CN104408281B - It is a kind of to mix type interactive evolution optimization method for what portable wine pot was designed - Google Patents
It is a kind of to mix type interactive evolution optimization method for what portable wine pot was designed Download PDFInfo
- Publication number
- CN104408281B CN104408281B CN201410538133.4A CN201410538133A CN104408281B CN 104408281 B CN104408281 B CN 104408281B CN 201410538133 A CN201410538133 A CN 201410538133A CN 104408281 B CN104408281 B CN 104408281B
- Authority
- CN
- China
- Prior art keywords
- design
- wine pot
- value
- adaptive value
- uncertainty
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 title claims abstract description 29
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 28
- 238000013461 design Methods 0.000 claims abstract description 62
- 230000003044 adaptive effect Effects 0.000 claims abstract description 58
- 230000006978 adaptation Effects 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 36
- 230000002068 genetic effect Effects 0.000 claims description 13
- 239000000284 extract Substances 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000010429 evolutionary process Effects 0.000 description 2
- 238000010353 genetic engineering Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 229910001220 stainless steel Inorganic materials 0.000 description 2
- 239000010935 stainless steel Substances 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses it is a kind of for portable wine pot design mix type interactive evolution optimization method, it is intended to improve the efficiency of portable wine pot personalized designs, comprise the following steps that：(1) evolve before starting, system provides the user design environment, and initial Advanced group species are generated at random；(2) in interactive process, estimation window is provided the user；(3) analysis of uncertainty is carried out to the individual fitness that user evaluates, two kinds of adaptation Value Types, i.e., single numeric type and interval numeric type is marked off based on adaptive value uncertainty；(4) system sets up corresponding mathematics model for adapting to Value Types, corrects individual fitness, and participate in follow-up evolve.The revised adaptive value of two classes simultaneously participates in evolutionary optimization, expects to generate the design for meeting user psychology demand, reaches effectively optimizing purpose.
Description
Technical field
The invention belongs to affection computation field, it is proposed that a kind of interactive evolutionary optimization side designed for portable wine pot
Method, the design of wine pot appearance scheme is carried out available for guiding user.
Background technology
Stainless steel wine pot is to be popular in a kind of outdoor consumer goods both domestic and external, it have it is graceful it is exquisite, attractive in appearance it is compact, be easy to
The characteristics of carrying with, it is deep to be favored by man.Due to the promotion of the level of consumption, the market demand in portable wine pot gradually increases,
Appearance requirement to wine pot is gradually stepped up.Traditional circumference flat type design is gradually personalized design substitution, in order to strengthen market
Competitiveness, the appearance design in wine pot proposes challenge to designer.In order to tackle this situation, the present invention thinks evolutionary optimization
Want to be incorporated into the appearance design of product, by the optimization ability of genetic algorithm, design is provided for designer's design
Inspiration.
At present, based on computer-aided engineering product (art) design system is gradually used, but by means of entering
The practical design system of change optimization method is simultaneously few.The target of portable wine pot design is to find out that " most satisfied wine pot outward appearance is set
Meter ", because different people has different standards to " satisfied design ", thus evaluation result has very strong uncertainty, and this is
The implicit performance indications optimization problem for being adapted to be solved with interactive genetic algorithm of one quasi-representative.
But simple to build design system using legacy interactive genetic algorithm, performance is unsatisfactory.Because interactive optimization
Every money product adaptation value (evaluation of estimate) evaluated and produce by people, so adaptive value reflects the subjective preferences of people, and the preference of people
It can make adaptive value that there is uncertainty, uncertainty increase, the levels of precision of adaptive value will be reduced, and evolutionary optimization effect will
It is deteriorated.Adaptive value levels of precision is improved, it is to make designer be put into more when evaluating individual to reduce probabilistic direct method
Many notices, but the fatigue of people so can be undoubtedly caused, evaluating uncertainty can strengthen on the contrary.So improving adaptive value precision
It is contradiction each other with the operating burden that reduces people, this is also the problem of interactive genetic algorithm application.
At present, product design is carried out using interactive evolution optimization method, has issued for some strategies.These plans
Two types are slightly roughly divided into, one is by setting up rational adaptive value assignment mode, improving man-machine interaction environment, people are reduced
Operating burden, improve adaptive value precision.The periodical published such as in March, 2008《Progress in Natural Science》
18th phase " Adaptive Interactive Genetic Algorithms with Interval Fitness of
The interval number and fuzzy number adaptive value assignment method that are proposed in the texts of Evolutionary Individuals " one and in dress designing
Application in system；Chinese invention patent " interactive evolution optimization method for being used for curtain design " (publication number：
CN10263249A, publication date：2011.08.24 many collection gesture fuzzy evaluations, exact value evaluation and the automatic Evaluation) provided.Compare
Perfect number and dispersion number, interval number and fuzzy number can preferably reflect evaluation procedure it is uncertain with it is gradual, significantly
Improve adaptive value precision.But when carrying out adaptive value assignment operation, interval number will carry out the adaptive value upper limit and lower limit twice
Evaluate；Fuzzy number will carry out the determination of central value and width, and this both increases the burden of designer in fact.The second is using conjunction
Suitable agent model replaces user to estimate the adaptive value mitigation human fatigue for evolving individual.Represent method such as in October, 2009 of publication
Periodical《Control and decision-making》The text of 24th phase " interval adaptive value interactive genetic algorithm neutral net agent model " one is proposed
By agent model prediction and evaluation result so as to reduce the method for the evaluation of people；The periodical that in May, 2013 publishes《Control theory with
Using》The machine estimation that 30th phase " the new interactive genetic algorithm that individual fitness is estimated based on similarity " text is proposed is suitable
Strategy should be worth；Chinese invention patent " the books individuation search method based on interactive evolutionary optimization " (publication number：
CN103984721A, publication date：2014.08.13) the user preference searching method that provides.This kind of machine learning techniques are expanded
Algorithm search ability, alleviates the operating burden of designer, with great importance.But these agent models are to be dependent on
Different adaptive value assignment modes, extracts valuable information and sets up, so the influence of adaptive value assignment mode is still present.More
Importantly, above-mentioned all methods are not directed to the natural change law of adaptive value form during evolution, do not embody
The numerical value diversity change of adaptive value.
Using interactive evolution optimization method development design system, have for medium-sized and small enterprises before wide market
Scape.Through consult pertinent literature, there is not yet at present using with it is a variety of adaptation Value Types simultaneously and depositing into interactive mode heredity
The method that algorithm is designed in portable wine pot.If developing the efficient design system of correlation, wine pot product can not only be set
Meter brings promotion to be worth, and will also have great inspiration meaning to other product designs.
The content of the invention
The present invention proposes the product generation of portable stainless-steel wine pot, interaction and the Evolutionary Design method of complete set, leads to
The design of wine pot outward appearance can be completed by crossing evolutionary optimization.Calculated the method have the characteristics that employing the interactive heredity of improved high-performance
Method carries out wine pot appearance design, and specific manifestation is to propose to mix adaptive value in type adaptive value concept, evolutionary process and simultaneously have
Two kinds of types of presentation, embody the complicated variety that interactive evolutionary optimization is evaluated.In addition, it is uncertain to give a kind of evaluation
Measure, adaptive value expanding policy is proposed based on this, for adaptive value classification provide new reference.With congenic method ratio
Compared with design result of the invention substantially takes advantage.
The present invention is divided into two large divisions.Part I is man-machine interactive unit.It is complete using friendly man-machine interactive platform
The design information of wine pot design is submitted to system into designer, i.e., determines designer by being given a mark to the evaluation for spilling kettle outward appearance
Preference and design direction.Part II is evolution unit.Specifically include：First, evolutionary optimization algorithm is set using wine pot
The uncertainty of every money product evaluation of meter is used as adaptive value Type division foundation, it is ensured that it is reasonable that wine pot design evaluatio value is classified
Property；Secondly, according to the design behavior of designer, single value type sharp interval number of the system to product Design modelling evaluation of estimate
Value Types build corresponding mathematics model respectively, improve the accuracy evaluated；Finally taken not for different types of Design modelling
Same individual evolution strategy, completes the Automated Design to wine pot outward appearance.
Advantages and positive effects of the present invention are：
1. effectively reducing the operating burden of designer, designer need to only evaluate a small amount of product style roughly, be
System is automatically performed adaptive value amendment on backstage；
2. improve designing quality, the amendment by algorithm to evaluation result, can while the burden of people is not increased,
Effective evaluation is carried out to individual；
3. improving design efficiency, polytype evaluation result participates in optimization jointly, more meets the design of designer
Behavior, optimization efficiency is higher than single type evaluation result.
Brief description of the drawings
Fig. 1 interactive evolution optimization method overview flow charts proposed by the present invention for wine pot appearance design；
The wine pot appearance design system interface figure that Fig. 2 is developed according to institute's extracting method of the present invention；
The evolutionary generation that Fig. 3 present invention is calculated with the championship that T-IGA roulettes method, IGA-IIF probability are dominant is compared；
The satisfactory solution number for the tournament algorithm that Fig. 4 present invention is dominant with T-IGA roulettes method, IGA-IIF probability is compared；
Embodiment
Present invention implementation is further described below, following examples are descriptive, are not limited, it is impossible to
Protection scope of the present invention is limited with this.
It is a kind of based on the portable wine pot design method for mixing type adaptive value interactive genetic algorithm, method flow such as Fig. 1
It is shown, it is as follows the step of this method：
System is initialized when step 1. design starts, that is, sets the evolution of evolutionary optimization on behalf of 0.Designer sets
Genetic algorithm parameter, such as intersection, mutation probability.System can be according to wine pot Hu Kou (band pot lid) and the two-part binary system of bottle body
Coding, reads in the wine pot structure model of 3ds forms from material database at random, using OpenGL completions are to the textures of model and show
Show, obtain a complete wine pot individual (sample).The process is repeated until initial Advanced group species are presented, i.e., 8 wine pots are initial
Design sample.Design system interface is as shown in Fig. 2 the slider bar under wherein each sample (individual) is given a mark for designer and evaluated
Use, the display numerical value of slider bar is the individual adaptive value, and marking scope is 1-100.
Step 2. user presses personal preference and each wine pot sample design marking is evaluated, and determines the adaptive value of each money product；
Step 3. product sample evaluates the measurement of uncertainty；
The t of portable wine pot evolutionary optimization design is evaluated individual (product sample) for i-th in Advanced group species x (t)
It is expressed as xi(t), i=1,2 ..., N, N represent all wine pot Design modelling numbers of samples (population scale), xi(t) adaptive value
It is expressed as f (xi(t)), xi(t)∈x(t).The sequence of values that then sample evaluation of estimate in wine pot is constituted is expressed as f (x (t))=(f (x1
(t)), f (x2(t)) ..., f (xN(t)))。
According to dyadic ordering principle, if by f (xi(t) uncertainty) is expressed as θ (xi(t)), then have
In formula, min (f (xi-1(t)), f (xi(t) f (x)) are representedi-1(t)), f (xi(t) smaller value in), max (f (xi-1
(t)), f (xi(t) f (x)) are representedi-1(t)), f (xi(t) higher value in).
(1) meaning of formula is：At portable wine pot style Evolutionary Design initial stage, obscured because people has to the preference of product
Property, so the degree of awareness of the sample style presented to system is than relatively low, widely different is evaluated to individual of sample, evaluation it is not true
It is qualitative larger, θ (xi(t) it is) also larger.With the continuous evolution of style sample population, wine pot style difference is gradually reduced, and is adapted to
Value reaches unanimity, and the uncertainty that designer evaluates accordingly diminishes.
The determination of step 4. sample adaptive value Type division threshold value；
It can be determined to evaluate uncertainty according to (1) formula, then had
(2) meaning of formula is：Designer evaluates uncertainty to the sample in same evolution generation and believed less than individual fitness
The maximum difference of breath.I.e. in each generation of evolving is evaluated, designer's design behavior follows dyadic ordering principle, and preference is to adapting to
The influence of value is mainly reflected in the evaluation of adjacent wine pot sample.
The evaluation of estimate of sample is divided according to (2) formula：Evaluation initial stage, it is larger that sample evaluates uncertainty, adaptive value
Show as interval numeric type；With going deep into for evaluation, cognition of the designer to environment is gradually clear, sample evaluation it is uncertain compared with
Small, adaptive value shows as single numeric type.
The interval extension of step 5. adaptive value；
Uncertainty larger situation is evaluated for sample, and the single numerical value that designer evaluates can not reflected appraisal comprehensively
Objectivity, now needs to be expanded to the larger interval numerical value of information capacity.Define δ (xi(t)) it is individual single adaptive value f
(xi(t) interval adaptive value f ' (x) are extended toi(t) interval radius).Because sample evaluates uncertainty θ (xi(t)) reflect
The uncertainty of evaluation, so the present invention is in θ (xi) and δ (x (t)i(t) with functional relation δ=g (θ) mappings between), function is intended
Close such as following formula：
K in formula, λ are adjustment factor, can be according to different design environment values.
So, by single evaluation value f (xi(t) interval numerical value) is expanded into, is expressed as follows：
In formula,It is the lower limit of interval numerical value,It is the upper limit of interval numerical value.
Further interval adaptive value is estimated, made
In formula, θ represents the point estimate to designer's satisfaction, and m represents the darkness of point estimation, and m is smaller, estimation
Hold bigger.M=0 means to be absolutely sure to satisfaction.
The foundation of the single numeric type adaptive value Grey Markov chain predicting model of step 6.；
When evaluation uncertainty is smaller, adaptive value shows as single numerical value.Now, wine pot design process is deep
Enter, wine pot difference in appearance is smaller, designer can produce fatigue.In order to further reduce the not true of designer's subjective assessment
It is qualitative, now it is applicable grey model and adaptive value is modeled, and to adaptive value amendment.
6.1. the foundation of grey model
In the present invention, the evaluation of estimate f (x of wine pot samplei(t) original series f) is constituted(0)(xi(t))=(f(0)(x1
(t)), f(0)(x2(t)) ..., f(0)(xN(t))).In each generation of evolving, is interior, the advanced row ash generation sequence of evaluation value sequence of wine pot sample
The conversion of row and sequence of average, grey formation sequence is expressed as f(1)(xi(t))=AGOf(0)(xi(t)), sequence of average is represented
For F(1)(xi(t))=MEANf(1)(xi(t)), then evolution individual fitness ash Verhulst model GMs (1,1, V) are built it is：
f(0)(xi(t))+aF(1)(xi(t))=b (F(1)(xi(t)))2 (7)
GM (1,1, V) albefaction response type is
In formulaAs wine pot style individual of sample xi+1(t) evaluation of estimate predicted value；A, b are Primary parameter.
GM (1,1, V) secondary parameters bag is expressed as follows：
Formula (10)-(14) are intermediate parameters, and the Primary parameter of grey model GM (1,1, V) can be tried to achieve by these intermediate parameters
(a, b).
6.2. individual fitness grey prediction
Because evolution ideal adaptation value sequence is the result of various factors effect under preference environment, it can be rolled by grey model
The preference distribution of dynamic inspection predictive designs personnel.The rolling residual epsilon (i+1) of wine pot sample evaluation of estimate is：
According to residual error is rolled, wine pot individual of sample x can be obtainedi(t) adaptive value confidence level pr(xi(t)) it is：
pr(xi(t))=and [100- | ε (i) |] % (18)
6.3. individual fitness amendment
The evolution individual fitness after evaluation is modified by adaptive value confidence level：
f′(xi(t))=pr(xi(t))·f(xi(t)) (19)
In formula：f′(xi(t) it is) the individual x that evolvesi(t) revised adaptive value, revised adaptive value is uncertain will drop
It is low, follow-up genetic manipulation is participated in, the deviation of optimum results can be reduced.
Step 7. genetic manipulation is made up of selection, intersection and mutation operation.Interval adaptive value for being extended to interval number,
Can be dominant carry out individual choice by interval；, can be by for the revised single numerical value adaptive value by grey model prediction
Roulette method carries out individual choice.Two kinds of selection mechanisms exist simultaneously in the present invention, are the outstanding features of the present invention.
After step 8. selection operation, generation population of new generation.If designer expires to the wine pot style sample of new population
Meaning, then preserve optimization design scheme, complete design.Otherwise, algorithm jump procedure 2, designer clicks on " next generation " evolution and pressed
Button, continues to give a mark to wine pot sample and evaluates.In whole evolutionary process, if designer to current wine pot scheme all the time not
It is enough satisfied, wine pot population can be reinitialized, starts new evolution.Designer is before Evolutionary Design terminates each time, statistics
The evolutionary generation number of this design, statistical result is as shown in Figure 3；In addition, terminating in each evolution generation marking evaluation
Afterwards, count this evaluation is satisfied with number of samples, is satisfied with sample and refers to perfect number adaptive value highest and secondary high wine pot in per generation
Individual, statistical result is as shown in Figure 4.
The comparison of the algorithm and current algorithm
The current existing algorithm applied to product design mainly has traditional interactive genetic algorithm (T-IGA) and is based on
The interval adaptive value interactive genetic algorithm (IGA-IIF) that probability is dominant.The present invention is from evolutionary generation, satisfactory solution number and takes
Algorithm performance is weighed Deng three aspects.
The evolutionary generation statistics of three kinds of methods is as shown in Figure 3.It can be seen that, evolutionary generation of the invention is minimum, and explanation is set
The operating burden of meter personnel is minimum.The statistical conditions that algorithm obtains satisfactory solution are as shown in Figure 4, it can be seen that what the present invention was obtained
Satisfactory solution number at most, illustrates the optimization quality highest of the present invention.
Can be seen that the present invention with reference to Fig. 3 and Fig. 4 for interior can obtain most satisfactory solution numbers in minimum evolution,
This increase algorithm the convergence speed, it is shown that good evolutionary optimization ability.
Finally, the time-consuming situation of statistic algorithm is as shown in the table.Because the evolutionary generation of the present invention is few, so experiment every time
It is time-consuming also fewer, contrast other two kinds of algorithms, the time-consuming only legacy interactive genetic algorithm of the present invention it is time-consuming about one
Half.Compared with IGA-IIF, operational ton of the present invention is greatly reduced, and can obtain comparison individual to individual evaluation exact numerical enters
Row interval assignment evaluates more preferable effect.And time-consuming reduce means to shorten the operating time of people, effectively reduce and set naturally
The operating burden of meter personnel.
Claims (2)
1. a kind of evolution optimization method designed for portable wine pot, it is characterized in that：Using the friendship for mixing type individual fitness
Mutual formula genetic algorithm is as optimized algorithm, and the optimized algorithm is divided into two parts, and Part I is man-machine interactive unit, utilizes friend
Good man-machine interactive platform, extracts the design information that designer submits wine pot design to system, by commenting wine pot outward appearance
Valency marking determines the preference and design direction of designer；Part II is evolution unit, first, evolutionary optimization algorithm profit
The uncertainty of the every money product evaluation designed with wine pot is as individual fitness Type division foundation, and individual fitness has simultaneously
There are interval adaptive value and single adaptive value form：Interval adaptive value is formed by the extension of single adaptive value, and expansion radius is：
In formula, δ (xi(t) it is) interval adaptive value expansion radius, θ (xi(t) uncertainty, K) are evaluated for sample, λ is for regulation
Number, can according to different design environment values,
Single adaptive value is characterized in set up Grey Markov chain predicting model：
In formula,As wine pot style individual of sample xi+1(t) adaptive value predicted value；A, b are Primary parameter,
Ensure the reasonability of wine pot design adaptive value classification, secondly, according to the design behavior of designer, system is to product style
The single adaptation Value Types of design and the interval Value Types that adapt to build corresponding mathematics model respectively, improve the accuracy evaluated；Most
Take different evolution strategies for the ideal adaptation Value Types of different Design modellings afterwards, complete to portable wine pot outward appearance from
Dynamic design.
2. the evolution optimization method according to claim 1 designed for portable wine pot, it is characterized in that：The evaluation is not
Degree of certainty is
In formula, θ (xi(t)) represent to evaluate uncertainty, min (f (xi-1(t)), f (xi(t) wine pot sample x)) is representedi-1(t) and
xi(t) adaptive value f (xi-1(t)), f (xi(t) smaller value in), max (f (xi-1(t)), f (xi(t) f (x)) are representedi-1
(t)), f (xi(t) higher value in).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410538133.4A CN104408281B (en) | 2014-10-14 | 2014-10-14 | It is a kind of to mix type interactive evolution optimization method for what portable wine pot was designed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410538133.4A CN104408281B (en) | 2014-10-14 | 2014-10-14 | It is a kind of to mix type interactive evolution optimization method for what portable wine pot was designed |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104408281A CN104408281A (en) | 2015-03-11 |
| CN104408281B true CN104408281B (en) | 2017-09-26 |
Family
ID=52645912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410538133.4A Expired - Fee Related CN104408281B (en) | 2014-10-14 | 2014-10-14 | It is a kind of to mix type interactive evolution optimization method for what portable wine pot was designed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104408281B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097418A (en) * | 2016-06-14 | 2016-11-09 | 江苏师范大学 | Cartoon character face verification method for designing based on Interactive evolutionary algorithm |
| CN106528964A (en) * | 2016-10-21 | 2017-03-22 | 浙江大学城市学院 | User preference oriented intelligent design method for beverage bottle product |
| CN107194073B (en) * | 2017-05-24 | 2020-08-28 | 郑州航空工业管理学院 | Fuzzy adaptive value interactive evolution optimization method for indoor wall clock design |
| CN107463309B (en) * | 2017-08-21 | 2020-12-25 | 郑州航空工业管理学院 | Entropy maximization criterion interactive evolution optimization method for wallpaper design |
| CN109544300A (en) * | 2018-11-27 | 2019-03-29 | 景德镇陶瓷大学 | A kind of design of ceramic products system and method based on interactive genetic algorithm |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7020588B2 (en) * | 2000-06-02 | 2006-03-28 | Sumitomo Chemical Company, Limited | Design variable optimization system and design variable optimization method |
| CN102298788A (en) * | 2011-08-12 | 2011-12-28 | 山东师范大学 | Interactive cartoon design realization method based on multi-target evaluation |
| CN102339473A (en) * | 2010-07-22 | 2012-02-01 | 山东师范大学 | Genetic algorithm-based method for design of cartoon model |
| CN103984721A (en) * | 2014-05-13 | 2014-08-13 | 中国矿业大学 | Personalized book searching method based on interactive evolutionary optimization |
-
2014
- 2014-10-14 CN CN201410538133.4A patent/CN104408281B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7020588B2 (en) * | 2000-06-02 | 2006-03-28 | Sumitomo Chemical Company, Limited | Design variable optimization system and design variable optimization method |
| CN102339473A (en) * | 2010-07-22 | 2012-02-01 | 山东师范大学 | Genetic algorithm-based method for design of cartoon model |
| CN102298788A (en) * | 2011-08-12 | 2011-12-28 | 山东师范大学 | Interactive cartoon design realization method based on multi-target evaluation |
| CN103984721A (en) * | 2014-05-13 | 2014-08-13 | 中国矿业大学 | Personalized book searching method based on interactive evolutionary optimization |
Non-Patent Citations (7)
| Title |
|---|
| adaptive interactive genetic algotithms with individual’s interval fitness;Dunwei Dong等;《progress in natural science》;20080128;第18卷(第3期);第359-365页 * |
| interactive genetic algotithms with individual’s fuzzy and stochastic fitness;Sun Xiaoyan等;《Chinese journal of electronics>;20101030;第18卷(第4期);第619-624页 * |
| surrogate model-assisted interactive genetic algorithms with individual’s fuzzy and stochasitc fitness;Xiaoyan Sun等;《journal of control theory and applications》;20100811;第8卷(第2期);摘要、第2.1节、第6.2节，图4 * |
| 基于区间适应值灰度的交互式遗传算法;郭广颂等;《计算机工程》;20090720;第35卷(第14期);第233-235页 * |
| 基于离散适应值灰度的交互式遗传算法;郭广颂等;《计算机工程与应用》;20100201;第46卷(第24期);第225-228页 * |
| 基于进化个体适应值灰度的自适应交互式遗传算法;郭广颂等;《计算机应用》;20081001;第28卷(第10期);第2.2节、第3节 * |
| 灰色verhulst模型的优化及其应用;何霞等;《重庆科技学院学报（自然科学版）》;20120615;第14卷(第3期);第1节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104408281A (en) | 2015-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104408281B (en) | It is a kind of to mix type interactive evolution optimization method for what portable wine pot was designed | |
| Kelly et al. | Integrated assessment models for climate change control | |
| CN109635291A (en) | A kind of recommended method of fusion score information and item contents based on coorinated training | |
| Hsiao et al. | Application of grey relational analysis to decision-making during product development | |
| CN106919951A (en) | A kind of Weakly supervised bilinearity deep learning method merged with vision based on click | |
| Dou et al. | A method for product personalized design based on prospect theory improved with interval reference | |
| CN106529503A (en) | Method for recognizing face emotion by using integrated convolutional neural network | |
| CN106897911A (en) | A kind of self adaptation personalized recommendation method based on user and article | |
| CN105740984A (en) | Product concept performance evaluation method based on performance prediction | |
| CN112000772A (en) | Sentence-to-semantic matching method based on semantic feature cube and oriented to intelligent question and answer | |
| CN104239496A (en) | Collaborative filtering method based on integration of fuzzy weight similarity measurement and clustering | |
| CN107122890A (en) | Personal credit score optimizing evaluation method | |
| CN106202377A (en) | A kind of online collaborative sort method based on stochastic gradient descent | |
| CN106484733A (en) | News clue personalized push method and system | |
| CN108491686B (en) | Bidirectional XGboost-based gene regulation and control network construction method | |
| Blasi | Scheduling food industry system using fuzzy logic | |
| CN105354644A (en) | Financial time series prediction method based on integrated empirical mode decomposition and 1-norm support vector machine quantile regression | |
| Brown | Early building design using multi-objective data approaches | |
| Romero et al. | Sophistication, productivity and trade: a sectoral investigation | |
| CN110739045B (en) | Interactive evolution optimization method for personalized recipe design | |
| CN110956528B (en) | Recommendation method and system for e-commerce platform | |
| CN107194073A (en) | The fuzzy fitness value interactive evolution optimization method designed for indoor wall clock | |
| Chen et al. | The Application of Adaptive Generalized NGBM (1, 1) To Sales Forecasting: A Case Study of an Underwear Shop. | |
| CN110335680A (en) | A kind of national physique health analysis method based on ɑ-RIPPER classifier | |
| CN106709510A (en) | Gaussian mixture model searching method based on immune clonal selection algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170926 Termination date: 20181014 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |