Personalized clothing production line personnel scheduling method and system based on genetic algorithm

Abstract

The present invention belongs to the technical field of production scheduling, and particularly relates to a personalized clothing production line personnel scheduling method and system based on a genetic algorithm. The method includes: S1, obtaining employee information of a production team and production plan information of a target personalized clothing; S2, constructing a shortest path parallel scheduling strategy and establishing a mathematical model with the completion time as the scheduling target; S3, using the proposed genetic algorithm-based method to solve the mathematical model and optimizing the technological process of the target personalized clothing production to generate an optimized technological process flow chart; S4, through the visualization of a production task Gantt chart, describing the scheduling process of the production task Gantt chart and verifying the rationality of the scheduling method. The present invention has the characteristics that the processes can be reasonably assigned to employees within a relatively short time, thereby improving the production efficiency of a garment factory.

Description

Technical Field

[0001] The present invention belongs to the technical field of production scheduling, and particularly relates to a personalized clothing production line personnel scheduling method and system based on a genetic algorithm. Background Art

[0002] Currently, the clothing manufacturing industry is facing intense market competition pressure and changing user demands. Enterprises hope to respond to future challenges through digital transformation. How to digitally upgrade traditional clothing manufacturing is an issue faced by small and medium-sized clothing enterprises at present. With the development of intelligent manufacturing, the production of enterprises is gradually transforming towards intelligence and automation. In order to meet the market's personalized customization needs, enterprises have changed from a large-volume production mode to a multi-order, small-batch production mode. In clothing enterprises, production plans are generally formulated by management personnel based on production experience. This solution has the disadvantages of low efficiency and difficulty in dealing with unexpected situations such as rework.

[0003] Modeling and simulation technologies can help the manufacturing industry achieve digital transformation and development. After years of development, modeling and simulation technologies can already provide very valuable information for enterprise decision-makers in various links such as design, production, testing, maintenance, and sales.

[0004] In the process of clothing production, there are many factors that affect clothing production efficiency, such as differences in clothing styles, processing equipment, order quantities, and personnel skills. This has caused the complexity of production scheduling, making it difficult for the current production scheduling plan formulation efficiency of clothing factories to meet the needs of clothing customized production. Therefore, it is necessary for enterprises to use a scheduling system to dynamically schedule the production line to ensure production stability and continuity and improve the real-time response ability of production scheduling.

[0005] Among the above factors affecting clothing production efficiency, the existing solutions have not given a production scheduling plan formulation solution for the impact of clothing production personnel skill differences on production scheduling plan formulation.

[0006] Based on the above problems, it is very important to design a personalized clothing production line personnel scheduling method and system based on a genetic algorithm that can reasonably allocate processes to employees in a short time, thereby improving the production efficiency of clothing factories.

[0007] For example, the Chinese patent document with the application number CN202010697974.5 describes an intelligent production scheduling method for a clothing hanging production line. The intelligent production scheduling includes the following steps: calculating the number of workstations required for each process according to the process complexity; screening out all workstations suitable for each process according to the configuration information of each workstation site; forming a preliminary assembly line allocation plan based on the login status of employees at each workstation and the historical production data of employees, and implementing the allocation; the intelligent prediction includes the following steps: measuring the production line balance rate according to the actual production capacity of each process, and judging the rationality of the current production line process allocation; when it is judged that the current production line balance rate is lower than the preset value, re-arrange the processes according to the actual production efficiency of each workstation and the workstation configuration information. Although real-time monitoring and balance management of each process are carried out to avoid affecting the rationality of process allocation and the production line balance rate due to the management level of managers, thereby maximizing the production line capacity, the disadvantage is that the impact of the skill differences of clothing production personnel on the formulation of the production scheduling plan is not considered, and the above production scheduling method has limitations. Summary of the Invention

[0008] The present invention aims to overcome the problem in the prior art that the existing clothing production scheduling scheme has not given a production scheduling plan formulation scheme for the impact of the skill differences of clothing production personnel on the formulation of the production scheduling plan, and provides a personalized clothing production line personnel scheduling method and system based on genetic algorithm that can reasonably allocate processes to employees in a short time, thereby improving the production efficiency of the clothing factory.

[0009] To achieve the above invention purpose, the present invention adopts the following technical solutions:

[0010] The personalized clothing production line personnel scheduling method based on genetic algorithm includes the following steps:

[0011] S1, obtaining the employee information of the production group and the production plan information of the target personalized clothing;

[0012] Wherein the employee information of the production group includes the proficiency of employees in the production group in the processes of the entire production process; the production plan information of the target personalized clothing includes the part name, process description, process type, standard process production time, and process flow of the target personalized clothing;

[0013] S2, constructing a shortest path parallel scheduling strategy and establishing a mathematical model with the completion time as the scheduling target;

[0014] S3, using the proposed method based on genetic algorithm to solve the mathematical model, and optimizing the process flow of the target personalized clothing production to generate an optimized process flow chart;

[0015] S4. Through the visualization of the production task Gantt chart, describe the scheduling process of the production task Gantt chart and verify the rationality of the scheduling method.

[0016] Preferably, step S1 includes the following steps:

[0017] S11. Obtain the employee information of the production team. The team leader of the production team formulates the employee proficiency according to the proficiency of the team members in the processes.

[0018] S12. Obtain the production plan information of the target personalized clothing. The analyst formulates the style process table and the process flow according to the personalized customized clothing.

[0019] Preferably, step S2 includes the following steps:

[0020] S21. Suppose there are n orders (D1, D2, …, D n ), which are processed by a processing team of m employees (S1, S2, …, S m ). Any order D i is composed of processes P i = {P ij , j ∈ (1, 2, …, n i )} with a known processing sequence. The set of optional employees for the j-th process of order i is The proficiency of employee S k in processing the j-th process of order i is E ij = {E ijk , k ∈ (1, 2, …, m)}; All processes P ij are assigned to employee S k for production to achieve the goal of minimizing the completion time.

[0021] S21. Model construction:

[0022] Considering the completion time, employee working hours, takt time, and balance rate, taking the minimization of the completion time T as the optimization goal to improve production efficiency, the specific formula is as follows:

[0023]

[0024] To balance the total duration TS i of the processes assigned to each employee, the takt time t and the balance rate α are introduced;

[0025] The takt time t is the average processing time of each employee, and the balance rate α is the ratio between the takt time and the maximum processing time of the employee, which is used to evaluate whether there will be process blockage and accumulation in the whole processing process;

[0026]

[0027] Where: TS k is the total actual production time of employee k, T ij is the standard processing time of the j-th process P ij of order i;

[0028]

[0029] Where: T ijk is the actual processing time of the j-th process P ij of order i;

[0030]

[0031]

[0032] Where: the closer the value of α is to 1, the smaller the difference in the total process duration allocated among employees;

[0033]

[0034] Where: set the arrival time of the first order TD1 = 0, TD i is the arrival time of the i-th order;

[0035] Set the constraint conditions:

[0036] For T ijk constrain that the actual processing time is affected by the proficiency of employees;

[0037] max(TS k ) ≤ t(1 + β) (7)

[0038] Among them, it is the constraint on the maximum total actual production time of employee k, and β is a user-defined parameter;

[0039]

[0040] Where: X ijk is the discrimination condition for whether the j-th process of order i is processed by employee k. When the process selects employee k for processing, it is 1, otherwise it is 0;

[0041] TB ijk ≥ TD i , k ∈ S ij (9)

[0042] Where: TB ij is the start time of the j-th process of order i;

[0043] TW ij ≤ TB i(j+1) (10)

[0044] Wherein: TW ij is the completion time of the j-th process of order i.

[0045] Preferably, the construction of the shortest path parallel scheduling strategy in step S2 includes the following steps:

[0046] Through the process flow chart, search for the shortest path from the start to the end of production in the process flow chart, and produce other production paths in parallel with the shortest path to achieve a smooth production line and reduce the clothing production time.

[0047] Preferably, the genetic algorithm in step S3 includes the following steps:

[0048] S31, by excluding employees with a proficiency of 0 for each process and excluding infeasible solutions, randomly generate an array code, form a corresponding chromosome, and form an initial population;

[0049] S32, take the reciprocal of the completion time as the fitness function. The smaller the total completion time, the greater the fitness;

[0050] S33, use the roulette wheel algorithm to select individuals;

[0051] S34, use the method of random mutation. Take a random probability. If the random probability is less than the set mutation probability, randomly select a gene in the interval for mutation.

[0052] Preferably, step S3 further includes a simulation process, and the simulation process includes the following steps:

[0053] S35, solve the shortest path for the corresponding clothing to complete the process according to the process flow chart of different clothing;

[0054] S36, for the process descriptions in the process sheets of different clothing styles, correspond the process descriptions with the process names in the employee process sheets to obtain the proficiency of the employees making the corresponding clothing for the processes.

[0055] The present invention also provides a personalized clothing production line personnel scheduling system based on a genetic algorithm, including:

[0056] An information acquisition module for acquiring employee information of the production team and production plan information of the target personalized clothing;

[0057] A strategy and model construction module for constructing a shortest path parallel scheduling strategy and establishing a mathematical model with the completion time as the scheduling target;

[0058] A solution and optimization module is used to solve the mathematical model by using the proposed genetic - algorithm - based method, optimize the process flow of target personalized clothing production, and generate an optimized process flow chart.

[0059] A verification module is used to describe the scheduling process of the production task Gantt chart through visualization of the production task Gantt chart and verify the rationality of the scheduling method.

[0060] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention is oriented to a personalized clothing production workshop, considering the proficiency and balance rate of personnel in the workshop production process, optimizing through the shortest - path parallel scheduling strategy, and using the genetic algorithm to solve problems to obtain the optimal personnel - allocation production scheduling plan; (2) The present invention uses the shortest - path parallel scheduling strategy through the process flow chart, searches for the shortest path from the start to the end of the process flow chart, and produces other production paths in parallel with the shortest path, reducing the clothing production time while ensuring the smooth flow of the production line; (3) The present invention takes the actual production of personalized customized clothing in a clothing factory as an example to verify the application of the model; in the case analysis, appropriate parameter weights are given according to the experimental results obtained from the analysis, providing a basis for the clothing factory to select a suitable production scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a process flow chart of a personalized clothing provided by an embodiment of the present invention;

[0062] Figure 2 It is a flow chart of a genetic algorithm for a personalized clothing provided by an embodiment of the present invention;

[0063] Figure 3 It is a process flow chart of a personalized customized skirt provided by an embodiment of the present invention;

[0064] Figure 4 It is a comparison chart of completion times of a genetic algorithm under different jitter rates provided by an embodiment of the present invention;

[0065] Figure 5 It is a comparison chart of cycle times of a genetic algorithm under different jitter rates provided by an embodiment of the present invention;

[0066] Figure 6 It is a Gantt chart of a scheduling result after optimization by the shortest - path parallel scheduling provided by an embodiment of the present invention;

[0067] Figure 7 It is a Gantt chart of a scheduling result after optimization by the shortest - path parallel scheduling in the first 600 s provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] To more clearly illustrate the embodiments of the present invention, the following will describe the specific implementation manners of the present invention with reference to the attached drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings, and other implementation manners can also be obtained.

[0069] Embodiment:

[0070] The personalized clothing production line personnel scheduling method based on genetic algorithm of the present invention includes the following steps:

[0071] S1. Obtain the employee information of the production team and the production plan information of the target personalized clothing;

[0072] Wherein the employee information of the production team includes the proficiency of the employees in the production team in the processes of the entire production process; the production plan information of the target personalized clothing includes the part name, process description, process type, standard process production time, and process flow of the target personalized clothing;

[0073] S2. Construct a shortest path parallel scheduling strategy and establish a mathematical model with the completion time as the scheduling goal;

[0074] S3. Use the proposed method based on genetic algorithm to solve the mathematical model, and optimize the process flow of the target personalized clothing production to generate an optimized process flow chart;

[0075] S4. Through the visualization of the production task Gantt chart, describe the scheduling process of the production task Gantt chart to verify the rationality of the scheduling method.

[0076] Among them, in step S1, to obtain the employee information of the production team, the team leader of the production team formulates an employee proficiency table according to the proficiency of the team members in the processes. The team leader does not participate in clothing production; to obtain the production plan information of the target personalized clothing, the analyst formulates a style process table and a process flow according to the personalized customized clothing.

[0077] The shortest path parallel scheduling strategy described in step S2 can reduce the production time in the actual production process of personalized clothing, and at the same time ensure the smoothness of the production line and no blockage in the production process; establishing a mathematical model with the completion time as the scheduling goal can clearly and detailedly describe the personnel scheduling problem of the personalized clothing production line.

[0078] For step S2, the problem that the clothing enterprise needs to solve is to formulate an order production scheduling plan with the goal of shortening the production time while ensuring the reasonable working hours of employees and the production line balance rate.

[0079] In the process of formulating the production scheduling plan for a garment factory, the goal of scheduling is to assign processes to each employee in a group. Therefore, step S2 specifically includes the following steps:

[0080] S21. Set that there are n orders (D1, D2, …, D n ), which are processed by a processing group of m employees (S1, S2, …, S m ). Any order D i consists of processes P i = {P ij , j ∈ (1, 2, …, n i ). The set of optional employees for the j-th process of order i is The proficiency of employee S k in processing the j-th process of order i is E ij = {E ijk , k ∈ (1, 2, …, m)}. All processes P ij are assigned to employee S k for production to achieve the goal of minimizing the completion time;

[0081] S21. Model construction:

[0082] Considering the completion time, employee working time, cycle time, and balance rate, minimizing the completion time T is taken as the optimization goal to improve production efficiency. The specific formula is as follows:

[0083]

[0084] To balance the total duration TS i of the processes assigned to each employee, the cycle time t and the balance rate α are introduced;

[0085] The cycle time t is the average processing time of each employee, and the balance rate α is the ratio between the cycle time and the maximum processing time of the employee, which is used to evaluate whether there will be process jams and accumulations in the whole processing process;

[0086]

[0087] In the formula: TS k is the actual total production time of employee k, and T ij is the standard processing time of the j-th process P ij of order i;

[0088]

[0089] In the formula: T ijk is the actual processing time of the j-th process P ij of order i;

[0090]

[0091] Where: t is the standard beat time of the production plan;

[0092]

[0093] Where: α is the production plan balance rate. The closer the value of α is to 1, the smaller the difference in the total process duration allocated among employees;

[0094]

[0095] Where: Set the arrival time of the first order TD1 = 0, and TD i is the arrival time of the i-th order;

[0096] Set the constraint conditions:

[0097] For T ijk The actual processing time is affected by the proficiency of employees;

[0098] max(TS k ) ≤ t(1 + β) (7)

[0099] Among them, it is the constraint on the maximum actual total production time of employee k, and β is a user-defined parameter;

[0100]

[0101] Where: X ijk is the discrimination condition for whether the j-th process of order i is processed by employee k. It is 1 when the process selects employee k for processing, and 0 otherwise;

[0102] TB ijk ≥ TD i , k ∈ S ij (9)

[0103] Where: TB ij is the start time of the j-th process of order i;

[0104] TW ij ≤ TB i(j+1) (10)

[0105] Where: TW ij is the completion time of the j-th process of order i.

[0106] The construction of the shortest path parallel scheduling strategy described in step S2 includes the following steps:

[0107] Such as Figure 1As shown, through the process flow chart, search for the shortest path from the start to the end of the process flow chart, and produce other production paths in parallel with the shortest path to achieve a smooth production line and reduce the clothing production time.

[0108] The genetic algorithm described in step S3 includes the following steps:

[0109] The genetic algorithm flow chart is as Figure 2 shown:

[0110] (1) Chromosome encoding

[0111] The present invention constructs a one-dimensional array and adopts a real number encoding method based on the array. The genes in the chromosome represent the serial numbers of the employees arranged for the corresponding processes.

[0112] (2) Generate the initial population

[0113] According to the above chromosome representation method, for each process, employees with a process proficiency of 0 are not selected. After excluding infeasible solutions, randomly generate an array code, and then form the corresponding chromosome to form the initial population.

[0114] (3) Fitness function

[0115] Taking the total completion time as the objective function, its reciprocal is used as the fitness function.

[0116]

[0117] (4) Selection

[0118] Select excellent individuals to pass on to the next generation. The present invention adopts the roulette wheel selection method. The probability of each individual being selected is related to its fitness value. The larger the fitness value, the greater the probability of being selected.

[0119] (5) Crossover

[0120] Traverse the genes of a pair of paternal chromosomes, and randomly generate a probability P c , if this probability is greater than P c , exchange the genes of the two paternal chromosomes at the corresponding positions. For example, these two paternal chromosomes are:

[0121] A = [5, 3, 1, 4, 7, 3, 9, 12, 6, 6]

[0122] B = [6, 2, 13, 6, 12, 4, 8, 1, 2, 3]

[0123] Traverse these two arrays, and randomly generate a probability during the traversal. If the randomly generated probability array is: [0.7, 0.6, 0.9, 0.1, 0.5, 0.9, 0.9, 0.1, 0.6, 0.5], P c= 0.5, and two offspring individuals are obtained by exchange:

[0124] A’ = [6, 2, 13, 4, 7, 4, 8, 12, 2, 6]

[0125] B’ = [5, 3, 1, 6, 12, 3, 9, 1, 6, 3]

[0126] (6) Mutation

[0127] The method of random mutation is used. Take a random probability. If the random probability is less than the set mutation probability, randomly select a gene a located in the interval [1, n] j for mutation, thus forming a new offspring individual.

[0128] Step S3 further includes a simulation process, and the simulation process includes the following steps:

[0129] S35, solve the shortest path of the corresponding clothing completion process according to the process flow chart of different clothing;

[0130] S36, for the process descriptions in the process sheets of different clothing styles, correspond the process descriptions with the process names in the employee process sheet to obtain the proficiency of the employees making the corresponding clothing in the processes.

[0131] Taking a production team as an example, currently, there are 19 employees in this team. Different clothing requires different processes for production, with a total of 120 processes, and the proficiency of each employee in each process is different. The process flow chart of clothing production is as Figure 3 shown. The clothes to be produced are divided into parts such as the front piece, back piece, sleeves, cuffs, placket, ear tabs, belt, accessories, etc. After each part is processed through multiple processes, they are finally combined into finished clothes.

[0132] The experimental results of the genetic algorithm. Without introducing the jitter rate and the shortest path parallel scheduling strategy, the average results of the process completion time and the algorithm running time in 50 experiments are shown in Table 1 below:

[0133] Table 1 Experimental result data table without introducing the jitter rate and the shortest path parallel scheduling strategy

[0134] Operation completion time / s Algorithm running time / s Genetic algorithm 4425.1 12.18

[0135] After setting the jitter rate to 60% and introducing the shortest path parallel scheduling strategy, the average results of the process completion time and the algorithm running time in 50 experiments are shown in Table 2 below:

[0136] Table 2 Experimental result data table introducing the jitter rate and the shortest path parallel scheduling strategy

[0137] Operation completion time / s Maximum operation time / s Algorithm running time / s Genetic algorithm 2909.5 365.2 14.86

[0138] The experimental results show that at different jitter rates, when the set jitter rate is smaller, the process completion time obtained by the genetic algorithm is larger, and the corresponding cycle time is smaller; conversely, the larger the jitter rate, the smaller the process completion time obtained by the genetic algorithm, and the larger the corresponding cycle time, as Figure 4 and Figure 5 shown.

[0139] However, when the jitter rate is too small, the genetic algorithm may not be able to solve the solution that meets the jitter rate within the set maximum number of iterations. At this time, the algorithm outputs the currently optimal solution after optimization, such as Figure 5 GA(55%) shown.

[0140] The garment factory can select an appropriate jitter rate according to the actual situation. When the garment factory requires a shorter production line production time, a higher jitter rate can be set to obtain a lower production time.

[0141] After multiple experiments, when the set jitter rate is 60%, after the shortest path parallel scheduling optimization, the garment production time is significantly shortened. At this time, the average time for producing one piece of clothing is 2909.5s, which is 39.6% lower than the original 4814.4s of the garment factory.

[0142] The Gantt chart of the production task of the present invention, such as Figure 6 and Figure 7 shown, visualizes the experimental results, describes its scheduling process, clearly expresses the time relationship of each process, verifies the rationality of the proposed method, and further ensures the smooth and orderly operation of the production process.

[0143] Based on this embodiment, the present invention also provides a personalized garment production line personnel scheduling system based on the genetic algorithm, including:

[0144] An information acquisition module for acquiring employee information of the production team and production plan information of the target personalized garment;

[0145] A strategy and model construction module for constructing a shortest path parallel scheduling strategy and establishing a mathematical model with the completion time as the scheduling target;

[0146] A solution and optimization module for using the proposed method based on the genetic algorithm to solve the mathematical model and optimize the process flow of the target personalized garment production to generate an optimized process flow chart;

[0147] A verification module for visualizing through the production task Gantt chart, describing the scheduling process of the production task Gantt chart, and verifying the rationality of the scheduling method.

[0148] The present invention is directed to a personalized clothing production workshop, taking into account the proficiency of personnel and the balance rate in the production and processing process of the workshop. It is optimized through a shortest path parallel scheduling strategy, and a genetic algorithm is used to solve the problem to obtain an optimal personnel allocation production scheduling plan. The present invention utilizes the shortest path parallel scheduling strategy to search for the shortest path from the start to the end of the production process through a process flow chart, and produces other production paths in parallel with the shortest path, reducing the clothing production time while ensuring the smooth flow of the production line. The present invention takes the actual production of personalized customized clothing in a garment factory as an example to verify the application of the model. In the case analysis, appropriate parameter weights are given according to the experimental results obtained from the analysis, providing a basis for the garment factory to select a suitable production scheduling plan.

[0149] The above is only a detailed description of the preferred embodiments and principles of the present invention. For those of ordinary skill in the art, according to the idea provided by the present invention, there will be changes in the specific implementation manners, and these changes should also be regarded as the protection scope of the present invention.

Claims

1. A personalized clothing production line personnel scheduling method based on a genetic algorithm, characterized in that, It includes the following steps: S1. Obtain the employee information of the production team and the production plan information of the target personalized clothing; The employee information of the production team includes the proficiency of employees in the production team for the processes of the entire production process; the production plan information of the target personalized clothing includes the part name, process description, process type, standard process production time, and process flow of the target personalized clothing; S2. Construct a shortest path parallel scheduling strategy and establish a mathematical model with the completion time as the scheduling objective; S3. Use the proposed genetic algorithm-based method to solve the mathematical model and optimize the process flow of the target personalized clothing production to generate an optimized process flow chart; S4. Through the visualization of the production task Gantt chart, describe the scheduling process of the production task Gantt chart and verify the rationality of the scheduling method; Step S2 includes the following steps: S21, there are n orders (D1, D2, …, D n ), which are processed by a processing team consisting of a group of m employees (S1, S2, …, S m ). Any order D i is composed of processes P i = {P ij , j ∈ (1, 2, …, n i )} with a known processing sequence. The set of optional employees for the j-th process of order i is The proficiency of employee S k in processing the j-th process of order i is E ij = {E ijk , k ∈ (1, 2, …, m)}; All processes P ij are assigned to employee S k for production to achieve the goal of minimizing the completion time; S21. Model construction: Considering the completion time, employee working time, takt time, and balance rate, minimize the completion time T as the optimization objective to improve production efficiency. The specific formula is as follows: To balance the total process duration TS assigned to each employee i , the takt time t and the balancing rate α are introduced; The takt time t is the average processing time of each employee, and the balance rate α is the ratio between the takt time and the maximum processing time of the employee, which is used to evaluate whether there will be process blockages and accumulations in the entire processing process; where: TS k is the total actual production time of employee k, T ij is the standard processing time of the jth process P ij of order i; Where: T ijk is the actual processing time of the j-th process P ij of order i; In the formula: the closer the value of α is to 1, the smaller the difference in the total process duration allocated among employees; where: Set the arrival time of the first order TD1 = 0, TD i is the arrival time of the i-th order; Set constraint conditions: For T ijk The actual processing time is restricted by the proficiency of employees; max(TS k ) ≤ t(1 + β) (7) Among them, the maximum actual total production time constraint of employee k, and β is a custom parameter; where: X ijk is the discriminant condition for whether the j-th process of order i is processed by employee k. It is 1 when employee k is selected for processing the process, and 0 otherwise; TB ijk ≥TD i , k ∈ S ij (9) where: TB ij is the start time of the j-th process of order i; TW ij ≤TB i(j+1) (10) Where: TW ij is the completion time of the j-th process of order i.

2. The personalized clothing production line personnel scheduling method based on the genetic algorithm according to claim 1, wherein Step S1 includes the following steps: S11. Obtain the employee information of the production team, and the team leader of the production team formulates the employee proficiency according to the proficiency of team members in the processes; S12. Obtain the production plan information of the target personalized clothing, and the analyst formulates a style process table and a process flow according to the personalized customized clothing.

3. The personalized clothing production line personnel scheduling method based on genetic algorithm according to claim 2, characterized in that, The construction of the shortest path parallel scheduling strategy in step S2 includes the following steps: Through the process flow chart, search for the shortest path from the start to the end of the process flow chart, and produce other production paths in parallel with the shortest path to ensure the smoothness of the production line and reduce the clothing production time.

4. The personalized clothing production line personnel scheduling method based on the genetic algorithm according to claim 3, characterized in that The genetic algorithm in step S3 includes the following steps: S31. By excluding employees with a proficiency of 0 for each process and excluding infeasible solutions, randomly generate an array code to form a corresponding chromosome and form an initial population; S32. Use the reciprocal of the completion time as the fitness function. The smaller the total completion time, the greater the fitness; S33. Use the roulette wheel algorithm to select individuals; S34. Use the method of random mutation. Take a random probability. If the random probability is less than the set mutation probability, randomly select a gene in the interval for mutation.

5. The personalized clothing production line personnel scheduling method based on genetic algorithm according to claim 4, characterized in that Step S3 also includes a simulation process, and the simulation process includes the following steps: S35. Solve the shortest path for the completion of the processes of the corresponding clothing according to the process flow charts of different clothing; S36. For the process descriptions in the process tables of different clothing styles, correspond the process descriptions with the process names in the employee process table to obtain the proficiency of employees in the processes for making the corresponding clothing.

6. A personalized clothing production line personnel scheduling system based on a genetic algorithm, which is used to implement the personalized clothing production line personnel scheduling method based on a genetic algorithm according to any one of claims 1-5, characterized in that, The personalized clothing production line personnel scheduling system based on the genetic algorithm includes: An information acquisition module, which is used to acquire the employee information of the production team and the production plan information of the target personalized clothing; A strategy and model construction module, which is used to construct a shortest path parallel scheduling strategy and establish a mathematical model with the completion time as the scheduling target; A solution and optimization module, which is used to solve the mathematical model by using the proposed genetic algorithm-based method, optimize the process flow of the target personalized clothing production, and generate an optimized process flow chart; A verification module, which is used to describe the scheduling process of the production task Gantt chart through the visualization of the production task Gantt chart and verify the rationality of the scheduling method.

Images