A multi-station collaborative scheduling method for a footwear production line

Abstract

The application provides a kind of shoes production line multi-station collaborative scheduling method, it is related to industrial production scheduling optimization technical field, including the following steps: collecting shoes multi-source data and carrying out pretreatment, generate shoe type process data set, calculate the complexity index of different shoe types based on shoe type process data set, and generate the dynamic processing complexity parameter of corresponding shoe type;Collect the multi-source data of each station of shoes production line, construct multi-station state matrix, based on dynamic processing complexity parameter and multi-station state matrix, the standard processing tempo of each station is dynamically corrected, and the real-time processing tempo is obtained.The application constructs multi-objective collaborative scheduling mechanism based on dynamic processing complexity parameter, order risk constraint parameter and die conflict constraint parameter, improves the station collaborative efficiency, scheduling real-time performance and production resource utilization rate of shoes production line in complex dynamic production environment.

Description

Technical Field

[0001] This invention relates to the field of industrial production scheduling optimization technology, and more specifically, to a multi-station collaborative scheduling method for a footwear production line. Background Technology

[0002] With the development of digital and intelligent technologies in the manufacturing industry, footwear manufacturers are gradually shifting from traditional large-scale production of a single product category to a multi-category, small-batch, and flexible production model. In the footwear production process, due to significant differences in shoe structure, process routes, and processing difficulty, the processing rhythm of different orders at workstations such as cutting, sewing, molding, and packaging often exhibits strong fluctuations. Existing footwear production lines typically integrate production execution systems, equipment monitoring systems, and workstation sensors to collect real-time data on production tasks, equipment status, and order progress, and to schedule and control the processing tasks at each workstation based on preset process parameters. Simultaneously, some footwear manufacturers have begun to introduce intelligent optimization methods such as heuristic scheduling algorithms, genetic algorithms, particle swarm optimization, and gray wolf optimization algorithms to solve problems related to production task allocation, workstation sequencing, and resource allocation, thereby improving the overall operating efficiency of the production line, reducing the risk of order delays, and increasing equipment utilization.

[0003] However, existing footwear production line scheduling technologies, in complex and dynamic production environments, typically rely primarily on fixed standard processing cycles or static process parameters for task allocation, failing to fully reflect the dynamic processing complexity variations of different shoe models during actual production. Furthermore, in multi-station collaborative production, factors such as real-time workstation load status, mold occupancy relationships, order rework risks, and real-time energy consumption are highly coupled, and existing scheduling methods have relatively limited collaborative modeling capabilities for multi-source dynamic constraint information. When the production line experiences frequent order changes, mold sharing conflicts, or workstation cycle time fluctuations, it can easily lead to task backlogs at some workstations, intensified competition for mold resources, and production cycle imbalances, thereby affecting overall production efficiency and scheduling stability. Moreover, traditional optimization algorithms, when solving multi-objective dynamic scheduling problems, often suffer from insufficient local optimization capabilities, limited constraint adaptability, and unstable dynamic search performance, making it difficult to meet the application requirements of real-time collaborative scheduling of multiple workstations in flexible footwear production scenarios. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention is proposed. A first aspect of this invention provides a multi-station collaborative scheduling method for a footwear production line, comprising the following specific steps:

[0005] Collect multi-source footwear data and preprocess it to generate a footwear process dataset. Calculate the complexity index of different footwear types based on the footwear process dataset and generate dynamic processing complexity parameters for the corresponding footwear types.

[0006] Collect multi-source data from each workstation of the footwear production line, construct a multi-workstation state matrix, and dynamically correct the standard processing cycle of each workstation based on dynamic processing complexity parameters and the multi-workstation state matrix to obtain the real-time processing cycle.

[0007] Based on historical production data, real-time operation data, current processing progress, process path and mold usage status, order risk constraint parameters and mold conflict constraint parameters are comprehensively calculated. Based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters and workstation real-time energy consumption data, a multi-objective collaborative scheduling objective function is constructed.

[0008] An improved gray wolf optimization algorithm is used to iteratively solve the objective function of multi-objective collaborative scheduling to obtain the optimal collaborative scheduling scheme for the footwear production line. The optimal collaborative scheduling scheme is then distributed to the corresponding production execution equipment, and multi-source data from the production line is continuously collected and uploaded to the database for storage.

[0009] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of collecting multi-source footwear data and preprocessing it to generate a footwear process dataset includes the following steps:

[0010] Collect footwear structure data, material data, process path data, and production task data corresponding to footwear orders;

[0011] Collect process flow information, workstation processing sequence information, and production batch information for footwear orders, and establish the relationship between orders and process paths;

[0012] The collected multi-source footwear data is preprocessed, and footwear processing feature parameters are extracted based on the preprocessed multi-source footwear data;

[0013] The extracted shoe model processing feature parameters are normalized and feature encoded to generate a shoe model process dataset.

[0014] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of calculating the complexity index of different footwear types based on the footwear process dataset and generating dynamic processing complexity parameters for the corresponding footwear types includes the following steps:

[0015] Based on the shoe design process dataset, a shoe design complexity evaluation model is constructed to quantitatively analyze the structural complexity, material processing complexity, and process processing complexity of different shoe designs, and to calculate the shoe design complexity index.

[0016] Based on the shoe structure parameters in the shoe structure data set, we analyze the differences in shoe piece splicing complexity, stitching structure complexity and spatial structure complexity among different shoe types, and generate shoe structure complexity parameters.

[0017] Based on the material parameters in the shoe model process dataset, we analyze the differences in material cutting difficulty, material composite processing difficulty, and material processing stability among different shoe models, and generate material processing complexity parameters.

[0018] Based on the process path parameters in the shoe model process dataset, analyze the process switching frequency, special process ratio, and workstation collaboration complexity in the corresponding process flow of different shoe models to generate process processing complexity parameters.

[0019] Based on the structural complexity parameters, material processing complexity parameters, and technological processing complexity parameters of the shoe type, a shoe type complexity evaluation model is constructed to quantify the comprehensive processing complexity of different shoe types and generate the complexity index of the corresponding shoe type.

[0020] By combining historical production data on workstation processing time, processing cycle time, and rework records, a dynamic complexity correction coefficient applicable to the current production environment is calculated.

[0021] Based on the historical processing time of each workstation, the deviation between the actual processing time and the standard processing time of the corresponding shoe model at each workstation is calculated, and the processing time deviation parameter is generated.

[0022] Based on historical actual processing rhythm and standard processing rhythm, analyze the rhythm fluctuation of the corresponding shoe model in different work stations, and generate rhythm deviation parameters;

[0023] Based on historical rework records, the rework occurrence of the corresponding shoe model in different workstations is statistically analyzed, and rework impact parameters are generated.

[0024] Based on the processing time deviation parameter, cycle time deviation parameter, and rework impact parameter, the deviation between the shoe complexity index and the actual production performance under the current production environment is analyzed, and a dynamic complexity correction coefficient is generated.

[0025] Based on the complexity index and dynamic complexity correction coefficient of the shoe type, the dynamic processing complexity parameters of the corresponding shoe type are generated.

[0026] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of collecting multi-source data from each station of the footwear production line and constructing a multi-station state matrix includes the following steps:

[0027] Multi-source data from each workstation on the footwear production line is collected and preprocessed. Based on the preprocessed multi-source data, state feature parameters characterizing the operating status of the workstation are extracted.

[0028] Based on the state characteristic parameters corresponding to each workstation, a multi-workstation state matrix is ​​constructed to represent the real-time operating status of the production line.

[0029] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of dynamically correcting the standard processing cycle time of each station based on dynamic processing complexity parameters and a multi-station state matrix to obtain the real-time processing cycle time includes the following steps:

[0030] Obtain the standard processing cycle time for each workstation and establish the association between the standard processing cycle time of each workstation and the corresponding shoe model processing task;

[0031] Based on dynamic processing complexity parameters, we analyze the changes in processing difficulty of different shoe types in corresponding workstations and calculate the complexity influence coefficient of shoe type complexity on workstation processing time.

[0032] Based on the multi-station status matrix, the real-time operating status parameters of each station are extracted, and the influence of the station operating status on the processing cycle time is analyzed.

[0033] Based on the degree of influence of the workstation's operating status on the processing cycle time, corresponding workstation status influence parameters are generated;

[0034] Based on the complexity influence coefficient and the station status influence parameter, the standard processing cycle time of each station is dynamically corrected to obtain the real-time processing cycle time of the corresponding station.

[0035] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of comprehensively calculating order risk constraint parameters and mold conflict constraint parameters based on historical production data, real-time operation data, current processing progress, process path, and mold usage status includes the following steps:

[0036] Based on historical production data and real-time operation data, analyze the rework risk and delay risk of each order in the production process, calculate the rework risk value of each order, and generate order risk constraint parameters based on the rework risk value.

[0037] Based on the current processing progress, process path, and mold usage status, predict the mold occupancy time window for each order and generate mold conflict constraint parameters.

[0038] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of constructing a multi-objective collaborative scheduling objective function based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters, and real-time energy consumption data of the workstations includes the following steps:

[0039] Based on real-time processing cycle time, calculate the estimated processing completion time and workstation task waiting time for each order in the current production state, and generate production cycle time optimization parameters;

[0040] Based on order risk constraint parameters, the delay risk and rework risk of different orders in the production process are analyzed, and order priority scheduling parameters are generated.

[0041] Based on mold conflict constraint parameters, we analyze the mold occupation conflict between different orders and the impact of mold switching, and generate mold resource coordination parameters.

[0042] Based on real-time energy consumption data of each workstation, calculate the unit processing energy consumption of each workstation under different processing tasks and the overall energy consumption level of the production line, and generate energy consumption optimization parameters.

[0043] Based on production cycle optimization parameters, order priority scheduling parameters, mold resource coordination parameters, and energy consumption optimization parameters, a multi-objective collaborative scheduling objective function is constructed for task allocation and workstation collaborative optimization in footwear production lines.

[0044] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of iteratively solving the multi-objective collaborative scheduling objective function using the improved gray wolf optimization algorithm to obtain the optimal collaborative scheduling scheme for the footwear production line includes the following steps:

[0045] Based on the multi-objective collaborative scheduling objective function, the task allocation order of each workstation, the order processing order, and the mold resource allocation result are used as the position coding information of the individual gray wolf to construct a collaborative scheduling population for the footwear production line;

[0046] Based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters and real-time energy consumption data of the workstation, the fitness value of the objective function of the scheduling scheme corresponding to each gray wolf individual is calculated, and the initial alpha wolf individual is determined according to the fitness value.

[0047] During the update of individual gray wolf positions, an order risk constraint guidance mechanism and a mold conflict penalty mechanism are introduced. The search priority of tasks corresponding to high-risk orders is dynamically adjusted according to the order risk constraint parameters, and the position constraints of gray wolf individuals with mold resource conflicts are corrected according to the mold conflict constraint parameters.

[0048] Based on the order risk constraint parameters, high-risk order tasks in each individual wolf are identified, and the search priority of high-risk order tasks in the location coding is adjusted according to the constraint weights corresponding to the order risk constraint parameters, so that high-risk order tasks will move to workstations with high processing capacity matching, short waiting time and low risk constraint cost during the location update process.

[0049] Based on the mold conflict constraint parameters, it is detected whether there is a situation where the same mold is occupied by multiple orders in the scheduling scheme corresponding to each individual gray wolf, and the order task, conflicting workstation and conflict time interval where mold resource conflict occurs are determined.

[0050] When a mold resource conflict is detected, the position code of the conflicting order task is constrained and corrected according to the mold conflict constraint parameters. The processing sequence, mold usage sequence and workstation allocation position of the conflicting order task are adjusted so that the corrected gray wolf individual meets the mold resource availability constraint.

[0051] After completing the order risk constraint guidance and mold conflict constraint correction, the fitness value of the corresponding scheduling scheme of the corrected gray wolf individual is recalculated, and the corrected gray wolf individual is used as the candidate individual for the next round of position update.

[0052] During the iterative update of individual gray wolves, a nonlinear dynamic convergence factor is used to adaptively adjust the position update step size of individual gray wolves, which improves the global search capability in the early stage of algorithm iteration and the local optimization capability in the later stage of algorithm iteration.

[0053] Obtain the current iteration number, the maximum iteration number, and the location encoding information corresponding to the current gray wolf individual. Based on the relationship between the current iteration number and the maximum iteration number, calculate the nonlinear dynamic convergence factor corresponding to the current iteration round.

[0054] Based on the nonlinear dynamic convergence factor, the position update step size control parameter of the gray wolf individual in the current iteration round is determined so that the position update step size changes nonlinearly with the iteration process.

[0055] In the early stages of algorithm iteration, the step size control parameter is updated based on a larger position to expand the search range of individual gray wolves in the task allocation order, order processing order and mold resource allocation space, thereby improving the algorithm's global search capability for different scheduling schemes.

[0056] In the later stages of algorithm iteration, the step size control parameter is updated based on the gradually decreasing position to narrow the search range of individual gray wolves around the current better scheduling scheme, thereby improving the fine optimization ability of local scheduling schemes.

[0057] The position update formula for individual gray wolves is adjusted based on a nonlinear dynamic convergence factor to generate the updated position code for each individual gray wolf in the current iteration.

[0058] Based on the changes in the fitness of the objective function for each individual gray wolf during the iteration process, the optimal scheduling individual is updated, and the optimal solution of the objective function is output when the preset iteration termination condition is met.

[0059] Obtain the objective function fitness value of the scheduling scheme for each individual gray wolf in the current iteration round, and compare it with the objective function fitness value of the corresponding gray wolf in the previous iteration round to determine the fitness change of each individual gray wolf.

[0060] Based on the fitness values ​​of each individual gray wolf, the gray wolf with the best fitness in the current iteration is selected and used as a candidate optimal scheduling individual.

[0061] The candidate optimal scheduler is compared with the optimal scheduler saved in the historical iteration. When the fitness value of the candidate optimal scheduler is better than that of the historical optimal scheduler, the optimal scheduler and its corresponding position encoding information are updated.

[0062] Based on the updated optimal scheduler, record its corresponding workstation task allocation order, order processing order, mold resource allocation result and objective function fitness value;

[0063] When the number of iterations reaches the preset maximum number of iterations, the fitness value of the objective function corresponding to the currently saved optimal scheduling individual is output as the optimal solution of the objective function.

[0064] Based on the optimal solution of the objective function, the optimal collaborative scheduling scheme for the footwear production line is generated.

[0065] As a preferred embodiment of the multi-station collaborative scheduling method for footwear production lines described in this invention, the step of distributing the optimal collaborative scheduling scheme to the corresponding production execution equipment and continuously collecting multi-source data from the production line and uploading it to the database for storage includes the following steps:

[0066] The optimal collaborative scheduling scheme is sent to the corresponding production execution equipment, and each workstation equipment is controlled to execute production tasks according to the scheduling scheme.

[0067] Multi-source data is collected in real time during the execution of production tasks as experience data and uploaded to the database for storage.

[0068] A second aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the above-described online voltage monitoring method for a glue-impregnated composite fiber capacitive voltage divider intelligent terminal.

[0069] Compared with existing technologies, the multi-station collaborative scheduling method for footwear production lines provided by this invention constructs a footwear process dataset and dynamically quantifies the processing complexity of different footwear types. This achieves correlation modeling between footwear processing characteristics and production cycle time. Based on the process differences, processing difficulty, and station load status of different footwear types in actual production, the standard processing cycle time of each station can be dynamically corrected, improving the real-time performance and accuracy of production cycle time calculation. This enhances the production line's adaptability to mixed-line production scenarios of multiple footwear types and reduces station waiting, task backlog, and production line cycle time imbalance caused by fixed cycle time scheduling. By combining historical production data, real-time operation data, order processing progress, process paths, and mold usage status, order risk constraint parameters and mold conflict constraint parameters are constructed. Furthermore, real-time processing cycle time and real-time energy consumption data of each station are integrated to establish a multi-objective collaborative scheduling method. With the same scheduling objective function, a joint collaborative analysis of order delay risk, rework risk, mold resource occupancy relationship, and production energy consumption status was achieved, improving the dynamic constraint perception capability and multi-objective collaborative optimization capability in the production scheduling process. By adopting an improved Grey Wolf optimization algorithm that introduces an order risk constraint guidance mechanism, a mold conflict penalty mechanism, and a nonlinear dynamic convergence factor, the multi-objective collaborative scheduling objective function is solved iteratively. This enables dynamic adaptive search and optimization adjustment of high-risk order priority, mold resource conflict relationship, and workstation collaboration status. During the iteration process, the algorithm can dynamically adjust the search direction and optimization step size according to the real-time production status, enhancing the global search capability and local optimization capability in complex scheduling scenarios, reducing the probability of the scheduling scheme getting stuck in local optima, and improving the collaborative scheduling efficiency, resource coordination capability, and production execution reliability of the footwear production line in a dynamic production environment. Attached Figure Description

[0070] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the 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 based on these drawings without creative effort. In the drawings:

[0071] Figure 1 This is a flowchart of a multi-station collaborative scheduling method for a footwear production line.

[0072] Figure 2 To obtain a real-time processing cycle flow chart.

[0073] Figure 3 Flowchart for obtaining the optimal collaborative scheduling scheme for the footwear production line. Detailed Implementation

[0074] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0075] As mentioned in the background section, traditional optimization algorithms often suffer from insufficient local optimization capabilities, limited constraint adaptability, and unstable dynamic search performance when solving multi-objective dynamic scheduling problems, making it difficult to meet the application requirements of real-time collaborative scheduling of multiple workstations in flexible footwear production scenarios.

[0076] Reference Figures 1-3 As an embodiment of the present invention, this embodiment provides a multi-station collaborative scheduling method for a footwear production line, comprising the following steps:

[0077] Collect and preprocess multi-source footwear data to generate a footwear process dataset. Calculate the complexity index of different footwear types based on the footwear process dataset and generate dynamic processing complexity parameters for the corresponding footwear types.

[0078] Specifically, collect shoe structure data, material data, process path data, and production task data corresponding to footwear orders;

[0079] Collect process flow information, workstation processing sequence information, and production batch information for footwear orders, and establish the relationship between orders and process paths;

[0080] The collected multi-source footwear data is preprocessed, and footwear processing feature parameters are extracted based on the preprocessed multi-source footwear data;

[0081] The extracted shoe model processing feature parameters are normalized and feature encoded to generate a shoe model process dataset.

[0082] By preprocessing the collected multi-source footwear data and extracting footwear processing feature parameters, the consistency and usability of the data were improved, and the ability to identify key processing features of footwear was enhanced. By normalizing and feature encoding the footwear processing feature parameters, a footwear process dataset was generated, realizing a unified expression and structured storage of process features of different types of footwear. This enabled subsequent complexity calculations and intelligent scheduling analysis processes to have better data adaptation and feature analysis capabilities, thereby improving the accuracy of footwear production line data modeling.

[0083] Furthermore, based on the shoe design process dataset, a shoe design complexity evaluation model is constructed to quantitatively analyze the structural complexity, material processing complexity, and process processing complexity of different shoe designs, and to calculate the shoe design complexity index.

[0084] Based on the shoe structure parameters in the shoe structure data set, we analyze the differences in shoe piece splicing complexity, stitching structure complexity and spatial structure complexity among different shoe types, and generate shoe structure complexity parameters.

[0085] Based on the material parameters in the shoe model process dataset, we analyze the differences in material cutting difficulty, material composite processing difficulty, and material processing stability among different shoe models, and generate material processing complexity parameters.

[0086] Based on the process path parameters in the shoe model process dataset, analyze the process switching frequency, special process ratio, and workstation collaboration complexity in the corresponding process flow of different shoe models to generate process processing complexity parameters.

[0087] Based on the structural complexity parameters, material processing complexity parameters, and manufacturing process complexity parameters of the shoe, a shoe complexity evaluation model is constructed. This model quantifies the overall processing complexity of different shoe types, generating a complexity index for each shoe type. The formula is as follows:

[0088] ;

[0089] in, For shoe type index, For the first The complexity index of each shoe model For the first Structural complexity parameters for each shoe model For the first Material processing complexity parameters for each shoe model For the first The manufacturing complexity parameters for each shoe model. , , These are the weighting coefficients for the structural complexity, material processing complexity, and manufacturing process complexity of the shoe model.

[0090] By combining historical production data on workstation processing time, processing cycle time, and rework records, a dynamic complexity correction coefficient applicable to the current production environment is calculated.

[0091] Based on the historical processing time of each workstation, the deviation between the actual processing time and the standard processing time of the corresponding shoe model at each workstation is calculated, and the processing time deviation parameter is generated.

[0092] Based on historical actual processing rhythm and standard processing rhythm, analyze the rhythm fluctuation of the corresponding shoe model in different work stations, and generate rhythm deviation parameters;

[0093] Based on historical rework records, the rework occurrence of the corresponding shoe model in different workstations is statistically analyzed, and rework impact parameters are generated.

[0094] Based on the processing time deviation parameter, cycle time deviation parameter, and rework impact parameter, the deviation between the shoe complexity index and actual production performance under the current production environment is analyzed, and a dynamic complexity correction coefficient is generated. The formula is as follows:

[0095] ;

[0096] in, For the first The dynamic complexity correction coefficient for each shoe model For the first Processing time deviation parameters for each shoe model For the first The beat deviation parameter for each shoe model For the first The parameters affecting rework for each shoe model. , , These are the weighting coefficients for the set processing time deviation parameter, cycle time deviation parameter, and rework impact parameter, respectively.

[0097] Based on the complexity index and dynamic complexity correction coefficient of the shoe type, the dynamic processing complexity parameters of the corresponding shoe type are generated.

[0098] By constructing a shoe design complexity evaluation model based on a shoe design process dataset and quantitatively analyzing the structural complexity, material processing complexity, and process processing complexity of different shoe designs, a comprehensive assessment of the processing difficulty and process differences of footwear products was achieved, improving the accuracy of complexity analysis and process adaptability in footwear production. By combining workstation processing time, processing cycle time, and rework records from historical production data, a dynamic complexity correction coefficient applicable to the current production environment was calculated. This enabled dynamic fusion analysis of actual production status and historical processing patterns, making the complexity assessment results more closely aligned with the current production line operation and enhancing the adaptability of complexity parameters to changes in the actual production environment. Furthermore, by generating dynamic processing complexity parameters for corresponding shoe designs based on the shoe design complexity index and the dynamic complexity correction coefficient, a dynamic correlation between shoe design processing complexity and production scheduling parameters was achieved, improving the precision of production scheduling and the rationality of production resource allocation.

[0099] Multi-source data from each workstation of the footwear production line is collected to construct a multi-workstation state matrix. Based on dynamic processing complexity parameters and the multi-workstation state matrix, the standard processing cycle time of each workstation is dynamically corrected to obtain the real-time processing cycle time.

[0100] Specifically, multi-source data from each workstation on the footwear production line is collected and preprocessed, and based on the preprocessed multi-source data, state feature parameters characterizing the operating status of the workstation are extracted.

[0101] Based on the state characteristic parameters corresponding to each workstation, a multi-workstation state matrix is ​​constructed to represent the real-time operating status of the production line.

[0102] By extracting state feature parameters representing the operating status of each workstation based on preprocessed multi-source data, a comprehensive feature expression of the operating load, processing cycle time, equipment operating status, and task execution of each workstation is achieved. This can more accurately reflect the real-time operating status of each workstation on the production line and the collaborative relationship between workstations. By constructing a multi-workstation state matrix representing the real-time operating status of the production line based on the state feature parameters corresponding to each workstation, a structured model of the overall operating status of the production line is realized. This enables dynamic analysis and decision-making in the processes of dynamic correction of production cycle time, order task allocation, and collaborative scheduling optimization, combined with the real-time status of each workstation. This improves the real-time performance of footwear production line operating status analysis, the coordination of production scheduling, and the overall stability of production operation.

[0103] Furthermore, the standard processing cycle time for each workstation is obtained, and the correlation between the standard processing cycle time of each workstation and the corresponding shoe model processing task is established.

[0104] Based on dynamic processing complexity parameters, we analyze the changes in processing difficulty of different shoe types in corresponding workstations and calculate the complexity influence coefficient of shoe type complexity on workstation processing time.

[0105] Based on the multi-station status matrix, the real-time operating status parameters of each station are extracted, and the influence of the station operating status on the processing cycle time is analyzed.

[0106] Based on the degree of influence of the workstation's operating status on the processing cycle time, corresponding workstation status influence parameters are generated;

[0107] Based on the complexity influence coefficient and the station status influence parameter, the standard processing cycle time of each station is dynamically corrected to obtain the real-time processing cycle time of the corresponding station.

[0108] By acquiring the standard processing cycle time for each workstation and establishing the correlation between the standard processing cycle time of each workstation and the corresponding shoe type processing task, an effective mapping between the processing capacity of each workstation and the specific production task is achieved, enabling different shoe type tasks to be matched with the processing characteristics of the corresponding workstation. By analyzing the changes in processing difficulty of different shoe types in the corresponding workstations based on dynamic processing complexity parameters, and calculating the complexity influence coefficient of shoe type complexity on workstation processing time, a quantitative expression of the actual processing requirements of the workstation based on shoe type processing characteristics is achieved. This accurately reflects the impact of different shoe types on the processing cycle time of the workstation, improving the pertinence and accuracy of processing cycle time assessment. Furthermore, by extracting the state matrix of each workstation... Real-time operating status parameters are analyzed, and the impact of workstation operating status on processing cycle time is analyzed to generate corresponding workstation status impact parameters. This enables dynamic perception of workstation load changes, equipment operating status, and task execution, allowing the processing cycle time to reflect the real-time operating status of the production line in a timely manner and enhancing the production process's adaptability to dynamic changes. By combining complexity impact coefficients and workstation status impact parameters to dynamically correct the standard processing cycle time of each workstation, the real-time processing cycle time of the corresponding workstation is obtained. This realizes the transformation of processing cycle time from static parameters to dynamic parameters, enabling production scheduling to make decisions based on a more realistic production status and improving the rationality of workstation task allocation and the coordination of production cycle time.

[0109] Based on historical production data, real-time operation data, current processing progress, process path, and mold usage status, order risk constraint parameters and mold conflict constraint parameters are comprehensively calculated. Based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters, and real-time energy consumption data of workstations, a multi-objective collaborative scheduling objective function is constructed.

[0110] Specifically, based on historical production data and real-time operational data, the rework risk and delay risk of each order in the production process are analyzed, the rework risk value of each order is calculated, and order risk constraint parameters are generated based on the rework risk value.

[0111] Based on the current processing progress, process path, and mold usage status, predict the mold occupancy time window for each order and generate mold conflict constraint parameters.

[0112] By combining historical production data and real-time operational data, the rework and delay risks of each order during the production process are analyzed, and the rework risk value corresponding to each order is calculated. This generates order risk constraint parameters, enabling early identification and quantification of potential production risks during order execution. It allows for full consideration of the risk differences between different orders during task allocation and production resource configuration, enabling targeted scheduling and management of high-risk orders, thus improving the executability of production plans and the stability of order delivery. Furthermore, by combining current processing progress, process paths, and mold usage status, the mold occupancy time window for each order is predicted, and mold conflict constraint parameters are generated. This enables early analysis of mold resource usage relationships and occupancy conflicts, allowing for the pre-identification of potential mold resource competition issues during the production task arrangement phase. It also allows for the rational coordination of mold usage order and resource allocation relationships between different orders, thereby reducing mold waiting times and resource conflicts, improving mold resource utilization efficiency, and enhancing production process continuity.

[0113] Furthermore, based on the real-time processing cycle time, the estimated processing completion time and workstation task waiting time for each order under the current production status are calculated, and production cycle time optimization parameters are generated.

[0114] Based on order risk constraint parameters, the delay risk and rework risk of different orders in the production process are analyzed, and order priority scheduling parameters are generated.

[0115] Based on mold conflict constraint parameters, we analyze the mold occupation conflict between different orders and the impact of mold switching, and generate mold resource coordination parameters.

[0116] Based on real-time energy consumption data of each workstation, calculate the unit processing energy consumption of each workstation under different processing tasks and the overall energy consumption level of the production line, and generate energy consumption optimization parameters.

[0117] Based on production cycle optimization parameters, order priority scheduling parameters, mold resource coordination parameters, and energy consumption optimization parameters, a multi-objective collaborative scheduling objective function is constructed for task allocation and workstation collaborative optimization in footwear production lines.

[0118] By calculating the estimated completion time of orders and the waiting time of workstation tasks based on real-time processing cycle time, production cycle time optimization parameters are generated, enabling dynamic evaluation of production progress and workstation coordination status. This provides a basis for production cycle time optimization and improves the continuity and coordination of the production process. By analyzing order delay and rework risks based on order risk constraint parameters, order priority scheduling parameters are generated, achieving correlation optimization between production risk and scheduling decisions, improving order execution stability and delivery assurance capabilities. By analyzing mold occupancy conflicts and the impact of switching based on mold conflict constraint parameters, mold resource coordination parameters are generated, achieving reasonable allocation of mold resources and conflict prevention, improving resource utilization efficiency. By generating energy consumption optimization parameters based on real-time workstation energy consumption data, dynamic analysis of production energy consumption status is achieved, improving the rationality of energy utilization. Furthermore, by combining production cycle time optimization parameters, order priority scheduling parameters, mold resource coordination parameters, and energy consumption optimization parameters, a multi-objective collaborative scheduling objective function is constructed, achieving synergistic optimization of production efficiency, order risk, resource utilization, and energy consumption levels. This provides a comprehensive basis for subsequent scheduling decisions and improves the scheduling quality and resource coordination capabilities of the footwear production line.

[0119] An improved gray wolf optimization algorithm is used to iteratively solve the objective function of multi-objective collaborative scheduling to obtain the optimal collaborative scheduling scheme for the footwear production line. The optimal collaborative scheduling scheme is then distributed to the corresponding production execution equipment, and multi-source data from the production line is continuously collected and uploaded to the database for storage.

[0120] Specifically, based on the multi-objective collaborative scheduling objective function, the task allocation order of each workstation, the order processing order, and the mold resource allocation result are used as the position coding information of individual wolves to construct a collaborative scheduling population for the footwear production line;

[0121] Based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters, and real-time energy consumption data of the workstation, the fitness value of the objective function of the scheduling scheme corresponding to each gray wolf individual is calculated, and the initial alpha wolf individual is determined according to the fitness value.

[0122] Based on real-time processing rhythm data, the task processing rhythm, waiting time and order flow rhythm of each workstation in the corresponding scheduling scheme of each individual gray wolf are statistically analyzed, and the real-time processing rhythm value of the corresponding scheduling scheme is calculated.

[0123] Based on the order risk constraint parameters, high-risk order tasks in the corresponding scheduling schemes for each individual gray wolf are identified. The risk constraint satisfaction of high-risk order tasks under the current workstation allocation order, processing order and waiting time conditions is analyzed, and the order risk constraint cost of the corresponding scheduling scheme is calculated.

[0124] Based on the mold conflict constraint parameters, it is detected whether the same mold is occupied by multiple orders in the overlapping time interval in the scheduling scheme corresponding to each individual gray wolf. The number of mold resource conflicts, the duration of the conflict and the number of workstations affected by the conflict are counted, and the mold conflict constraint cost of the corresponding scheduling scheme is calculated.

[0125] Based on real-time energy consumption data of workstations, the energy consumption of equipment operation, standby energy consumption and workstation switching during the order processing of each workstation in the corresponding scheduling scheme of each individual Grey Wolf is statistically analyzed, and the energy consumption cost of the workstation in the corresponding scheduling scheme is calculated.

[0126] Based on the real-time processing cycle value, order risk constraint value, mold conflict constraint value, and workstation energy consumption value, the values ​​of each value are linearly weighted according to preset weight coefficients to construct the objective function fitness value of the scheduling scheme for each individual gray wolf.

[0127] The fitness values ​​of the objective function corresponding to each individual gray wolf are sorted and compared. The gray wolf with the best fitness value is selected and its corresponding position encoding information is used as the initial alpha wolf.

[0128] During the update of individual gray wolf positions, an order risk constraint guidance mechanism and a mold conflict penalty mechanism are introduced. The search priority of tasks corresponding to high-risk orders is dynamically adjusted according to the order risk constraint parameters, and the position constraints of gray wolf individuals with mold resource conflicts are corrected according to the mold conflict constraint parameters.

[0129] Based on order risk constraint parameters, high-risk order tasks are identified among each individual wolf. The search priority of these high-risk order tasks in location coding is adjusted according to the constraint weights corresponding to the order risk constraint parameters. This ensures that high-risk order tasks move preferentially towards workstations with high processing capacity matching, short waiting times, and low risk constraint costs during location updates. The formula is as follows:

[0130] ;

[0131] in, For order task indexing, For the first Search priority for each order task For the first Order risk constraint parameters for each order task. This is the sum of the order risk constraint parameters for all order tasks within the current gray wolf individual.

[0132] Based on the mold conflict constraint parameters, it is detected whether there is a situation where the same mold is occupied by multiple orders in the scheduling scheme corresponding to each individual gray wolf, and the order task, conflicting workstation and conflict time interval where mold resource conflict occurs are determined.

[0133] When a mold resource conflict is detected, the position code of the conflicting order task is constrained and corrected according to the mold conflict constraint parameters. The processing sequence, mold usage sequence and workstation allocation position of the conflicting order task are adjusted so that the corrected gray wolf individual meets the mold resource availability constraint.

[0134] After completing the order risk constraint guidance and mold conflict constraint correction, the fitness value of the corresponding scheduling scheme of the corrected gray wolf individual is recalculated, and the corrected gray wolf individual is used as the candidate individual for the next round of position update.

[0135] During the iterative update of individual gray wolves, a nonlinear dynamic convergence factor is used to adaptively adjust the position update step size of individual gray wolves, which improves the global search capability in the early stage of algorithm iteration and the local optimization capability in the later stage of algorithm iteration.

[0136] Obtain the current iteration number, the maximum iteration number, and the location encoding information corresponding to the current gray wolf individual. Based on the relationship between the current iteration number and the maximum iteration number, calculate the nonlinear dynamic convergence factor corresponding to the current iteration round, as shown in the formula:

[0137] ;

[0138] in, This represents the current iteration number. For the first The nonlinear dynamic convergence factor corresponding to the next iteration. This represents the maximum number of iterations.

[0139] Based on the nonlinear dynamic convergence factor, the position update step size control parameter for individual gray wolves in the current iteration is determined, so that the position update step size changes nonlinearly with the iteration process, as shown in the formula:

[0140] ;

[0141] in, For individual gray wolf indexes, For the first The position update step size for each individual gray wolf. For the first The current location code of each individual gray wolf. Encode the position of the current best gray wolf individual.

[0142] In the early stages of algorithm iteration, the step size control parameter is updated based on a larger position to expand the search range of individual gray wolves in the task allocation order, order processing order and mold resource allocation space, thereby improving the algorithm's global search capability for different scheduling schemes.

[0143] In the later stages of algorithm iteration, the step size control parameter is updated based on the gradually decreasing position to narrow the search range of individual gray wolves around the current better scheduling scheme, thereby improving the fine optimization ability of local scheduling schemes.

[0144] The position update formula for individual gray wolves is adjusted based on a nonlinear dynamic convergence factor to generate the updated position code for each individual gray wolf in the current iteration.

[0145] Based on the changes in the fitness of the objective function for each individual gray wolf during the iteration process, the optimal scheduling individual is updated, and the optimal solution of the objective function is output when the preset iteration termination condition is met.

[0146] Obtain the objective function fitness value of the scheduling scheme for each individual gray wolf in the current iteration round, and compare it with the objective function fitness value of the corresponding gray wolf in the previous iteration round to determine the fitness change of each individual gray wolf.

[0147] Based on the fitness values ​​of each individual gray wolf, the gray wolf with the best fitness in the current iteration is selected and used as a candidate optimal scheduling individual.

[0148] The candidate optimal scheduler is compared with the optimal scheduler saved in the historical iteration. When the fitness value of the candidate optimal scheduler is better than that of the historical optimal scheduler, the optimal scheduler and its corresponding position encoding information are updated.

[0149] Based on the updated optimal scheduler, record its corresponding workstation task allocation order, order processing order, mold resource allocation result and objective function fitness value;

[0150] When the number of iterations reaches the preset maximum number of iterations, the fitness value of the objective function corresponding to the currently saved optimal scheduling individual is output as the optimal solution of the objective function.

[0151] Based on the optimal solution of the objective function, the optimal collaborative scheduling scheme for the footwear production line is generated.

[0152] By encoding the workstation task allocation order, order processing order, and mold resource allocation results as individual "gray wolves," a collaborative scheduling population for footwear production lines is constructed. This achieves a unified expression and parallel search for complex scheduling schemes, improving the problem-solving capability of scheduling. By combining real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters, and real-time workstation energy consumption data to calculate fitness values ​​and determine the initial alpha wolf, a comprehensive evaluation of the scheduling scheme's merits is achieved, improving the accuracy of the search direction. Introducing an order risk constraint guidance mechanism and a mold conflict penalty mechanism during position updates enables priority scheduling of high-risk orders and avoidance of mold resource conflicts, improving the adaptability of scheduling results to actual production constraints. Adaptive adjustment of the position update step size using a nonlinear dynamic convergence factor achieves a dynamic balance between global search and local optimization capabilities, improving algorithm optimization efficiency and solution quality. Continuous updating of the optimal scheduling individual based on fitness changes and outputting the optimal solution of the objective function enables continuous optimization of the production scheduling scheme, ultimately generating the optimal collaborative scheduling scheme and improving the scheduling efficiency, resource utilization, and production operation stability of the footwear production line.

[0153] Furthermore, the optimal collaborative scheduling scheme is distributed to the corresponding production execution equipment, and each workstation equipment is controlled to execute production tasks according to the scheduling scheme;

[0154] Multi-source data is collected in real time during the execution of production tasks as experience data and uploaded to the database for storage.

[0155] By distributing the optimal collaborative scheduling scheme to the corresponding production execution equipment and controlling each workstation to execute production tasks according to the scheduling scheme, the scheduling decision and the production execution process are effectively linked, enabling the optimization results to be quickly transformed into actual production actions and improving the accuracy and coordination of production task execution. At the same time, by collecting multi-source data in real time during the production task execution process as experience data and uploading it to the database for storage, the continuous accumulation and complete recording of production process information are realized, providing data support for subsequent production status analysis, scheduling model optimization, and reuse of historical experience, thereby improving the traceability of production management and the ability to continuously improve scheduling optimization.

[0156] Example 2

[0157] According to one aspect of the present invention, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0158] In another aspect, the present invention also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the multi-station collaborative scheduling method for footwear production lines described in the above embodiments.

[0159] It should be noted that although several modules or units of the device for performing actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0160] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of the present invention.

[0161] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein.

[0162] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A multi-station collaborative scheduling method for a footwear production line, characterized in that, The specific steps include the following: Collect multi-source footwear data and preprocess it to generate a footwear process dataset. Calculate the complexity index of different footwear types based on the footwear process dataset and generate dynamic processing complexity parameters for the corresponding footwear types. Collect multi-source data from each workstation of the footwear production line, construct a multi-workstation state matrix, and dynamically correct the standard processing cycle of each workstation based on dynamic processing complexity parameters and the multi-workstation state matrix to obtain the real-time processing cycle. Based on historical production data, real-time operation data, current processing progress, process path and mold usage status, order risk constraint parameters and mold conflict constraint parameters are comprehensively calculated. Based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters and workstation real-time energy consumption data, a multi-objective collaborative scheduling objective function is constructed. An improved gray wolf optimization algorithm is used to iteratively solve the objective function of multi-objective collaborative scheduling to obtain the optimal collaborative scheduling scheme for the footwear production line. The optimal collaborative scheduling scheme is then distributed to the corresponding production execution equipment, and multi-source data from the production line is continuously collected and uploaded to the database for storage.

2. The multi-station collaborative scheduling method for footwear production lines according to claim 1, characterized in that, The process of collecting and preprocessing multi-source footwear data to generate a footwear manufacturing process dataset includes the following steps: Collect footwear structure data, material data, process path data, and production task data corresponding to footwear orders; Collect process flow information, workstation processing sequence information, and production batch information for footwear orders, and establish the relationship between orders and process paths; The collected multi-source footwear data is preprocessed, and footwear processing feature parameters are extracted based on the preprocessed multi-source footwear data; The extracted shoe model processing feature parameters are normalized and feature encoded to generate a shoe model process dataset.

3. The multi-station collaborative scheduling method for footwear production lines according to claim 2, characterized in that, The process of calculating the complexity index of different shoe models based on the shoe model manufacturing dataset and generating dynamic manufacturing complexity parameters for the corresponding shoe models includes the following steps: Based on the shoe design process dataset, a shoe design complexity evaluation model is constructed to quantitatively analyze the structural complexity, material processing complexity, and process processing complexity of different shoe designs, and to calculate the shoe design complexity index. By combining historical production data on workstation processing time, processing cycle time, and rework records, a dynamic complexity correction coefficient applicable to the current production environment is calculated. Based on the complexity index and dynamic complexity correction coefficient of the shoe type, the dynamic processing complexity parameters of the corresponding shoe type are generated.

4. The multi-station collaborative scheduling method for footwear production lines according to claim 3, characterized in that, The process of collecting multi-source data from each workstation on the footwear production line and constructing a multi-workstation status matrix includes the following steps: Multi-source data from each workstation on the footwear production line is collected and preprocessed. Based on the preprocessed multi-source data, state feature parameters characterizing the operating status of the workstation are extracted. Based on the state characteristic parameters corresponding to each workstation, a multi-workstation state matrix is ​​constructed to represent the real-time operating status of the production line.

5. The multi-station collaborative scheduling method for footwear production lines according to claim 4, characterized in that, The process of dynamically correcting the standard processing cycle time of each station based on dynamic processing complexity parameters and multi-station state matrix to obtain the real-time processing cycle time includes the following steps: Obtain the standard processing cycle time for each workstation and establish the association between the standard processing cycle time of each workstation and the corresponding shoe model processing task; Based on dynamic processing complexity parameters, we analyze the changes in processing difficulty of different shoe types in corresponding workstations and calculate the complexity influence coefficient of shoe type complexity on workstation processing time. Based on the multi-station status matrix, the real-time operating status parameters of each station are extracted, and the influence of the station operating status on the processing cycle time is analyzed. Based on the degree of influence of the workstation's operating status on the processing cycle time, corresponding workstation status influence parameters are generated; Based on the complexity influence coefficient and the station status influence parameter, the standard processing cycle time of each station is dynamically corrected to obtain the real-time processing cycle time of the corresponding station.

6. The multi-station collaborative scheduling method for footwear production lines according to claim 5, characterized in that, The step of comprehensively calculating order risk constraint parameters and mold conflict constraint parameters based on historical production data, real-time operation data, current processing progress, process path, and mold usage status includes the following steps: Based on historical production data and real-time operation data, analyze the rework risk and delay risk of each order in the production process, calculate the rework risk value of each order, and generate order risk constraint parameters based on the rework risk value. Based on the current processing progress, process path, and mold usage status, predict the mold occupancy time window for each order and generate mold conflict constraint parameters.

7. The multi-station collaborative scheduling method for footwear production lines according to claim 6, characterized in that, The process involves constructing a multi-objective collaborative scheduling objective function based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters, and real-time energy consumption data at the workstation. This includes the following steps: Based on real-time processing cycle time, calculate the estimated processing completion time and workstation task waiting time for each order in the current production state, and generate production cycle time optimization parameters; Based on order risk constraint parameters, the delay risk and rework risk of different orders in the production process are analyzed, and order priority scheduling parameters are generated. Based on mold conflict constraint parameters, we analyze the mold occupation conflict between different orders and the impact of mold switching, and generate mold resource coordination parameters. Based on real-time energy consumption data of each workstation, calculate the unit processing energy consumption of each workstation under different processing tasks and the overall energy consumption level of the production line, and generate energy consumption optimization parameters. Based on production cycle optimization parameters, order priority scheduling parameters, mold resource coordination parameters, and energy consumption optimization parameters, a multi-objective collaborative scheduling objective function is constructed for task allocation and workstation collaborative optimization in footwear production lines.

8. The multi-station collaborative scheduling method for footwear production lines according to claim 7, characterized in that, The step of iteratively solving the multi-objective cooperative scheduling objective function using the improved gray wolf optimization algorithm to obtain the optimal cooperative scheduling scheme for the footwear production line includes the following steps: Based on the multi-objective collaborative scheduling objective function, the task allocation order of each workstation, the order processing order, and the mold resource allocation result are used as the position coding information of the individual gray wolf to construct a collaborative scheduling population for the footwear production line; Based on real-time processing cycle time, order risk constraint parameters, mold conflict constraint parameters and real-time energy consumption data of the workstation, the fitness value of the objective function of the scheduling scheme corresponding to each gray wolf individual is calculated, and the initial alpha wolf individual is determined according to the fitness value. During the update of individual gray wolf positions, an order risk constraint guidance mechanism and a mold conflict penalty mechanism are introduced. The search priority of tasks corresponding to high-risk orders is dynamically adjusted according to the order risk constraint parameters, and the position constraints of gray wolf individuals with mold resource conflicts are corrected according to the mold conflict constraint parameters. During the iterative update of individual gray wolves, a nonlinear dynamic convergence factor is used to adaptively adjust the position update step size of individual gray wolves, which improves the global search capability in the early stage of algorithm iteration and the local optimization capability in the later stage of algorithm iteration. Based on the change in the fitness of the objective function for each individual gray wolf during the iteration process, the optimal scheduling individual is updated, and the optimal solution of the objective function is output when the preset iteration termination condition is met. Based on the optimal solution of the objective function, an optimal collaborative scheduling scheme is generated for the footwear production line.

9. The multi-station collaborative scheduling method for footwear production lines according to claim 8, characterized in that, The process of distributing the optimal collaborative scheduling scheme to the corresponding production execution equipment and continuously collecting multi-source data from the production line and uploading it to the database for storage includes the following steps: The optimal collaborative scheduling scheme is sent to the corresponding production execution equipment, and each workstation equipment is controlled to execute production tasks according to the scheduling scheme. Multi-source data is collected in real time during the execution of production tasks as empirical data and uploaded to the database for storage.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the multi-station collaborative scheduling method for footwear production lines according to any one of claims 1-9.

Images