Optimized arrangement method, system and equipment for ethnic garment sewing production line

Through the genetic taboo mix optimization algorithm, the process arrangement of ethnic clothing production lines is optimized, and the uniform distribution of processes in the workstation and the synchronization of rhythm are achieved, the problems of low production line balance and efficiency are solved, and the production efficiency is improved.

CN118917572APending Publication Date: 2024-11-08INNER MONGOLIA UNIV OF TECH
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410885115.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-03
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

There is a balance in the process arrangement of ethnic clothing production lines, which leads to low production efficiency and long and low efficiency of traditional manual arrangement.

Method used

The genetic taboo mixed optimization algorithm is adopted to obtain production information, set decision variables and constraints, calculate the objective function, and optimize the process arrangement model to achieve uniform distribution of processes in the workstation and synchronize the rhythm.

Benefits of technology

It improves the balance and efficiency of the production line, shortens the orchestration time, improves production efficiency, and solves the problems of long and low efficiency of traditional manual orchestration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917572A_ABST
    Figure CN118917572A_ABST
Patent Text Reader

Abstract

The invention discloses an optimized arrangement method, system and equipment for a national garment sewing production line, and belongs to the technical field of intelligent optimized scheduling in the production process of the manufacturing industry. Comprising the steps of obtaining national garment production information to be sewn and produced, and obtaining decision variables of a national garment sewing production operation arrangement model based on the national garment production information; adding constraint conditions for decision variables of the ethnic garment sewing production operation arrangement model; calculating a target function to obtain an optimization target of ethnic garment sewing production operation arrangement; based on the optimization target, adopting a genetic taboo hybrid optimization algorithm to obtain an optimal ethnic garment sewing production operation arrangement model; and performing an optimized arrangement process of the ethnic garment sewing production line through the optimal ethnic garment sewing production operation arrangement model. The takt of each station of the production line can be equal to or close to the average takt of the production line, the production efficiency is improved by balancing the production line, and the problems of long manual arrangement time and low arrangement efficiency in the prior art are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent optimization scheduling of manufacturing production processes, and more specifically to a method, system and equipment for optimizing the scheduling of a national clothing sewing production line. Background Art

[0002] The main goal of designing and analyzing ethnic clothing production lines is to solve the problem of production line balance, that is, to reasonably allocate a series of processes to a specified number of workstations to achieve the desired production efficiency. According to the principle of process arrangement balance of ethnic clothing production lines, there are many parameters to consider in the balance of ethnic clothing production lines, such as the number of processes, process time, equipment used, process sequence, etc., which constitutes a very difficult combinatorial optimization problem.

[0003] In the process of process scheduling, it is necessary to determine the operators of each process, that is, the operating procedures arranged at each workstation. There are only two possibilities for the operation of each process at the workstation, that is, a certain process works at the workstation or not. The decision variable in the model is "whether a certain process works at a certain workstation", and the purpose is to obtain a balanced process scheduling combination for the assembly line. The goals of assembly line balance in the clothing production process are diverse. To balance the load at the workstation, each process should be evenly distributed to each workstation as much as possible, and the rhythm of each workstation should be synchronized. After the process scheduling is determined, suitable workers can be selected for operation according to the actual situation.

[0004] Therefore, how to provide an efficient method, system and equipment for optimizing the arrangement of a national clothing sewing production line is a problem that technicians in this field need to solve urgently. Summary of the invention

[0005] In view of this, the present invention provides a method for optimizing the arrangement of a national clothing sewing production line to solve the technical problems existing in the above-mentioned prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A method for optimizing the arrangement of a national clothing sewing production line comprises the following steps:

[0008] S1: Obtain the production information of ethnic clothing to be sewn and produced, and obtain the decision variables of the ethnic clothing sewing production operation scheduling model based on the ethnic clothing production information;

[0009] S2: Add constraints to the decision variables of the ethnic clothing sewing production operation scheduling model;

[0010] S3: Calculate the objective function and obtain the optimization goal of the arrangement of the sewing production operation of ethnic clothing;

[0011] S4: Based on the optimization objective, the hybrid optimization algorithm of genetic taboo is used to obtain the optimal operation scheduling model of ethnic clothing sewing production;

[0012] S5: The optimization process of the ethnic clothing sewing production line is carried out through the optimal ethnic clothing sewing production operation scheduling model.

[0013] Optionally, step S1: obtaining production information of ethnic clothing to be sewn and produced, and obtaining decision variables of the ethnic clothing sewing production operation scheduling model based on the ethnic clothing production information, including:

[0014] S1.1: Set the number of processes for the ethnic costumes to be arranged to be I, and the process number is i, i = 1, 2, ..., I;

[0015] S1.2: Set the number of workstations for the ethnic costumes to be arranged to J; one workstation represents one operator, and they are arranged in the order of the production line, numbered j=1, 2, ..., J;

[0016] S1.3: Based on the number of processes and workstations, the decision variables of the ethnic clothing sewing production operation scheduling model are:

[0017]

[0018] Where, X ij Indicates that the jth workstation processes the i-th process. If “processing”, X ij The value is 1, if "not processed", X ij is 0, based on the optimal solution obtained ij The value of can clarify the relationship between process i and work location j, so as to carry out job scheduling design.

[0019] Optionally, step S2: adding constraints to the decision variables of the ethnic clothing sewing production operation scheduling model, including:

[0020] The first constraint is that process i must complete processing at the jth workstation;

[0021] The second constraint condition is the constraint of the immediate predecessor process. It is assumed that the immediate predecessor process of the i-th process has m i Dao, denoted as i1,i2,…,i mi , if there is no immediate predecessor process, then m i is 0; the immediate preceding process of process i cannot be operated on the work site behind process i, and the expression is:

[0022]

[0023] The third constraint is the constraint on the use of equipment;

[0024] The fourth constraint is the total process duration constraint, setting the processing time of the i-th process to t i , T j It represents the total operation time of the jth workstation, and the expression is:

[0025]

[0026] The fifth constraint is the constraint of the scheduling efficiency η, which is expressed as:

[0027]

[0028] in,

[0029] In the formula, SPT refers to the theoretical average cycle time of the pipeline. max Refers to the maximum cycle time of the assembly line.

[0030] Considering the synchronization of the beats of each workstation on the production line and the balance of process load when allocating work, the operation time in each workstation should be within the beat boundary [LPT, UPT] range (where LPT = 2SPT-UPT, UPT = SPT / η). The efficiency of the establishment (η) is a coefficient that indicates the degree of process balance. Generally, the closer η is to 1, the better the degree of synchronization of the production line.

[0031] The sixth constraint is the process duration constraint. For processes with too large or too small cycles, if the operation process is complex and is limited by the order of previous and next processing, multiple processes can be combined to make their operation time basically close to the multiple of the effective average cycle, or the process can be split and assigned to 2 to 3 workstations to complete collaboratively, so that the operation time of each workstation is within the cycle limit.

[0032] Optionally, step S3: calculating the objective function to obtain the optimization target of the arrangement of the sewing production operation of ethnic clothing, including:

[0033] The objective function is the equilibrium index SI and the difference between the maximum beat and the minimum beat Fmin. The model solves the minimum value of SI and the minimum value of Fmin. The formula is as follows:

[0034]

[0035] F min =SPT max -SPT min ;

[0036] The model assumes that the number of processes in the garment assembly line is I, the number of workstations is J, and the operation time of each process is t i Known.

[0037] Optionally, the final model includes the above decision variables, constraints and objective function, which can be described as the expected X when the constraints are satisfied and the objective function is minimized. ij value, thereby determining the optimal solution for the process arrangement of the ethnic clothing production line.

[0038] Optionally, step S4: based on the optimization target, a hybrid optimization algorithm of genetic taboo is used to obtain an optimal arrangement model for the sewing production operation of ethnic clothing, including:

[0039] S4.1: Initialize the encoding of each individual in the population and set the number of iterations;

[0040] S4.2: Randomly generate an initial population, generate a given number of individuals to form the initial population;

[0041] S4.3: Calculate the fitness value of each individual in the current generation according to the fitness function, select the objective function as the fitness function, and the fitness function expression is:

[0042]

[0043] Fit(f(x))=F min =SPT max -SPT min ;

[0044] Calculate the fitness value of each individual in the current generation according to the objective function, and obtain the optimal individual in the current generation based on the fitness value;

[0045] S4.4: Find the optimal solution in the non-taboo neighborhood, compare the optimal individual of the current generation with the global optimal solution, and update the global optimal solution;

[0046] S4.5: Determine whether the termination condition is met. If so, output the result; otherwise, go to S4.7.

[0047] S4.6: Update the best individual of the current generation to the taboo table;

[0048] S4.7: Select operation;

[0049] S4.8: Crossover operation;

[0050] S4.9: Mutation operation;

[0051] S4.10: Update the population, update the population that has undergone the genetic taboo mixing operation to a new population, go to S4.3, and perform a round of iteration on the population P(k). This time, the maximum number of iterations is used as the stopping condition.

[0052] S4.11: Determine whether the number of iterations has been reached. If so, stop the iteration to obtain the optimal ethnic clothing sewing production operation scheduling model.

[0053] Optionally, use the maximum number of iterations as the stopping condition and set the number of iterations to 500.

[0054] Optionally, step S4.1: initializing and coding each individual in the population, including: a real number coding method based on the process priority sequence, intuitively reflecting the sequence of production processes through the chromosome coding order, each gene represents a process element, and is combined into chromosomes according to the job priority relationship, and initializing and coding each individual in the population.

[0055] Optionally, step S4.2: randomly generate an initial population, generate a given number of individuals to form an initial population, store in pops, including segmenting the chromosome code according to the optimization target requirements, and assigning the processing procedures to each work site, specifically:

[0056] S4.21: According to the production process operation sequence, the production process is branched according to the process table calculated according to the immediate predecessor process;

[0057] S4.22: Calculate the theoretical average beat SPT and the range of beat limits based on the number of custom workstations, the maximum number of equipment that can be used at each workstation, and the constraints of the beat limit;

[0058] S4.23: Generate gene fragments according to the average beat SPT and the priority of the operation process, obtain the process sequence, and assign the I process to J workstations in sequence, where the processing time of each workstation is T1, T2, ..., T J ;

[0059] S4.24: If the processing time of the Jth workstation is less than the cycle time lower limit LPT, then add the i+1th process to this workstation, and determine whether the processing time of the Jth workstation is within the cycle time limit after adding the i+1th process;

[0060] S4.25: If the processing time of the Jth workstation is greater than the cycle limit UPT, the process on this workstation is assigned to the J+1th workstation, and whether the processing time meets the cycle limit value range is determined, and return to S4.23.

[0061] S4.26: Repeat the above allocation process until all the processes in the chromosome are allocated.

[0062] Optionally, step S4.7: selection operation includes: sorting according to individual fitness values. The specific genetic taboo hybrid algorithm selection operation is as follows:

[0063] S4.71: The best individuals are retained and enter the new population;

[0064] S4.71: When the length of the taboo table is exceeded, the tabooed optimal values ​​are put back into the new population in turn;

[0065] S4.72: Roulette selection is used. The probability of each individual entering the next generation is equal to the ratio of its fitness value to the sum of the fitness values ​​of individuals in the entire population. The specific operation is as follows:

[0066] ① Calculate the fitness of each individual and sum them up.

[0067] ②For individual i, let its fitness value be f i , the population size is POP, then the selection probability of the individual can be expressed as:

[0068]

[0069] ③ Construct a roulette wheel. Divide the roulette wheel according to the individual selection probability table. Selecting N individuals from a given population is equivalent to rotating the roulette wheel N times. After multiple rounds of selection, enough individuals are selected to produce the next generation. Therefore, the same individual can be selected multiple times.

[0070] ④ Set the preset value. Generate a random number between [0,1]. Assume that the random number generated each time is q k , if q k If the individual falls into a certain interval of the selection probability value, the individual is selected, that is, when q i-1 k i , individual i is selected to enter the new population.

[0071] S4.71: Set taboo conditions, traverse the chromosomes in the population, compare the gap between each individual in the population and the individuals in the taboo table, and those that exceed the preset gap will enter the new population.

[0072] Since the individuals obtained by the selection operation do not meet the population size, crossover and mutation operations are required to supplement the population size.

[0073] Optionally, step S4.8: the crossover operation includes: for each individual, if the random number r≤Pc, where Pc is the crossover probability, then crossover is performed on the chromosome.

[0074] Optionally, the specific crossover steps are:

[0075] (1) Randomly select two crossover points in the parent chromosome to determine the crossover region. Assume that the two parent chromosomes are:

[0076] A: 12|3456|78; B: 21|6354|87, where || represents the intersection area.

[0077] ​​(2) Exchange the chromosome fragments of two individuals between the two set intersection points, that is, exchange the chromosomes of two rows in the individual matrix, that is, exchange the processing stations of a certain process in the two individual matrices.

[0078] A: 12|6354|78; B: 21|3456|87.

[0079] (3) Conflicting genes are mapped and converted.

[0080] Optionally, step S4.9: mutation operation, including: based on the new individuals obtained by the crossover operation, for each individual, if the random number r≤P m , where P m is the mutation probability, then the chromosome is mutated, otherwise the next chromosome is considered. The specific steps are:

[0081] S4.91: Randomly select two mutation points on the chromosome. Assume that the chromosome is A: 12|6354|78, where 6 and 4 are selected as mutation points. By exchanging the positions of the mutation points and changing the positions of the processes at the workstations, the processes are assigned to each workstation in sequence to obtain a new chromosome A': 12435678.

[0082] S4.92: Set taboo conditions. Traverse the chromosomes in the population and compare the gap between each individual in the population and the individuals in the taboo table. Individuals with a gap exceeding a certain value can enter a new population. The purpose is to escape from the local optimum.

[0083] S4.93: If the fitness is better, pardon it, otherwise discard it.

[0084] S4.94: Generate individual matrix Date_station.

[0085] Through the above technical solutions, it can be known that compared with the prior art, the present invention discloses a method for optimizing the arrangement of a national clothing sewing production line, which adopts a multi-objective genetic taboo hybrid algorithm to balance the process arrangement of the national clothing production line. The algorithm for balancing the national clothing production line is designed according to the mathematical model of national clothing production line balance, and an intelligent algorithm is used to replace manual work, and the processing procedures are allocated to each workstation, so that the beat of each station of the production line is equal to or close to the average beat of the production line. By balancing the production line, the production efficiency is improved, and the problems of long time and low efficiency of traditional manual arrangement are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] 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 only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0087] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0088] Figure 2 The operation flow chart of intelligent optimization of ethnic clothing production line by using hybrid optimization algorithm of genetic taboo;

[0089] Figure 3 It is a schematic diagram of the cross operation process;

[0090] Figure 4 Schematic diagram of the mutation operation process. DETAILED DESCRIPTION

[0091] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0092] The purpose of the present invention is to provide a method for optimizing the arrangement of a national clothing sewing production line, which belongs to the technical field of intelligent optimization scheduling of manufacturing production processes. It includes: obtaining the production information of national clothing to be sewn, and obtaining the decision variables of the national clothing sewing production operation arrangement model based on the national clothing production information; adding constraints to the decision variables of the national clothing sewing production operation arrangement model; calculating the objective function to obtain the optimization target of the national clothing sewing production operation arrangement; based on the optimization target, using a hybrid optimization algorithm with genetic taboos to obtain the optimal national clothing sewing production operation arrangement model; and optimizing the arrangement process of the sewing production line of national clothing through the optimal national clothing sewing production operation arrangement model. The present invention can make the beat of each station of the production line equal to or close to the average beat of the production line, improve the production efficiency by balancing the production line, and solve the problems of long time and low efficiency of traditional manual arrangement.

[0093] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0094] See also Figure 1As shown, the embodiment of the present invention discloses a method for optimizing the arrangement of a national clothing sewing production line, comprising the following steps:

[0095] S1: Obtain the production information of ethnic clothing to be sewn and produced, and obtain the decision variables of the ethnic clothing sewing production operation scheduling model based on the ethnic clothing production information;

[0096] S2: Add constraints to the decision variables of the ethnic clothing sewing production operation scheduling model;

[0097] S3: Calculate the objective function and obtain the optimization goal of the arrangement of the sewing production operation of ethnic clothing;

[0098] S4: Based on the optimization objective, the hybrid optimization algorithm of genetic taboo is used to obtain the optimal operation scheduling model of ethnic clothing sewing production;

[0099] S5: The optimization process of the ethnic clothing sewing production line is carried out through the optimal ethnic clothing sewing production operation scheduling model.

[0100] Specifically, three elements should be considered in the modeling of optimization problems, namely, decision variables, objective functions and constraints. Decision variables refer to the amount that can be changed, the amount that can be optimized, and better results can be obtained by changing the variables. It can be understood as a control variable, or some decisive parameters. Constraints refer to prerequisites, which limit the specific domain of the decision variable to limit the setting range. The objective function is divided into a single objective function and a multi-objective function, which can be understood as the more superior the objective function value is under the premise of satisfying the constraints. The present invention constructs a mathematical modeling of the balance optimization of the national clothing assembly line through problem raising, model decision variables, model constraints, and the setting of the model objective function.

[0101] In a specific embodiment, the model decision variables include:

[0102] Assume that a certain type of clothing has a total of I processes (divided into the smallest process), and the process number is i, then i = 1, 2, ..., I. And suppose that the number of workstations for this type of clothing is J (one workstation represents one operator), arranged in the order of the production line, and numbered j = 1, 2, ..., J. X ij Indicates that the jth workstation processes the i-th process. If “processing”, X ij The value is 1, if "not processed", X ij The decision variable definition is shown in formula (1-1). Based on the optimal solution obtained, X ij The value of can clarify the affiliation between process i and workstation j, so as to carry out job scheduling design.

[0103]

[0104] In a specific embodiment, the constraints include:

[0105] The order batch of ethnic clothing products is known, the operation time and processing equipment of each process and the production process flow are determined, the workers' operation level and proficiency of each process are roughly the same, and each worker can skillfully complete any process. According to the principle of balance in the process arrangement of ethnic clothing production lines, constraints mainly refer to the constraints on production by processes, equipment, personnel or raw materials, or they can be artificially defined limits, so that the final optimization plan is a balance of various factors. In the process arrangement of the production line, the constraints that need to be considered or met are reflected in the model as follows:

[0106] (1) Taking into account the proficiency of production workers and the neatness of process quality, the process cannot be further divided and is no longer split, indicating that process i is completed at a certain work location.

[0107] Specifically, the constraint that process i is completed at the jth workstation is considered. Taking into account the proficiency of production workers and the process quality requirements, the process cannot be divided any further and is no longer split, indicating that process i is completed at a certain workstation.

[0108] (2) Consider the operation sequence of the processes on the assembly line and set constraints on the preceding processes. Assume that the preceding processes of the i-th process have m i Dao, denoted as i1,i2,…,i mi , if there is no immediate predecessor process, then m i = 0. This means that the process immediately preceding process i cannot operate on the work site behind process i, which is expressed as formula (1-2).

[0109]

[0110] (3) Considering the increase in float time caused by changing equipment during production, it is known that workers will use all equipment S j In order to avoid the increase of production idle time caused by workers changing equipment, a worker is required to use a maximum of 2 types of equipment, and manual work can be combined with any equipment.

[0111] (4) Assume that the processing time of the i-th process is t i , T j represents the total operation time of the jth workstation, so the sum of the processing time of all the operations at the jth workstation should be equal to T j , see formula (1-3). SPT refers to the theoretical average cycle time of the assembly line, which is the processing time required for the assembly line to produce a piece of garment, see formula (1-4).

[0112]

[0113]

[0114] (5) Considering the synchronization of the beats of each workstation on the production line and the balance of process load when allocating work, the operation time in each workstation should be within the beat boundary [LPT, UPT] range (where LPT = 2SPT-UPT, UPT = SPT / η). The establishment efficiency (η) is a coefficient that indicates the degree of process balance. Generally, the closer η is to 1, the better the degree of synchronization of the production line. See formula (1-5).

[0115]

[0116] (6) Constraints on process duration: For processes with too large or too small cycles, if the operation process is complex and is limited by the order of previous and subsequent processing, multiple processes can be combined so that their operation time is basically close to a multiple of the effective average cycle. Alternatively, the process can be split and assigned to 2 to 3 workstations to collaborate and complete, so that the operation time of each workstation is within the cycle limit.

[0117] In a specific embodiment, the objective function includes:

[0118] The amount of work completed by each operator is measured by the standard processing time required to process that part of the work. In order to ensure continuous and balanced production at each workstation, each process needs to be evenly distributed to each workstation. The objective function is the balance index SI and the difference between the maximum beat and the minimum beat Fmin. The model solves the minimum value of SI and the minimum value of Fmin, see equations (1-9) and (1-10). The model assumes that the number of processes in the clothing assembly line is I, the number of workstations is J, and the operation time of each process is t i Known.

[0119]

[0120] F min =SPT max -SPT min (1-10)

[0121] The final model includes the above decision variables, constraints and objective function, which can be described as the expected X when the constraints are met and the objective function is minimized. ij value, thereby determining the optimal solution for the process arrangement of the ethnic clothing production line.

[0122] In a specific embodiment, the operation flow chart of intelligent optimization of the ethnic clothing production line using the hybrid optimization algorithm of genetic taboo is as follows: Figure 2 shown.

[0123] The hybrid optimization algorithm of genetic taboo is used to intelligently optimize the production line of ethnic clothing. The specific steps will be elaborated in detail below.

[0124] Step 1: Coding. The processes of ethnic clothing production lines are complex and numerous. This study chooses a real number coding method based on the process priority sequence, initializes the coding of the population individuals, and each gene represents a process element. The processes are organized into a chromosome with a length equal to the number of processes according to the job priority order. The chromosome coding order can intuitively reflect the sequence of production processes. Each operation process corresponds to a gene position in the chromosome, and the processes are assigned to each workstation in turn according to the process processing order. Real number coding has good adaptability to the objective function and genetic operator, and the algorithm has high execution efficiency and strong search ability, thereby improving the accuracy of the optimization results.

[0125] Step 2: Generate the initial population and decode. This embodiment uses a random method to generate the initial population, so that the initial population is as evenly distributed as possible in the entire solution space. The population is composed of chromosomes, each individual is a chromosome, and each chromosome corresponds to a solution to the problem. Before calculating the chromosome fitness value, the chromosome code needs to be segmented according to the optimization target requirements, the processing procedures are assigned to each workstation, and a given number of individuals are generated to form an initial population P(k), k=0.

[0126] (1) According to the process operation sequence, the production process is branched according to the process table calculated based on the immediately preceding process.

[0127] (2) Calculate the theoretical average cycle time SPT and the range of cycle time limits based on constraints such as the number of custom workstations (num_Station), the maximum number of equipment that can be used at each workstation (max_equipment_num), and cycle time limits (LPT, UPT).

[0128] (3) Generate gene fragments, that is, process sequences, according to the average cycle time SPT and job priority, and assign process I to J workstations in sequence, where the processing time of each workstation is T1, T2, ..., T J .

[0129] (4) If the processing time of the Jth workstation is less than the cycle time lower limit LPT, then add the i+1th process to this workstation, and then determine whether the processing time of the Jth workstation is within the cycle time limit after adding the i+1th process.

[0130] ① If the i+1th process is added and the processing time of the Jth workstation is within the cycle limit, the i+1th process will be allocated to the Jth workstation.

[0131] ② If the i+1th process is added and the processing time of the Jth workstation is less than the cycle time lower limit LPT, the i+2th process will be assigned to the Jth workstation until the constraint is met.

[0132] (5) If the processing time of the Jth workstation is greater than the cycle limit UPT, the process on this workstation is assigned to the J+1th workstation, and whether the processing time meets the cycle limit value range is determined, and then return to step (3).

[0133] (6) Repeat the above allocation process until all processes in the chromosome are allocated.

[0134] S4.3: Evaluate fitness. Calculate the fitness value of each individual in the current generation according to the fitness function, which is the objective function. And sort them in order from small to large according to the fitness value, the smaller the better, and the first individual after sorting is the best individual in the current generation. The fitness function is shown in Formula 2-13 and Formula 2-14. Calculate the fitness value of each individual in the current generation according to the objective function and store it in pops_fitness. And sort them in order from small to large according to the fitness value, the smaller the better, and the first individual after sorting is the best individual in the current generation.

[0135]

[0136] Fit(f(x))=F min =SPT max -SPT min ; (2-14)

[0137] Step 4: Update the global optimal solution. Find the optimal solution in the non-taboo neighborhood, compare the optimal individual of the current generation with the global optimal solution, and update the global optimal solution.

[0138] Step 5: Determine whether the termination condition is met. If so, output the result; otherwise, go to step 7.

[0139] Step 6: Update the taboo table. Update the best individual of the current generation to the taboo table.

[0140] Step 7: Selection operation. This embodiment first sorts individuals according to their fitness values. The better the fitness value, the greater the probability of entering the next generation. The specific genetic taboo hybrid algorithm selection operation is as follows:

[0141] (1) During the selection process, the individuals with the highest fitness enter the next generation directly without selection, ensuring that the optimal solution is preserved. In this embodiment, the top 5% of the best individuals are retained to enter the new population.

[0142] (2) When the length of the taboo table is exceeded, the tabooed optimal values ​​are put back into the new population one by one.

[0143] (3) Roulette selection is used. The probability of each individual entering the next generation is equal to the ratio of its fitness value to the sum of the fitness values ​​of individuals in the entire population. The specific operation is as follows:

[0144] ① Calculate the fitness of each individual and sum them up.

[0145] ②For individual i, let its fitness value be f i , the population size is POP, then the selection probability of the individual can be expressed as, as shown in formula 2-12, and set the taboo condition, traverse the chromosomes in the population, compare the gap between each individual in the population and the individuals in the taboo table, and those with a gap exceeding a certain value can enter the new population. The purpose is to jump out of the local optimum.

[0146]

[0147] ③Construct a roulette wheel and divide it according to the individual selection probability table. Selecting N individuals from a given population is equivalent to rotating the roulette wheel N times. After multiple rounds of selection, enough individuals are selected to produce the next generation. Therefore, the same individual can be selected multiple times.

[0148] ④ Set the preset value. Generate a random number between [0,1]. Assume that the random number generated each time is q k , if q k If the individual falls into a certain interval of the selection probability value, the individual is selected, that is, when q i-1 k i , individual i is selected to enter the new population.

[0149] (4) Set taboo conditions. Traverse the chromosomes in the population and compare the gap between each individual in the population and the individuals in the taboo table. Individuals with a gap exceeding a certain value can enter a new population. The purpose is to escape the local optimum.

[0150] Since the individuals obtained by the selection operation do not meet the population size, crossover and mutation operations are required to supplement the population size.

[0151] Step 8: Crossover operation. For each individual, if the random number r≤Pc (where Pc is the crossover probability), the chromosome is crossovered. For the sewing production line balance problem, this crossover operation adopts the partial matching crossover method, which ensures that the gene of each chromosome appears only once, avoiding gene duplication. The schematic diagram of the crossover operation process is as follows Figure 3 As shown, the specific crossover steps are:

[0152] (1) Randomly select two crossover points in the parent chromosome to determine the crossover region. Assume that the two parent chromosomes are:

[0153] A: 12|3456|78; B: 21|6354|87, where || represents the intersection area.

[0154] ​​(2) Exchange the chromosome fragments of two individuals between the two set intersection points, that is, exchange the chromosomes of two rows in the individual matrix, that is, exchange the processing stations of a certain process in the two individual matrices.

[0155] A: 12|6354|78; B: 21|3456|87.

[0156] (3) Conflicting genes are mapped and converted.

[0157] Step 9: Mutation operation. The schematic diagram of the mutation operation process is as follows Figure 4 As shown, the specific mutation operation steps are:

[0158] The mutation operation is based on the new individuals obtained by the crossover operation. For each individual, if the random number r≤P m (where P m is the mutation probability), then the chromosome is mutated, otherwise the next chromosome is considered. The following are the detailed steps:

[0159] ① Randomly select two mutation points on the chromosome. Assume that the chromosome is A: 12|6354|78, where 6 and 4 are selected as mutation points. By exchanging the positions of the mutation points and changing the positions of the processes at the workstations, the processes are assigned to each workstation in sequence to obtain a new chromosome A': 12435678.

[0160] ② Set taboo conditions. Traverse the chromosomes in the population and compare the gap between each individual in the population and the individuals in the taboo table. Individuals with a gap exceeding a certain level can enter a new population. The purpose is to escape from the local optimum.

[0161] ③If the fitness is better, then pardon it, otherwise discard it.

[0162] ④Generate individual process scheduling matrix.

[0163] Step 10: Update the population, update the population that has undergone the genetic taboo mixing operation to a new population, go to S4.3, and perform a round of iteration on the population P(k). This time, the maximum number of iterations is used as the stopping condition.

[0164] Step 11: Determine the stopping condition. This time, the maximum number of iterations is used as the stopping condition, and the number of iterations is set to 500.

[0165] Specifically, based on the characteristics of genetic algorithm and taboo search algorithm, a genetic taboo hybrid algorithm is designed. Since the genetic algorithm has strong global search ability through selection, crossover and mutation genetic operations, it is used as the main part of the algorithm. The initial group in the global space quickly traverses most areas of the solution space in parallel. When the iteration terminates, the optimization result is stabilized in the better area of ​​the solution space. The taboo search algorithm has strong local search ability through the taboo table and amnesty criteria. It is used as an auxiliary algorithm. Starting from each individual in the optimization area, the taboo search algorithm is used to search in a small range in the local space. The hybrid algorithm effectively makes up for the defects of the poor local search ability of the genetic algorithm and the weak global search ability and strong dependence on the initial solution of the taboo search algorithm.

[0166] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0167] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined in the present invention may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in the present invention, but will conform to the widest scope consistent with the principles and novel features disclosed in the present invention.

Claims

1. A method for optimizing the arrangement of a national clothing sewing production line, characterized in that: The following steps are involved: S1: Obtain the production information of ethnic clothing to be sewn and produced, and obtain the decision variables of the ethnic clothing sewing production operation scheduling model based on the ethnic clothing production information; S2: Add constraints to the decision variables of the ethnic clothing sewing production operation scheduling model; S3: Calculate the objective function and obtain the optimization goal of the arrangement of the sewing production operation of ethnic clothing; S4: Based on the optimization objective, the hybrid optimization algorithm of genetic taboo is used to obtain the optimal operation scheduling model of ethnic clothing sewing production; S5: The optimization process of the ethnic clothing sewing production line is carried out through the optimal ethnic clothing sewing production operation scheduling model.

2. The method for optimizing the arrangement of a national clothing sewing production line according to claim 1, characterized in that: S1: Obtain the production information of ethnic clothing to be sewn and produced, and obtain the decision variables of the ethnic clothing sewing production operation scheduling model based on the ethnic clothing production information, including: S1.1: Set the number of processes for the ethnic costumes to be arranged to be I, and the process number is i, i = 1, 2, ..., I; S1.2: Set the number of workstations for the ethnic costumes to be arranged to J; one workstation represents one operator, and they are arranged in the order of the production line, numbered j = 1, 2, ..., J; S1.3: Based on the number of processes and workstations, the decision variables of the ethnic clothing sewing production operation scheduling model are: In the formula, X ij Indicates that the jth workstation processes the i-th process. If processing, X ij The value is 1, if not processed, X ij is 0.

3. The method for optimizing the arrangement of a national clothing sewing production line according to claim 1, characterized in that: S2: Add constraints to the decision variables of the national clothing sewing production operation scheduling model, including: The first constraint is that process i must complete processing at the jth workstation; The second constraint condition is the constraint of the immediate predecessor process. It is assumed that the immediate predecessor process of the i-th process has m i Dao, denoted as i1,i2,…,i mi , if there is no immediate predecessor process, then m i is 0; the immediate preceding process of process i cannot be operated on the work site behind process i, and the expression is: The third constraint is the constraint on the use of equipment; The fourth constraint is the total process duration constraint, setting the processing time of the i-th process to t i , T j It represents the total operation time of the jth workstation, and the expression is: The fifth constraint is the constraint of the scheduling efficiency η, which is expressed as: in, In the formula, SPT refers to the theoretical average cycle time of the pipeline. max Refers to the maximum beat of the assembly line; The sixth constraint condition is the constraint on process duration.

4. The method for optimizing the arrangement of a national clothing sewing production line according to claim 1, characterized in that: S3: Calculate the objective function and obtain the optimization goal of the arrangement of the sewing production operation of ethnic clothing, including: The objective function is the equilibrium index SI and the difference between the maximum beat and the minimum beat Fmin. The model solves the minimum value of SI and the minimum value of Fmin. The formula is as follows: F min =SPT max -SPT min 。 5. The method for optimizing the arrangement of a national clothing sewing production line according to claim 1, characterized in that: S4: Based on the optimization objective, the hybrid optimization algorithm of genetic taboo is used to obtain the optimal operation scheduling model of ethnic clothing sewing production, including: S4.1: Initialize the encoding of each individual in the population and set the number of iterations; S4.2: Randomly generate an initial population, generate a given number of individuals to form the initial population; S4.3: Calculate the fitness value of each individual in the current generation according to the fitness function, select the objective function as the fitness function, calculate the fitness value of each individual in the current generation according to the objective function, and obtain the optimal individual in the current generation based on the fitness value; S4.4: Find the optimal solution in the non-taboo neighborhood, compare the optimal individual of the current generation with the optimal solution, and update the global optimal solution; S4.5: Determine whether the termination condition is met. If so, output the result. Otherwise, go to S4.

7. S4.6: Update the best individual of the current generation to the taboo table; S4.7: Select operation; S4.8: Crossover operation; S4.9: Mutation operation; S4.10: Update the population, update the population that has undergone the genetic taboo mixing operation to a new population, go to S4.3, and iterate the population P(k) for one round. This time, the maximum number of iterations is used as the stopping condition; S4.11: Determine whether the number of iterations has been reached. If so, stop the iteration to obtain the optimal ethnic clothing sewing production operation scheduling model.

6. The method for optimizing the arrangement of a national costume sewing production line according to claim 5, characterized in that: S4.1: Initialize and encode each individual in the population, including: real number encoding based on process priority sequence, intuitively reflecting the sequence of production processes through chromosome encoding sequence, each gene represents a process element, and is combined into chromosomes according to the job priority relationship, and initializes and encodes each individual in the population.

7. The method for optimizing the arrangement of a national costume sewing production line according to claim 6, characterized in that: S4.2: Randomly generate an initial population, generate a given number of individuals to form the initial population, including: S4.21: According to the production process operation sequence, the production process is branched according to the process table calculated according to the immediate predecessor process; S4.22: Calculate the theoretical average beat SPT and the range of beat limits based on the number of custom workstations, the maximum number of equipment that can be used at each workstation, and the constraints of the beat limit; S4.23: Generate gene fragments according to the average beat SPT and the priority of the operation process, obtain the process sequence, and assign the I process to J workstations in sequence, where the processing time of each workstation is T1, T2, ..., T J ; S4.24: If the processing time of the Jth workstation is less than the cycle time lower limit LPT, then add the i+1th process to this workstation, and determine whether the processing time of the Jth workstation is within the cycle time limit after adding the i+1th process; S4.25: If the processing time of the Jth workstation is greater than the cycle limit UPT, the process on this workstation is assigned to the J+1th workstation, and whether the processing time meets the cycle limit value range is determined, and then return to S4.23; S4.26: Repeat the above allocation process until all the processes in the chromosome are allocated.

8. The method for optimizing the arrangement of a national costume sewing production line according to claim 5, characterized in that: S4.7: Selection operation, including: sorting according to individual fitness values. The specific genetic taboo hybrid algorithm selection operation is as follows: S4.71: The best individuals are retained and enter the new population; S4.72: When the length of the taboo table is exceeded, the tabooed optimal values ​​are put back into the new population in turn; S4.73: Using roulette wheel selection, the probability of each individual entering the next generation is equal to the ratio of its fitness value to the sum of the fitness values ​​of individuals in the entire population; S4.74: Set taboo conditions, traverse the chromosomes in the population, compare the gap between each individual in the population and the individuals in the taboo table, and those that exceed the preset gap will enter the new population.

9. A system for optimizing the arrangement of a national clothing sewing production line using the method for optimizing the arrangement of a national clothing sewing production line according to any one of claims 1 to 8, characterized in that: include: Data acquisition module: obtains the production information of ethnic clothing to be sewn and produced, and obtains the decision variables of the ethnic clothing sewing production operation scheduling model based on the ethnic clothing production information; Constraint setting module: add constraints to the decision variables of the ethnic clothing sewing production operation scheduling model; Calculation module: calculate the objective function and obtain the optimization target of the arrangement of the sewing production operation of ethnic clothing; Model building module: Based on the optimization target, a hybrid optimization algorithm with genetic taboo is used to obtain the optimal operation arrangement model for sewing production of ethnic clothing; Optimization module: optimize the arrangement process of the ethnic clothing sewing production line through the optimal ethnic clothing sewing production operation arrangement model.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for optimizing the arrangement of the ethnic clothing sewing production line as described in any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Garment sewing assembly line optimization method

    CN110135707A

  • Scheduling optimization method based on combination of tabu search algorithm and genetic algorithm

    CN113656156A

  • Automobile engine flexible production line batching and scheduling method

    CN114492895A

  • Genetic algorithm optimization scheduling method for multi-objective flexible job-shop problem

    CN116560313A

  • Adaptive learning intelligent scheduling unified computing framework and system for industrial personalized customized production

    WO2022099596A1