A garment production process distribution method considering hanging connectivity constraints

Abstract

The application provides a garment production process distribution method considering hanging connectivity constraints, comprising the following steps: obtaining work station information of a production workshop, process information of a workpiece to be processed and connectivity information of a hanging system between work stations; taking the connectivity information of the hanging system between the work stations as a constraint condition to establish a work station distance matrix of the production workshop; generating a population of an NSGA-II algorithm according to the work station distance matrix, the work station information of the production workshop and the process information of the workpiece to be processed by using a greedy rule; taking the minimum total walking distance of the hanging system and the minimum total processing time difference between all activated work stations as optimization objectives to construct a multi-objective optimization model; and solving the multi-objective optimization by using the NSGA-II algorithm based on the population generated in step S3 to obtain an optimal garment production process distribution scheme. The application effectively improves the production efficiency of the garment and reduces the production cost.

Description

Technical Field

[0001] The invention belongs to the technical field of garment processing, and in particular relates to a garment production process allocation method considering hanging connectivity constraints. Background Art

[0002] In the modern apparel industry, with the expansion of production scale and increasing consumer demands for product quality and delivery time, optimizing and intelligently managing production processes are key to improving competitiveness. Traditional manual process allocation and scheduling methods are not only inefficient but also difficult to cope with complex and changing production demands, leading to resource waste and increased production costs. Therefore, developing a production process optimization and allocation system based on intelligent algorithms is particularly important.

[0003] In the garment production process, the layout of workstations in the production workshop, the process flow of workpieces to be processed, and the transportation efficiency of the hanging system directly impact production efficiency and costs. The workstation layout determines the paths and distances required for workpieces to be transferred between different processes. As a key transportation tool connecting the various workstations, the connectivity and efficiency of the hanging system are crucial to the smooth flow of the production process. However, traditional methods often overlook the interplay between these factors, resulting in irrational process allocation, increased hanging system travel distances, and idle waiting time at workstations, thereby reducing overall production efficiency and costs. Summary of the Invention

[0004] In order to solve the problems existing in the background technology, improve the efficiency of clothing production, and reduce the cost of clothing production, the present invention provides a clothing production process allocation method considering hanging connectivity constraints, comprising:

[0005] S1: Obtain the workstation information of the production workshop, the process information of the workpiece to be processed, and the connectivity information of the hanging system between the workstations;

[0006] S2: Using the connectivity information of the hanging system between workstations as a constraint condition to establish the workstation distance matrix of the production workshop;

[0007] S3: Generate the population of the NSGA-II algorithm using the greedy rule according to the workstation distance matrix, the workstation information of the production workshop, and the process information of the workpiece to be processed;

[0008] S4: Construct a multi-objective optimization model by taking the minimum total travel distance of the hanging system and the minimum average difference in total processing time between all activated workstations as the optimization objectives;

[0009] S5: Based on the population generated in step S3, the NSGA-II algorithm is used to solve the multi-objective optimization and obtain the optimal clothing production process allocation plan.

[0010] Preferably, the establishment of the workstation distance matrix of the production workshop includes: transporting work-in-progress between different workstations through a hanging system, and constructing a workstation distance matrix based on the moving distance of the hanging system between different workstations, wherein the distance between two workstations that cannot be connected to each other is represented as -1.

[0011] Preferably, step S3 includes:

[0012] S31: Initialize the population size to N;

[0013] S32: for each first process of the workpiece to be processed that has no preceding process, randomly select a workstation from its set of assignable workstations as its assigned workstation;

[0014] S33: Using the front-end and back-end relationships between processes as constraints, traverse all processes and use the greedy rule based on the workstation distance matrix to select the workstation closest to the front-end workstation as the assigned workstation for the back-end process; until all processes are assigned to the assigned workstations, individuals in the NSGA-II algorithm population are generated;

[0015] S34: Repeat steps S32-S34 until the number of individuals reaches N, and obtain the population of the NSGA-II algorithm.

[0016] Preferably, the multi-objective optimization model includes:

[0017]

[0018] Among them, O1 and O2 represent two optimization goals, G represents the process set of the workpiece to be processed, l and u represent two different processes, and process u is the subsequent process of process l; k1 and k2 represent two different workstations; Y luk1k represents a binary variable, when process l is scheduled at k1 and process u is scheduled at k2, Y luk1k2 Equal to 1, otherwise Y luk1k Equal to 0; D k1k2 K represents the distance between station k1 and station k2 in the station distance matrix; ava Indicates the total number of all activated workstations; CA k represents the total processing time of station k, Indicates the average processing time of all activated workstations.

[0019] Preferably, step S5 includes:

[0020] S51: Perform non-dominated sorting on the population of the NSGA-II algorithm to obtain the rank of each individual in the population;

[0021] S52: traverse each optimization objective in the multi-objective optimization model, calculate the crowding degree of each individual in the population under the optimization objective, and sum up the crowding degree of each individual under all optimization objectives to obtain the final crowding degree of each individual in the population;

[0022] S53: Based on the individual's level and the individual's final crowding degree, an elite retention strategy is used to select X individuals from the population as elite individuals for retention, and a tournament selection strategy is used to select parent individuals from the population to generate a parent population;

[0023] S54: Generate a child population using a simulated binary crossover and mutation algorithm on the parent population, and merge the parent population and the child population to form a temporary population;

[0024] S55: Y individuals are selected from the temporary population according to the preset probability model, X+Y=N, where N represents the size of the population;

[0025] S56: The individuals screened out in step S55 and the retained elite individuals are combined to form the population for the next iteration, and steps S51-S56 are repeated until the preset number of iterations is reached, and the optimal solution is output.

[0026] Preferably, the non-dominated sorting of the population of the NSGA-II algorithm comprises:

[0027] S511: For each individual P in the population, initialize the set S p and counter n p ;

[0028] S512: For each individual p in the population, traverse the other individuals q in the population. If individual p dominates individual q, add individual q to the set S p If individual p is dominated by individual q, then n p Add 1;

[0029] S513: Traverse the individuals in the population, if there is a counter n for individual p p When it is 0, individual p is placed in the non-dominated frontier set F1, and the rank of individual p is set to 0;

[0030] S514: For each non-dominated front set F i , traverse the non-dominated frontier set F i For each individual p in the set S of individual p p For each individual q in the q Subtract 1 if n q If it decreases to 0, the rank of individual q is set to i+1, and individual q is added to the next non-dominated frontier set F i+1 ;

[0031] S515: When the non-dominated frontier set is empty, the sorting process ends and the rank of each individual in the population is obtained.

[0032] Preferably, the step of selecting X individuals from the population as elite individuals using an elite retention strategy includes:

[0033] S5211: Calculate the population size N, the number of elite individuals retained X = [α·N] 取整 ,α is a real number in the interval (0,1];

[0034] S5212: Starting from the first non-dominated frontier set F1, individuals are sequentially selected from the non-dominated frontier set as elite individuals until the predetermined number of elite individuals X is reached. The selection strategy is as follows:

[0035] First, select all individuals in the non-dominated frontier set F1. If the number of individuals in set F1 is less than X, continue to select from the non-dominated frontier set F2, and so on. If the number of selected elite individuals reaches X or all non-dominated frontier sets have been traversed, stop selecting. If in a non-dominated frontier set F i It is necessary to select some individuals as elite individuals, then according to the set F i The final crowding degree of individuals in the pool is selected from high to low.

[0036] Preferably, the crowding degree of each individual under the optimization objective includes:

[0037]

[0038] Where m∈{O1, O2} represents the optimization target; Im(i) represents the crowding degree of individual i under the optimization target m; f m (i+1) represents the value of individual i+1 under the optimization target m; f m (i-1) represents the value of individual i-1 under the optimization target m; Represents the maximum value of all individuals under the optimization target m; Represents the minimum value of all individuals under the optimization target m.

[0039] Preferably, the step of selecting parent individuals from a population using a tournament selection strategy to generate a parent population comprises:

[0040] S5221: Randomly select k individuals from the current population to form a tournament group;

[0041] S5222: In a tournament population, the best individual is selected as the parent individual by comparing the individual's rank and final crowding degree. The selection strategy is as follows:

[0042] For individuals p and q, if the rank(p) of individual p is less than the rank(q) of individual q, then select individual p; if the rank(p) of individual p is greater than the rank(q) of individual q, then select individual q; if the rank(p) of individual p is equal to the rank(q) of individual q, then select the individual with the larger final crowding degree between individuals p and q; if the final crowding degrees of individuals p and q are also the same, then randomly select an individual from individuals p and q as the parent individual;

[0043] S5223: Repeat steps S5221 to S5223 until the number of parent individuals reaches a set threshold to generate a parent population.

[0044] Preferably, the generating the offspring population by using a simulated binary crossover and mutation algorithm on the parent population comprises:

[0045] Simulating binary crossover selection includes: randomly selecting two parent individuals from the parent population, randomly selecting some genes from the two parent individuals to exchange, and generating two offspring individuals;

[0046] The mutation algorithm selection includes: randomly selecting a parent individual from the parent population, changing the workstation assigned to a randomly selected process from the parent to generate a child individual;

[0047] Based on the connectivity of the hanging system and the workstation information, the generated offspring individuals are judged to be reasonable. If not, the unreasonable offspring individuals are discarded.

[0048] A preset number of offspring populations are generated based on the simulated binary crossover and / or mutation algorithm.

[0049] The present invention has at least the following beneficial effects

[0050] By optimizing process allocation and reducing the total distance the hanging system travels between workstations, this method directly reduces the time cost of material transportation and speeds up the production process. It also balances the average processing time differences between workstations, preventing some workstations from being idle or overly busy for extended periods, thereby improving overall production efficiency. Reducing the travel distance of the hanging system means lowering energy consumption and equipment wear, which helps reduce maintenance costs and energy consumption in the long term. Furthermore, optimizing process allocation reduces production stoppages caused by waiting or congestion, further reducing production costs. This solution takes into account the actual environment of the production workshop and the connectivity of the hanging system, making process allocation more flexible and adaptable. When production demand or workshop layout changes, the optimal process allocation solution can be regenerated by adjusting the parameters in the optimization model, ensuring continued high efficiency of the production process. This solution introduces an intelligent algorithm for process allocation optimization, providing strong support for intelligent management in garment manufacturing companies. Through data-driven and algorithmic optimization, companies can more accurately grasp production status and achieve real-time monitoring and dynamic adjustment of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0052] The following describes the embodiments of the present invention by means of specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0053] See also Figure 1 The present invention provides a method for allocating garment production processes considering hanging connectivity constraints, comprising:

[0054] S1: Obtain the workstation information of the production workshop, the process information of the workpiece to be processed, and the connectivity information of the hanging system between the workstations;

[0055] S2: Using the connectivity information of the hanging system between workstations as a constraint condition to establish the workstation distance matrix of the production workshop;

[0056] S3: Generate the population of the NSGA-II algorithm using the greedy rule according to the workstation distance matrix, the workstation information of the production workshop, and the process information of the workpiece to be processed;

[0057] S4: Construct a multi-objective optimization model by taking the minimum total travel distance of the hanging system and the minimum average difference in total processing time between all activated workstations as the optimization objectives;

[0058] S5: Based on the population generated in step S3, the NSGA-II algorithm is used to solve the multi-objective optimization and obtain the optimal clothing production process allocation plan.

[0059] In this embodiment, the workstation information includes the workstation ID, the workstation location, and the set of processes that can be processed at the workstation. The process information of the workpiece to be processed includes all the processes of the workpiece to be processed, the standard working time of each process, and the set of subsequent processes of each process. The upstream and downstream relationships of the processes are expressed as one process must be completed before another process can begin, which is a common representation in this field. The workstations are connected and transported through a hanging system.

[0060] By taking the minimum total travel distance of the hanging system and the minimum average difference in total processing time between all activated workstations as the optimization goals, the total travel distance of the hanging system between workstations is reduced, which directly reduces the time cost of material transportation, speeds up the production process, balances the average difference in processing time between each workstation, avoids the situation where some workstations are idle for a long time or are overly busy, and thus improves overall production efficiency.

[0061] Preferably, the establishment of the workstation distance matrix of the production workshop includes: transporting work-in-progress between different workstations through a hanging system, and constructing a workstation distance matrix based on the moving distance of the hanging system between different workstations, wherein the distance between two workstations that cannot be connected to each other is represented as -1.

[0062] In this example, by precisely measuring and recording the actual travel distances of the hanging system between different workstations and constructing a workstation distance matrix, a more accurate data foundation is provided for subsequent process allocation optimization. This helps the algorithm more accurately assess transportation costs under different process allocation schemes, thereby generating optimization results that are more closely aligned with actual needs. Setting the distances between non-connected workstations to -1 effectively reflects the actual layout of the production workshop and the connectivity limitations of the hanging system. This makes the optimization model more closely aligned with production reality, avoids generating unrealistic process allocation schemes, and enhances the model's applicability and practicality.

[0063] Preferably, step S3 includes:

[0064] S31: Initialize the population size to N;

[0065] S32: for each first process of the workpiece to be processed that has no preceding process, randomly select a workstation from its set of assignable workstations as its assigned workstation;

[0066] S33: Taking the front-rear relationship between processes as a constraint condition, traversing all processes, and selecting the station closest to the distribution station of the front process as the distribution station of the rear process according to the station distance matrix by using the greedy rule, until all processes are distributed to the distribution stations, and an individual in the NSGA-II algorithm population is generated;

[0067] S34: Repeating steps S32-S34 until the number of individuals reaches N, and the NSGA-II algorithm population is obtained.

[0068] In this embodiment, the number of processes m=6 and the number of stations s=4 are taken as examples, and the processes o1 to o6 represent the processing order from small to large according to the serial number. Since the machines of the stations are determined, the distribution stations of each process are also determined, and Table 1 shows the distribution stations of each process. In this example, it is assumed that the four stations are all communicable, and the distance between them increases with the increase of the serial number.

[0069] Table 1 Distribution stations of each process

[0070]

[0071] Search for the first process; that is, search for the process without a front process in all process pairs with a front-rear order relationship, and o1 is the first process in this example;

[0072] Starting from the first process o1, randomly select s1 from the distribution station set [s1, s2] of o1 as the final distribution station of o1, and take the front-rear relationship between workpiece processes as a constraint condition, and the post-process of o1 is o2. According to the distribution station set of the post-process o2 of o1, the station is selected by using the greedy rule;

[0073] For the distribution station set [s3, s4] of the post-process of the first process o1, assuming that the distance matrix of each station is dis, the station closest to the distance of the selected station of o2 is selected according to the greedy rule, and the selection formula is as follows:

[0074] sel_station = min(dis[1, 2], dis[1, 4])

[0075] After the distribution station of the process o2 is determined, the above steps are repeated until all processes are distributed to the stations. For this example, the final scheme is (s1, s2, s3, s4, s4, s4).

[0076] In the embodiment, before step S32 is performed, the following steps can also be included: searching a historical database, judging whether the process information of each allocation scheme stored in the historical database is consistent with the process information of the workpiece to be processed, if yes, taking the allocation scheme in the historical database as an individual, storing the obtained allocation scheme in the historical database after step S5 is performed, and then performing step S32.

[0077] In the embodiment, the allocation stations for the first process are randomly selected (S32), and then the allocation stations for the subsequent processes are allocated step by step using the greedy rule (S33) starting from the first process until all the processes are allocated. This method can quickly generate an initial population, improve the convergence speed, reduce the calculation amount of the algorithm, and enhance the sensitivity and reaction speed of the algorithm. The scheme has significant beneficial effects in terms of accuracy, efficiency, resource utilization, solution diversity, subsequent optimization support, and algorithm convergence speed.

[0078] Preferably, the multi-objective optimization model comprises:

[0079]

[0080] wherein O1 and O2 represent two optimization objectives, G represents a process set of the workpiece to be processed, l and u represent two different processes, and process u is a subsequent process of process l; k1 and k2 represent two different stations; Y luk1k represents a binary variable, Y luk1k2 equals 1 when process l is arranged at k1 and process u is arranged at k2, and Y luk1k equals 0 otherwise; D k1k2 represents the distance between station k1 and station k2 in the station distance matrix; K ava represents the total number of all active stations; CA k represents the total processing time of station k, represents the average processing time of all active stations.

[0081] In the embodiment, the total walking distance of the hanging system and the average processing time difference between all active stations are minimized as optimization objectives to reduce the total walking distance of the hanging system between stations, directly reduce the time cost of material transportation, speed up the production process, balance the processing time difference between stations, avoid the situation that some stations are idle for a long time or are too busy, and thus improve the overall production efficiency.

[0082] Preferably, step S5 comprises:

[0083] S51: non-dominant sorting is performed on the population of the NSGA-II algorithm to obtain the rank of each individual in the population;

[0084] S52: traverse each optimization objective in the multi-objective optimization model, calculate the crowding degree of each individual in the population under the optimization objective, and sum up the crowding degree of each individual under all optimization objectives to obtain the final crowding degree of each individual in the population;

[0085] S53: Based on the individual's level and the individual's final crowding degree, an elite retention strategy is used to select X individuals from the population as elite individuals for retention, and a tournament selection strategy is used to select parent individuals from the population to generate a parent population;

[0086] S54: Generate a child population using a simulated binary crossover and mutation algorithm on the parent population, and merge the parent population and the child population to form a temporary population;

[0087] S55: Y individuals are selected from the temporary population according to the preset probability model, X+Y=N, where N represents the size of the population;

[0088] S56: The individuals screened out in step S55 and the retained elite individuals are combined to form the population for the next iteration, and steps S51-S56 are repeated until the preset number of iterations is reached, and the optimal solution is output.

[0089] In this embodiment, step S51 uses non-dominated sorting to enable the algorithm to distinguish between the merits and demerits of different individuals in the population and classify them into different levels (frontiers). This helps prioritize superior individuals in the subsequent selection process, thereby guiding the algorithm toward the global optimal solution. Crowding is a metric that measures the density of solutions surrounding an individual in the population. By calculating the crowding of each individual under all optimization objectives and summing the final crowding, the algorithm can further distinguish between superior and inferior individuals within the same level, maintaining population diversity. This helps the algorithm avoid falling into local optimal solutions during the search process. The elite retention strategy directly retains the best individuals in the current population to the next generation, preventing the loss of excellent solutions. This helps the algorithm continuously accumulate excellent solutions during the iteration process, improving the algorithm's convergence speed and solution quality. Tournament selection is a selection strategy based on random competition that selects parent individuals by comparing the fitness of a small number of individuals. This method can maintain population diversity to a certain extent and help the algorithm escape local optimal solutions. Merging the parent and child populations to form a temporary population helps the algorithm search for the optimal solution in a larger solution space. A certain number of individuals are selected from the temporary population based on a pre-set probability model to keep the population size constant. This process can further filter out poor solutions and retain better solutions.

[0090] In this embodiment, the preset probability model includes: a random selection mechanism (roulette selection) or a deterministic selection mechanism (tournament selection strategy).

[0091] Preferably, the non-dominated sorting of the population of the NSGA-II algorithm comprises:

[0092] S511: For each individual P in the population, initialize the set S p and counter n p ;

[0093] S512: For each individual p in the population, traverse the other individuals q in the population. If individual p dominates individual q, add individual q to the set S p If individual p is dominated by individual q, then n p Add 1;

[0094] S513: Traverse the individuals in the population, if there is a counter n for individual p p When it is 0, individual p is placed in the non-dominated frontier set F1, and the rank of individual p is set to 0;

[0095] S514: For each non-dominated front set F i , traverse the non-dominated frontier set F i For each individual p in the set S of individual p p For each individual q in the q Subtract 1 if n q If it decreases to 0, the rank of individual q is set to i+1, and individual q is added to the next non-dominated frontier set F i+1 ;

[0096] S515: When the non-dominated frontier set is empty, the sorting process ends and the rank of each individual in the population is obtained.

[0097] Preferably, the step of selecting X individuals from the population as elite individuals using an elite retention strategy includes:

[0098] S5211: Calculate the population size N, the number of elite individuals retained X = [α·N] 取整 ,α is a real number in the interval (0,1];

[0099] S5212: Starting from the first non-dominated frontier set F1, individuals are sequentially selected from the non-dominated frontier set as elite individuals until the predetermined number of elite individuals X is reached. The selection strategy is as follows:

[0100] First, select all individuals in the non-dominated frontier set F1. If the number of individuals in set F1 is less than X, continue to select from the non-dominated frontier set F2, and so on. If the number of selected elite individuals reaches X or all non-dominated frontier sets have been traversed, stop selecting. If in a non-dominated frontier set Fi It is necessary to select some individuals as elite individuals, then according to the set F i The final crowding degree of individuals in the pool is selected from high to low.

[0101] Preferably, the crowding degree of each individual under the optimization objective includes:

[0102]

[0103] Where m∈{O1, O2} represents the optimization objective; I m (i) represents the crowding degree of individual i under the optimization target m; f m (i+1) represents the value of individual i+1 under the optimization target m; f m (i-1) represents the value of individual i-1 under the optimization target m; Represents the maximum value of all individuals under the optimization target m; Represents the minimum value of all individuals under the optimization target m.

[0104] Preferably, the step of selecting parent individuals from a population using a tournament selection strategy to generate a parent population comprises:

[0105] S5221: Randomly select k individuals from the current population to form a tournament group;

[0106] S5222: In a tournament population, the best individual is selected as the parent individual by comparing the individual's rank and final crowding degree. The selection strategy is as follows:

[0107] For individuals p and q, if the rank(p) of individual p is less than the rank(q) of individual q, then select individual p; if the rank(p) of individual p is greater than the rank(q) of individual q, then select individual q; if the rank(p) of individual p is equal to the rank(q) of individual q, then select the individual with the larger final crowding degree between individuals p and q; if the final crowding degrees of individuals p and q are also the same, then randomly select an individual from individuals p and q as the parent individual;

[0108] S5223: Repeat steps S5221 to S5223 until the number of parent individuals reaches a set threshold to generate a parent population.

[0109] Preferably, the generating the offspring population by using a simulated binary crossover and mutation algorithm on the parent population comprises:

[0110] Simulating binary crossover selection includes: randomly selecting two parent individuals from the parent population, randomly selecting some genes from the two parent individuals to exchange, and generating two offspring individuals;

[0111] The mutation algorithm selection includes: randomly selecting a parent individual from the parent population, changing the workstation assigned to a randomly selected process from the parent to generate a child individual; judging whether the generated child individual is reasonable based on the connectivity of the hanging system and the workstation information, and discarding the unreasonable child individual if it is unreasonable;

[0112] A preset number of offspring populations are generated based on the simulated binary crossover and / or mutation algorithm.

[0113] In this embodiment, the probability ratio of binary crossover and mutation algorithms is selected to be 0.9:0.1;

[0114] In this example, assume that the two parent chromosomes are p1 = [2, 2, 2, 3, 3, 5, 6, 7, 8] and p2 = [1, 1, 2, 3, 4, 5, 6, 6, 8]. When performing the crossover operation, the starting and ending positions are first randomly selected, for example, 2 and 4. Then, the segments from positions 2 to 4 are swapped between the two, resulting in the new daughter chromosomes c1 = [2, 2, 2, 3, 4, 5, 6, 7, 8] and c2 = [1, 1, 2, 3, 3, 5, 6, 6, 8].

[0115] Chromosome mutation: Assume that the parent chromosome is d1[2, 2, 2, 3, 3, 5, 6, 7, 8], randomly select a position, and then change the arrangement of the process. For example, if the selected sequence number is 4, it means that process 4 is arranged at station 3. Assuming that process 4 can also be arranged at station 2, the mutation method at this time is to change 3 to 2

[0116] Assume the parent chromosome is p1 = [2,2,2,3,3,5,6,7,8]. During the mutation operation, a random position is selected and the workstation assignment for that process is changed. For example, if the selected sequence number is 3, this means that process 4 is assigned to workstation 3. Assuming that process 4 can also be assigned to workstation 2, the mutation method is to adjust the workstation assignment of process 4 from 3 to 2. Through this mutation operation, the new mutant chromosome is m1 = [2,2,2,2,3,5,6,7,8].

[0117] In this embodiment, the encoding of an individual is represented by {a1, a2, ..., a M}, M represents the serial number of the workstation, a M Represents the set of processes assigned to a workstation, represented by a tensor.

[0118] In this embodiment, judging whether the intersection is reasonable based on the connectivity of the hanging system and the workstation information includes:

[0119] Determine whether the workstation where the previous process and the workstation where the subsequent process of each process assigned to the workstation are connected to the workstation, and whether each workstation can process the assigned process. If so, the offspring individual is reasonable, otherwise it is unreasonable.

[0120] In this embodiment, the optimal solution is represented by the individual with the smallest rank. If the ranks of two individuals are the same, the individual with the greater congestion degree is the optimal solution.

[0121] In summary, the present invention optimizes process allocation and reduces the total distance the hanging system travels between workstations, directly reducing the time cost of material transportation and speeding up the production process. At the same time, it balances the average processing time differences between workstations, avoiding situations where some workstations are idle for long periods of time or are overly busy, thereby improving overall production efficiency. Reducing the travel distance of the hanging system means reducing energy consumption and equipment wear, which helps reduce maintenance costs and energy consumption in the long term. Furthermore, by optimizing process allocation, production stoppages caused by waiting or congestion are reduced, further reducing production costs. This solution takes into account the actual environment of the production workshop and the connectivity of the hanging system, making process allocation more flexible and adaptable. When production demand or workshop layout changes, the optimal process allocation solution can be regenerated by adjusting the parameters in the optimization model, ensuring the continued efficiency of the production process. This solution introduces an intelligent algorithm to optimize process allocation, providing strong support for intelligent management of clothing manufacturers. Through data-driven and algorithmic optimization, companies can more accurately grasp production status and achieve real-time monitoring and dynamic adjustment of the production process.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for allocating garment production processes considering hanging connectivity constraints, characterized in that: include: S1: Obtain the workstation information of the production workshop, the process information of the workpiece to be processed, and the connectivity information of the hanging system between the workstations; S2: Using the connectivity information of the hanging system between workstations as a constraint condition to establish the workstation distance matrix of the production workshop; The establishment of the workstation distance matrix of the production workshop includes: transporting work-in-progress between different workstations through a hanging system, and constructing the workstation distance matrix based on the movement distance between different workstations of the hanging system, wherein the distance between two workstations that cannot be connected to each other is represented as -1; S3: Generate the population of the NSGA-II algorithm using the greedy rule according to the workstation distance matrix, the workstation information of the production workshop, and the process information of the workpiece to be processed; The step S3 comprises: S31: Initialize the population size to N; S32: for each first process of the workpiece to be processed that has no preceding process, randomly select a workstation from its set of assignable workstations as its assigned workstation; S33: Using the front-end and back-end relationships between processes as constraints, traverse all processes and use the greedy rule based on the workstation distance matrix to select the workstation closest to the front-end workstation as the assigned workstation for the back-end process; until all processes are assigned to the assigned workstations, individuals in the NSGA-II algorithm population are generated; S34: Repeat steps S32-S34 until the number of individuals reaches N, and obtain the population of the NSGA-II algorithm; S4: Construct a multi-objective optimization model by taking the minimum total travel distance of the hanging system and the minimum average difference in total processing time between all activated workstations as the optimization objectives; The multi-objective optimization model includes: in, and Represents two optimization objectives, Represents the set of processes for the workpiece to be processed, and Indicates two different processes, and the process It is a process The subsequent process; and Indicates two different workstations; Represents a binary variable, when the process Arranged in Simultaneous process Arranged in hour Equal to 1, otherwise =0; Indicates the workstation in the workstation distance matrix With workstation the distance between them; Indicates the total number of all activated workstations; Indicates workstation Total processing hours, Indicates the average processing time of all activated workstations; S5: Based on the population generated in step S3, the NSGA-II algorithm is used to solve the multi-objective optimization and obtain the optimal clothing production process allocation plan.

2. A method for allocating garment production processes considering hanging connectivity constraints according to claim 1, characterized in that: The step S5 comprises: S51: Perform non-dominated sorting on the population of the NSGA-II algorithm to obtain the rank of each individual in the population; S52: traverse each optimization objective in the multi-objective optimization model, calculate the crowding degree of each individual in the population under the optimization objective, and sum up the crowding degree of each individual under all optimization objectives to obtain the final crowding degree of each individual in the population; S53: Select from the population using an elite retention strategy based on the individual's rank and the individual's final crowding degree Individuals are retained as elite individuals, and the parent individuals are selected from the population using the tournament selection strategy to generate the parent population; S54: using a simulated binary crossover and / or mutation algorithm on the parent population to generate a child population, and merging the parent population and the child population to form a temporary population; S55: Filter from the temporary population according to the preset probability model Individuals, , N represents the size of the population; S56: The individuals screened out in step S55 and the retained elite individuals are combined to form the population for the next iteration, and steps S51-S56 are repeated until the preset number of iterations is reached, and the optimal solution is output.

3. The method for allocating garment production processes considering hanging connectivity constraints according to claim 2, characterized in that: The non-dominated sorting of the population of the NSGA-II algorithm includes: S511: For each individual in the population , initialize the collection and counter ; S512: For each individual in the population , traverse other individuals q in the population, if individual p dominates individual q, then add individual q to the set If individual p is dominated by individual q, then Add 1; S513: Traverse the individuals in the population, if there is an individual Counter When is 0, the individual Put it into the non-dominated frontier set , and the individual Level Set to 0; S514: For each non-dominated frontier set , traverse the non-dominated frontier set Each individual in , for individuals Collection Each individual in ,Will Counter Subtract 1 if Reduced to 0, the level of individual 𝑞 Set it as i+1, and set individual Add to the next non-dominated front set ; S515: When the non-dominated frontier set is empty, the sorting process ends and the rank of each individual in the population is obtained. .

4. The method for allocating garment production processes considering hanging connectivity constraints according to claim 3, characterized in that: The elite retention strategy is used to select Individuals considered as elite individuals include: S5211: Calculate the number of elite individuals retained when the population size is N , Belong to the interval real number; S5212: From the first non-dominated frontier set At the beginning, individuals are selected from the non-dominated frontier set as elite individuals in turn until the predetermined number of elite individuals is reached. ; The selection strategy is as follows: First, select the non-dominated frontier set All individuals in The number of individuals is less than , then continue from the non-dominated frontier set Select from, and so on; if the number of elite individuals selected reaches Or if all non-dominated frontier sets have been traversed, the selection is stopped; if in a non-dominated frontier set It is necessary to select some individuals as elite individuals, then according to the set The final crowding degree of individuals in the pool is selected from high to low.

5. The method for allocating garment production processes considering hanging connectivity constraints according to claim 2, characterized in that: The crowding degree of each individual under the optimization objective includes: in, represents the optimization objective; Represents an individual In the optimization goal The degree of congestion under Represents an individual In the optimization goal The value below; Represents an individual In the optimization goal The value below; Indicates that all individuals are optimizing the target The maximum value under Indicates that all individuals are optimizing the target The minimum value under .

6. The method for allocating garment production processes considering hanging connectivity constraints according to claim 2, characterized in that: The method of selecting parent individuals from a population using a tournament selection strategy to generate a parent population includes: S5221: Randomly select from the current population Individuals form a tournament group; S5222: In a tournament population, the best individual is selected as the parent individual by comparing the individual's rank and final crowding degree. The selection strategy is as follows: For individuals and , if the individual Level Smaller than an individual Level , then select individual If the individual Level Larger than an individual Level , then select individual If the individual Level Equal to individual Level , then select individual and individuals The individual with the highest final crowding degree is and individuals The final congestion degree is also the same, then from the individual and individuals Randomly select an individual as the parent individual; S5223: Repeat steps S5221 to S5223 until the number of parent individuals reaches a set threshold to generate a parent population.

7. The method for allocating garment production processes considering hanging connectivity constraints according to claim 2, characterized in that: The method of generating a child population by using a simulated binary crossover and / or mutation algorithm on a parent population includes: Simulating binary crossover selection includes: randomly selecting two parent individuals from the parent population, randomly selecting some genes from the two parent individuals to exchange, and generating two offspring individuals; The mutation algorithm selection includes: randomly selecting a parent individual from the parent population, changing the workstation assigned to a randomly selected process from the parent to generate a child individual; Based on the connectivity of the hanging system and the workstation information, the generated offspring individuals are judged to be reasonable. If not, the unreasonable offspring individuals are discarded. A preset number of offspring populations are generated based on the simulated binary crossover and / or mutation algorithm.

Images