Clothing production line worker scheduling method based on analytic hierarchy process and NSGA-II algorithm

Through the combination of hierarchical analysis method and NSGA-II algorithm, the problems of workers' skills differences and data islands in clothing production lines are solved, and the optimization of worker scheduling and productivity improvement are achieved. It is suitable for a variety of production line workers' scheduling scenarios.

CN118917606APending Publication Date: 2024-11-08DALIAN POLYTECHNIC UNIVERSITY
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202410990324.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing clothing production line workers' scheduling methods lack objective evaluation and data utilization of workers' skills differences, resulting in low production efficiency and difficult to apply scheduling solutions, and unable to adapt to workers' heterogeneity and mobility.

Method used

Using the worker scheduling method based on hierarchical analysis and NSGA-II algorithm, the worker skill evaluation index is determined by collecting production data, calculating the worker skill maturity, and using greedy algorithms and adaptive cross-mutation operators to improve the NSGA-II algorithm, establishing Multi-objective optimization model to achieve optimization of worker scheduling.

Benefits of technology

It improves the production efficiency of the clothing production line, reduces the waste of scheduling resources, enhances data utilization, provides scientific scheduling decision-making basis, and is suitable for scheduling situations of workers in various production line.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917606A_ABST
    Figure CN118917606A_ABST
Patent Text Reader

Abstract

The invention provides a clothing production line worker scheduling method based on analytic hierarchy process and an NSGA-II algorithm, and the method comprises the specific steps: collecting production data of a production group, including station production data, worker data, production logs of a production line, and the like; determining worker skill evaluation indexes by using an analytic hierarchy process, determining the importance of every two indexes through a plurality of experts, determining the weight of the evaluation indexes, and evaluating the worker skill according to the production data; respectively calculating the skill maturity of a worker in a certain station process and the skill maturity of a production line; aiming at skill maturity and yield stability of worker scheduling, establishing a multi-objective optimization model based on an NSGA-II algorithm; and calculating an optimal worker scheduling strategy according to the multi-objective optimization model. The method not only considers the skill level difference of workers for different station processes, but also fully considers the yield stability problem before and after production line scheduling, and realizes the effectiveness of production line worker scheduling through iterative optimization.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of production scheduling, and in particular to a method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm. Background Art

[0002] The clothing production line is composed of many workers and production stations, and the processing capabilities of workers vary. In the process of personnel scheduling and dispatching, the skill evaluation of clothing production line workers is mainly based on subjective evaluation, lacking objective and quantitative inherent attributes as the basis for analysis. The traditional empirical worker scheduling model and skill evaluation method are greatly affected by human fluctuations in thought and can no longer adapt to changes in market demand. At the same time, with the deepening of the digitalization of clothing companies, data silos surrounding workers' production data have become more serious. Therefore, how to make full use of labor data and reasonably consider the differences in the skill levels of production line workers can make production line production more adaptable to the heterogeneity and mobility of workers, which has important guiding significance for the dispatch of workers in clothing production lines.

[0003] Regarding the factors affecting clothing production efficiency, less attention has been paid to the use and analysis of production line labor data, as well as the impact of differences in worker skills on production scheduling. Existing solutions have not yet combined labor data to implement skill evaluation of clothing production personnel, and have not provided a production scheduling plan based on this. It can be seen that in the research on the evaluation of clothing production line workers' skills, there are practical problems such as insufficient understanding of the actual production situation, low utilization of workers' production data resources, lack of exploration of workers' heterogeneity and instability, and difficulty in applying scheduling plans.

[0004] Based on the above problems, it is very important to design a clothing production line worker scheduling method based on hierarchical analysis method and NSGA-II genetic algorithm, which can make full use of labor data and combine data analysis to quickly optimize worker scheduling, thereby improving the production efficiency of the clothing production line.

[0005] The Chinese patent document with application number CN202211432872.6 describes a personnel scheduling method and system for a personalized clothing production line based on a genetic algorithm. The relevant steps are mainly: by obtaining the employee information of the production team and the production plan information of the target personalized clothing, optimizing through the shortest path parallel scheduling strategy, using the genetic algorithm to solve the problem, and obtaining the optimal personnel allocation production scheduling plan. Although the personnel proficiency and balance rate issues in the workshop production and processing process are taken into account, the shortcoming is that there is no consideration of the judgment of the workers' skill evaluation based on the production data, but it is determined by the subjective judgment of the team leader of the production team, and the process proficiency of the employees in the production team for the entire production process is directly obtained. Summary of the invention

[0006] According to the above, the existing clothing production scheduling scheme has not yet carried out the analysis of the skill differences of clothing production personnel around the production line data, and the problem of formulating a production scheduling plan is given, and a clothing production line worker scheduling method based on hierarchical analysis and NSGA-II algorithm is provided. The present invention makes full use of labor data, a clothing production line worker scheduling method based on hierarchical analysis and NSGA-II algorithm, and combines data analysis to quickly optimize worker scheduling, thereby improving the production efficiency of the clothing production line.

[0007] The technical means adopted by the present invention are as follows:

[0008] A method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm, the specific steps include:

[0009] S1. Collect production data of the production team, including workstation production data, worker data and production log of the production line;

[0010] S2. Use the analytic hierarchy process to determine the worker skill evaluation indicators, and determine the weights of the evaluation indicators through the judgment matrix between the indicators;

[0011] S3, evaluate the workers' skills based on the production data in S1, and calculate the workers' skill maturity in the workstation process and the production line skill maturity respectively;

[0012] S4. Aiming at the skill maturity and output stability of worker scheduling, a greedy algorithm is used to locally optimize an objective function, and then the NSGA-II algorithm is improved through the adaptive crossover and mutation operator methods, and a multi-objective optimization model is established based on the improved NSGA-II algorithm;

[0013] S5. Calculate the optimal worker scheduling strategy based on the multi-objective optimization model in S4.

[0014] Furthermore, step S1 specifically includes:

[0015] The worker data includes: age, gender, basic information of education, equipment data, process data, historical production efficiency, historical rework rate, skill distribution of workers, process steps they have been responsible for during the task cycle, current process steps they are responsible for, historical attendance rate, and whether there is a machine failure in the event during the cycle;

[0016] The workstation production data includes: process table, process flow, equipment data and process data;

[0017] The production log of the production line includes the daily output, whether there is personnel scheduling on the current working day, the output log of each workstation and the rework rate.

[0018] Furthermore, step S2 specifically includes:

[0019] S21. Use the analytic hierarchy process to determine the evaluation indicators and build a multi-layer structure to determine whether the worker is competent for the current work process; set the primary and secondary indicators for worker evaluation and build a skill evaluation model for production line workers in clothing enterprises;

[0020] The first-level indicators include: basic attributes, effort level, proficiency level and ability range;

[0021] The secondary indicators include: age, gender, education level, historical production data, historical attendance rate, production efficiency, rework rate, skill distribution, learning ability, and event handling ability;

[0022] S22. According to the skill evaluation model of the workers in the production line of the garment enterprise in S21, the weight of each indicator is calculated through the judgment matrix of the importance of each pair of worker skill indicators:

[0023]

[0024] Among them, a ij is the comparison result of the relative importance of indicator factor i and indicator factor j;

[0025] For the first-level and second-level indicators, compare each indicator element in pairs and evaluate them according to their importance to form a judgment matrix A;

[0026] Each level of matrix uses the consistency test index CR to judge the rationality of the weight distribution of each indicator in the matrix.

[0027] Furthermore, step S3 specifically includes:

[0028] S31. Design a method for calculating the skill maturity of workers in a certain workstation process, calculate the score values ​​of workers' indicators at all levels by normalizing the production data, and realize the quantification of evaluation indicators;

[0029] Combined with the evaluation weights of indicators at all levels, the worker's score is weighted and calculated to obtain the worker's skill maturity M in a certain workstation process:

[0030]

[0031] In the formula, X is the production data of workers under a certain indicator factor, X norm is the standardized value of worker production data under a certain indicator factor, that is, the score value R; Z min Indicates the minimum production value under this indicator when workers are concentrated; Z max Indicates the maximum production value under this indicator in the concentration of workers;

[0032] M=Σω bc *rbc

[0033] In the formula, ω bc is the indicator weight of the cth secondary indicator under the bth primary indicator; r bc Provide workers with scoring values ​​for each level of indicators;

[0034] S32. Design a method for calculating the skill maturity of a production line. Use the decision variable k to determine the competence relationship between workstation d and person e, and construct the overall skill maturity of workers in the clothing production line:

[0035]

[0036]

[0037] In the formula, h de represents the skill maturity of the dth workstation and the eth person, that is, the M value in S31, k is the decision variable, which determines whether there is production data of this workstation in the worker's skill distribution, k de =1 indicates that the worker is competent, that is, worker e can be assigned to workstation d, k de When =0, it means that the worker is not competent, that is, worker e cannot be assigned to workstation d.

[0038] Furthermore, step S4 specifically includes:

[0039] S41. Assume that the garment assembly line has m workstations, d = 1, 2, ..., m, and n workers, e = 1, 2, ..., n;

[0040] Design objective functions f1 and f2. The scheduling goal is to maximize the sum of the skill maturity of all workers in the production line, and to ensure that the output of the production line under the selected workers is stable:

[0041]

[0042]

[0043] Among them, f1 is the skill maturity of the production line workers, f2 is the output stability of the production line workers; Y represents the output difference between the production line workers in two weeks, is the average value of the difference in output between two cycles of workers on the production line, maxY is the maximum value of the difference in output between two cycles among workers on the production line, ω de31 represents the historical production efficiency of worker e in the dth workstation, ω de21 represents the current production efficiency of worker e in the dth workstation;

[0044] S42. Use the fast non-dominated sorting method in the NSGA-II algorithm to determine the crowding distance of the individual:

[0045]

[0046] Where CDlo represents the crowding degree of the th individual in the oth objective function, o = 1, 2, X max represents the maximum value of all individuals under the oth objective function, X min Represents the minimum value of all individuals under the oth objective function;

[0047] S43, population initialization, design a heuristic rule of a greedy algorithm to generate the initial population, first locally optimize an optimization target of f1, and construct the initial population;

[0048] S44. Design of adaptive crossover operator:

[0049]

[0050] Among them, P c is the crossover probability, G is the number of iterations; P cmax Represents the maximum crossover probability, P cmin represents the minimum crossover probability;

[0051] S45. Design an adaptive mutation operator and a method that coexists with multiple mutation methods to mutate individuals:

[0052]

[0053] Among them, P m is the mutation probability, P mmax Represents the maximum mutation probability, P mmin Indicates the minimum crossover probability; uses exchange mutation, flip mutation, and sliding mutation, and selects them with equal probability.

[0054] Furthermore, step S5 specifically includes:

[0055] The adaptive genetic algorithm is used to solve the multi-objective optimization function of the production line. After the NSGA-II algorithm is optimized, a multi-objective optimization solution exists.

[0056] Introduce human resource utilization rate D, and use the sum of the skill maturity scores of the selected on-the-job workers M PA The sum of the highest skill maturity scores of all workers M AA The percentage of the ratio indicates the selection of the optimal worker scheduling strategy:

[0057]

[0058] Among them, M PA represents the sum of the skill maturity scores of the on-the-job workers selected by the scheduling plan, M AARepresents the sum of the highest skill maturity scores of each worker in the worker set.

[0059] Compared with the prior art, the present invention has the following advantages:

[0060] The clothing production line worker scheduling method based on hierarchical analysis and NSGA-II algorithm provided by the present invention can be combined with actual production scenarios to quickly find better personnel scheduling decisions, reduce the waste of scheduling resources in production, effectively utilize worker data to a certain extent, improve the utilization rate of worker data, strengthen the closeness of the relationship between data, and help eliminate data islands.

[0061] The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm provided by the present invention makes full use of the group decision-making of experts to achieve the transformation from subjective experience to objective evaluation. By quantifying various indicators through the actual production data of workers, it can provide direction for the effective use of production data of personnel in the clothing production line and provide a basis for personnel scheduling decisions.

[0062] The clothing production line worker scheduling method based on hierarchical analysis and NSGA-II algorithm provided by the present invention not only takes into account the differences in workers' skill levels for different workstation processes, but also fully considers the output stability problem before and after production line scheduling, and realizes the effectiveness of production line worker scheduling through iterative optimization.

[0063] The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm provided by the present invention adopts a greedy algorithm for locally optimizing an optimization target of f1 to construct an initial population when improving the genetic algorithm. On this basis, a method of using an adaptive mutation operator and multiple mutation modes to coexist is used to generate mutations, which can achieve the generation of rich chromosome types and prevent the invalidation of some excellent chromosome evolution results.

[0064] The clothing production line worker scheduling method based on hierarchical analysis and NSGA-II algorithm provided by the present invention is suitable for worker scheduling situations of various production lines, has strong flexibility and broad application prospects, can provide scheduling ideas for clothing production decision makers, provide a scientific basis for worker scheduling of clothing production lines, and promote the innovation and development of production line scheduling.

[0065] Based on the above reasons, the present invention can be widely promoted in the field of production scheduling technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0067] Figure 1 This is the worker scheduling process of the clothing production line based on the analytic hierarchy process and the NSGA-II algorithm of the present invention.

[0068] Figure 2 This is a skill maturity analysis model for workers in a clothing production line based on hierarchical analysis.

[0069] Figure 3 This is the flow chart of the improved NSGA-II algorithm of the present invention.

[0070] Figure 4 These are three mutation operators in the improved NSGA-II algorithm of the present invention.

[0071] Figure 5 It is a Pareto frontier solution set sought by the embodiment of the present invention after the scheduling of workers in the clothing production line is improved by using the hierarchical analysis method and the NSGA-II algorithm. DETAILED DESCRIPTION

[0072] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0073] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0074] like Figure 1As shown, the present invention provides a method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm, and the specific steps include:

[0075] S1. Collect production data of the production team, including workstation production data, worker data and production logs of the production line;

[0076] In specific implementation, as a preferred embodiment of the present invention, step S1 specifically includes:

[0077] The worker data includes: basic information data such as age, gender, education background, equipment data, process data, historical production efficiency, historical rework rate, skill distribution of workers, process steps they have been responsible for during the task cycle, current process steps they are responsible for, historical attendance rate, and whether there is a machine failure during the cycle.

[0078] The workstation production data includes: process table, process flow, equipment data and process data, etc.;

[0079] The production log of the production line includes daily output, whether there is personnel scheduling on the current working day, the output log of each workstation and the rework rate, etc.

[0080] S2. Use the analytic hierarchy process to determine the worker skill evaluation indicators, and determine the weights of the evaluation indicators through the judgment matrix between the indicators;

[0081] In specific implementation, as a preferred embodiment of the present invention, step S2 specifically includes:

[0082] S21. Use the analytic hierarchy process to determine the evaluation indicators and build a multi-layer structure to determine whether the worker is competent for the current work process; set the primary and secondary indicators for worker evaluation and build a skill evaluation model for production line workers in clothing enterprises;

[0083] The first-level indicators include: basic attributes, effort level, proficiency level and ability range;

[0084] The secondary indicators include: age, gender, education level, historical production data, historical attendance rate, production efficiency, rework rate, skill distribution, learning ability, and event handling ability;

[0085] S22. According to the skill evaluation model of the workers in the production line of the garment enterprise in S21, the weight of each indicator is calculated through the judgment matrix of the importance of each pair of worker skill indicators:

[0086]

[0087] Among them, a ij is the comparison result of the relative importance of indicator factor i and indicator factor j;

[0088] For the first-level and second-level indicators, compare each indicator element in pairs and evaluate them according to their importance to form a judgment matrix A;

[0089] Each matrix at each level uses the consistency test index CR to judge the rationality of the weight distribution of each indicator in the matrix. During implementation, a judgment matrix question-based questionnaire was designed, and experts in the clothing production management industry and senior production line workers were invited to conduct pairwise evaluations on the correlation and importance between the skill maturity evaluation indicators of clothing production line workers, and the weights were obtained by analysis using decision-making software such as Yaanp.

[0090] S3, evaluate the workers' skills based on the production data in S1, and calculate the workers' skill maturity in the workstation process and the production line skill maturity respectively;

[0091] In specific implementation, as a preferred embodiment of the present invention, step S3 specifically includes:

[0092] During implementation, worker skill maturity: Use the mapminmax function to normalize production data, compress all data within the range of [0, 1], and keep the mathematical units of the data consistent, thereby eliminating the defect of not being able to analyze multiple data together due to data dimension problems. In this way, the position of each indicator of the worker in the entire assembly line workers is obtained, and the score R of the worker's indicators at all levels is calculated to quantify the evaluation indicators. Combined with the evaluation weights of indicators at all levels, the worker's score is weighted and calculated, and finally the worker's skill maturity M for a certain workstation process is obtained.

[0093] S31. Design a method for calculating the skill maturity of workers in a certain workstation process, calculate the score values ​​of workers' indicators at all levels by normalizing the production data, and realize the quantification of evaluation indicators;

[0094] Combined with the evaluation weights of indicators at all levels, the worker's score is weighted and calculated to obtain the worker's skill maturity M in a certain workstation process:

[0095]

[0096] In the formula, X is the production data of workers under a certain indicator factor, X norm is the standardized value of worker production data under a certain indicator factor, that is, the score value R; Z min Indicates the minimum production value under this indicator when workers are concentrated; Z max Indicates the maximum production value under this indicator in the concentration of workers;

[0097] M=Σω bc *r bc

[0098] In the formula, ωbc is the indicator weight of the cth secondary indicator under the bth primary indicator; r bc Provide workers with scoring values ​​for each level of indicators;

[0099] S32. Design a method for calculating the skill maturity of a production line. Use the decision variable k to determine the competence relationship between workstation d and person e, and construct the overall skill maturity of workers in the clothing production line:

[0100]

[0101]

[0102] In the formula, h de represents the skill maturity of the dth workstation and the eth person, that is, the M value in S31, k is the decision variable, which determines whether there is production data of this workstation in the worker's skill distribution, k de =1 indicates that the worker is competent, that is, worker e can be assigned to workstation d, k de When =0, it means that the worker is not competent, that is, worker e cannot be assigned to workstation d.

[0103] In implementation, the skill maturity of the production line: The personnel scheduling arrangement of the clothing production line can be described as obtaining the worker-workstation skill competence H through the worker's skill evaluation model and the worker's cycle production data. That is, the skill maturity of the production line composed of the workers selected for scheduling.

[0104] S4. Aiming at the skill maturity and output stability of worker scheduling, a greedy algorithm is used to locally optimize an objective function, and then the NSGA-II algorithm is improved through the adaptive crossover and mutation operator methods, and a multi-objective optimization model is established based on the improved NSGA-II algorithm;

[0105] In specific implementation, as a preferred embodiment of the present invention, step S4 specifically includes:

[0106] S41. Assume that the garment assembly line has m workstations, d = 1, 2, ..., m, and n workers, e = 1, 2, ..., n;

[0107] During implementation, the number of workstations is less than the number of personnel, and there is maturity between any workstation Oi and personnel Pj. The personnel and workstations of the production line are reallocated according to the skill maturity, so that the skill maturity of the workers on the production line reaches the maximum.

[0108] Design objective functions f1 and f2. The scheduling goal is to maximize the sum of the skill maturity of all workers in the production line, and to ensure that the output of the production line under the selected workers is stable:

[0109]

[0110]

[0111] Among them, f1 is the skill maturity of the production line workers, f2 is the output stability of the production line workers; Y represents the output difference between the production line workers in two weeks, is the average value of the difference in output between two cycles of workers on the production line, maxY is the maximum value of the difference in output between two cycles among workers on the production line, ω de31 represents the historical production efficiency of worker e in the dth workstation, ω de21 represents the current production efficiency of worker e in the dth workstation;

[0112] In implementation, the difference between the labor productivity of workers between two unit cycles is used as the labor status of workers. This formula reflects the degree of stability of the output of production line workers. The higher the skill level of the workers in the production line, the more stable the output of the production line, the smaller the fluctuation of the production line, and the smaller the value of f2. The optimal strategy is made when weighing multiple goals.

[0113] S42. Use the fast non-dominated sorting method in the NSGA-II algorithm to determine the crowding distance of the individual:

[0114]

[0115] Where CDlo represents the crowding degree of the th individual in the oth objective function, o = 1, 2, X max represents the maximum value of all individuals under the oth objective function, X min Represents the minimum value of all individuals under the oth objective function;

[0116] In implementation, real number coding (decimal coding) is adopted, and each chromosome is m gene bits in length, where m means that each chromosome contains m production workstations; each gene bit represents a production staff, and the gene value is the staff number.

[0117] Fitness function: The Pareto ranking method is used to determine the fitness function based on the individual's position on the Pareto front. The Pareto front is a curve composed of all non-dominated solutions. The closer the individual's position on the Pareto front is, the higher the value of the fitness function.

[0118] S43, population initialization, design a heuristic rule of a greedy algorithm to generate the initial population, first locally optimize an optimization target of f1, and construct the initial population;

[0119] S44. Design of adaptive crossover operator:

[0120]

[0121] Among them, P c is the crossover probability, G is the number of iterations; P cmax Represents the maximum crossover probability, P cmin represents the minimum crossover probability;

[0122] S45. Design an adaptive mutation operator and a method that coexists with multiple mutation methods to mutate individuals:

[0123]

[0124] Among them, P m is the mutation probability, P mmax Represents the maximum mutation probability, P mmin Indicates the minimum crossover probability; uses exchange mutation, flip mutation, and sliding mutation, and selects them with equal probability.

[0125] S5. Calculate the optimal worker scheduling strategy based on the multi-objective optimization model in S4.

[0126] In specific implementation, as a preferred embodiment of the present invention, step S5 specifically includes:

[0127] The adaptive genetic algorithm is used to solve the multi-objective optimization function of the production line. After the NSGA-II algorithm is optimized, a multi-objective optimization solution exists.

[0128] Introduce human resource utilization rate D, and use the sum of the skill maturity scores of the selected on-the-job workers M PA The sum of the highest skill maturity scores of all workers M AA The percentage of the ratio indicates the selection of the optimal worker scheduling strategy:

[0129]

[0130] Among them, M PA represents the sum of the skill maturity scores of the on-the-job workers selected by the scheduling plan, M AA Represents the sum of the highest skill maturity scores of each worker in the worker set.

[0131] Example

[0132] like Figure 1 As shown in the figure, taking the men's T-shirt production line of a clothing company as an example, the production line has 20 positions and 25 personnel, 5 of whom are candidates, and each employee has different proficiency in each process. After the clothing production line experts determine the weight of the evaluation index, they combine the production data of the production line workers and calculate the skill maturity of the workers. After calculation, it can be obtained that the current skill maturity of the personnel is 10.739. Calculating the optimal worker scheduling strategy includes the following steps:

[0133] The experimental results of worker skill evaluation based on hierarchical analysis are shown in Table 1 below:

[0134] Table 1 Skill maturity and skill distribution of production line workers

[0135]

[0136]

[0137] The adaptive genetic algorithm is used to solve the multi-objective optimization function of the production line, such as Figure 5 As shown in the figure, after optimization by the NSGA-II algorithm, there is a relatively obvious Pareto frontier and a multi-objective optimization solution.

[0138] As shown in Table 2 below, Schemes 1, 2, and 3 are selected from the optimal solution set obtained by the method of the present invention, and their production line skill proficiency M PA They are 12.412, 12.814, and 13.074 respectively. The sum of the highest skill maturity scores of each worker in the worker set is M AA is 15.587. The human resource utilization rate before optimization is D = 68.9%. After optimization, the human resource utilization rates are D = 79.6%, 82.2%, and 83.9%, respectively. However, while improving the utilization rate of human resources, the stability of the output before and after the production line will also be affected. For Scheme 3, the improvement in human resources is the highest, at 15%, but the improvement in the stability of the production line is low. For Scheme 1, human resources are increased by 10.7%, but its stability is the best among the schemes, which is 0.18 higher than the original scheme. Scheme 2 is a compromise scheme, with a 13.3% increase in human resources and a 0.158 increase in stability. It can be seen that in the process of personnel scheduling, if decision makers pursue the utilization rate of human resources, they can refer to Scheme 3. If you pursue the utilization rate of human resources while taking into account the stability of the production line, you can choose to refer to Schemes 1 and 2.

[0139] Table 2 Optimization scheme for scheduling workers in clothing production lines

[0140]

[0141]

[0142] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0143] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0146] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0147] If the integrated unit is implemented in the form of 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 the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm, characterized in that: The specific steps include: S1. Collect production data of the production team, including workstation production data, worker data and production log of the production line; S2. Use the analytic hierarchy process to determine the worker skill evaluation indicators, and determine the weights of the evaluation indicators through the judgment matrix between the indicators; S3, evaluate the workers' skills based on the production data in S1, and calculate the workers' skill maturity in the workstation process and the production line skill maturity respectively; S4. Aiming at the skill maturity and output stability of worker scheduling, a greedy algorithm is used to locally optimize an objective function, and then the NSGA-II algorithm is improved through the adaptive crossover and mutation operator methods, and a multi-objective optimization model is established based on the improved NSGA-II algorithm; S5. Calculate the optimal worker scheduling strategy based on the multi-objective optimization model in S4.

2. The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm according to claim 1 is characterized in that: Step S1 specifically includes: The worker data includes: age, gender, basic information of education, equipment data, process data, historical production efficiency, historical rework rate, skill distribution of workers, process steps they have been responsible for during the task cycle, current process steps they are responsible for, historical attendance rate, and whether there is a machine failure in the event during the cycle; The workstation production data includes: process table, process flow, equipment data and process data; The production log of the production line includes the daily output, whether there is personnel scheduling on the current working day, the output log of each workstation and the rework rate.

3. The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm according to claim 1 is characterized in that: Step S2 specifically includes: S21. Use the analytic hierarchy process to determine the evaluation indicators and build a multi-layer structure to determine whether the worker is competent for the current work process; set the primary and secondary indicators for worker evaluation and build a skill evaluation model for production line workers in clothing enterprises; The first-level indicators include: basic attributes, effort level, proficiency level and ability range; The secondary indicators include: age, gender, education level, historical production data, historical attendance rate, production efficiency, rework rate, skill distribution, learning ability, and event handling ability; S22. According to the skill evaluation model of the workers in the production line of the garment enterprise in S21, the weight of each indicator is calculated through the judgment matrix of the importance of each pair of worker skill indicators: Among them, a ij is the comparison result of the relative importance of indicator factor i and indicator factor j; For the first-level and second-level indicators, compare each indicator element in pairs and evaluate them according to their importance to form a judgment matrix A; Each level of matrix uses the consistency test index CR to judge the rationality of the weight distribution of each indicator in the matrix.

4. The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm according to claim 1 is characterized in that: Step S3 specifically includes: S31. Design a method for calculating the skill maturity of workers in a certain workstation process, calculate the score values ​​of workers' indicators at all levels by normalizing the production data, and realize the quantification of evaluation indicators; Combined with the evaluation weights of indicators at all levels, the worker's score is weighted and calculated to obtain the worker's skill maturity M in a certain workstation process: In the formula, X is the production data of workers under a certain indicator factor, X norm is the standardized value of worker production data under a certain indicator factor, that is, the score value R; Z min Indicates the minimum production value under this indicator when workers are concentrated; Z max Indicates the maximum production value under this indicator in the concentration of workers; M=∑ω bc *R bc In the formula, ω bc is the indicator weight of the cth secondary indicator under the bth primary indicator; R bc Provide workers with scoring values ​​for each level of indicators; S32. Design a method for calculating the skill maturity of a production line. Use the decision variable k to determine the competence relationship between workstation d and person e, and construct the overall skill maturity of workers in the clothing production line: In the formula, h de represents the skill maturity of the dth workstation and the eth person, that is, the M value in S31, k is the decision variable, which determines whether there is production data of this workstation in the worker's skill distribution, k de =1 indicates that the worker is competent, that is, worker e can be assigned to workstation d, k de When =0, it means that the worker is not competent, that is, worker e cannot be assigned to workstation d.

5. The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm according to claim 1 is characterized in that: Step S4 specifically includes: S41. Assume that there are m workstations in the garment assembly line, d = 1, 2, ..., m, and n workers, e = 1, 2, ..., n; Design objective functions f1 and f2. The scheduling goal is to maximize the sum of the skill maturity of all workers in the production line, and to ensure that the output of the production line under the selected workers is stable: Among them, f1 is the skill maturity of the production line workers, f2 is the output stability of the production line workers; Y represents the output difference between the production line workers in two weeks, is the average value of the difference in output between two cycles of workers on the production line, maxY is the maximum value of the difference in output between two cycles among workers on the production line, ω de31 represents the historical production efficiency of worker e in the dth workstation, ω de21 represents the current production efficiency of worker e in the dth workstation; S42. Use the fast non-dominated sorting method in the NSGA-Ⅱ algorithm to determine the crowding distance of the individual: Where CDlo represents the crowding degree of the lth individual in the oth objective function, o = 1, 2, X max represents the maximum value of all individuals under the oth objective function, X min Represents the minimum value of all individuals under the oth objective function; S43, population initialization, design a heuristic rule of a greedy algorithm to generate the initial population, first locally optimize an optimization target of f1, and construct the initial population; S44. Design of adaptive crossover operator: Among them, P c is the crossover probability, G is the number of iterations; P cmax Represents the maximum crossover probability, P cmin represents the minimum crossover probability; S45. Design an adaptive mutation operator and a method that coexists with multiple mutation methods to mutate individuals: Among them, P m is the mutation probability, P mmax Represents the maximum mutation probability, P mmin Indicates the minimum crossover probability; uses exchange mutation, flip mutation, and sliding mutation, and selects them with equal probability.

6. The method for scheduling workers in a clothing production line based on hierarchical analysis and NSGA-II algorithm according to claim 1 is characterized in that: Step S5 specifically includes: The adaptive genetic algorithm is used to solve the multi-objective optimization function of the production line. After the NSGA-II algorithm is optimized, a multi-objective optimization solution exists. Introduce human resource utilization rate D, and use the sum of the skill maturity scores of the selected on-the-job workers M PA The sum of the highest skill maturity scores of all workers M AA The percentage of the ratio indicates the selection of the optimal worker scheduling strategy: Among them, M PA represents the sum of the skill maturity scores of the on-the-job workers selected by the scheduling plan, M AA Represents the sum of the highest skill maturity scores of each worker in the worker set.

Citation Information

Cited By

  • Building enterprise project group human resource allocation system based on multi-objective optimization

    CN120355385A

  • Human resource allocation system for construction enterprise project groups based on multi-objective optimization

    CN120355385B

  • Construction enterprise project group human resource allocation method based on multi-objective optimization

    CN120450664A