CN113657647A - An order distribution method used in the textile and garment industry Internet - Google Patents
An order distribution method used in the textile and garment industry Internet Download PDFInfo
- Publication number
- CN113657647A CN113657647A CN202110807678.0A CN202110807678A CN113657647A CN 113657647 A CN113657647 A CN 113657647A CN 202110807678 A CN202110807678 A CN 202110807678A CN 113657647 A CN113657647 A CN 113657647A
- Authority
- CN
- China
- Prior art keywords
- order
- chromosomes
- order distribution
- chromosome
- production
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000009826 distribution Methods 0.000 title abstract description 56
- 239000004753 textile Substances 0.000 title abstract description 25
- 238000000034 method Methods 0.000 title abstract description 22
- 238000004519 manufacturing process Methods 0.000 abstract description 52
- 230000002068 genetic effect Effects 0.000 abstract description 22
- 238000005457 optimization Methods 0.000 abstract description 15
- 230000000694 effects Effects 0.000 abstract description 2
- 210000000349 chromosome Anatomy 0.000 description 72
- 230000035772 mutation Effects 0.000 description 18
- 108090000623 proteins and genes Proteins 0.000 description 16
- 230000011218 segmentation Effects 0.000 description 14
- 238000010187 selection method Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 230000009466 transformation Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physiology (AREA)
- Evolutionary Computation (AREA)
- Manufacturing & Machinery (AREA)
- Biodiversity & Conservation Biology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Factory Administration (AREA)
Abstract
本发明涉及用于纺织服装工业互联网中的订单分配方法，步骤S1，m个订单；将订单进行拆解，每个订单中的服装能拆分的基本单元为若干种产品，每种产品的数量为m个；步骤S2，在纺织服装工业互联网平台中存在n个工厂，其中，n选自大于等于1的整数，每个工厂对不同种的产品的生产均有不同的生产参数；针对工厂的生产参数及订单分配的优化目标，确定模型的约束条件及目标函数；步骤S3，将m个订单通过设定的遗传算法分配给n个工厂。本发明提供了一种用于纺织服装工业互联网中的订单分配方法；通过启发式遗传算法解决工业互联网中的订单分配问题，实现提高平台制造效率以及产品准时交货率、提升客户满意度的效果。
The invention relates to an order distribution method used in the textile and garment industrial Internet. In step S1, m orders are placed; the orders are disassembled, and the basic units of clothing that can be disassembled in each order are several products, and the quantity of each product is is m; in step S2, there are n factories in the textile and garment industry Internet platform, where n is selected from an integer greater than or equal to 1, and each factory has different production parameters for the production of different kinds of products; The optimization objectives of production parameters and order allocation are determined, and the constraints and objective functions of the model are determined; in step S3, m orders are allocated to n factories through the set genetic algorithm. The invention provides an order distribution method used in the textile and garment industrial Internet; the problem of order distribution in the industrial Internet is solved through a heuristic genetic algorithm, so as to achieve the effects of improving platform manufacturing efficiency, product on-time delivery rate, and improving customer satisfaction .
Description
Technical Field
The invention relates to the technical field of textile industry Internet in the technical field of resource scheduling, in particular to an order allocation method taking a textile and clothing industry Internet platform as a background, and provides a basis for making a reasonable manufacturing resource scheduling plan for the platform.
Background
With the continuous deepening of a new technological revolution and industrial change, the digital technology is utilized to carry out all-around, all-angle and all-chain transformation on the traditional manufacturing enterprises, the deepened digital transformation of the manufacturing industry is a key measure for promoting the manufacturing industry to be greatly strengthened and transformed and upgraded in China, and new vitality can be injected into the enterprise development. Under the digital background, the textile and clothing industry also faces significant organization change, the optimization of organization structure, the improvement of operation efficiency and benefit are the key points of digital transformation in the textile and clothing industry. The industrial internet is used as a foundation for digital transformation, and a plurality of factories which are upstream and downstream of an enterprise and have various equal production capacities are integrated in a platform to carry out real-time connection and intelligent interaction.
Production and manufacturing are an important part of the supply chain, and the task of allocating production orders to factories in a platform according to various indexes is particularly important. The reasonable degree of order arrangement directly influences the resource utilization rate of the platform, and simultaneously determines the economic benefit and the market share of the platform to a certain degree. In the textile and clothing industry internet platform, a customer provides an order, the platform is responsible for organizing factories to process and produce the order, and a plurality of factories of different types complete the raw material processing of each sub-order. The order distribution is completed by a platform, and at present, the production requirements of a large number of garment orders of the platform are difficult to meet mainly by a manual mode. In the face of the arrival of a large number of orders, how to arrange the reasonable distribution of the orders among different factories enables the platform to complete production on time and realize the maximization of profits, and is a big problem and challenge faced by the Internet platform of the textile and clothing industry at present.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides an order distribution method for the Internet in the textile and clothing industry; the problem of order allocation in the industrial Internet is solved through a heuristic algorithm, and the effects of improving the platform manufacturing efficiency and the on-time delivery rate of products and improving the customer satisfaction degree are achieved.
In order to achieve the purpose, the invention adopts the technical scheme that: an order distribution method used in the textile and clothing industry internet comprises the following steps;
step S1, m orders, wherein m is selected from integers which are more than or equal to 1; disassembling the orders, wherein basic units of the clothing in each order, which can be disassembled, are a plurality of products, and the number of each product is m;
step S2, there are n factories in the textile and clothing industry Internet platform, wherein n is selected from integers of 1 or more, each factory has different production parameters for the production of different products, and the production parameters include one or more of quotation, fixed cost, maximum production and delivery delay rate; aiming at the production parameters of a factory and the optimization goal of order distribution; determining the constraint condition or/and the objective function of the model;
in step S3, m orders are assigned to n factories by a set genetic algorithm.
Specifically, from the perspective of processing habits, the detachable basic units of the garment should be a jacket and trousers. Therefore, the production task of the split order mainly comprises two products, namely m pieces of upper clothes and m pieces of lower clothes.
Specifically, the constraints of the model are the principles that include order allocation, which enables orders to be delivered on schedule and balances plant load within the platform to achieve relatively optimal order allocation goals.
In a preferred embodiment of the present invention, in step S2, an optimization objective is selected according to actual order production requirements, a fitness function is set through the objective function according to production parameters of a plant and characteristics of a genetic algorithm, individual fitness is calculated, population iteration is performed through one or more of selection operation, crossover operation, and mutation operation in the genetic algorithm, and when a termination condition is satisfied, the selected optimal order allocation scheme is output.
In a preferred embodiment of the present invention, the genetic algorithm is configured to include the steps of;
step a, n factories and m orders are arranged in a known platform, and each order comprises a plurality of products; each gene position corresponds to n-1 dividing points from 0 to m, the order is divided into n intervals, the number of the product orders obtained by each factory is obtained after decoding, and the length of the order distribution chromosome is 2 (n-1);
b, determining a fitness function, wherein the fitness function is used for evaluating whether the order distribution chromosome code is inherited into an evaluation function of the next generation, and the fitness function is a basis for executing the eligibility and the rejection of a genetic algorithm; the order dividing point coding chromosome in the order distribution chromosome with high fitness is preferentially inherited to the next generation; establishing an order optimization model through an objective function or/and a fitness function in combination with variables;
c, iteration of the population is performed through selection operation, cross operation and mutation operation in the genetic algorithm in sequence, and the selected optimal order distribution scheme is output after the termination condition is met;
step d, terminating conditions; step d, terminating conditions; and when the actual iteration times of the algorithm are more than or equal to the preset maximum iteration times, stopping the algorithm, and obtaining an optimal solution, namely a relatively optimal order distribution scheme required by the textile garment industry Internet platform in the multiple order distribution schemes.
In a preferred embodiment of the present invention, in step a, dpiDenotes the ith tangent point position, i is 1,2, n-1, then dp is [ dp ]1，dp2，...，dpi，...，dpn-1]An order cut point code chromosome representing an order allocation chromosome; decoding the chromosome to obtain corresponding each order dividing point in the order distribution chromosomeFactory order quantity [ dp ]1，dp2-dp1，...，dpi-dpi-1，...，m-dpn-1]。
In a preferred embodiment of the present invention, in step b, an order optimization model is established using variables;
comprises parameters or/and related parameters, wherein the parameters comprise i, j and yi、xij、aijOne or more of; the relevant parameters include pij、fi、bij、dij、ALi、AUiOne or more of;
i is a factory serial number, i is taken from a natural number not greater than n; n at this time is the total number of plants;
j is order number, and j is taken from a natural number not greater than m; m at this time is the number of orders;
yiis a variable of 0-1, when the platform selection factory i is responsible for the production of the order, y i1 is ═ 1; otherwise, yi＝0；
xijIs a variable of 0 to 1, x when factory i produces order j ij1 is ═ 1; otherwise, xij＝0；
aijIs the task volume of factory i production order j;
a correlation parameter;
pijis the unit production quote for order j for plant i;
fiis the total fixed cost of production for plant i;
bijis the capacity, i.e., maximum production, of plant i production order j;
dijis the delivery delay rate of plant i for order j;
ALiis the lowest order number acceptable for candidate plant i;
AUiis the highest order quantity acceptable for candidate plant i;
or/and, taking the minimum cost as the optimization target, namely, minimizing the sum of the fixed cost of the factory and the product cost in the production process to obtain the objective function
The fitness function is as follows
Wherein f represents an objective function value of the individual; fmaxThe maximum objective function value that has occurred in the evolution process so far; namely, chromosomes with high fitness are preferentially inherited to the next generation;
or/and setting constraint conditions in the establishment of the order optimization model on the basis of the objective function, wherein the constraint conditions comprise bij、dij、ALi、AUiOne or more of (a).
In a preferred embodiment of the present invention, the crossover in the crossover operation is the most important operator in the genetic algorithm for disseminating the order cut point in the order allocation chromosome encoding the excellent order cut point gene or order cut point gene fragment in the order cut point chromosome; the crossover operator selects any combination point for each group of two order distribution chromosomes participating in crossover operation according to the crossover probability, and in order to ensure that the number of the orders distributed by each factory is not negative, namely to prevent generation of unqualified order distribution chromosome order cut-off point coding chromosomes, the combination point of each group of two order distribution chromosomes participating in crossover operation in the crossover process keeps that the numerical value of the order cut-off point gene positioned at the front position is smaller than the numerical value of the order cut-off point gene positioned at the back position; the order segmentation point code chromosomes in the order distribution chromosomes after the combination point are at least partially interchanged to generate two new order distribution chromosomes.
In a preferred embodiment of the present invention, the mutation in the mutation operation is an order cut point code chromosome that is applied individually to each order allocation chromosome after the crossover operation, helping to extend the search process to the entire solution space; the mutation operation randomly transforms each order cut point gene in order cut point code chromosomes of order distribution chromosomes with a small mutation probability; randomly assigning values according to a method for assigning values to order dividing point code chromosomes of order distribution chromosomes again in initialization during mutation to generate new order dividing point code chromosomes of order distribution chromosomes; the mutation operation adopts substitution mutation, namely, an order segmentation point gene position on an order segmentation point coding chromosome of an order distribution chromosome is randomly selected, and then a nonnegative integer which is not more than the maximum production capacity of a corresponding factory after cross point decoding is randomly generated to replace the original order segmentation point gene on the position.
In a preferred embodiment of the present invention, the selection operation determines which order segmentation point code chromosomes of the order distribution chromosomes are selected by the selection operator to perform an alternating calculation of order segmentation point code chromosomes of a new order distribution chromosome in the next generation population; the selection operator can employ one or more of a roulette selection method, a random traversal sampling method, and a tournament selection method.
In a preferred embodiment of the invention, the roulette selection method accelerates the convergence of the algorithm by selecting a greater probability with a smaller offset; a roulette selection method is adopted; defining the number of times of alternation as a population scale, wherein the population scale is z, and in the roulette selection method, in order to prevent the genetic algorithm from falling into the local optimal solution, the value of z is an integer of 100-200, and then the probability that the order distribution chromosome c is selected is
Among them, FitnesscAnd allocating fitness function values of the chromosomes c to the orders, wherein the population size z is the total number of the population.
In a preferred embodiment of the invention, the order distribution system is used in the textile and clothing industry internet, and the computer is provided with an order distribution model established by an order distribution method used in the textile and clothing industry internet.
The invention solves the defects existing in the background technology, and has the beneficial effects that:
the invention provides a genetic algorithm based on order allocation, which is used for modeling the manufacturing capacity of all enterprises entering a platform, formulating a reasonable objective function by analyzing parameters and constraints of an Internet platform in the textile and clothing industry and finally providing an order allocation scheme with actual production and relatively optimal comprehensive performance.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a graph of the number of orders taken per factory after decoding in a preferred embodiment of the present invention.
FIG. 2 is an example of order assignment chromosome coding in a preferred embodiment of the present invention;
fig. 3 is a flow chart of an order allocation method using genetic algorithm for textile and clothing industry internet in the preferred embodiment of the invention.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings and examples, which are simplified schematic drawings and illustrate only the basic structure of the invention in a schematic manner, and thus show only the constituents relevant to the invention.
It should be noted that, if directional indications (such as up, down, bottom, top, etc.) are involved in the embodiment of the present invention, the directional indications are only used for explaining the relative position relationship, motion situation, etc. of each component in a certain posture, and if the certain posture is changed, the directional indications are changed accordingly. The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Unless expressly stated or limited otherwise, the terms "disposed," "connected," and "connected" are intended to be inclusive and mean, for example, that there may be a fixed connection, a removable connection, or an integral connection; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example one
As shown in fig. 3, an order distribution method for use in the textile garment industry internet comprises the steps of;
step S1, m orders, wherein m is selected from integers which are more than or equal to 1; and (3) disassembling the orders, wherein the basic unit capable of disassembling the clothes in each order is a plurality of products, and the number of each product is m.
Specifically, from the perspective of processing habits, the detachable basic unit of the garment should be an upper garment and a lower garment. Therefore, the production task of the split order mainly comprises two products, namely m pieces of upper clothes and m pieces of lower clothes.
Step S2, there are n factories in the textile and clothing industry Internet platform, wherein n is selected from integers of 1 or more, each factory has different production parameters for the production of different products, and the production parameters include one or more of quotation, fixed cost, maximum production and delivery delay rate; and determining the constraint conditions and the objective function of the model according to the production parameters of the factory and the optimization target of order distribution.
In step S3, m orders are assigned to n factories by a set genetic algorithm. Specifically, the principle of order allocation is to enable orders to be delivered on schedule and to equalize the factory load within the platform to achieve relatively optimal order allocation goals.
Further, in step S2, selecting an optimization target according to the actual order production requirement, setting a fitness function according to the production parameters of the plant and the characteristics of the genetic algorithm through the target function, and calculating the individual fitness; in step S3, iteration of the population is performed through one or more of selection operation, crossover operation, and mutation operation in the genetic algorithm, and when a termination condition is satisfied, the selected optimal order allocation plan is output. Specifically, the optimization objective includes minimizing order costs. Populations refer to sets of chromosomes, and the sets of chromosomes are updated at different stages or steps of the genetic algorithm, i.e., after different numbers of iterations in the genetic algorithm.
Further, setting the genetic algorithm includes the following steps;
step a, n factories and m orders are arranged in a known platform, and each order comprises a plurality of products; each gene position corresponds to n-1 cut points from 0 to m, the order is divided into n intervals, the number of the product orders obtained by each factory is obtained after decoding, and the length of the order distribution chromosome is 2 (n-1).
dpiDenotes the ith tangent point position, i is 1,2, n-1, then dp is [ dp ]1，dp2，...，dpi，...，dpn-1]Representing an order cut point decoding chromosome; the order dividing point decodes the chromosome to obtain the corresponding order quantity [ dp ] of each factory1，dp2-dp1，...，dpi-dpi-1，...，m-dpn-1]。
For example, in a particular embodiment, when m orders are 200, the orders are divided into tops and bottoms. The upper loading cut-out points 35, 77, 144 in fig. 2. The lower garment of fig. 2 has cut points 3, 54, 172. Each group of top loading dividing points and bottom loading dividing points form order dividing points of a factory. Decoding the coding example of the segmentation point chromosome in the figure 2 to form a decoding example of the segmentation point chromosome in the figure 1, and obtaining the number of orders corresponding to different factory allocations; namely the upper assembly of points 35, 42, 67, 56 of fig. 1. The lower garment of fig. 1 has cut points 3, 51, 118, 28. The single upper binding order number and the single lower binding order number form the whole order information of a factory.
B, determining a fitness function, wherein the fitness function is used for evaluating whether the order dividing point coding chromosome of the order distribution chromosome is inherited into an evaluation function of the next generation, and the fitness function is a basis for executing the eligibility and the rejection of a genetic algorithm; the order dividing point coding chromosome of the order distribution chromosome with high fitness is preferentially inherited to the next generation; and establishing an order optimization model by combining an objective function or/and a fitness function with variables.
Establishing an order optimization model by using variables; comprises parameters or/and related parameters, wherein the parameters comprise i, j and yi、xij、aijOne or more of; the relevant parameters include pij、fi、bij、dij、ALi、AUiOne or more of;
i is a factory serial number, i is taken from a natural number not greater than n; n at this time is the total number of plants;
j is order number, and j is taken from a natural number not greater than m; m at this time is the number of orders;
yiis a variable of 0-1, when the platform selection factory i is responsible for the production of the order, y i1 is ═ 1; otherwise, yi＝0；
xijIs a variable of 0 to 1, x when factory i produces order j ij1 is ═ 1; otherwise, xij＝0；
aijIs the task volume of factory i production order j;
a correlation parameter;
pijis the unit production quote for order j for plant i;
fiis the total fixed cost of production for plant i;
bijis the capacity, i.e., maximum production, of plant i production order j;
dijis the delivery delay rate of plant i for order j;
ALiis the lowest order number acceptable for candidate plant i;
AUiis the highest order quantity acceptable by the candidate factory i.
The minimum cost is taken as an optimization target, namely the sum of the fixed cost of a factory and the product cost in the production process is minimized to obtain an objective function
Fitness function
Wherein f represents an objective function value of the individual; fmaxThe maximum objective function value that has occurred in the evolution process so far; i.e. chromosome preference with high fitnessAnd is inherited to the next generation.
Further, on the basis of the objective function, setting a constraint condition in the establishment of the order optimization model, wherein the constraint condition comprises bij、dij、ALi、AUiOne or more of (a). Further, in this embodiment, the constraint condition is; condition a1, formula bij≥aij(ii) a I.e., to ensure that the plant capacity load is met, the plant is able to limit within a stage (maximum capacity ≧ production supply) for each product. Condition b1, formula aij≥0，y i0 or 1, xij0 or 1; the value ranges of the decision variables are shown to be non-negative constraint of the yield and 0-1 variable constraint respectively. Condition c1, formula aij∈[ALi，AUi](ii) a I.e. to ensure that the number of orders assigned to plant i is within its acceptable range. Condition d1, equation
That is, a certain proportion of products are guaranteed to be delivered on time (the delivery rate on time is not less than 90%).
And c, sequentially carrying out selection operation, cross operation and mutation operation in the genetic algorithm to iterate the population, and outputting the selected optimal order distribution scheme after the termination condition is met.
The crossover in the crossover operation is the most important operator in the genetic algorithm and is used for disseminating the order cut point genes or order cut point gene segments which are excellent in the order cut point coding chromosome of the order distribution chromosome; the crossover operator selects any combination point for the order cut point code chromosomes of the two order distribution chromosomes of each group participating in the crossover operation according to the crossover probability, and in order to ensure that the number of the orders distributed by each factory is not negative, namely, the order cut point code chromosomes of the unqualified order distribution chromosomes are prevented from being generated, the combination point of the order cut point code chromosomes of the two order distribution chromosomes of each group participating in the crossover operation in the population keeps that the numerical value of the order cut point gene positioned at the front position is smaller than the numerical value of the order cut point gene positioned at the back position in the crossover process; the order segmentation point code chromosomes of the order distribution chromosomes after the combination point are at least partially interchanged to generate order segmentation point code chromosomes of two new order distribution chromosomes.
The mutation in the mutation operation is an order cut point code chromosome that is individually applied to each order allocation chromosome after the crossover operation, contributing to the expansion of the search process to the entire solution space; the mutation operation randomly transforms each order cut point gene in order cut point code chromosomes of order distribution chromosomes with a small mutation probability; randomly assigning values according to an assignment method of re-assigning the order distribution chromosomes in the initialization during mutation to generate order segmentation point coding chromosomes of new order distribution chromosomes; the mutation operation adopts substitution mutation, namely, an order segmentation point gene position on an order segmentation point coding chromosome of an order distribution chromosome is randomly selected, and then a nonnegative integer which is not more than the maximum production capacity of a corresponding factory after cross point decoding is randomly generated to replace the original order segmentation point gene on the position.
The selection operation can decide which order dividing point code chromosomes of the order distribution chromosomes are selected through a selection operator to carry out the alternation calculation of new order distribution chromosomes in the next generation of population; the selection operator can employ one or more of a roulette selection method, a random traversal sampling method, and a tournament selection method. The embodiment adopts a roulette selection method, and the smaller the offset in the roulette selection method, the higher the probability of selection, and the convergence of the algorithm can be accelerated; adopting a roulette selection method; defining the number of times of alternation as a population scale, wherein the population scale is z, and in the roulette selection method, in order to prevent the genetic algorithm from falling into the local optimal solution, the value of z is an integer of 100-200, and then the probability that the order distribution chromosome c is selected is
Among them, FitnesscAnd allocating fitness function values of the chromosomes c to the orders, wherein the population size z is the total number of the population.
Step d, terminating conditions; and when the actual iteration times of the algorithm are more than or equal to the preset maximum iteration times, stopping the algorithm, and obtaining an optimal solution, namely a relatively optimal order distribution scheme required by the textile garment industry Internet platform in the multiple order distribution schemes.
Example two
An order distribution system used in the textile and clothing industry internet is provided, and an order distribution model established by the order distribution method used in the textile and clothing industry internet is arranged in a computer.
The working principle is as follows: and modeling the manufacturing capability of all enterprises entering the platform, formulating a reasonable objective function by analyzing parameters and constraints of the Internet platform of the textile and clothing industry, and finally providing an order distribution scheme with relatively optimal comprehensive performance in actual production.
In light of the foregoing description of the preferred embodiment of the present invention, it is to be understood that various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. An order distribution method used in the textile garment industry internet is characterized in that: comprises the following steps;
step S1, m orders, wherein m is selected from integers which are more than or equal to 1; disassembling the orders, wherein basic units of the clothing in each order, which can be disassembled, are a plurality of products, and the number of each product is m;
step S2, there are n factories in the textile and clothing industry Internet platform, wherein n is selected from integers of 1 or more, each factory has different production parameters for the production of different products, and the production parameters include one or more of quotation, fixed cost, maximum production and delivery delay rate; determining a constraint condition or/and an objective function of a model aiming at the production parameters of a factory and the optimization objective of order distribution;
in step S3, m orders are assigned to n factories by a set genetic algorithm.
2. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: in step S2, an optimization objective is selected according to actual order production requirements, a fitness function is set through the objective function according to production parameters of a plant and characteristics of a genetic algorithm, individual fitness is calculated, population iteration is performed through one or more of selection operation, crossover operation, and mutation operation in the genetic algorithm, and when a termination condition is satisfied, a selected optimal order allocation scheme is output.
3. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: the genetic algorithm is set up to include the following steps;
step a, n factories and m orders are arranged in a known platform, and each order comprises a plurality of products; each gene position corresponds to n-1 dividing points from 0 to m, the order is divided into n intervals, the number of the product orders obtained by each factory is obtained after decoding, and the length of the order distribution chromosome is 2 (n-1);
b, determining a fitness function, wherein the fitness function is used for evaluating whether the order distribution chromosome code is inherited into an evaluation function of the next generation, and the fitness function is a basis for executing the eligibility and the rejection of a genetic algorithm; the order dividing point coding chromosome in the order distribution chromosome with high fitness is preferentially inherited to the next generation; establishing an order optimization model through an objective function or/and a fitness function in combination with variables;
c, iteration of the population is performed through selection operation, cross operation and mutation operation in the genetic algorithm in sequence, and the selected optimal order distribution scheme is output after the termination condition is met;
step d, terminating conditions; step d, terminating conditions; and when the actual iteration times of the algorithm are more than or equal to the preset maximum iteration times, stopping the algorithm, and obtaining an optimal solution, namely a relatively optimal order distribution scheme required by the textile garment industry Internet platform in the multiple order distribution schemes.
4. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: in step a, dpiDenotes the ith tangent point position, i is 1,2, n-1, then dp is [ dp ]1，dp2，...，dpi，...，dpn-1]An order cut point code chromosome representing an order allocation chromosome; decoding the chromosome of the order dividing point in the order distribution chromosome to obtain the corresponding order quantity [ dp ] of each factory1，dp2-dp1，...，dpi-dpi-1，...，m-dpn-1]。
5. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: in the step b, establishing an order optimization model by using variables;
comprises parameters or/and related parameters, wherein the parameters comprise i, j and yi、xij、aijOne or more of; the relevant parameters include pij、fi、bij、dij、ALi、AUiOne or more of;
i is a factory serial number, i is taken from a natural number not greater than n; n at this time is the total number of plants;
j is order number, and j is taken from a natural number not greater than m; m at this time is the number of orders;
yiis a variable of 0-1, when the platform selection factory i is responsible for the production of the order, yi1 is ═ 1; otherwise, yi＝0；
xijIs a variable of 0 to 1, x when factory i produces order jij1 is ═ 1; otherwise, xij＝0；
aijIs the task volume of factory i production order j;
a correlation parameter;
pijis the unit production quote for order j for plant i;
fiis the total fixed cost of production for plant i;
bijis the capacity, i.e., maximum production, of plant i production order j;
dijis the delivery delay rate of plant i for order j;
ALiis the lowest order number acceptable for candidate plant i;
AUiis the highest order quantity acceptable for candidate plant i;
or/and, taking the minimum cost as the optimization target, namely, minimizing the sum of the fixed cost of the factory and the product cost in the production process to obtain the objective function
Fitness function
Wherein f represents an objective function value of the individual; fmaxThe maximum objective function value that has occurred in the evolution process so far; namely, chromosomes with high fitness are preferentially inherited to the next generation;
or/and setting constraint conditions in the establishment of the order optimization model on the basis of the objective function, wherein the constraint conditions comprise bij、dij、ALi、AUiOne or more of (a).
6. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: the crossover in the crossover operation is the most important operator in the genetic algorithm and is used for disseminating order cut point genes or order cut point gene segments which are excellent in order cut point coding chromosomes in order distribution chromosomes; the crossover operator selects any combination point for each group of two order distribution chromosomes participating in crossover operation according to the crossover probability, and in order to ensure that the number of the orders distributed by each factory is not negative, namely to prevent generation of unqualified order distribution chromosome order cut-off point coding chromosomes, the combination point of each group of two order distribution chromosomes participating in crossover operation in the crossover process keeps that the numerical value of the order cut-off point gene positioned at the front position is smaller than the numerical value of the order cut-off point gene positioned at the back position; the order segmentation point code chromosomes in the order distribution chromosomes after the combination point are at least partially interchanged to generate two new order distribution chromosomes.
7. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: the mutation in the mutation operation is an order cut point code chromosome that is individually applied to each order allocation chromosome after the crossover operation, contributing to the expansion of the search process to the entire solution space; the mutation operation randomly transforms each order cut point gene in order cut point code chromosomes of order distribution chromosomes with a small mutation probability; randomly assigning values according to a method for assigning values to order dividing point code chromosomes of order distribution chromosomes again in initialization during mutation to generate new order dividing point code chromosomes of order distribution chromosomes; the mutation operation adopts substitution mutation, namely, an order segmentation point gene position on an order segmentation point coding chromosome of an order distribution chromosome is randomly selected, and then a nonnegative integer which is not more than the maximum production capacity of a corresponding factory after cross point decoding is randomly generated to replace the original order segmentation point gene on the position.
8. An order distribution method in the textile garment industry internet as claimed in claim 1, characterized in that: the selection operation determines which order dividing point code chromosomes of the order distribution chromosomes are selected through a selection operator to carry out the alternating calculation of the order dividing point code chromosomes of the new order distribution chromosomes in the next generation of population; the selection operator can employ one or more of a roulette selection method, a random traversal sampling method, and a tournament selection method.
9. The method of claim 8An order distribution method used in the textile garment industry internet is characterized in that: the roulette selection method has the advantages that the smaller the offset, the higher the probability of selection, and the convergence of the algorithm can be accelerated; adopting a roulette selection method; defining the number of times of alternation as a population scale, wherein the population scale is z, and in the roulette selection method, in order to prevent the genetic algorithm from falling into the local optimal solution, the value of z is an integer of 100-200, and then the probability that the order distribution chromosome c is selected is
Among them, FitnesscAnd allocating fitness function values of the chromosomes c to the orders, wherein the population size z is the total number of the population.
10. An order distribution system for use in the textile garment industry internet, characterized by: the computer is provided with an order distribution model established by the order distribution method for the textile and clothing industry internet as claimed in any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110807678.0A CN113657647B (en) | 2021-07-16 | 2021-07-16 | Order distribution method for textile and clothing industry Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110807678.0A CN113657647B (en) | 2021-07-16 | 2021-07-16 | Order distribution method for textile and clothing industry Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657647A true CN113657647A (en) | 2021-11-16 |
| CN113657647B CN113657647B (en) | 2023-10-10 |
Family
ID=78489563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110807678.0A Active CN113657647B (en) | 2021-07-16 | 2021-07-16 | Order distribution method for textile and clothing industry Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657647B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648221A (en) * | 2022-03-21 | 2022-06-21 | 深圳市库宝软件有限公司 | Order processing method, device, equipment, warehousing system and storage medium |
| CN114862192A (en) * | 2022-05-07 | 2022-08-05 | 北京航空航天大学 | Low-cost production task allocation and resource scheduling method for heterogeneous industrial internet system |
| CN117151431A (en) * | 2023-10-30 | 2023-12-01 | 四川省致链数字科技有限公司 | Automatic distribution method and system for wooden furniture order tasks |
| CN119338213A (en) * | 2024-12-20 | 2025-01-21 | 绍兴柯桥富强植绒水洗有限公司 | A textile order allocation method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000042520A (en) * | 1998-12-26 | 2000-07-15 | 이구택 | Method of distributing orders for many factories in iron manufacturing processes |
| JP2009134399A (en) * | 2007-11-29 | 2009-06-18 | Jfe Steel Corp | Sales production planning method, sales production planning system and computer program |
| CN106779406A (en) * | 2016-12-14 | 2017-05-31 | 重庆川仪自动化股份有限公司 | MES system based on RFID |
| JP2017187979A (en) * | 2016-04-07 | 2017-10-12 | 新日鐵住金株式会社 | Scheduling device, scheduling method, and program |
| CN107292702A (en) * | 2017-05-26 | 2017-10-24 | 青岛海日高科模型有限公司 | A kind of intelligence manufacture method and system |
| CN108898200A (en) * | 2018-07-05 | 2018-11-27 | 汕头市诸事帮科技有限公司 | The singulated system of intelligence, manufacturing schedule management system and its implementation, operating method |
| CN111665808A (en) * | 2020-06-16 | 2020-09-15 | 北京经纬纺机新技术有限公司 | Production scheduling plan optimization method based on genetic algorithm |
| WO2020191735A1 (en) * | 2019-03-28 | 2020-10-01 | 西门子股份公司 | Blockchain-based industrial manufacturing resource sharing method, device and system |
-
2021
- 2021-07-16 CN CN202110807678.0A patent/CN113657647B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000042520A (en) * | 1998-12-26 | 2000-07-15 | 이구택 | Method of distributing orders for many factories in iron manufacturing processes |
| JP2009134399A (en) * | 2007-11-29 | 2009-06-18 | Jfe Steel Corp | Sales production planning method, sales production planning system and computer program |
| JP2017187979A (en) * | 2016-04-07 | 2017-10-12 | 新日鐵住金株式会社 | Scheduling device, scheduling method, and program |
| CN106779406A (en) * | 2016-12-14 | 2017-05-31 | 重庆川仪自动化股份有限公司 | MES system based on RFID |
| CN107292702A (en) * | 2017-05-26 | 2017-10-24 | 青岛海日高科模型有限公司 | A kind of intelligence manufacture method and system |
| CN108898200A (en) * | 2018-07-05 | 2018-11-27 | 汕头市诸事帮科技有限公司 | The singulated system of intelligence, manufacturing schedule management system and its implementation, operating method |
| WO2020191735A1 (en) * | 2019-03-28 | 2020-10-01 | 西门子股份公司 | Blockchain-based industrial manufacturing resource sharing method, device and system |
| CN111665808A (en) * | 2020-06-16 | 2020-09-15 | 北京经纬纺机新技术有限公司 | Production scheduling plan optimization method based on genetic algorithm |
Non-Patent Citations (6)
| Title |
|---|
| 刘昌慧, 徐春丽, 华东平: "纺织企业生产调度问题的研究", 纺织科学研究, no. 04 * |
| 周金宏, 汪定伟: "软计算求解分布式多工厂单件制造业的提前/拖期生产计划问题", 控制理论与应用, no. 02 * |
| 孙鹤旭;李晓婷;花季伟;雷兆明;: "基于改进型遗传算法的热轧生产计划调度系统", 自动化与仪表, no. 01 * |
| 程方启;叶飞帆;杨建国;: "水平型制造协作联盟订单分配多目标优化模型研究", 计算机集成制造系统, no. 12, pages 2317 - 2321 * |
| 郭靖: "基于大规模定制的板式家具", 中国优秀硕士学位论文全文数据库, no. 05 * |
| 马慧民;叶春明;许圣良;张爽;: "基于粒子群算法的分布式多工厂批量计划问题研究", 运筹与管理, no. 03 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114648221A (en) * | 2022-03-21 | 2022-06-21 | 深圳市库宝软件有限公司 | Order processing method, device, equipment, warehousing system and storage medium |
| CN114862192A (en) * | 2022-05-07 | 2022-08-05 | 北京航空航天大学 | Low-cost production task allocation and resource scheduling method for heterogeneous industrial internet system |
| CN117151431A (en) * | 2023-10-30 | 2023-12-01 | 四川省致链数字科技有限公司 | Automatic distribution method and system for wooden furniture order tasks |
| CN117151431B (en) * | 2023-10-30 | 2024-01-26 | 四川省致链数字科技有限公司 | Automatic distribution method and system for wooden furniture order tasks |
| CN119338213A (en) * | 2024-12-20 | 2025-01-21 | 绍兴柯桥富强植绒水洗有限公司 | A textile order allocation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657647B (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113657647A (en) | An order distribution method used in the textile and garment industry Internet | |
| CN109190857B (en) | An Optimization Algorithm Based on Multi-objective Resource Constrained Project Scheduling Model | |
| Gan et al. | Joint optimization of maintenance, buffer, and spare parts for a production system | |
| CN102411306B (en) | Mixed flow assembly production scheduling control method based on bee society self-organization model | |
| CN107146039B (en) | Multi-target cooperative control customized mixed-flow assembly production method and device | |
| JP2003256635A (en) | Support method for manufacture instruction quantity determination and program therefor | |
| CN118627867B (en) | Product formula material management method and system based on artificial intelligence | |
| CN112561225A (en) | Flexible job shop scheduling method based on benchmarking coevolution algorithm | |
| CN112926896A (en) | Production scheduling method for cigarette cut tobacco production | |
| CN115239198A (en) | Work order distribution method, related device, electronic equipment, medium and program product | |
| Chen et al. | A modified adaptive switching-based many-objective evolutionary algorithm for distributed heterogeneous flowshop scheduling with lot-streaming | |
| Tao et al. | Optimization of the seru production system with demand fluctuation: A Mean-CVaR model | |
| Vaghefinezhad et al. | A genetic algorithm approach for solving a flexible job shop scheduling problem | |
| CN114792220A (en) | Multi-information fusion inventory management method based on individual customized furniture of upstream and downstream enterprises | |
| CN119204746A (en) | A method and system for generating production plan of medical auxiliary socks based on artificial intelligence | |
| CN118095739A (en) | A method for optimizing scheduling costs in textile workshops | |
| CN109085804A (en) | It is a kind of for electronic product multiplexing factory manufacture process Optimization Scheduling | |
| CN118586660A (en) | A dynamic scheduling method for heterogeneous parallel machine workshops used in traditional Chinese medicine granulation | |
| Jannat et al. | Optimal solution for multi-objective facility layout problem using genetic algorithm | |
| CN116739362A (en) | Productivity rechecking system based on Internet of things | |
| Ballin et al. | Optimization of sampling strata with the SamplingStrata package | |
| Yildiz et al. | Development of a neural network algorithm for estimating the makespan in jobshop production scheduling | |
| Germanos et al. | An asexual genetic algorithm for the smallholders' demand selection problem | |
| Liu et al. | Items assignment optimization for complex automated picking Systems | |
| Chunxiao et al. | Order Allocation in Industrial Internet Platform for Textile and Clothing. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |