A method, system, medium, terminal, and program product for collaborative scheduling of flat knitting machines and sweater loops based on genetic algorithms and constraint reduction.

By adopting a collaborative scheduling method for knitting flat knitting machines and sweater binding processes based on genetic algorithms and constraint reduction, the problem of low collaborative efficiency between the flat knitting machines and sweater binding processes in knitting production is solved. This method enables efficient generation of scheduling schemes and utilization of equipment resources, reduces the backlog of semi-finished products, and improves production efficiency and the feasibility of the scheme.

CN123070537APending Publication Date: 2026-11-10SUZHOU FEILIU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611146685.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-07-30
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

In sweater production, the coordination efficiency between the flat knitting machine and the lacing process is low, it is difficult to balance multiple objectives in optimization, the existing production scheduling methods are inefficient, the utilization rate of equipment resources is low, the changeover time is high, the process coordination is difficult, and it is difficult to cope with emergencies.

Method used

A collaborative scheduling method for knitwear flat knitting machines and sweater loopers based on genetic algorithms and constraint reduction is adopted. By acquiring scheduling input data, calculating order priorities, performing constraint reduction and locking processing, an initial scheduling plan is constructed. The genetic algorithm is used for iterative optimization to generate the final scheduling plan, and the sweater looper control strategy is combined to determine the start time of the sweater looper scheduling.

Benefits of technology

It improved the production scheduling efficiency and equipment utilization rate of sweater production, reduced the backlog of semi-finished products between the flat knitting machine and the fabrication machine, and enhanced the coordination efficiency of the two processes and the on-site feasibility of the production scheduling plan.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123070537A_ABST
    Figure CN123070537A_ABST
Patent Text Reader

Abstract

This application provides a method, system, medium, terminal, and program product for collaborative scheduling of flat knitting machines and sweater binding based on genetic algorithms and constraint reduction. The method includes: acquiring scheduling input data and calculating the priority of each order; acquiring a priority order sequence and performing constraint reduction on the priority order sequence to obtain a reduced order sequence; constructing an initial flat knitting machine scheduling scheme set based on the reduced order sequence and the flat knitting machine equipment data; iteratively optimizing the initial flat knitting machine scheduling scheme set using a genetic algorithm to generate a final flat knitting machine scheduling scheme; determining the binding process requirements and acquiring a candidate binding personnel set based on the final flat knitting machine scheduling scheme; and calculating the binding scheduling start time for each order based on the binding control strategy, thereby constructing a binding scheduling scheme. This application can coordinate the scheduling of flat knitting machines and binding processes and improve production efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of collaborative scheduling technology for knitting flat knitting machines and fabric overlays, and in particular to a method, system, medium, terminal and program product for collaborative scheduling of knitting flat knitting machines and fabric overlays based on genetic algorithms and constraint reduction. Background Technology

[0002] Sweater production mainly includes two core processes: flat knitting and sewing. The flat knitting machine weaves the yarn into garment pieces (body, sleeves, collar, etc.), while the sewing machine sews these pieces together to form the finished garment. Balancing the production capacity of these two processes is a challenge in production management.

[0003] Currently, sweater manufacturers mainly rely on the following methods for production scheduling:

[0004] First, manual production scheduling: Experienced planners manually schedule production based on order delivery dates, equipment status, and material availability using Excel spreadsheets or paper-based dashboards. Planners need to comprehensively consider multiple factors such as order priority, equipment needle type matching, changeover time (usually half a day), material kitting time, and outsourced return time, allocating orders to each flat knitting machine and each kitting employee, and determining start and end times.

[0005] Second, general-purpose APS software: Some companies have introduced general-purpose advanced planning and scheduling systems, such as SAP APO and Siemens Opcenter. These systems are mainly geared towards discrete manufacturing or process manufacturing industries and use methods such as integer programming and constraint programming for scheduling.

[0006] However, existing technologies have the following problems:

[0007] (1) Manual scheduling is inefficient. When manually scheduling 20-30 orders and 10-20 machines, it often takes 4-8 hours and is difficult to deal with unexpected situations such as order insertion or equipment failure.

[0008] (2) Low utilization rate of equipment resources. Manual scheduling makes it difficult to accurately balance the load of multiple flat knitting machines, resulting in some machines being idle and others being overloaded. The overall equipment efficiency is usually below 70%.

[0009] (3) Significant time loss due to style changeovers. In sweater production, changing yarns, adjusting density, and testing pieces on the flat knitting machine require a long preparation time for style changeovers, typically 4-8 hours. Manual scheduling makes it difficult to effectively identify and merge orders for the same or similar styles, resulting in excessive style changeovers.

[0010] (4) Difficulty in process coordination. The production capacity of the flat knitting machine and the rigging machine needs to be matched. Manual production scheduling often only focuses on the flat knitting machine, causing the flat knitting machine to "knit frantically" while the rigging machine "cannot keep up", resulting in a large backlog of semi-finished products and work-in-process.

[0011] (5) It is difficult to balance multiple objectives. Production scheduling needs to simultaneously meet multiple objectives such as on-time delivery, high equipment utilization, few product changes, and low overtime costs. There are inherent conflicts among these objectives.

[0012] Therefore, it is necessary to provide a method, system, medium, terminal, and program product for collaborative scheduling of knitting flat knitting machines and sweater seams based on genetic algorithms and constraint reduction, in order to solve the above-mentioned problems existing in the prior art. Summary of the Invention

[0013] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method, system, medium, terminal and program product for collaborative scheduling of flat knitting machines and sweater binding based on genetic algorithm and constraint reduction, so as to solve the problems of low collaborative efficiency of flat knitting machine and sweater binding process and difficulty in taking into account multiple optimization objectives.

[0014] To achieve the above and other related objectives, a first aspect of this application provides a method for collaborative scheduling of knitwear flat knitting machines and sweater seams based on genetic algorithms and constraint reduction. The method includes: acquiring scheduling input data, which includes order data, flat knitting machine data, seam resource data, and constraint data; wherein the order data includes several orders and corresponding order information; calculating the priority of each order based on the order information, sorting the orders according to the priority to obtain a priority order sequence, and performing constraint reduction on the priority order sequence to obtain a reduced order sequence; the constraint reduction includes grouping based on the sweater styles corresponding to the orders in the priority order sequence, locking orders that have already started production in the priority order sequence, and performing hard constraint filtering on the priority order sequence; and constructing an initial... A set of initial flat knitting machine scheduling schemes is generated, and a genetic algorithm is used to iteratively optimize the initial set of flat knitting machine scheduling schemes to generate a final flat knitting machine scheduling scheme. Specifically, the fitness of candidate flat knitting machine scheduling schemes generated during the iterative optimization process is calculated based on a preset fitness model to meet preset termination conditions. The candidate flat knitting machine scheduling scheme with the highest fitness and meeting preset constraints is determined as the final flat knitting machine scheduling scheme. Predicted flat knitting machine shedding data for each order is obtained from the final flat knitting machine scheduling scheme. Based on the predicted flat knitting machine shedding data and the order information, the tailing process requirements for each order are determined. A set of candidate tailing personnel that meets the tailing process requirements is selected from a preset tailing personnel database. The tailing production start time for each order is calculated based on the tailing control strategy. Tailoring personnel are assigned to each order according to the candidate tailing personnel set, and a tailing production scheduling scheme is constructed by combining the tailing production start time with the tailing production start time.

[0015] In some embodiments of the first aspect of this application, the specific process of calculating the priority of each order based on the order information includes:

[0016] ;

[0017] ;

[0018] in, Let i be the priority of the i-th order. The score is given for the inspection date of the i-th order. The order type score for the i-th order. The score for the secondary processing type of the i-th order. Let N be the remaining number of days for the inspection of the i-th order, N be the preset delivery date evaluation period, and a, b, and c be the corresponding weight coefficients.

[0019] In some embodiments of the first aspect of this application, the process of constraining and reducing the priority order sequence to obtain the reduced order sequence specifically includes: classifying orders with the same sweater style in the priority order sequence into the same style group based on order information; when orders in the same style group are assigned to the same flat knitting machine, they are arranged consecutively in the order scheduling sequence corresponding to the flat knitting machine.

[0020] Orders with a "production started" status in the priority order sequence are locked, ensuring that the allocated knitting machine, production sequence, and determined production time corresponding to the locked orders remain unchanged during subsequent production scheduling optimization. Orders that do not meet preset hard constraints are removed from the priority order sequence. The preset hard constraints include: order needle type matching check, order material completeness check, and order sample sealing completion check.

[0021] In some embodiments of the first aspect of this application, the fitness of candidate flat knitting machine scheduling schemes generated during iterative optimization is calculated based on a preset fitness model. The specific process includes:

[0022] ;

[0023] Wherein, Fitness refers to fitness level. These are delivery time satisfaction, flat knitting machine utilization rate, style change evaluation value, and production line balance; P represents a constraint / penalty term. These are the corresponding weighting coefficients.

[0024] In some embodiments of the first aspect of this application, the delivery date satisfaction is calculated based on the time difference between the expected completion time of each order in the candidate flat knitting machine production schedule and the corresponding inspection date; the flat knitting machine equipment utilization rate is determined based on the ratio of the effective production time of each flat knitting machine to its available production time; the style change evaluation value is determined comprehensively based on the differences in sweater styles between adjacent production schedule orders and the resulting style change time loss; and the production line balance is determined based on the degree of matching between the flat knitting machine's sheathing capacity and its edge processing capacity.

[0025] In some embodiments of the first aspect of this application, the calculation of the tailing schedule start time for each order based on the tailing control strategy specifically includes: obtaining the number of pieces dropped in each scheduling cycle corresponding to the order based on the predicted flat knitting machine drop data for any order; and calculating the current tailing work-in-process quantity based on the number of pieces dropped in the order using the following formula:

[0026] ;

[0027] Wherein, WIP(t) is the current work-in-process inventory at the end of the t-th production cycle, P_m(t) is the number of wafers finished per day in the t-th production cycle, and C_s(t) is the number of wafers completed in the t-th production cycle as estimated based on the processing capacity per unit time of the candidate wafer setters and the available working hours; when WIP(t) is greater than or equal to the preset safety stock threshold, the t-th production cycle corresponding to it is taken as the start time of wafer setter production.

[0028] To achieve the above and other related objectives, a second aspect of this application provides a collaborative scheduling system for knitwear flat knitting machines and sweater seams based on genetic algorithms and constraint reduction. The system includes: a data acquisition module for acquiring scheduling input data, which includes order data, flat knitting machine equipment data, seam resource data, and constraint data; wherein the order data includes several orders and corresponding order information; a constraint processing module for calculating the priority of each order based on the order information, sorting the orders according to the priority to obtain a priority order sequence, and performing constraint reduction on the priority order sequence to obtain a reduced order sequence; the constraint reduction includes grouping based on the sweater styles corresponding to the orders in the priority order sequence, locking orders that have already started production in the priority order sequence, and performing hard constraint filtering on the priority order sequence; and a genetic optimization module for optimizing the reduced order sequence based on the knitwear styles of the knitwear knitting machines and the sweater seams. The machine equipment data is used to construct an initial set of flat knitting machine scheduling schemes, and a genetic algorithm is used to iteratively optimize the initial set of flat knitting machine scheduling schemes to generate a final flat knitting machine scheduling scheme. Specifically, the fitness of candidate flat knitting machine scheduling schemes generated during the iterative optimization process is calculated based on a preset fitness model to meet preset termination conditions. The candidate flat knitting machine scheduling scheme with the highest fitness and meeting preset constraints is determined as the final flat knitting machine scheduling scheme. A tailoring scheduling module is used to obtain predicted flat knitting machine shedding data for each order from the final flat knitting machine scheduling scheme, determine the tailoring process requirements for each order based on the predicted flat knitting machine shedding data and the order information, filter a set of candidate tailoring personnel from a preset tailoring personnel database that meets the tailoring process requirements, calculate the tailoring scheduling start time for each order based on the tailoring control strategy, assign tailoring personnel to each order according to the candidate tailoring personnel set, and construct a tailoring scheduling scheme based on the tailoring scheduling start time.

[0029] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for collaborative scheduling of knitwear flat knitting machines and fabric seams based on genetic algorithms and constraint reduction.

[0030] To achieve the above and other related objectives, a fourth aspect of this application provides a computer program product, which includes computer program code. When the computer program code is run on a computer, the computer implements the method for collaborative scheduling of knitwear flat knitting machines and fabric seams based on genetic algorithms and constraint reduction.

[0031] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the method for collaborative scheduling of knitwear flat knitting machines and fabric seams based on genetic algorithms and constraint reduction.

[0032] As described above, this application has the following beneficial effects:

[0033] This application transforms the original scheduling problem into a reduced, feasible scheduling problem by prioritizing order data, grouping similar styles, locking orders already in production, and using hard constraint filtering. This reduces the search range of the genetic algorithm among invalid and unexecutable solutions, improving the convergence efficiency of flat knitting machine scheduling optimization. Simultaneously, it introduces multi-objective fitness evaluations such as delivery date satisfaction, flat knitting machine equipment utilization, style change evaluation, and production line balance during the flat knitting machine scheduling optimization process, ensuring that the generated flat knitting machine scheduling scheme can balance delivery date, equipment load, and style change losses. Furthermore, this application uses the predicted flat knitting machine shedding data in the final flat knitting machine scheduling scheme as input for overlay scheduling, and combines the candidate overlay personnel set and work-in-process (WIP) control strategy to determine the overlay scheduling start time and overlay personnel allocation results. This ensures that overlay processing capacity matches the flat knitting machine shedding cycle time, thereby reducing the backlog of semi-finished products and overlay waiting between the flat knitting machine and overlay processes, improving the collaborative efficiency of the two processes, and ultimately enhancing the production scheduling efficiency, equipment utilization, and on-site executability of the scheduling scheme for sweater production. Attached Figure Description

[0034] Figure 1 The diagram shown is a flowchart of a method for collaborative scheduling of knitwear flat knitting machines and fabric seams based on genetic algorithms and constraint reduction in one embodiment of this application.

[0035] Figure 2 The diagram shown is a schematic representation of the knitting machine and the sleeve working together in one embodiment of this application.

[0036] Figure 3 The diagram shown is a structural schematic of a sweater flat knitting machine and a sweater tailoring collaborative scheduling system based on genetic algorithm and constraint reduction in one embodiment of this application.

[0037] Figure 4 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0038] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0039] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0040] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0041] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0042] To facilitate understanding of the embodiments of this application, firstly, in conjunction with Figure 1 Detailed explanation. Figure 1 This document illustrates a flowchart of a collaborative scheduling method for knitting knitting machines and sweater seams based on genetic algorithms and constraint reduction, as described in an embodiment of the present invention. The collaborative scheduling method for knitting knitting machines and sweater seams based on genetic algorithms and constraint reduction in this embodiment mainly includes the following steps:

[0043] Step S11: Obtain production scheduling input data, which includes order data, flat knitting machine equipment data, tailoring resource data, and constraint data; wherein, the order data includes several orders and corresponding order information.

[0044] Specifically, the sweater manufacturing process consists of different production orders. These orders share several flat knitting machines and binding personnel. Therefore, after obtaining several orders, a production schedule needs to be created based on the current flat knitting machines and binding personnel. Furthermore, the order information of these orders, along with existing flat knitting machine data, binding resource data, and pre-acquired constraint data of these orders, together constitute the production scheduling input data.

[0045] The order information is used to characterize the production object, delivery requirements, and process attributes of each order. This order information includes, but is not limited to, order identifier, order quantity, inspection date, order type, secondary processing type, sweater style information, flat knitting machine processing time, and seam binding processing time. Specifically, the order identifier uniquely identifies the corresponding order; the order quantity is used to calculate the planned processing time required for the order; the inspection date determines the order delivery deadline; the order type and secondary processing type are used to calculate order priority; the sweater style information is used to group orders with the same or similar styles; the flat knitting machine processing time is used to calculate the production load of the flat knitting machine's fabrication process; and the seam binding processing time is used to calculate the processing load of the seam binding and sewing process.

[0046] The data on the flat knitting machine is used to characterize the production capacity of the flat knitting machine. The data includes, but is not limited to, the equipment identification, needle type, daily working hours, current tasks, and estimated availability.

[0047] The constraint data is used to limit the constraints that must be met when an order enters production scheduling and when a production scheduling plan is generated. This constraint data includes, but is not limited to, material kitting time, sample sealing time, knitting machine inspection lead time, webbing inspection lead time, safety stock threshold, and changeover time loss. It should be noted that the sources of the production scheduling input data include, but are not limited to, ERP systems, sweater process BOMs, MES systems, historical cached data, and manual input; no specific limitations are made here.

[0048] After obtaining the production scheduling input data, the order data, flat knitting machine equipment data, stitching resource data, and constraint data are subjected to data verification and formatting processing to remove data records with missing order identifiers, missing inspection dates, missing equipment needle types, or abnormal time fields. The data that passes the verification is used as the basis data for subsequent constraint reduction and flat knitting machine production scheduling optimization.

[0049] In one embodiment, after obtaining the production scheduling input data, a preset settling personnel database is invoked. The preset settling personnel database includes settling personnel identifiers, skill data, availability status data, current task data, and production capacity data, which are used to subsequently screen a set of candidate settling personnel.

[0050] Step S12: Calculate the priority of each order based on the order information, sort each order according to the priority, obtain a priority order sequence, and perform constraint reduction on the priority order sequence to obtain a reduced order sequence; the constraint reduction includes grouping based on the sweater styles corresponding to the orders in the priority order sequence, locking the orders that have started production in the priority order sequence, and performing hard constraint filtering on the priority order sequence.

[0051] In one embodiment of this application, the specific process of calculating the priority of each order based on the order information includes:

[0052] ;(Formula 1)

[0053] ;(Formula 2)

[0054] in, Let i be the priority of the i-th order. The score is given for the inspection date of the i-th order. The order type score for the i-th order. The score for the secondary processing type of the i-th order. Let N be the remaining number of days for the inspection of the i-th order, N be the preset delivery date evaluation period, and a, b, and c be the corresponding weight coefficients.

[0055] Specifically, after obtaining information on several orders, the remaining number of days for inspection of each order is calculated based on the difference between the inspection date corresponding to the order and the current time. The inspection date score for each order is calculated based on the above formula 2, which represents the urgency of the order's timeliness. N is the preset delivery date evaluation period, preferably 30.

[0056] Furthermore, an order type score is determined based on the order type of each order. Preferably, the order type score is 1 for a follow-up order, 0.9 for a repeat order, 0.7 for a trade fair order, 0.5 for ribbing, 0.3 for work clothes, and 0.1 for emergency orders. By establishing a mapping relationship between order type and score, order types with higher delivery time sensitivity, stronger customer response requirements, or higher production continuity requirements correspond to higher order type scores, while ordinary orders or lower priority order types correspond to lower order type scores, ensuring that the production scheduling process balances delivery time requirements and order business attributes.

[0057] Furthermore, the secondary processing type score is determined based on the secondary processing type of each order; preferably, when the secondary processing type is one of brushing, printing, embroidery, or crochet, the secondary processing type score is 1; when the secondary processing type is flatbed sewing or fabric, the secondary processing type score is 0.7; when the secondary processing type is button sewing, the secondary processing type score is 0.3; when the secondary processing type is empty, the secondary processing type score is 0.

[0058] It should be noted that the above-mentioned order type scores and secondary processing type scores are merely exemplary configurations and do not constitute a limitation on the scope of protection of this application. In practical applications, the scores corresponding to different order types and secondary processing types can be adjusted according to the enterprise's production scheduling strategy, order urgency, customer level, process complexity, or production resource allocation. When a new order type or a new secondary processing type is added, a corresponding score can also be configured for it, and it should participate in the production scheduling process according to the same priority calculation logic. All of these should fall within the scope of protection of this application.

[0059] Furthermore, based on Formula 1 above, the priority of each order is calculated and sorted from high to low priority to obtain a priority order sequence.

[0060] In one embodiment of this application, the process of constraining and reducing the priority order sequence to obtain a reduced order sequence includes: classifying orders with the same sweater style in the priority order sequence into the same style group based on order information; when orders in the same style group are assigned to the same flat knitting machine, they are arranged consecutively in the order scheduling sequence corresponding to that flat knitting machine; locking orders in the priority order sequence that have a production start status identifier, so that the assigned flat knitting machine, production sequence, and determined production time corresponding to the locked orders remain unchanged in the subsequent scheduling optimization process; and removing orders from the priority order sequence that do not meet preset hard constraints, the preset hard constraints including: order needle type matching check, order material completeness check, and order sample sealing completion check.

[0061] Specifically, the constraint reduction is used to preprocess the priority order sequence before the genetic algorithm is executed, in order to reduce invalid scheduling combinations and retain order constraints that have a real impact on the scheduling results.

[0062] Specifically, based on the sweater style information in the order information, orders with the same sweater style are first categorized into the same style group. Since orders with the same style usually have the same or similar yarn, needle type, density, process parameters and changeover preparation requirements in the flat knitting machine production process, prioritizing the continuous processing of orders within the same style group in subsequent iterations and optimizations can reduce the changeover time loss caused by switching between different styles on the flat knitting machine and improve the continuous production efficiency of the flat knitting machine.

[0063] Secondly, orders with a "production started" status in the priority order sequence are locked. For orders that have already started production, their corresponding knitting machines, production sequences, and determined production times should generally not be readjusted during subsequent scheduling processes; otherwise, it would cause frequent changes in on-site production plans, equipment task conflicts, or invalidation of issued production instructions. Therefore, this application treats these orders as locked orders, ensuring that their assigned knitting machines, production sequences, and determined production times remain unchanged during subsequent scheduling optimization processes, and only unlocked orders are optimized and adjusted.

[0064] Finally, the priority order sequence is filtered based on preset hard constraints to remove orders that do not meet the pre-production conditions. These preset hard constraints include order needle type matching checks, order material completeness checks, and order sample sealing completion checks. Specifically, the order needle type matching check determines whether the needle type required by the order matches the needle type of the available flat knitting machine; the order material completeness check determines whether the required yarn or accessories meet the production conditions; and the order sample sealing completion check determines whether the corresponding sample garment or process confirmation has been completed. For orders that do not meet these hard constraints, even if they have a high priority, they cannot form an executable production task within the current production cycle, and therefore are removed from the current production set and set to a postponed production status.

[0065] Through the aforementioned constraint reduction process, the original order set can be transformed into a reduced order sequence more suitable for optimization before the genetic algorithm starts. Specifically, grouping and continuously processing orders of the same style reduces the number of order permutations and combinations that the genetic algorithm needs to search, and lowers the computational complexity due to style changeover time. Locking orders already in production reduces the number of genes that need to be modified in the genetic algorithm, avoiding unnecessary disturbances to the existing production plan. Hard constraint screening preemptively excludes orders that cannot be actually produced, preventing the genetic algorithm from repeatedly searching in the infeasible solution space. Therefore, the subsequent genetic algorithm only needs to iteratively optimize orders that meet production conditions and are still adjustable, thereby narrowing the search space, increasing convergence speed, and improving the executability of the final flat knitting machine production scheduling scheme.

[0066] Step S13: Based on the simplified order sequence and the flat knitting machine equipment data, construct an initial flat knitting machine production scheduling scheme set, and use a genetic algorithm to iteratively optimize the initial flat knitting machine production scheduling scheme set to generate a final flat knitting machine production scheduling scheme; wherein, based on a preset fitness model, calculate the fitness of the candidate flat knitting machine production scheduling schemes generated during the iterative optimization process to meet the preset termination condition, and determine the candidate flat knitting machine production scheduling scheme with the highest fitness and meeting the preset constraint condition as the final flat knitting machine production scheduling scheme.

[0067] Specifically, based on the priority order of each order in the simplified order sequence, flat knitting machines and production times are allocated to each order in turn to form several initial flat knitting machine production scheduling schemes, which constitute the set of initial flat knitting machine production scheduling schemes. Among them, when selecting flat knitting machines for any order, priority is given to selecting flat knitting machines that meet the needle type requirements of the order and have the same or similar change preparation conditions as the order, followed by selecting flat knitting machines that are in an idle state, and then selecting the flat knitting machine with the earliest expected completion time.

[0068] Furthermore, after forming the initial flat knitting machine scheduling scheme set, the initial flat knitting machine scheduling scheme set is subjected to simulated annealing perturbation processing. Specifically, the initial temperature T0, annealing coefficient α, and perturbation probability P are set. mutate Wherein, according to the perturbation probability P mutate A partial disturbance is applied to some orders in the initial candidate flat knitting machine scheduling scheme. This partial disturbance includes adjusting at least one of the following: the flat knitting machine equipment corresponding to the order, the production sequence, or the production start time. If the fitness of the disturbed candidate flat knitting machine scheduling scheme is higher than that of the original scheme, the disturbed scheme is accepted. If the fitness of the disturbed scheme is not higher than that of the original scheme, the scheme is accepted according to the annealing acceptance probability P. accept Determine whether to accept the candidate flat knitting machine scheduling plan after the disturbance, wherein P accept =exp(-ΔF / T), where ΔF represents the difference between the fitness of the candidate flat knitting machine scheduling scheme before the disturbance and the fitness of the candidate flat knitting machine scheduling scheme after the disturbance. ΔF is non-negative when the fitness after the disturbance is not higher than the fitness before the disturbance, and T represents the current annealing temperature.

[0069] Furthermore, in one specific embodiment, the initial temperature T0 is set to 1000, the annealing coefficient α is set to 0.95, and the disturbance probability P... mutate Set to 0.3. After each round of perturbation processing is completed, update the current annealing temperature according to T=αT, and continue to execute the next round of perturbation processing until the preset annealing termination condition is met.

[0070] In one embodiment of this application, the fitness of candidate flat knitting machine scheduling schemes generated during iterative optimization is calculated based on a preset fitness model. The specific process includes:

[0071] ;(Formula 3)

[0072] Wherein, Fitness refers to fitness level. These are delivery time satisfaction, flat knitting machine utilization rate, style change evaluation value, and production line balance; P represents a constraint / penalty term. These are the corresponding weighting coefficients. Preferably, =0.35, =0.25, =0.15, =0.15, =0.1, no specific limit is set here.

[0073] In one embodiment of this application, the delivery date satisfaction is calculated based on the time difference between the expected completion time of each order in the candidate flat knitting machine production schedule and the corresponding inspection date; the flat knitting machine equipment utilization rate is determined based on the ratio of the effective production time of each flat knitting machine to its available production time; the style change evaluation value is determined comprehensively based on the differences in sweater styles between adjacent production schedule orders and the resulting style change time loss; and the production line balance is determined based on the degree of matching between the flat knitting machine's sheathing capacity and its edge processing capacity.

[0074] Specifically, the delivery date satisfaction rate is calculated as follows:

[0075] ;(Formula 4)

[0076] in, Indicates the order quantity. The completion time corresponding to the candidate flat knitting machine production scheduling plan. The inspection date is the specified delivery date. The delivery date satisfaction score is used to evaluate the degree of matching between the expected completion time of each order in the candidate flat knitting machine production plan and the corresponding inspection date; when the expected completion time of an order is not later than the inspection date, the corresponding order has a high delivery date satisfaction score; when the expected completion time of an order is later than the inspection date, the delivery date satisfaction score of the corresponding order is reduced according to the delay time.

[0077] The specific calculation method for the utilization rate of the flat knitting machine is as follows:

[0078] ;(Formula 5)

[0079] Where M represents the number of flat knitting machines. Let m be the effective production time of the m-th flat knitting machine. Let m be the available production time of the m-th flat knitting machine within the production scheduling cycle. The flat knitting machine utilization rate is used to evaluate the degree of utilization of the flat knitting machine capacity by the candidate flat knitting machine production scheduling scheme; by calculating the ratio between the effective production time and available production time of each flat knitting machine, and summarizing the corresponding ratios of each flat knitting machine, the equipment utilization level of the candidate flat knitting machine production scheduling scheme is determined.

[0080] The specific calculation method for the model replacement evaluation value is as follows:

[0081] ;(Formula 6)

[0082] in, For the model change rating, The number of style changes in the current candidate flat knitting machine production plan is denoted by O, where O represents the order quantity. The style change evaluation value is used to evaluate the production preparation loss caused by the flat knitting machine switching between adjacent orders in the candidate flat knitting machine production plan; the fewer the number of style changes or the lower the style change time loss, the higher the style change evaluation value; the more the number of style changes or the higher the style change time loss, the lower the style change evaluation value.

[0083] The specific calculation method for the production line balance is as follows:

[0084] ;(Formula 7)

[0085] in, This indicates the flat knitting machine's ability to weave or its ability to drop fabric. This indicates the tailing processing capacity. The production line balance is used to evaluate the degree of capacity matching between the flat knitting machine's weaving process and the tailing sewing process; the closer the flat knitting machine's shedding capacity and the tailing processing capacity are, the higher the production line balance is; the greater the difference between the two, the lower the production line balance is, in order to reduce the backlog of work-in-process after flat knitting machine shedding or the waiting time in the tailing process.

[0086] In addition, the constraint penalty item P includes several constraints. When the candidate flat knitting machine scheduling scheme violates the several constraints, the fitness of the candidate flat knitting machine scheduling scheme is reduced by the constraint penalty item P, or the candidate flat knitting machine scheduling scheme is directly eliminated when the degree of violation reaches the preset elimination condition.

[0087] Specifically, the constraints include at least one of the following: when the date of the flat knitting machine's production off-line is later than the first preset lead time before the inspection date, a delivery penalty value for the flat knitting machine is calculated based on the number of days the flat knitting machine is delayed; when the date of the tailoring machine's production off-line is later than the second preset lead time before the inspection date, a delivery penalty value for the tailoring machine is calculated based on the tailoring machine's delay days; when the needle type required by the order does not match the needle type of the allocated flat knitting machine equipment, the corresponding candidate flat knitting machine production plan is directly eliminated; when the order's production start time is earlier than the material matching time, a penalty value for incomplete material matching is calculated; when the daily capacity of any resource in the candidate flat knitting machine production plan exceeds the corresponding resource limit, a capacity over-limit penalty value is calculated based on the over-limit ratio.

[0088] By setting the constraint penalty term P, the genetic algorithm can optimize delivery time satisfaction, equipment utilization, style change evaluation value and production line balance, while avoiding generating unexecutable solutions that violate needle type matching, material completeness, inspection lead time or resource capacity limitations, thereby improving the on-site executability of the final flat knitting machine scheduling plan and the tailoring scheduling plan.

[0089] Furthermore, when iteratively optimizing the set of initial flat knitting machine scheduling schemes using a genetic algorithm, an initial flat knitting machine scheduling scheme is represented as a chromosome. The chromosome is used to characterize the allocation relationship, production order, and production time between each order and the flat knitting machine in the reduced order sequence. The genes in the chromosome are used to represent the scheduling information of a single order on the corresponding flat knitting machine, and the scheduling information includes the order identifier, the flat knitting machine identifier, the start time, and the end time.

[0090] Further, an initial population is formed by initializing the set of flat knitting machine scheduling schemes, and the fitness of each chromosome is calculated based on a preset fitness model. Then, selection, crossover, and mutation operations are performed on the population to generate new candidate flat knitting machine scheduling schemes. The fitness calculation and selection, crossover, and mutation processes are repeated until a preset termination condition is met, and the candidate flat knitting machine scheduling scheme with the highest fitness is determined as the final flat knitting machine scheduling scheme. The preset termination condition is that the number of iterations exceeds a preset maximum number of iterations or the fitness change is within a preset range in 50 consecutive iterations. Preferably, the preset maximum number of iterations is 1000, and the preset range is preferably [-0.5%, 0.5%], but this is not specifically limited and can be set according to actual needs.

[0091] Step S14: Obtain the predicted flat knitting machine shedding data for each order from the final flat knitting machine scheduling plan; determine the tailing process requirements for each order based on the predicted flat knitting machine shedding data and the order information; select a set of candidate tailing personnel who meet the tailing process requirements from the preset tailing personnel database; calculate the tailing scheduling start time for each order based on the tailing control strategy; assign tailing personnel to each order according to the set of candidate tailing personnel and construct a tailing scheduling plan in combination with the tailing scheduling start time.

[0092] First, since the overlocking process can only be started after some garment pieces of the corresponding order have been finished, and can be executed in parallel with the flat knitting process when the flat knitting task has not been completed, this step first calculates the predicted flat knitting fabrication data for each order from the final flat knitting production plan. The predicted flat knitting fabrication data includes the flat knitting fabrication time, the number of fabric pieces per day or the cumulative number of fabric pieces, as the upstream input for overlocking production.

[0093] Furthermore, based on the predicted knitting machine fabrication data and the order information, the overlocking process requirements for each order are determined. These overlocking process requirements may include at least one of the following: overlocking processing time, overlocking completion time requirements, style difficulty requirements, personnel skill requirements, and unit-time production capacity requirements. Specifically, the overlocking processing time can be determined based on the order quantity and the processing time per overlock piece; the overlocking completion time requirements can be determined based on the order's inspection date and the overlocking inspection lead time; and the personnel skill requirements can be determined based on the sweater style, secondary processing type, or process difficulty of the order.

[0094] Furthermore, a set of candidate tailoring personnel who meet the tailoring process requirements is selected from the preset tailoring personnel database. The preset tailoring personnel database can store the personnel identifier, skill level, preferred styles, available working hours, current workload, and processing capacity per unit time for each tailoring personnel. Based on the tailoring process requirements corresponding to each order, the system selects tailoring personnel from the preset tailoring personnel database whose skills match, are available, and whose production capacity meets the requirements, thus forming a set of candidate tailoring personnel.

[0095] Furthermore, the start time for tailoring production is calculated for each order based on the tailoring control strategy. This tailoring control strategy can be based on work-in-process (WIP) control, which determines whether the tailoring process, if started at a certain time, will experience delays due to insufficient garment pieces or lead to a backlog of semi-finished products between the flat knitting machine and the tailoring process, based on predicted flat knitting machine data, the processing capacity of the tailoring personnel, and a preset safety stock threshold. When the amount of WIP reaches the preset safety stock threshold and can support continuous tailoring processing, the corresponding time is determined as the start time for tailoring production.

[0096] In one example of this application, the calculation of the tailing schedule start time for each order based on the tailing control strategy specifically includes: obtaining the number of pieces dropped in each scheduling cycle corresponding to the order based on the predicted flat knitting machine drop data for any order; and calculating the current tailing work-in-process quantity based on the number of pieces dropped in the order using the following formula:

[0097] ;(Formula 8)

[0098] in, Let be the current work-in-process inventory at the end of the t-th production cycle. Let be the number of films discarded per day in the t-th production cycle. The number of sets to be completed in the t-th production cycle is estimated based on the unit time processing capacity and available working hours of the candidate setters.

[0099] When the When the safety stock threshold is greater than or equal to the preset safety stock threshold, the production start time of the corresponding t-th production cycle shall be used as the start time of the production schedule.

[0100] Furthermore, based on the candidate set of matching personnel, matching personnel are assigned to each order, and a matching production scheduling plan is constructed in conjunction with the matching production scheduling start time. Specifically, the allocation can be determined based on the candidate matching personnel's skill level, preferred styles, current workload, and processing capacity per unit time, prioritizing personnel with higher skill levels or better matching styles to handle corresponding orders; when multiple personnel meet the requirements, priority can be given to personnel with lower current workloads or more available working hours. The resulting matching production scheduling plan includes the matching production start time, matching end time, assigned personnel, and planned processing quantity for each order.

[0101] In one embodiment, the final flat knitting machine scheduling plan and the tailoring scheduling plan can be presented in the form of an allocation matrix or a Gantt chart. The final flat knitting machine scheduling plan can represent the allocation relationship between each order and the flat knitting machine through an order-flat knitting machine allocation matrix, or it can represent the production start time, production end time, and changeover period for each order on the corresponding flat knitting machine through a flat knitting machine Gantt chart. The tailoring scheduling plan can represent the task allocation relationship between each order and the tailoring personnel through an order-tailoring personnel allocation matrix, or it can represent the tailoring scheduling start time, tailoring end time, and processing quantity for each order at the corresponding tailoring personnel through a tailoring tailoring Gantt chart. It should be noted that the allocation matrix is ​​mainly used to represent the correspondence between orders and resources, while the Gantt chart is mainly used to represent the execution process of order tasks on the timeline. Both can be used individually or in combination to intuitively display the collaborative scheduling results of the flat knitting and tailoring processes.

[0102] Through the above processing, the fabric overlay scheduling plan is not generated independently, but rather based on the predicted flat knitting machine fabric drop data output by the final flat knitting machine scheduling plan, enabling downstream collaborative scheduling. This ensures that the start time and personnel allocation of the fabric overlay process match the flat knitting machine fabric drop cycle. On the one hand, it avoids the situation where fabric overlay starts too early, resulting in waiting due to incomplete garment pieces; on the other hand, it avoids the situation where fabric overlay starts too late, leading to a large backlog of semi-finished and work-in-process products, thereby achieving a balance in production capacity between the flat knitting machine fabrication process and the fabric overlay sewing process.

[0103] Figure 3 This is a schematic block diagram of a collaborative scheduling system 300 for a flat knitting machine and sweater seams based on genetic algorithms and constraint reduction, provided in an embodiment of this application. Figure 3 As shown, the system includes a data acquisition module 301, a constraint processing module 302, a genetic optimization module 303, and a production scheduling module 304.

[0104] The data acquisition module 301 is used to acquire production scheduling input data, which includes order data, flat knitting machine equipment data, tailoring resource data, and constraint data. The order data includes several orders and their corresponding order information. The tailoring resource data characterizes the production scheduling capability of the tailoring process, including at least one of tailoring personnel identification, skill level, preferred styles, available working hours, current workload, and processing capacity per unit time. The tailoring resource data can be obtained from a preset tailoring personnel database.

[0105] The constraint processing module 302 is used to calculate the priority of each order based on the order information, sort the orders according to the priority, obtain a priority order sequence, and perform constraint reduction on the priority order sequence to obtain a reduced order sequence; the constraint reduction includes grouping based on the sweater styles corresponding to the orders in the priority order sequence, locking the orders in the priority order sequence that have started production, and performing hard constraint filtering on the priority order sequence;

[0106] The genetic optimization module 303 is used to construct an initial set of flat knitting machine production scheduling schemes based on the reduced order sequence and the flat knitting machine equipment data, and to iteratively optimize the initial set of flat knitting machine production scheduling schemes using a genetic algorithm to generate a final flat knitting machine production scheduling scheme; wherein, the fitness of the candidate flat knitting machine production scheduling schemes generated during the iterative optimization process is calculated based on a preset fitness model to meet a preset termination condition, and the candidate flat knitting machine production scheduling scheme with the highest fitness and meeting the preset constraints is determined as the final flat knitting machine production scheduling scheme;

[0107] The tailing scheduling module 304 is used to obtain the predicted flat knitting machine shedding data for each order from the final flat knitting machine scheduling plan, determine the tailing process requirements for each order based on the predicted flat knitting machine shedding data and the order information; filter the set of candidate tailing personnel that meet the tailing process requirements from the preset tailing personnel database, calculate the tailing scheduling start time for each order based on the tailing control strategy, assign tailing personnel to each order according to the set of candidate tailing personnel, and construct a tailing scheduling plan in combination with the tailing scheduling start time.

[0108] It should be understood that the specific process of each module performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0109] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0110] Figure 4 This is a schematic block diagram of the electronic terminal provided in an embodiment of this application. Figure 4 As shown, the electronic terminal 400 includes at least one processor 401, a memory 402, at least one network interface 403, and a user interface 405. The various components in the electronic terminal 400 are coupled together via a bus system 404. It is understood that the bus system 404 is used to implement communication between these components. In addition to a data bus, the bus system 404 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 4 The general will label all buses as bus systems.

[0111] The user interface 405 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0112] It is understood that memory 402 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0113] In this embodiment of the invention, the memory 402 is used to store various types of data to support the operation of the electronic terminal 400. Examples of this data include: any executable program for operation on the electronic terminal 400, such as the operating system 4021 and application program 4022; the operating system 4021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 4022 may contain various applications, such as media players, browsers, etc., for implementing various application services. The method for collaborative scheduling of knitwear flat knitting machines and loop fasteners based on genetic algorithms and constraint reduction provided in this embodiment of the invention can be included in the application program 4022.

[0114] The methods disclosed in the above embodiments of the present invention can be applied to processor 401, or implemented by processor 401. Processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 401 or by instructions in the form of software. The processor 401 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 401 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 401 may be a microprocessor or any conventional processor, etc. The steps of the sweater flat knitting machine and loop-joint production scheduling method based on genetic algorithm and constraint reduction provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in a memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0115] In an exemplary embodiment, the electronic terminal 400 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0116] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to perform the method of any of the embodiments described above.

[0117] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to perform the method of any of the embodiments described above.

[0118] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0119] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0120] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0124] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0125] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] In summary, this application provides a method, system, medium, terminal, and program product for collaborative scheduling of flat knitting machines and sweater seams based on genetic algorithms and constraint reduction. The method includes: acquiring scheduling input data and calculating the priority of each order; acquiring a priority order sequence; performing constraint reduction on the priority order sequence to obtain a reduced order sequence; constructing an initial flat knitting machine scheduling scheme set based on the reduced order sequence and the flat knitting machine equipment data; iteratively optimizing the initial flat knitting machine scheduling scheme set using a genetic algorithm to generate a final flat knitting machine scheduling scheme; determining the seaming process requirements and acquiring a candidate seaming personnel set based on the final flat knitting machine scheduling scheme; and calculating the seaming scheduling start time for each order based on the seaming control strategy, thereby constructing a seaming scheduling scheme. This application can coordinate the scheduling of flat knitting machines and seams and improve production efficiency. Therefore, this application effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0127] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for collaborative scheduling of knitting flat knitting machines and fabric seams based on genetic algorithms and constraint reduction, characterized in that, include: Obtain production scheduling input data, which includes order data, flat knitting machine equipment data, tailoring resource data, and constraint data; wherein, the order data includes several orders and their corresponding order information; Based on the order information, the priority of each order is calculated, and the orders are sorted according to the priority to obtain a priority order sequence. The priority order sequence is then constrained and reduced to obtain a reduced order sequence. The constraint reduction includes grouping based on the sweater styles corresponding to the orders in the priority order sequence, locking the orders in the priority order sequence that have started production, and performing hard constraint filtering on the priority order sequence. Based on the simplified order sequence and the flat knitting machine equipment data, an initial flat knitting machine production scheduling scheme set is constructed, and a genetic algorithm is used to iteratively optimize the initial flat knitting machine production scheduling scheme set to generate a final flat knitting machine production scheduling scheme; wherein, based on a preset fitness model, the fitness of the candidate flat knitting machine production scheduling schemes generated during the iterative optimization process is calculated to meet a preset termination condition, and the candidate flat knitting machine production scheduling scheme with the highest fitness and meeting the preset constraints is determined as the final flat knitting machine production scheduling scheme; Obtain the predicted flat knitting machine shedding data for each order from the final flat knitting machine production schedule. Determine the tailing process requirements for each order based on the predicted flat knitting machine shedding data and the order information. Select a set of candidate tailing personnel who meet the tailing process requirements from the preset tailing personnel database. Calculate the tailing production start time for each order based on the tailing control strategy. Assign tailing personnel to each order according to the set of candidate tailing personnel and construct a tailing production schedule based on the tailing production start time.

2. The method for collaborative scheduling of knitting flat knitting machines and loopback fabrication based on genetic algorithm and constraint reduction as described in claim 1, characterized in that, The specific process of calculating the priority of each order based on the order information includes: ; ; in, Let i be the priority of the i-th order. The score is given for the inspection date of the i-th order. The order type score for the i-th order. The score for the secondary processing type of the i-th order. Let N be the remaining number of days for the inspection of the i-th order, N be the preset delivery date evaluation period, and a, b, and c be the corresponding weight coefficients.

3. The method for collaborative scheduling of knitting flat knitting machines and loopback fabrication based on genetic algorithm and constraint reduction as described in claim 1, characterized in that, The specific process of constraining and reducing the priority order sequence to obtain the reduced order sequence includes: Based on the order information, orders with the same sweater style in the priority order sequence are classified into the same style group. When orders in the same style group are assigned to the same flat knitting machine, they are arranged consecutively in the order scheduling sequence corresponding to that flat knitting machine. Orders with a "production started" status in the priority order sequence are locked, so that the allocated flat knitting machine, production sequence, and determined production time corresponding to the locked orders remain unchanged in the subsequent production scheduling optimization process. Orders that do not meet the preset hard constraints are removed from the priority order sequence. The preset hard constraints include: order needle type matching check, order material completeness check, and order sample sealing completion check.

4. The method for collaborative scheduling of knitting flat knitting machines and loopback fabrication based on genetic algorithm and constraint reduction as described in claim 1, characterized in that, The fitness of candidate flat knitting machine scheduling schemes generated during iterative optimization is calculated based on a pre-defined fitness model. The specific process includes: ; Wherein, Fitness refers to fitness level. These are delivery time satisfaction, flat knitting machine utilization rate, style change evaluation value, and production line balance; P represents a constraint / penalty term. These are the corresponding weighting coefficients.

5. The method for collaborative scheduling of knitting flat knitting machines and loopback fabrication based on genetic algorithm and constraint reduction according to claim 4, characterized in that, The delivery time satisfaction is calculated based on the time difference between the expected completion time of each order and the corresponding inspection date in the candidate flat knitting machine production plan; the flat knitting machine equipment utilization rate is determined based on the ratio of the effective production time of each flat knitting machine to its available production time; the style change evaluation value is determined based on the differences in sweater styles between adjacent production orders and the resulting style change time loss; the production line balance is determined based on the degree of matching between the flat knitting machine's sheathing capacity and its overlock processing capacity.

6. The method for collaborative scheduling of knitting flat knitting machines and loopback fabrication based on genetic algorithm and constraint reduction according to claim 1, characterized in that, The calculation of the set-out scheduling start time for each order based on the set-out control strategy specifically includes: The number of pieces dropped in each production cycle corresponding to any order is obtained based on the predicted flat knitting machine drop data of any order. The current work-in-process quantity is calculated based on the number of pieces dropped in the order using the following formula: ; in, Let be the current work-in-process inventory at the end of the t-th production cycle. Let be the number of films discarded per day in the t-th production cycle. The number of sets to be completed in the t-th production cycle is estimated based on the unit time processing capacity and available working hours of the candidate setters. When the When the safety stock threshold is greater than or equal to the preset safety stock threshold, the production start time of the corresponding t-th production cycle shall be used as the start time of the production schedule.

7. A collaborative scheduling system for knitting flat knitting machines and loopback fabrication based on genetic algorithms and constraint reduction, characterized in that, include: The data acquisition module is used to acquire production scheduling input data, which includes order data, flat knitting machine equipment data, tailoring resource data, and constraint data; wherein, the order data includes several orders and corresponding order information; The constraint processing module is used to calculate the priority of each order based on the order information, sort the orders according to the priority, obtain a priority order sequence, and perform constraint reduction on the priority order sequence to obtain a reduced order sequence; the constraint reduction includes grouping based on the sweater styles corresponding to the orders in the priority order sequence, locking the orders in the priority order sequence that have started production, and performing hard constraint filtering on the priority order sequence; The genetic optimization module is used to construct an initial set of flat knitting machine scheduling schemes based on the reduced order sequence and the flat knitting machine equipment data, and to iteratively optimize the initial set of flat knitting machine scheduling schemes using a genetic algorithm to generate a final flat knitting machine scheduling scheme. Specifically, the fitness of candidate flat knitting machine scheduling schemes generated during the iterative optimization process is calculated based on a preset fitness model to meet preset termination conditions. The candidate flat knitting machine scheduling scheme with the highest fitness and meeting preset constraints is determined as the final flat knitting machine scheduling scheme. The tailoring scheduling module is used to obtain the predicted flat knitting machine shedding data for each order from the final flat knitting machine scheduling plan, determine the tailoring process requirements for each order based on the predicted flat knitting machine shedding data and the order information, filter the candidate tailoring personnel set that meets the tailoring process requirements from the preset tailoring personnel database, calculate the tailoring scheduling start time for each order based on the tailoring control strategy, assign tailoring personnel to each order according to the candidate tailoring personnel set, and construct the tailoring scheduling plan in combination with the tailoring scheduling start time.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for collaborative scheduling of knitwear flat knitting machines and fabric seams based on genetic algorithms and constraint reduction as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes computer program code, which, when run on a computer, enables the computer to implement the collaborative scheduling method for knitwear flat knitting machines and fabric seams based on genetic algorithms and constraint reduction as described in any one of claims 1 to 6.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the collaborative scheduling method for knitwear flat knitting machines and overlock machines based on genetic algorithms and constraint reduction as described in any one of claims 1 to 6.