre-assembly process is scheduled, update the start time and end time of the process; when the pre-assembly process of the process is not scheduled, obtain the first process of the planned item corresponding to the pre-assembly process, wherein the pre-assembly process is the process preceding the process on the assembly unit; Repeat step S501 until all processes are arranged, and obtain the final completion time of each process.

5. The method according to claim 1, characterized in that, Step S305 includes: The retention probability is calculated using the following formula: ,in, The retention probability is... For the optimized particle execution time, The execution time of the first-generation particle. The initial execution time.

6. The method according to claim 1, characterized in that, Step S104 includes: Calculate the fitness of all the initial optimized particles, and select the initial optimized particle with the highest fitness as the initial optimal particle. The calculation formula is as follows: ,in, For the fitness, To optimize the final completion time of the first-generation particles, The weight of the final completion time of the first-generation optimized particles in the final evaluation. The imbalance of machine load. The weight of the load imbalance of the first-generation optimized particles. = (Current algebra / optimized algebra upper limit), .

7. The method according to claim 1, characterized in that, Repeat steps S103-S104 up to a preset number of times to obtain the final optimal particle, including: Based on the set vector length, select two processes to be swapped or moved, including: Two processes are randomly selected, and their positions are compared with the positions of the processes swapped during the initial optimal particle optimization. If the positions of the two processes are the same as those swapped during the initial optimal particle optimization, two processes are selected again. If the positions of the two processes after swapping are the same as those swapped during the initial optimal particle optimization, a preset probability is used to determine whether to retain or restore them.

8. An execution design apparatus for hybrid production, characterized in that, include: A generation unit is used to generate an event set, which includes a production entity identifier, online time, production constraints, and a process set. The arrangement unit is used to arrange the event set to obtain the first generation particle. When the first generation particle reaches a preset number, the first generation particle group is obtained. Each event set corresponds to one first generation particle. The first generation particle includes at least one planned item. The planned item includes at least one process set. The process set includes at least one process. An optimization unit is used to execute step S103 to optimize the first-generation particles and obtain first-generation optimized particles. The optimization unit includes: Set a subunit for executing step S301, setting the optimization vector length, the number of particle optimization rounds, and the particle optimization target percentage, wherein the optimization vector length is the distance between the positions of two processes on different assembly units, the optimization target percentage is the percentage of the consumption time of the first-generation optimization particles to the consumption time of the first-generation particles, and the position is a certain assembly unit where a certain production entity is located. The exchange subunit is used to execute step S302, which selects two processes to be exchanged or moved in the optimization stage particles according to the set optimization vector length. The optimization stage particles include the initial particles and the particles obtained in each optimization. The processes to be exchanged are any two processes on two assembly units of the same type, or any two processes on one assembly unit. An integration subunit is used to perform step S303, which re-integrates the exchanged optimization stage particles to obtain the final completion time of each process. The detection subunit is used to execute step S304, which detects the integrated optimization stage particles, including: when the integrated optimization stage particles meet the production constraints, the optimized particles are obtained; when the integrated optimization stage particles do not meet the production constraints, steps S301-S304 are repeated. The judgment subunit is used to execute step S305, which determines whether the optimized particles should be retained. This includes: when the total consumption time of the optimized particles is less than the optimized stage particles obtained in the previous optimization, recording the optimized particles as the latest value and retaining the optimized stage particles obtained in the previous optimization as historical records; when the total consumption time of the optimized particles is greater than the optimized stage particles obtained in the previous optimization, determining whether to retain the optimized particles as the latest value based on the retention probability, including: when it is determined based on the retention probability that the optimized particles are not retained as the latest value, ignoring this optimization; wherein, when performing the first optimization, the optimized stage particles obtained in the previous optimization are the initial particles; The confirmation subunit is used to repeatedly execute steps S302-S305 until the particle in the optimization stage reaches the number of particle optimization rounds or the percentage of the particle optimization target, and to confirm that the latest value is the initial optimized particle. An evaluation unit is used to perform step S104 to evaluate the first-generation optimized particles and obtain the first-generation optimal particles. An execution unit is used to repeatedly execute steps S103-S104 up to a preset number of times to obtain the final optimal particle.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform an execution design method for hybrid production as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including an execution design method for performing a hybrid production as described in any one of claims 1 to 7.

Images