CN116307213A - Automatic cotton distribution method and device based on NSGA-III algorithm - Google Patents
Automatic cotton distribution method and device based on NSGA-III algorithm Download PDFInfo
- Publication number
- CN116307213A CN116307213A CN202310295982.0A CN202310295982A CN116307213A CN 116307213 A CN116307213 A CN 116307213A CN 202310295982 A CN202310295982 A CN 202310295982A CN 116307213 A CN116307213 A CN 116307213A
- Authority
- CN
- China
- Prior art keywords
- cotton
- population
- nsga
- automatic cotton
- automatic
- 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.)
- Pending
Links
- 229920000742 Cotton Polymers 0.000 title claims abstract description 239
- 238000009826 distribution Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000000137 annealing Methods 0.000 claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 37
- 239000002994 raw material Substances 0.000 claims abstract description 34
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 32
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 32
- 230000008569 process Effects 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 91
- 230000002068 genetic effect Effects 0.000 claims description 25
- 238000002156 mixing Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 11
- 239000004753 textile Substances 0.000 abstract description 2
- 241000219146 Gossypium Species 0.000 description 194
- 230000035772 mutation Effects 0.000 description 14
- 238000005457 optimization Methods 0.000 description 7
- 210000000349 chromosome Anatomy 0.000 description 6
- 235000012343 cottonseed oil Nutrition 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000835 fiber Substances 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 108090000623 proteins and genes Proteins 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010020112 Hirsutism Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007614 genetic variation Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000009827 uniform distribution 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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Genetics & Genomics (AREA)
- Finance (AREA)
- Physiology (AREA)
- Accounting & Taxation (AREA)
- Manufacturing & Machinery (AREA)
Abstract
The application discloses an automatic cotton distribution method and device based on NSGA-III algorithm, which relate to the technical field of textile, and comprise the following steps: creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function; according to each function and preset constraint conditions, an automatic cotton distribution model is established; the amount to be optimized of the automatic cotton matching model is the amount of the raw material; optimizing the consumption of each raw material of an automatic cotton distribution model through an NSGA-III algorithm to obtain a cotton distribution scheme; and in the optimizing process of NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individuals of the new parent population after annealing search processing are used as the optimal solution of the automatic cotton distribution model when the cut-off condition is met, so that a cotton distribution scheme is obtained. The method can realize a good high-dimensional target space optimizing effect and obtain a more reasonable cotton distribution scheme.
Description
Technical Field
The application relates to the technical field of textile, in particular to an automatic cotton distribution method based on NSGA-III algorithm; also relates to an automatic cotton distribution device, equipment and a computer readable storage medium based on NSGA-III algorithm.
Background
The traditional manual cotton distribution mode has the problems of low efficiency, difficulty in finding an optimal cotton distribution scheme and the like. With the development of computer and artificial intelligence, automatic cotton distribution by a computer is gradually raised. The traditional combination scheme method and linear programming method are emerging genetic (Genetic Algorithm, GA) algorithm, particle swarm optimization (Particle Swarm Optimization, PSO) algorithm and the like. The conventional algorithm is suitable for optimizing a single multimodal function problem, namely single objective optimization, and the cotton distribution problem has the characteristics of multiple objectives, multimodal values, constraint of multiple conditions and the like, has high solving complexity, and is difficult to achieve a satisfactory cotton distribution effect.
The second-generation Non-dominant ranking genetic algorithm (Non-dominated Sorting Genetic Algorithm II, NSGA-II) can be optimized under the conditions of multiple targets, multiple peaks and multiple constraints, however, the second-generation Non-dominant ranking genetic algorithm selects individuals with the same Non-dominant ranking through crowding degree, when three or more multi-target optimization problems are faced, most individuals in a population are Non-dominant due to larger target space dimension, if a crowding comparison operator is continuously adopted, the convergence and the diversity of the NSGA-II algorithm are poor, the local optimum is easily trapped, and the obtained cotton distribution scheme is poor.
In view of this, how to achieve a good high-dimensional target space optimizing effect and obtain a more reasonable cotton distribution scheme has become a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The purpose of the application is to provide an automatic cotton distribution method based on NSGA-III algorithm, which can realize a good high-dimensional target space optimizing effect and obtain a more reasonable cotton distribution scheme. Another object of the present application is to provide an automatic cotton dispensing device, apparatus and computer readable storage medium based on NSGA-III algorithm, which have the above technical effects.
In order to solve the technical problems, the application provides an automatic cotton distribution method based on NSGA-III algorithm, which comprises the following steps:
creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function;
creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials;
optimizing the consumption of each raw material of the automatic cotton matching model through an NSGA-III algorithm to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
Optionally, the creating the automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the integrated quality index of the finished yarn, the carbon emission function and the preset constraint condition includes:
and under the preset constraint condition, respectively taking the minimum value of the cost function of the mixed cotton, the minimum value of the objective function of the comprehensive quality index of the yarn and the minimum value of the carbon emission function to obtain the automatic cotton distribution model.
Optionally, the preset constraint condition includes:
inventory constraints, mixed cotton total mass constraints, raw material type constraints, raw material mix upper limit constraints, quality and quality index boundary constraints.
Optionally, the obtaining the cotton matching scheme by using the individual after the new parent population is subjected to the annealing search treatment when the cutoff condition is met as the optimal solution of the automatic cotton matching model includes:
and taking the median value of a plurality of optimal solutions as the cotton matching scheme.
Optionally, the optimizing the usage of each raw material of the automatic cotton matching model through NSGA-III algorithm includes:
constructing an initial population, and carrying out GA genetic processing on the initial population through a GA genetic algorithm to generate a offspring population; the individuals in the population comprise a preset number of the raw materials to be optimized;
combining said progeny population with said initial population;
carrying out elite treatment on the combined populations to determine new parent populations;
carrying out annealing search treatment on the new parent population, and carrying out GA genetic treatment on the population subjected to the annealing search treatment when the iteration times do not meet the cut-off condition, so as to generate a new offspring population;
carrying out annealing search treatment on the new offspring population;
repeating the operations of merging the parent population and the offspring population, elite selection and annealing search until the cut-off condition is met.
Optionally, elite processing is performed on the combined population, and determining the new parent population includes:
non-dominant ordering is carried out on individuals in the combined population, and Pareto grades of the individuals are determined;
determining reference points, respectively associating individuals in the combined population to the corresponding reference points, and taking the reference point closest to the individuals as a small lens of the individuals;
and determining a new parent population according to the Pareto grade, the small mirror and a small mirror operator of the individual.
Optionally, performing an annealing search on the population includes:
generating new individuals according to individuals of the current population;
and when the new individual is dominant to the corresponding individual in the current population, accepting the new individual, and replacing the corresponding individual in the current population with the new individual.
In order to solve the technical problem, the application also provides an automatic cotton distribution device based on NSGA-III algorithm, comprising:
the first creation module is used for creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function;
the second creation module is used for creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials;
the optimizing module is used for optimizing the consumption of each raw material of the automatic cotton distribution model through an NSGA-III algorithm to obtain a cotton distribution scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
In order to solve the technical problem, the application also provides an automatic cotton distribution device based on NSGA-III algorithm, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the NSGA-III algorithm-based automatic cotton dispensing method as described in any one of the above when executing the computer program.
To solve the above technical problem, the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program is executed by a processor to implement the steps of the automatic cotton matching method based on NSGA-III algorithm as described in any one of the above.
The automatic cotton distribution method based on NSGA-III algorithm provided by the application comprises the following steps: creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function; creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials; optimizing the consumption of each raw material of the automatic cotton matching model through an NSGA-III algorithm to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
Therefore, the automatic cotton distribution method based on the NSGA-III algorithm comprehensively considers the mixed cotton cost, the mixed cotton quality index, the resultant yarn comprehensive quality index and the carbon emission, and builds a more reasonable automatic cotton distribution model. In addition, the NSGA-III algorithm is adopted for optimizing, and three or more multi-objective optimization problems can be better solved. Meanwhile, the annealing algorithm is introduced on the basis of the NSGA-III algorithm, and the annealing search is carried out on individuals in the population in each evolution process, so that the method has a remarkable high-dimensional target space optimizing effect, and a more reasonable cotton distribution scheme can be obtained.
The automatic cotton distribution device, the equipment and the computer readable storage medium based on the NSGA-III algorithm have the technical effects.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly explain the drawings needed in the prior art and embodiments, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an automatic cotton distribution method based on NSGA-III algorithm according to an embodiment of the present application;
fig. 2 is an automatic cotton distribution block diagram based on NSGA-III algorithm provided in an embodiment of the present application;
fig. 3 is a schematic diagram of an automatic cotton distribution device based on NSGA-III algorithm according to an embodiment of the present application;
fig. 4 is a schematic diagram of an automatic cotton distribution device based on NSGA-III algorithm according to an embodiment of the present application.
Detailed Description
The core of the application is to provide an automatic cotton distribution method based on NSGA-III algorithm, which can realize good high-dimensional target space optimizing effect and obtain a more reasonable cotton distribution scheme. Another core of the present application is to provide an automatic cotton distribution device, an apparatus and a computer readable storage medium based on NSGA-III algorithm, which all have the above technical effects.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Referring to fig. 1, fig. 1 is a flow chart of an automatic cotton distribution method based on NSGA-III algorithm according to an embodiment of the present application, and referring to fig. 1, the method includes:
s101: creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function;
s102: creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials;
the computer cotton blending is used for determining the dosage of various raw cotton in the cotton blending scheme, so that the quality index of the mixed cotton is superior to or close to that of standard cotton, and the cost is lower than or close to that of the standard cotton. The cotton blending is divided into raw cotton blending and chemical fiber cotton blending, and the raw materials used in cotton blending are different. The application describes automatic cotton blending by taking raw cotton blending as an example.
Let the total weight of standard cotton be U, the unit kg, the stock raw cotton type (different batches) quantity be L, the raw cotton stock collection be S= { S i },i∈[1,L],s i For the stock of the ith raw cotton, the number of the key quality indexes of the raw cotton is N, and the quality index set is H= { H j },j∈[1,N],h j Is a certain quality index of raw cotton, such as a micronaire value, maturity, yellowness, average length, short fiber index, specific strength at break, cotton impurities and the like.
The evaluation types of the raw cotton quality index comprise: smaller and more optimal indexes, interval indexes and larger and more optimal indexes. Smaller and more optimal index set is H max Comprising: short fiber index, cotton impurity, etc., the upper limit set of the quality index is B max ={B j,max };B j,max Is the upper limit of the better type index for a certain item. The interval index set is H mid Comprising: the upper interval set of the quality index is B upper ={B j,upper Lower interval set is B lower ={B j,lower };B j,upper For a certain kindUpper interval of term interval index, B j,lower Is the lower interval of a certain interval type index. The larger and more optimal index set is H min Comprising: average length, fracture specific strength, etc., and the lower limit set of the quality index is B min ={B j,min };B j,min Is the lower limit of the better type index for a certain item. The number of the key quality indexes of the yarn is M, and the key quality indexes comprise yarn strength, toughness, breaking elongation, evenness non-uniformity, hairiness, cotton impurities and the like.
In this embodiment, one of the cotton blending objectives is to minimize the sum of the costs of each raw cotton in the cotton blending scheme, thus constructing a cost function for the hybrid cotton:
in the method, in the process of the invention,the price of the ith raw cotton in the mixed cotton can be expressed in the unit of Yuan/kg, u i The unit of the usage amount of the i-th raw cotton in the mixed cotton can be kg.
The second goal of cotton blending is to optimize the comprehensive quality index of the mixed cotton, so that the objective function of each quality index of the mixed cotton is constructed:
wherein f FQ,j An objective function of the j-th quality index of the mixed cotton, q j,ref Is the reference value of the j-th quality index of standard cotton,is the j-th quality index value of the mixed cotton and meets the following requirements
Wherein,,for the duty ratio of the ith raw cotton in the mixed cotton, q ij The j-th quality index value of the i-th raw cotton in the mixed cotton.
Further, constructing an objective function of the comprehensive quality index of the mixed cotton:
wherein lambda is FQ,j Is the weight of the j-th quality index of the mixed cotton and meets the following conditions
Wherein R is jk The gray correlation degree of the jth quality index of the mixed cotton and the kth quality index of the yarn.
The third goal of cotton distribution is to optimize the comprehensive quality index of the yarn, so that the objective function of each quality index of the yarn is constructed:
f YQ,j =|y j,p -y j,ref |;
wherein f YQ,j Is the objective function of the j-th quality index of the yarn, y j,ref Is the reference value, y, of the j-th quality index of the yarn j,p And predicting the j-th quality index of the yarn for the quality prediction model. The prediction of the quality index of the yarn by the quality prediction model may refer to the existing related documents, and will not be described herein.
Further, constructing an objective function of the yarn comprehensive quality index:
wherein lambda is YQ,j The j-th quality index of the yarn can be based on a large number of test data or production numbersDetermined by regression analysis or artificial neural network methods.
The fourth goal of cotton distribution is to minimize the carbon emissions produced by the final yarn. The advantages and disadvantages of the cotton blending scheme can affect the yarn quality, the yarn breaking frequency, the spinning speed and the like, thereby affecting the gas emission, the liquid emission, the solid emission and the like in the spinning process, namely, generating different carbon emissions. Aiming at different cotton distribution schemes, assuming that the conditions of the processing technology, the environment and the like are the same, constructing a carbon emission function:
f 4 =C e (u 1 ,u 2 ,…,u L );
wherein C is e Representing the mapping of carbon emissions to cotton distribution schemes, regression analysis or artificial neural networks may be employed to fit the relationship based on a large number of test or production data.
In some embodiments, the preset constraints may include:
inventory constraint:
the raw cotton usage amount is smaller than the stock amount, namely:
0≤u i ≤s i ,i∈[1,L];
total weight constraint:
the weight of the mixed cotton is consistent with that of the standard cotton, namely:
raw cotton type constraint:
in order to conveniently and rapidly schedule raw cotton in stock, the selected raw cotton types in the cotton distribution scheme are not too much, and then:
2≤Σ{u i >0}≤l,i∈[1,L];
where l is the upper limit of the selected raw cotton species, Σ {. Cndot } represents the total number of raw cotton species satisfying the condition in statistics.
Upper limit constraint of mixing:
and comprehensively considering the conditions of customer customization requirements, cost, inventory and the like, and restraining the upper limit of raw cotton mixed use.
Wherein, c i The number of the used cotton seeds is the number of the i-th raw cotton seeds, and the cotton seeds are rounded upwards when the number of the used cotton seeds is less than the number of the whole cotton seeds, C i,lim Is the upper limit of the use of the ith raw cotton, C max The upper limit of the total package number of raw cotton is used.
Quality index boundary constraint:
the boundary constraint of each quality index in the cotton matching scheme is as follows:
in the formula, h j Is a certain quality index of raw cotton, j is E [1, N ]]。
Furthermore, under the preset constraint condition, respectively taking the minimum value of the cost function of the mixed cotton, the minimum value of the objective function of the comprehensive quality index of the yarn and the minimum value of the carbon emission function, and obtaining the automatic cotton distribution model as follows:
the constraint conditions form a constraint space for solving the optimizing problem, and the computer automatically distributes cotton to be converted into a problem for solving the minimum value of the multi-objective function in the constraint space.
S103: optimizing the consumption of each raw material of the automatic cotton matching model through an NSGA-III algorithm to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
Wherein, in some embodiments, optimizing the usage of each raw material of the automatic cotton matching model through NSGA-III algorithm comprises:
constructing an initial population, and carrying out GA genetic processing on the initial population through a GA genetic algorithm to generate a offspring population; the individuals in the population comprise a preset number of the raw materials to be optimized;
combining said progeny population with said initial population;
carrying out elite treatment on the combined populations to determine new parent populations;
carrying out annealing search treatment on the new parent population, and carrying out GA genetic treatment on the population subjected to the annealing search treatment when the iteration times do not meet the cut-off condition, so as to generate a new offspring population;
carrying out annealing search treatment on the new offspring population;
repeating the operations of merging the parent population and the offspring population, elite selection and annealing search until the cut-off condition is met.
With reference to FIG. 2, the population size is G, and the individuals in the population contain L raw cotton usage amounts u to be optimized 1 ,u 2 ,…,u L . In order to ensure the superiority and diversity of the population and the overall evolutionary capability of the algorithm, G individuals are generated by adopting a heuristic generation and random generation combination mode based on a priori knowledge base, and are subjected to real number coding, so that the feasible solution of the optimizing problem is mapped to the search space of the genetic algorithm from the solution space.
And carrying out GA genetic processing on the generated initial population through a GA genetic algorithm to generate first generation offspring, and combining the parent, namely the initial population, with the first generation offspring.
Wherein, GA genetic treatment mainly comprises:
selection operation, crossover operation and adaptive mutation operation.
The selection operation is used to win or lose the population, so that individuals with higher fitness in the genetic process are easier to select. In order to avoid the damage of the optimal individual in the crossing process, the worst individual in the iteration of the round can be replaced by the optimal individual in the previous iteration, and then probability selection is carried out on the rest individuals. Defining the probability that the ith individual is selected as:
wherein f i Is the fitness of the ith individual. If p i >p rand ,p rand For the random probability generated in the (0, 1) interval, the ith individual is selected.
Crossover operations are the exchange of one or some genes on both chromosomes, which determines the global search capability of the genetic algorithm. According to a certain crossover probability, crossover operation is carried out on the j-th bit of two chromosomes:
wherein a is k,j Is the kth chromosome, a l,j Is the first chromosome;
where ζ is a random number of (0, 1), and σ is a distribution factor.
The new individuals generated after the crossover operation have a certain probability of genetic variation. A mutation operation is a modification of one or more genes on a chromosome, which determines the local search capability of the genetic algorithm. According to a certain mutation probability, the ith chromosome a i,j The mutation operation of the j-th gene of (2) is as follows:
wherein a is max And a min A is respectively a i,j Upper and lower bounds of r i Is [0,1]F (G) =ζ (1-G/G max ) 2 Zeta is [0,1]G is the current algebra of evolution, G max To cut off the evolution algebra. If p rand <p mutation ,p mutation And performing mutation operation for the designed mutation probability.
Mutation operators are designed to maintain diversity of populations and avoid algorithms that fall into local optima, however, for good individuals it is necessary to reduce the rate of mutation to increase their likelihood of survival. Therefore, in order to consider the diversity of the population and the inheritance of good individuals, the embodiment provides a method for quantifying the adaptive mutation probability:
where λ is a scaling factor. Compared with the preset mutation probability, the method automatically adjusts the corresponding mutation probability according to the individual fitness, and can better avoid the destructiveness of mutation operators to the system.
Performing elite processing on the combined population, and determining a new parent population comprises:
non-dominant ordering is carried out on individuals in the combined population, and Pareto grades of the individuals are determined;
determining reference points, respectively associating individuals in the combined population to the corresponding reference points, and taking the reference point closest to the individuals as a small lens of the individuals;
and determining a new parent population according to the Pareto grade, the small mirror and a small mirror operator of the individual.
First, pareto dominance and Pareto class are described as follows:
for any given two decision variables x a 、x b If toAll have f i (x a )≤f i (x b ) Hold true and->So that f i (x a )<f i (x b ) If true, then call x a Dominant x b 。
If for one decision variable there is no other decision variable that can dominate it, then that decision variable is said to be a non-dominated solution, i.e., a Pareto optimal solution. The set of optimal solutions of the objective function is called Pareto optimal set, and the curved surface formed by the optimal set in space is called Pareto front surface.
The non-dominant ranking process for individuals in a population is as follows:
let R p Pareto class, n, for individuals p in the population p S is the number of individuals in the population that can dominate the individual p p For a set of individuals in a population that are dominated by individuals p, non-dominated ordering of the individuals in the population:
step1: by comparing the size of the objective function, two parameters n of each individual in the population are calculated p 、S p ;
Step2: will be n in the population p Individual deposit set f=0 1 And mark the grade R p =1;
Step3: for set F 1 The subject i of the group is S i Traversing set S i Individual p, execution n p =n p -1, at which point n p Individual deposit set f=0 2 And mark the grade R p =2;
Step4: for set F 2 Step3 is repeated for the individuals in (a), and so on, until the entire population is completely classified.
And (3) normalizing the target space, namely converting the target functions into minimized optimized target functions in order to facilitate the unification of the optimizing problem, wherein the ideal point is that each target function can be minimized. The dimension of the target space is the same as the number of the target functions.
Specifically, ideal points are calculated, namely target values of all individuals in the first generation population on each dimension target are solved, minimum values on each dimension target are selected, and then ideal points of the current population are formed. The solution space zero point is moved to the ideal point. And finding out extreme points on each dimension of the target, wherein the extreme points form a hyperplane. The main modes of selecting reference points on the hyperplane include: presetting a reference point by a user; the Das and Dennis method, i.e. a uniform distribution over the simplex (simplex is a generalization of triangles and tetrahedra). Regarding the number of reference points, the preferred choice is the same as the population size, one for each solution.
The individuals in the population are respectively associated with corresponding reference points, and the reference point closest to the individuals is used as the niche of the individuals, namely one reference point corresponds to one niche, so that the living environment division of all the individuals is realized. The niche operators are as follows:
and sequentially selecting the niche with the least individuals, and if the number of the individuals contained in the niche is 0, selecting the individuals nearest to the niche, and adding the individuals into the offspring population. If the niche contains individuals that are not equal to 0, then one individual is randomly selected from the niche to be added to the offspring population.
The elite selection process is as follows:
first, the offspring population Q generated by the kth generation k With parent population P k Merging into a new population E p The population size was 2G. Then for the new population E p Non-dominant ranking is carried out, then the parent population is put in the order from low to high according to Pareto grades, the population size exceeds G when the parent population is put to a certain grade, then individuals under the grade are selected according to a niche operator, and the parent population is put in the order until the parent population size is G, and the k+1th generation parent population P is obtained k+1 。
And carrying out annealing search treatment on the generated offspring population and the new parent population. Referring to fig. 2, after a new parent population is generated, an annealing search is performed on this parent population. After the annealing search, if the cut-off condition is not met at present, GA genetic processing is carried out on the population after the annealing search to generate new offspring, then the annealing search is carried out on the generated offspring, and further parent-offspring combination and the like are carried out. And (3) circulating in this way until the cut-off condition is met, and taking the individual subjected to annealing treatment on the new parent population at the time as the optimal solution of the automatic cotton matching model to obtain a cotton matching scheme.
Annealing the population includes:
generating new individuals according to individuals of the current population;
and when the new individual is dominant to the corresponding individual in the current population, accepting the new individual, and replacing the corresponding individual in the current population with the new individual.
Specifically, let the annealing search initiation temperature be T 0 The method comprises the steps of carrying out a first treatment on the surface of the The temperature decay coefficient is delta k A constant slightly less than 1 is generally desirable.
Adopting a random search mode to construct a new population:
x * =max{min{x+R L δ k T 0 ,x max },x min };
wherein x represents individuals of the current population, x * Representing new individuals generated by random search method, R L Is a random vector of L dimension, x max 、x min The L-dimensional vector is respectively the upper limit and the lower limit of the dosage of L raw cotton.
An acceptance policy is employed to receive new individuals and replace current individuals. The objective of the acceptance strategy is to accept solutions worse than the current solutions with a certain probability, so that the solutions can jump out of local optimum to a certain extent when entering a local extremum trap. According to Pareto dominance, if x * Subject to x, then accept the new individual and replace the current individual. Repeating the above operation until the whole population is searched completely.
The capability of searching the global optimal solution of the high-dimensional function can be effectively enhanced through annealing search, and a more reasonable cotton distribution scheme is obtained.
Further, in some embodiments, the obtaining the cotton matching scheme by using the individual after the new parent population is subjected to the annealing search treatment when the cutoff condition is met as the optimal solution of the automatic cotton matching model includes:
and taking the median value of a plurality of optimal solutions as the cotton matching scheme.
Repeating the optimizing operation for a plurality of times to obtain a series of optimal solutions, and further performing median processing on each optimal solution to obtain a group of optimal cotton distribution schemes.
Further, in some embodiments, further comprising:
and recording a feasible solution and a preset constraint condition of the automatic cotton distribution model, and constructing a shared knowledge base. The shared knowledge base can be used for inspiring the generation of individuals in the initialization stage to accelerate the solving speed, and can provide guidance for scientific cotton distribution in a yarn factory.
In summary, the automatic cotton distribution method based on NSGA-III algorithm provided by the application comprehensively considers the mixed cotton cost, the mixed cotton quality index, the resultant yarn comprehensive quality index and the carbon emission, and builds a more reasonable automatic cotton distribution model. In addition, the NSGA-III algorithm is adopted for optimizing, and three or more multi-objective optimization problems can be better solved. Meanwhile, the annealing algorithm is introduced on the basis of the NSGA-III algorithm, and the annealing search is carried out on individuals in the population in each evolution process, so that the method has a remarkable high-dimensional target space optimizing effect, and a more reasonable cotton distribution scheme can be obtained.
The application also provides an automatic cotton distribution device based on NSGA-III algorithm, and the device can be referred to in a mutual correspondence manner with the method described above. Referring to fig. 3, fig. 3 is a schematic diagram of an automatic cotton distribution device based on NSGA-III algorithm according to an embodiment of the present application, and with reference to fig. 3, the device includes:
a first creation module 10 for creating a cost function of the hybrid cotton, an objective function of the hybrid cotton comprehensive quality index, an objective function of the resultant yarn comprehensive quality index, and a carbon emission function;
a second creation module 20, configured to create an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the integrated quality index of the resultant yarn, the carbon emission function, and a preset constraint condition; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials;
the optimizing module 30 is configured to optimize the usage amount of each raw material of the automatic cotton matching model through NSGA-III algorithm, so as to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
On the basis of the above embodiment, as a specific implementation manner, the second creation module 20 is specifically configured to:
and under the preset constraint condition, respectively taking the minimum value of the cost function of the mixed cotton, the minimum value of the objective function of the comprehensive quality index of the yarn and the minimum value of the carbon emission function to obtain the automatic cotton distribution model.
On the basis of the foregoing embodiment, as a specific implementation manner, the preset constraint condition includes:
inventory constraints, mixed cotton total mass constraints, raw material type constraints, raw material mix upper limit constraints, quality and quality index boundary constraints.
Based on the above embodiment, as a specific implementation manner, the optimizing module 30 is specifically configured to:
and taking the median value of a plurality of optimal solutions as the cotton matching scheme.
Based on the above embodiment, as a specific implementation manner, the optimizing module 30 includes:
the construction unit is used for constructing an initial population, carrying out GA genetic processing on the initial population through a GA genetic algorithm, and generating a offspring population; the individuals in the population comprise a preset number of the raw materials to be optimized;
a merging unit for merging the offspring population with the initial population;
the elite processing unit is used for carrying out elite processing on the combined populations and determining new parent populations;
the first annealing search unit is used for carrying out annealing search processing on the new parent population, and carrying out GA genetic processing on the population subjected to the annealing search processing when the iteration times do not meet the cut-off condition, so as to generate a new child population;
the second annealing search unit is used for carrying out annealing search treatment on the new child population;
and the repeating unit is used for repeating the operations of merging the parent population and the child population, elite selection and annealing search until the cut-off condition is met.
On the basis of the above embodiment, as a specific implementation manner, the elite processing unit includes:
a non-dominant ranking subunit, configured to perform non-dominant ranking on the individuals in the combined population, and determine Pareto levels of the individuals;
a reference point determining subunit, configured to determine reference points, associate the individuals in the combined population to the corresponding reference points, and use the reference point closest to the individual as a small mirror of the individual;
and the population determining subunit is used for determining a new parent population according to the Pareto grade, the small mirror and the small mirror operator of the individual.
On the basis of the above embodiment, as a specific implementation manner, the first annealing search unit and the second annealing search unit are specifically configured to:
generating new individuals according to individuals of the current population;
and when the new individual is dominant to the corresponding individual in the current population, accepting the new individual, and replacing the corresponding individual in the current population with the new individual.
The automatic cotton distribution device based on NSGA-III algorithm comprehensively considers the mixed cotton cost, the mixed cotton quality index, the resultant yarn comprehensive quality index and the carbon emission, and builds a more reasonable automatic cotton distribution model. In addition, the NSGA-III algorithm is adopted for optimizing, and three or more multi-objective optimization problems can be better solved. Meanwhile, the annealing algorithm is introduced on the basis of the NSGA-III algorithm, and the annealing search is carried out on individuals in the population in each evolution process, so that the method has a remarkable high-dimensional target space optimizing effect, and a more reasonable cotton distribution scheme can be obtained.
The application also provides an automatic cotton distribution device based on NSGA-III algorithm, and referring to FIG. 4, the device comprises a memory 1 and a processor 2.
A memory 1 for storing a computer program;
a processor 2 for executing a computer program to perform the steps of:
creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function; creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials; optimizing the consumption of each raw material of the automatic cotton matching model through an NSGA-III algorithm to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
For the description of the apparatus provided in the present application, reference is made to the above method embodiments, and the description is omitted herein.
The present application also provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor, performs the steps of:
creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function; creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials; optimizing the consumption of each raw material of the automatic cotton matching model through an NSGA-III algorithm to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
The computer readable storage medium may include: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
For the description of the computer-readable storage medium provided in the present application, reference is made to the above method embodiments, and the description is omitted herein.
In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the apparatus, device and computer readable storage medium of the embodiment disclosure, since it corresponds to the method of the embodiment disclosure, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The automatic cotton matching method, device, equipment and computer readable storage medium based on NSGA-III algorithm provided by the application are described in detail above. Specific examples are set forth herein to illustrate the principles and embodiments of the present application, and the description of the examples above is only intended to assist in understanding the methods of the present application and their core ideas. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present application without departing from the principles of the present application, and such improvements and modifications fall within the scope of the claims of the present application.
Claims (10)
1. An automatic cotton distribution method based on NSGA-III algorithm is characterized by comprising the following steps:
creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function;
creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials;
optimizing the consumption of each raw material of the automatic cotton matching model through an NSGA-III algorithm to obtain a cotton matching scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
2. The automatic cotton blending method according to claim 1, wherein the creating an automatic cotton blending model according to the cost function of the mixed cotton, the objective function of the mixed cotton comprehensive quality index, the objective function of the resultant yarn comprehensive quality index, the carbon emission function, and a preset constraint condition comprises:
and under the preset constraint condition, respectively taking the minimum value of the cost function of the mixed cotton, the minimum value of the objective function of the comprehensive quality index of the yarn and the minimum value of the carbon emission function to obtain the automatic cotton distribution model.
3. The automatic cotton blending method according to claim 1, wherein the preset constraint condition includes:
inventory constraints, mixed cotton total mass constraints, raw material type constraints, raw material mix upper limit constraints, quality and quality index boundary constraints.
4. The automatic cotton matching method according to claim 3, wherein the obtaining the cotton matching scheme by using the individual subject to the annealing search treatment of the new parent population when the cutoff condition is satisfied as the optimal solution of the automatic cotton matching model comprises:
and taking the median value of a plurality of optimal solutions as the cotton matching scheme.
5. The automatic cotton blending method according to claim 1, wherein optimizing the amount of each of the raw materials of the automatic cotton blending model by NSGA-III algorithm comprises:
constructing an initial population, and carrying out GA genetic processing on the initial population through a GA genetic algorithm to generate a offspring population; the individuals in the population comprise a preset number of the raw materials to be optimized;
combining said progeny population with said initial population;
carrying out elite treatment on the combined populations to determine new parent populations;
carrying out annealing search treatment on the new parent population, and carrying out GA genetic treatment on the population subjected to the annealing search treatment when the iteration times do not meet the cut-off condition, so as to generate a new offspring population;
carrying out annealing search treatment on the new offspring population;
repeating the operations of merging the parent population and the offspring population, elite selection and annealing search until the cut-off condition is met.
6. The method of automatic cotton blending according to claim 5, wherein elite processing the combined population to determine a new parent population comprises:
non-dominant ordering is carried out on individuals in the combined population, and Pareto grades of the individuals are determined;
determining reference points, respectively associating individuals in the combined population to the corresponding reference points, and taking the reference point closest to the individuals as a small lens of the individuals;
and determining a new parent population according to the Pareto grade, the small mirror and a small mirror operator of the individual.
7. The method of automatic cotton blending according to claim 5, wherein performing an annealing search on the population comprises:
generating new individuals according to individuals of the current population;
and when the new individual is dominant to the corresponding individual in the current population, accepting the new individual, and replacing the corresponding individual in the current population with the new individual.
8. An automatic cotton distribution device based on NSGA-III algorithm, which is characterized by comprising:
the first creation module is used for creating a cost function of the mixed cotton, an objective function of the comprehensive quality index of the resultant yarn and a carbon emission function;
the second creation module is used for creating an automatic cotton distribution model according to the cost function of the mixed cotton, the objective function of the comprehensive quality index of the finished yarn, the carbon emission function and preset constraint conditions; the amount to be optimized of the automatic cotton distribution model is the amount of raw materials;
the optimizing module is used for optimizing the consumption of each raw material of the automatic cotton distribution model through an NSGA-III algorithm to obtain a cotton distribution scheme; and in the optimizing process of the NSGA-III algorithm, annealing search processing is carried out on the generated child population and the new parent population, and the individual of the new parent population after the annealing search processing is used as the optimal solution of the automatic cotton matching model when the cut-off condition is met, so that the cotton matching scheme is obtained.
9. An automatic cotton distribution device based on NSGA-III algorithm, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the NSGA-III algorithm-based automatic cotton dispensing method according to any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the NSGA-III algorithm-based automatic cotton distribution method according to any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310295982.0A CN116307213A (en) | 2023-03-23 | 2023-03-23 | Automatic cotton distribution method and device based on NSGA-III algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310295982.0A CN116307213A (en) | 2023-03-23 | 2023-03-23 | Automatic cotton distribution method and device based on NSGA-III algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116307213A true CN116307213A (en) | 2023-06-23 |
Family
ID=86777694
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310295982.0A Pending CN116307213A (en) | 2023-03-23 | 2023-03-23 | Automatic cotton distribution method and device based on NSGA-III algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116307213A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117151428A (en) * | 2023-10-27 | 2023-12-01 | 泉州装备制造研究所 | NSGA-II-based warp knitting machine stock planning method |
CN117994593A (en) * | 2024-04-03 | 2024-05-07 | 青岛大学 | Automatic cotton distribution method based on multi-source data composite model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108805434A (en) * | 2018-05-25 | 2018-11-13 | 河海大学 | A kind of step power station Multiobjective Optimal Operation method based on improvement NSGA- III |
AU2021101920A4 (en) * | 2021-04-14 | 2021-06-03 | Guiyang Urban Rall Transit CO.,LTD | Multi-objective intelligent optimization control method of shield construction parameters based on data mining |
CN114399043A (en) * | 2021-06-16 | 2022-04-26 | 北京理工大学 | Vehicle position routing method based on non-dominated sorting particle swarm genetic algorithm |
-
2023
- 2023-03-23 CN CN202310295982.0A patent/CN116307213A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108805434A (en) * | 2018-05-25 | 2018-11-13 | 河海大学 | A kind of step power station Multiobjective Optimal Operation method based on improvement NSGA- III |
AU2021101920A4 (en) * | 2021-04-14 | 2021-06-03 | Guiyang Urban Rall Transit CO.,LTD | Multi-objective intelligent optimization control method of shield construction parameters based on data mining |
CN114399043A (en) * | 2021-06-16 | 2022-04-26 | 北京理工大学 | Vehicle position routing method based on non-dominated sorting particle swarm genetic algorithm |
Non-Patent Citations (1)
Title |
---|
李成国 等: "改进混合遗传算法在自动配棉上的应用", 《纺织学报》, vol. 30, no. 3, pages 28 - 33 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117151428A (en) * | 2023-10-27 | 2023-12-01 | 泉州装备制造研究所 | NSGA-II-based warp knitting machine stock planning method |
CN117151428B (en) * | 2023-10-27 | 2024-03-01 | 泉州装备制造研究所 | NSGA-II-based warp knitting machine stock planning method |
CN117994593A (en) * | 2024-04-03 | 2024-05-07 | 青岛大学 | Automatic cotton distribution method based on multi-source data composite model |
CN117994593B (en) * | 2024-04-03 | 2024-06-21 | 青岛大学 | Automatic cotton distribution method based on multi-source data composite model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116307213A (en) | Automatic cotton distribution method and device based on NSGA-III algorithm | |
Kaur et al. | A novel multi-objective bacteria foraging optimization algorithm (MOBFOA) for multi-objective scheduling | |
Li et al. | Bi-goal evolution for many-objective optimization problems | |
CN110084512B (en) | Multi-robot task allocation method for intelligent warehousing system | |
Gong et al. | An improved multiobjective differential evolution based on Pareto-adaptive ϵ-dominance and orthogonal design | |
CN109066710A (en) | A kind of multi-objective reactive optimization method, apparatus, computer equipment and storage medium | |
CN113569483A (en) | Method for solving multi-target flexible job shop scheduling based on artificial bee colony algorithm | |
Teekeng et al. | A combination of shuffled frog leaping and fuzzy logic for flexible job-shop scheduling problems | |
CN108776461A (en) | A kind of flexible job shop scheduling method and system | |
Li et al. | A two-archive algorithm with decomposition and fitness allocation for multi-modal multi-objective optimization | |
Yalcin et al. | Determining weights in multi-objective linear programming under fuzziness | |
CN108470237A (en) | A kind of more preference higher-dimension purpose optimal methods based on coevolution | |
CN117236523B (en) | Combined heuristic carbon emission optimization method based on pareto strategy | |
CN117075545A (en) | Multi-target flexible job shop scheduling method, electronic equipment and medium | |
CN112085318A (en) | Client demand modular process configuration method based on multi-target ant lion algorithm | |
CN116307214A (en) | Automatic cotton distribution method based on NSGA-II algorithm and related device | |
Zhang et al. | Multi-hive artificial bee colony algorithm for constrained multi-objective optimization | |
CN114240091A (en) | Flexible job shop scheduling method based on self-adaptive layering strategy | |
Xu et al. | Genetic programming for dynamic flexible job shop scheduling: Evolution with single individuals and ensembles | |
CN115249113A (en) | Distributed zero-waiting flow shop scheduling method and system with preparation time | |
CN113157381B (en) | Multi-workflow scheduling method based on non-dominated sorting and owl search | |
Tan et al. | A cooperative coevolutionary algorithm for multiobjective optimization | |
CN110633784B (en) | Multi-rule artificial bee colony improvement algorithm | |
CN115545406A (en) | Production and distribution cooperative scheduling method and system for different-address machines | |
CN113792494A (en) | Multi-target flexible job shop scheduling method based on migrating bird group algorithm and cross fusion |
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 |