CN106919979A - A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control - Google Patents
A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control Download PDFInfo
- Publication number
- CN106919979A CN106919979A CN201510982293.2A CN201510982293A CN106919979A CN 106919979 A CN106919979 A CN 106919979A CN 201510982293 A CN201510982293 A CN 201510982293A CN 106919979 A CN106919979 A CN 106919979A
- Authority
- CN
- China
- Prior art keywords
- cotton
- processing
- equipment
- fitness
- iaga
- 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 132
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012545 processing Methods 0.000 title claims abstract description 60
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 21
- 238000003062 neural network model Methods 0.000 claims abstract description 17
- 230000002068 genetic effect Effects 0.000 claims abstract description 13
- 238000013461 design Methods 0.000 claims abstract description 7
- 238000012804 iterative process Methods 0.000 claims abstract description 4
- 238000003754 machining Methods 0.000 claims abstract description 3
- 210000000349 chromosome Anatomy 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 239000000835 fiber Substances 0.000 claims description 6
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 238000011524 similarity measure Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 3
- 241000219146 Gossypium Species 0.000 description 89
- 238000007599 discharging Methods 0.000 description 4
- 230000013872 defecation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000000332 black box Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000001726 chromosome structure Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000002019 doping agent Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
Abstract
The invention discloses a kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control, regain and character parameter according to unginned cotton calculate the optimal processing scheme of cotton machining process automatically.Cotton processing equipment is together in series first, the BP neural network model of each equipment is respectively trained using the input and output result of equipment, this is variable computational space of the genetic algorithm in iterative process is run, then set up cotton grade and judge BP neural network model, on this basis, the index method evaluation method of cotton is determined, next single goal Multi-variables optimum design function model is set up using linear weight sum method, as genetic algorithm fitness function in the process of running, finally cotton processing Based Intelligent Control is realized using improved adaptive GA-IAGA.
Description
Technical field
It is more particularly to a kind of to realize cotton using improved adaptive GA-IAGA the invention belongs to cotton processing field of intelligent control
The method of flower process Based Intelligent Control.
Background technology
China is cotton planting and processing big country, and the quality of cotton processing is very big for the Efficiency of Cotton Industry.When
The yield of preceding domestic cotton and processing capacity steady-state growth, but cotton level of processing is also very low, during processing only with manually from
The method of line analysis unginned cotton material quality manually adjusts the parameter of process equipment, lacks on-line checking link, it is impossible to real-time root
According to unginned cotton quality adjust automatically process equipment parameter, different quality, the unginned cotton raw material of different impurity contents is easily caused to be processed simultaneously,
Process is intelligent, automaticity is low, seriously reduces the quality of surface finished product, causes that production cost is high, profit margin is low.
Cotton processing is influenceed by regain, percentage of impurity amount, dopant species, device parameter, and these influence factors
It is nonlinear, there are problems that coupling and time-varying, it is impossible to realize the Synchronous fluorimetry of each factor.Therefore, cotton processing intelligence
Control belongs to multi-objective optimization question.
In developed country, cotton processing equipment just towards automation, maximization, complete set direction develop, process and
Processing method develop with Based Intelligent Control direction towards becoming more meticulous.
Cotton processing high investment, the present situation of low output seriously govern running business big and strong for China's cotton spinning industry.With city
The technological means of cotton processing intelligentized control method is badly in need of realizing in raising of the field to the requirement of cotton final product quality, China.
The content of the invention
For defect and deficiency present in existing cotton process technology, the present invention proposes that one kind utilizes improved adaptive GA-IAGA
The method for realizing cotton processing Based Intelligent Control.
To achieve the above object, the technical solution adopted in the present invention is as follows：
A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control, comprises the following steps：
(1) cotton processing equipment is together in series, the BP of each equipment is respectively trained using the input and output result of equipment
Neural network model.
(2) cotton grade evaluation BP neural network model is set up.
Using the standarded cotton sample data after a large amount of manual grading skills, the cotton grade for setting up 6-15-1 structures judges BP nerve nets
Network model, realizes by the Nonlinear Mapping of cotton characteristic parameter to cotton grade.
(3) gined cotton index method judgment criteria is set up.
By cotton type, cotton grade and length scale, these three factors are determined gined cotton index method, by cotton
Index method is set up with current market price and is contacted, and obtains the per unit area yield gross profit of gined cotton.
(4) cotton processing Nonlinear Multiobjective static optimization model is set up.
Lint quality according to required by cotton processing is good, the requirement of high efficiency and high production, sets up Optimized model
For：
Max f (x)=max [f1(x1…xp…x14)f2(x1…xp…x14)x1)]T
s.t. xp min≤xp≤xp max
1≤p≤14
Wherein：
f1X () is the related cotton comprehensive quality index of process equipment；
f2X () is the fiber yield index related to process equipment；
x1…xp…x14It is system throughput and 14 parameters of process equipment.
(5) single goal Multi-variables optimum design model is set up using linear weight sum method.
In cotton processing Model for Multi-Objective Optimization, the credit rating of gined cotton, fiber yield and processing efficiency are direct
It is related to the ultimate yield of gined cotton.The single object optimization number that maximum revenue is processed based on cotton is set up using linear weight sum method
Learn model：
s.t. xp min≤xp≤xp max
1≤p≤14
In formula：
xpIt is each process equipment parameter, 14 design variables are respectively x1…xp…x14；
RQualityIt is cotton index method；
PRankIt is cotton unit price；
MSCIt is unginned cotton weight；
ψ is fiber yield；
CTimeIt is processing cost hourly；
x1It is cotton single rate；
MSCψ is qualified gined cotton quantum of output；
MSC/x1Process total used time.
(6) cotton processing Based Intelligent Control is realized using improved adaptive GA-IAGA.
According to currently preferred, be together in series for cotton processing equipment by the step (1), uses the input and output of equipment
Result is respectively trained the BP neural network model of each equipment, concretely comprises the following steps：
(1-1) is set up by the black-box model of the production process of unginned cotton to gined cotton using BP neural network, is input into as before processing
Character parameter P, the unginned cotton regain M and process equipment parameter of unginned cotton, are output as character parameter, the gined cotton moisture regain of gined cotton after processing
Rate.
(1-2) for BP neural network model there is a problem of it is excessively huge, be difficult training, each process equipment is individually set
Meter BP neural network model, the training for carrying out repeatedly using live process data obtains accurate BP neural network model.Will be preceding
The output of face processing equipment neural network model realizes the sequentially concatenation of each equipment, so as to build from seed as input below
BP neural network model of the cotton to the whole production process of surface.
According to currently preferred, the step (6) realizes cotton processing Based Intelligent Control using improved adaptive GA-IAGA,
Concretely comprise the following steps：
(6-1) is based on the mixing real coding of genome：By each process equipment it is abstract be genome, by several according to
The process equipment composition of genome item chromosome that processing sequence is arranged in order, each process equipment genome includes the equipment
Variable parameter and the discrete variable 0,1 for whether using.
(6-2) is by object function directly as fitness function：
Fitness function is：
s.t. xp min≤xp≤xp max
1≤p≤16
In formula：xpRepresent 16 parameters of each equipment in process.
(6-3) does not contain the miscellaneous condition of weight according in gined cotton after cotton ginning machining, is calculated about using Means of Penalty Function Methods
Beam condition meets situation.
If being unsatisfactory for constraints, follow-up calculating is skipped, directly by the adaptive value zero setting of the program, punished.
Adjustment mode to individual adaptation degree is：
In formula：F (x) is former fitness；F (x) is the fitness after being adjusted through Means of Penalty Function Methods
(6-4) constructs initial population using expertise
In cotton processing, conventional processing experience is extremely important, chooses 5 groups of experience schemes and adds the first of genetic algorithm
In beginning population；Because cotton to be processed is in goods yard storage in heaps, the character parameter change of a collection of cotton is little, all to lose
The control program in preceding 2 cycles in propagation algorithm iterative process is added in initial population in the lump；In order to play hereditary calculation
The multi-direction search advantage of method, the residue using random fashion generation Population in Genetic Algorithms is individual.
(6-5) is based on the improved adaptive GA-IAGA of ranking fitness
According to the characteristics of cotton system of processing itself, two chromosome H are constructedm(x) and HnThe coefficient of similarity S of (x)mn：
In formula：P=16；xpm、xpnRespectively chromosome Hm(x) and HnEach gene position of (x), and xp min≤xpm, xpn≤
xp max。
In the algorithm, if N is the quantity of individuality in population, F (Hj(x)) it is chromosome HjX the original fitness of () is through punishment
Final fitness value after function method adjustment, then fitness average value F individual in populationMeanFor：
Fitness is chosen in colony and is more than FMeanIndividuality carry out Similarity Measure two-by-two, if SGAFor similarity judges
A threshold value, work as Smn＜ SGAWhen, that is, think that the two individualities are similar.
According to currently preferred, improved adaptive GA-IAGA of the step (6-5) based on ranking fitness, specific steps
For：
(6-5-1) in the iterative process in kth generation, population G(k)In individualityNumber is N,
(6-5-2) is to population G(k)In all individualities seek fitness average value FMean, in population G(k)Middle selection is more than FMean
Individuality, set up new population using these individualitiesNumber is NTemp.Step operation is individual in order to exclude low fitness
To the interference effect of Population in Genetic Algorithms evolution general orientation.
(6-5-3) is to populationAccording to the threshold value S of the selected individual similarity of a reflection of test experienceGA.Distinguish first
Calculate the individual similarity S with remaining individuality in population of fitness value highestmn, by populationIn be less than SGAIndividuality go
Fall.Calculate fitness value time individual and remaining individual similarity S high respectively againmn, will be less than SGAIt is individual from population
In remove.After these are operated, the population for ultimately formingIn individual amount be NTemp.Step operation deletes population
In similar individuals, it is to avoid the excessive multiplication between similar individuals is on the multifarious influence of Evolution of Population.
(6-5-4) is N to quantityTempPopulationUsing the two-point crossover of genetic algorithm, uniform mutation operation so that
PopulationIndividual reproduction, individual amount increases to 2N.The step computing is the routine operation of genetic algorithm, for retaining variation
Expansion is oriented under the conditions of multifarious to population scale.
(6-5-5) calculates populationIn all individual fitness, the maximum individuality of selection wherein fitness, so far
The generation population of kth+1 G is iterated to calculate out(k+1)。
(6-5-6) calculates iteration and carries out, until the genetic algorithm stop condition of setting meets.
Brief description of the drawings
Fig. 1 cottons character parameter, technological parameter data flow；
The grade Evaluation model experiment of Fig. 2 cottons；
The relation of Fig. 3 cotton grades and cotton per unit area yield gross profit；
Fig. 4 chromosome structures；
Fig. 5 cottons character parameter, technological parameter data flow；
Fig. 6 is based on the Revised genetic algorithum operational flowchart of ranking fitness.
Specific embodiment
The present invention will be further described with Figure of description with reference to embodiments, but not limited to this.
The method that cotton processing Based Intelligent Control is realized using improved adaptive GA-IAGA, is comprised the following steps：
(1) cotton processing equipment is together in series, the BP of each equipment is respectively trained using the input and output result of equipment
Neural network model.As shown in Figure 1, using the output of above process equipment neural network model as input below, realize each
The sequentially concatenation of equipment, so as to build the BP neural network model of the whole production process from unginned cotton to surface.
(2) set up cotton grade and judge BP neural network model.
Maturity coefficient, color characteristic and Ginning Quality by the use of cotton etc. as BP neural network model input, real number 1
The cotton grade of~7 displays is the output of model.Such as Fig. 2, it can be seen that the discrimination of the model is good, with important finger
Lead meaning.
(3) gined cotton index method judgment criteria is set up.
By cotton type, cotton grade and length scale, these three factors are determined gined cotton index method.Such as Fig. 3 institutes
Show, the index method of cotton is set up with current market price and is contacted, obtain the per unit area yield gross profit of gined cotton.
(4) cotton processing Nonlinear Multiobjective static optimization model is set up.
(5) single goal Multi-variables optimum design model is set up using linear weight sum method.
(6) cotton processing Based Intelligent Control is realized using improved adaptive GA-IAGA.
It is illustrated in figure 4 the final chromosome construction set up.Wherein, A ', B ', C ', D ', E ', F ', G ', H ' difference
Represent the genome of each process equipment.
The use of tilting seed clear and defecation formula seed clear is determined by the selection position of each process equipment genome.Serration type
The use number of units of skin clear is determined by impurity-discharging knife quantity.Impurity-discharging knife quantity is not used when being 0；Impurity-discharging knife quantity makes when being 1~7
With 1；2 are used when impurity-discharging knife quantity is 8~14.
In algorithm, when using tilting seed clear, defecation formula seed clear and serration type skin clear, it is necessary to pay close attention to B '1、C
′1、H′1Whether the equipment is enabled effectively, and only in the case of effective, the equipment could participate in genetic algorithm optimization iteration, no
Then the equipment will be bypassed, and its data flow is as shown in Figure 5.
According to the characteristics of cotton system of processing itself, two chromosome H are constructedm(x) and HnThe coefficient of similarity S of (x)mn：
In formula：P=16；xpm、xpnRespectively chromosome Hm(x) and HnEach gene position of (x), and xp min≤xpm, xpn≤
xp max。
In the algorithm, if N is the quantity of individuality in population, F (Hj(x)) it is chromosome HjX the original fitness of () is through punishment
Final fitness value after function method adjustment, then fitness average value F individual in populationMeanFor：
Fitness is chosen in colony and is more than FMeanIndividuality carry out Similarity Measure two-by-two, if SGAIt is similarity judgement
One threshold value, works as Smn＜ SGAWhen, that is, think that the two individualities are similar.
The control flow of improved adaptive GA-IAGA is as shown in Figure 6.
The beneficial effects of the invention are as follows：The present invention provides one kind and realizes cotton processing intelligence using improved adaptive GA-IAGA
The method of control, can be prevented effectively from the blindness of device parameter regulation in current cotton processing, to improve cotton processing
The extensive cooked mode of industry provides a set of feasible solution.The present invention sets up BP models for cotton processing equipment,
This is final optimised control operation object；The grade evaluation criterion of artificial range estimation feel is abandoned, has been established based on detection
The gined cotton index method judgment criteria of data, without manual intervention, it is convenient that this is provided for the automatic computing of computer is solved；
Single goal Multi-variables optimum design model is established, for the quality of Processing Strategies provides quantitative evaluation index；Use improved something lost
Propagation algorithm is solved to multivariate model, ensure that the real-time control of cotton processing is required.The control that the present invention is provided
Strategy, can effectively reduce damage of the process to cotton fiber, can realize the maximum revenue of cotton processing enterprise, real
Existing cotton processing lean production.
Claims (2)
1. a kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control, comprises the following steps：
(1) cotton processing equipment is together in series, the BP nerves of each equipment is respectively trained using the input and output result of equipment
Network model；
(2) set up cotton grade and judge BP neural network model：Using the standarded cotton sample data after a large amount of manual grading skills, 6- is set up
The cotton grade of 15-1 structures judges BP neural network model, and realization is reflected by the non-linear of cotton characteristic parameter to cotton grade
Penetrate；
(3) gined cotton index method judgment criteria is set up：Gined cotton index method is by cotton type, cotton grade and length
Grade these three factors decision, the index method of cotton is set up with current market price and is contacted, and obtains the per unit area yield of gined cotton
Gross profit；
(4) cotton processing Nonlinear Multiobjective static optimization model is set up：Gined cotton according to required by cotton processing
Quality is good, the requirement of high efficiency and high production, and setting up Optimized model is：
Maxf (x)=max [f1(x1…xp…x14) f2(x1…xp…x14) x1)]T
s.t.xp min≤xp≤xp max
1≤p≤14
Wherein：
f1X () is the related cotton comprehensive quality index of process equipment,
f2X () is the fiber yield index related to process equipment,
x1…xp…x14It is system throughput and 14 parameters of process equipment；
(5) single goal Multi-variables optimum design model is set up using linear weight sum method：In cotton processing Model for Multi-Objective Optimization
In, the credit rating of gined cotton, fiber yield and processing efficiency are directly connected to the ultimate yield of gined cotton；Using linear weight sum method
Set up the single object optimization Mathematical Modeling that maximum revenue is processed based on cotton：
s.t.xp min≤xp≤xp max
1≤p≤14
In formula：
xpIt is each process equipment parameter, 14 design variables are respectively x1…xp…x14,
RQualityIt is cotton index method,
PRankIt is cotton unit price,
MSCIt is unginned cotton weight,
ψ is fiber yield,
CTimeIt is processing cost hourly,
x1It is cotton single rate,
MSCψ is qualified gined cotton quantum of output,
MSC/x1Process total used time；
(6) cotton processing Based Intelligent Control is realized using improved adaptive GA-IAGA.
2. method according to claim 1, it is characterised in that the step (6) realizes cotton using improved adaptive GA-IAGA
Process Based Intelligent Control, concretely comprises the following steps：
(6-1) is based on the mixing real coding of genome：By each process equipment it is abstract be genome, by several according to processing
The process equipment composition of genome item chromosome that order is arranged in order, variable of each process equipment genome comprising the equipment
Parameter and the discrete variable 0,1 for whether using；
(6-2) is by object function directly as fitness function：
Fitness function is：
s.t.xp min≤xp≤xp max
1≤p≤16
In formula：xpRepresent 16 parameters of each equipment in process；
(6-3) does not contain the miscellaneous condition of weight according in gined cotton after cotton ginning machining, and constraint bar is calculated using Means of Penalty Function Methods
Part meets situation；
If being unsatisfactory for constraints, follow-up calculating is skipped, directly by the adaptive value zero setting of the program, punished；
Adjustment mode to individual adaptation degree is：
In formula：F (x) is former fitness, and F (x) is the fitness after being adjusted through Means of Penalty Function Methods；
(6-4) constructs initial population using expertise：
In cotton processing, conventional processing experience is extremely important, chooses the initial kind that 5 groups of experience schemes add genetic algorithm
In group；Because cotton to be processed is in goods yard storage in heaps, the character parameter change of a collection of cotton is little, all to calculate heredity
The control program in preceding 2 cycles in method iterative process is added in initial population in the lump；In order to play genetic algorithm
Multi-direction search advantage, the residue using random fashion generation Population in Genetic Algorithms is individual；
(6-5) is based on the improved adaptive GA-IAGA of ranking fitness：
According to the characteristics of cotton system of processing itself, two chromosome H are constructedm(x) and HnThe coefficient of similarity S of (x)mn：
In formula：P=16；xpm、xpnRespectively chromosome Hm(x) and HnEach gene position of (x), and xp min≤xpm, xpn≤
xp max；
In the algorithm, if N is the quantity of individuality in population, F (Hj(x)) it is chromosome HjX the original fitness of () is through penalty
Final fitness value after method adjustment, then fitness average value F individual in populationMeanFor：
Fitness is chosen in colony and is more than FMeanIndividuality carry out Similarity Measure two-by-two, if SGAIt is one of similarity judgement
Threshold value, works as Smn＜ SGAWhen, that is, think that the two individualities are similar.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510982293.2A CN106919979A (en) | 2015-12-25 | 2015-12-25 | A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510982293.2A CN106919979A (en) | 2015-12-25 | 2015-12-25 | A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106919979A true CN106919979A (en) | 2017-07-04 |
Family
ID=59456951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510982293.2A Pending CN106919979A (en) | 2015-12-25 | 2015-12-25 | A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106919979A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615144A (en) * | 2018-12-20 | 2019-04-12 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Setting method, device, equipment and the storage medium of cotton regain target value |
| CN109629010A (en) * | 2018-12-20 | 2019-04-16 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Parameter regulation means, device, equipment and the storage medium of cotton processing equipment |
| CN110009191A (en) * | 2019-03-04 | 2019-07-12 | 中国地质大学（武汉） | A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10134019A (en) * | 1996-09-06 | 1998-05-22 | Fujitsu Ltd | Global search device for parallel genetic algorithm utilizing local solution and storage medium stored global search program of parallel genetic algorithm using search device and local solution |
| CN101231720A (en) * | 2008-02-01 | 2008-07-30 | 北京航空航天大学 | Enterprise process model multi-target parameter optimizing method based on genetic algorithm |
| CN101599138A (en) * | 2009-07-07 | 2009-12-09 | 武汉大学 | Land evaluation method based on artificial neural network |
| CN102419549A (en) * | 2011-09-13 | 2012-04-18 | 浙江大学 | Complex chemical process modeling method of hybrid DNA (Deoxyribose Nucleic Acid) genetic algorithm |
| CN103092074A (en) * | 2012-12-30 | 2013-05-08 | 重庆邮电大学 | Parameter optimization control method of semiconductor advance process control |
| CN103426027A (en) * | 2013-07-24 | 2013-12-04 | 浙江大学 | Intelligent normal pool level optimal selection method based on genetic neural network models |
| CN104573820A (en) * | 2014-12-31 | 2015-04-29 | 中国地质大学（武汉） | Genetic algorithm for solving project optimization problem under constraint condition |
-
2015
- 2015-12-25 CN CN201510982293.2A patent/CN106919979A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10134019A (en) * | 1996-09-06 | 1998-05-22 | Fujitsu Ltd | Global search device for parallel genetic algorithm utilizing local solution and storage medium stored global search program of parallel genetic algorithm using search device and local solution |
| CN101231720A (en) * | 2008-02-01 | 2008-07-30 | 北京航空航天大学 | Enterprise process model multi-target parameter optimizing method based on genetic algorithm |
| CN101599138A (en) * | 2009-07-07 | 2009-12-09 | 武汉大学 | Land evaluation method based on artificial neural network |
| CN102419549A (en) * | 2011-09-13 | 2012-04-18 | 浙江大学 | Complex chemical process modeling method of hybrid DNA (Deoxyribose Nucleic Acid) genetic algorithm |
| CN103092074A (en) * | 2012-12-30 | 2013-05-08 | 重庆邮电大学 | Parameter optimization control method of semiconductor advance process control |
| CN103426027A (en) * | 2013-07-24 | 2013-12-04 | 浙江大学 | Intelligent normal pool level optimal selection method based on genetic neural network models |
| CN104573820A (en) * | 2014-12-31 | 2015-04-29 | 中国地质大学（武汉） | Genetic algorithm for solving project optimization problem under constraint condition |
Non-Patent Citations (1)
| Title |
|---|
| 张成梁: "棉花加工过程智能化关键技术研究", 《CNKI》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615144A (en) * | 2018-12-20 | 2019-04-12 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Setting method, device, equipment and the storage medium of cotton regain target value |
| CN109629010A (en) * | 2018-12-20 | 2019-04-16 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Parameter regulation means, device, equipment and the storage medium of cotton processing equipment |
| CN109629010B (en) * | 2018-12-20 | 2022-01-28 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Parameter adjusting method, device and equipment of cotton processing equipment and storage medium |
| CN109615144B (en) * | 2018-12-20 | 2022-11-01 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Method, device, equipment and storage medium for setting target value of moisture regain of cotton |
| CN110009191A (en) * | 2019-03-04 | 2019-07-12 | 中国地质大学（武汉） | A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103577694B (en) | Aquaculture water quality short-time combination forecast method on basis of multi-scale analysis | |
| CN108876132B (en) | Industrial enterprise energy efficiency service recommendation method and system based on cloud | |
| CN108846526A (en) | A kind of CO2 emissions prediction technique | |
| CN105243437B (en) | The method of prediction coke quality and Optimized Coal Blending ratio for tamping coking | |
| CN102540879A (en) | Multi-target evaluation optimization method based on group decision making retrieval strategy | |
| Fallahpour et al. | An evolutionary-based predictive soft computing model for the prediction of electricity consumption using multi expression programming | |
| CN113300380B (en) | Load curve segmentation-based power distribution network reactive power optimization compensation method | |
| CN106919979A (en) | A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control | |
| CN107464017A (en) | Based on the adaptive soft-sensor Forecasting Methodology with time difference Bayesian network | |
| CN116911962B (en) | Article selecting device and method based on data model | |
| CN112085156B (en) | Partial pressure line loss rate prediction and loss reduction potential evaluation method and system | |
| CN115986728A (en) | Power grid situation prediction method considering uncertainty factors and terminal | |
| CN113344467A (en) | Method and device for predicting capital of electric power engineering | |
| CN112883993B (en) | Machine learning-based method for predicting optimal single-time-consumption working condition of coal mill powder production | |
| CN110298506A (en) | A kind of urban construction horizontal forecast system | |
| CN109190810A (en) | The prediction technique of grassland in northern China area NDVI based on TDNN | |
| CN109272144A (en) | The prediction technique of grassland in northern China area NDVI based on BPNN | |
| CN107679651A (en) | A kind of moon electricity demand forecasting method based on grey forecasting model Yu BP artificial nerve network models | |
| CN104182854A (en) | Mixed energy consumption measuring method for enterprise energy management system | |
| Balandin et al. | Evaluation of the efficiency of sugar beet processing strategies based on the data of the Sergach Sugar Factory | |
| CN111126827A (en) | Input-output accounting model construction method based on BP artificial neural network | |
| Astria et al. | System Dynamics Modelling Approach for Palm Oil Supply Chain under Various Policy Interventions: A Case Study in Indonesia’s Private Company | |
| CN107358295A (en) | Distribution operation maintenance expense Forecasting Methodology based on genetic algorithm and SVMs | |
| Kutlu | Changes in exchange rates and the balance of trade: a literature survey with reference to Turkey’s foreign trade | |
| CN111401651A (en) | Method for predicting material purchasing demand based on L STM network |
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 |