CN107220435A - The product form gene network model construction method of image driving - Google Patents
The product form gene network model construction method of image driving Download PDFInfo
- Publication number
- CN107220435A CN107220435A CN201710381753.5A CN201710381753A CN107220435A CN 107220435 A CN107220435 A CN 107220435A CN 201710381753 A CN201710381753 A CN 201710381753A CN 107220435 A CN107220435 A CN 107220435A
- Authority
- CN
- China
- Prior art keywords
- gene
- product form
- image
- mrow
- network
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of product form gene network model construction method of image driving, the technical problem for solving existing product design method poor practicability.Technical scheme is to annotate product gene network using the scales-free network based on power-law distribution, image target gene concept is introduced from the angle of bioinformatics, analyze mechanism of action of the image target gene in product form structure, build the product form idiotype network K FGN driven by the image of some image target gene interactions, understand the topological structure of product form idiotype network, recognize and predict that the Hub genes in the product form idiotype network that image drives are combined with preferred gene, concrete proposals are provided for follow-up Design Stage, practicality is good.
Description
Technical field
The present invention relates to a kind of product design method, more particularly to a kind of product form gene network model of image driving
Construction method.
Background technology
Document " product gene regulated and control network model and its auxiliary to design process, computer integrated manufacturing system,
2013, Vol19 (7), p1463-1471 " discloses a kind of product design method based on complex network.This method is based on graph theory
Set up it is a kind of describe the mapping relations model, borrow gene regulatory network part concept, using design considerations as node, with will
Dependency relation between element is side, sets up the gene regulatory network model of product and draws its Gene network, passes through gene
Regulated and control network figure is classified to numerous design considerations in product, and recognizes its node type and node group, is used as precipitation
Knowledge supplies designer's planning and designing activity, and products scheme optimization design prototype system is developed based on interactive genetic algorithm, and
Optimize program using the Knowledge Discovery housekeeping arrangement of gene regulatory network, work out Optimizing Search strategy, have necessarily to design process
Booster action.Document methods described considers slightly to be short of for the complexity of design problem, is set using gene regulatory network pair
Meter element, which is modeled, can not comprehensively describe the correlation between each design element.
The content of the invention
In order to overcome the shortcomings of existing product design method poor practicability, the present invention provides a kind of product shape of image driving
State gene network model construction method.This method annotates product gene network using the scales-free network based on power-law distribution,
Image target gene concept, effect machine of the analysis image target gene in product form structure are introduced from the angle of bioinformatics
System, builds the product form idiotype network K-FGN driven by the image of some image target gene interactions, understands product form
The topological structure of idiotype network, recognizes and predicts the Hub genes and preferred gene in the product form idiotype network that image drives
Combination, provides concrete proposals, practicality is good for follow-up Design Stage.
The technical solution adopted for the present invention to solve the technical problems：A kind of product form idiotype network mould of image driving
Type construction method, is characterized in comprising the following steps：
Step 1: gene code is carried out to target morphology using follow-on curve controlled method, using characteristic synthetic
Canny operators carry out morphological feature edge extracting to target product, and this step is based on programming realization in Matlab, and uses GUI
Tool making view plug-ins.
Step 2: being encoded using 3 power Beziers to product form gene, product form characteristic curve is split
If the set collectively constituted for main section, wherein every curved section L is by two endpoint curve P (Pi, i=1,2 ..., n) with one
Individual anchor point C (Ci, i=1,2 ..., n) express：
l(Li)=(Pi,Pj,Ci), j=i+1,1≤i≤n (1)
The mathematic(al) representation of 3 power Beziers is：
B (t)=P0(1-t)3+3P1t(1-t)2+3P2 2t(1-t)+P3 3t,t∈[0,1] (2)
In formula, P0, P1, P2, P3It is respectively defined as 4 nodes of 3 power Beziers.By the way that product gene is carried out
Form fitting coding, obtains the function expression of product form gene.
Step 3: product form idiotype network is abstracted into a figure M, wherein, each node viRepresent a product
The interaction relationship e between line representative products configuration gene between configuration gene, nodei, i.e. ei=(vi,vi+1) represent
Node viWith vi+1Between interaction.Remember any kansei image D={ d1,d2,d3,...,dk, with any kansei image D phases
The product form idiotype network of pass is a M subgraph, is designated as Gd(Vd,Vd).Wherein,It is GdIn any node, represent appoint
One product form gene related to kansei image of meaning；It is figure GdIn any a line, represent nodeWithBetween interaction relationship.
Step 4: according to specific kansei image D, analysis is investigated with reference to scaling method using experiment, its fuzzy meaning is found out
As gene sets Geneset={ g1,g2,g3,...,gm}；Specific method is that organizing user enters to several target product forms
Row image is investigated, according to the corresponding product form of some specific kansei images of Weight Acquisition, and is passed through to decompose and obtained specific perception
The corresponding product form gene of image.Find out each element g in GenesetiNeighborhood G in product form structurei=
{gi1,gi2,gi3,...,gik}.Specific algorithm is, for each gi, initialize gi=gi0.For product form idiotype network
Scheme any a line e in Mi=(vi,vi+1), if gi=vi, then Gi=Gi∪{vi+1}；If gi=vi+1, then Gi=Gi∪
{vi+1, otherwise GiIt is constant, so repeat, until all sides in M all check and finished.Calculate the possible gene sets of image D
Vd'.Specific algorithm is, Vd'=Geneset ∪ G1∪G2∪G3∪...∪Gn。
Step 5: building the line set E of the related product form idiotype networks of image Dd.Specific algorithm is, initial Ed=
e0, for any a line e in product form idiotype network figure Mi=(vi,vi+1), check viWith vi+1Whether V is belonged to simultaneouslyd,
If belonged to simultaneously, Ed=Ed∪{ei}；If do not met, EdIt is constant.So repeat, until all sides in M are all checked
Finish.
Step 6: using the degree in complex network and degree distribution as analysis object, excavating and contacting close in gene the most
Hub nodes.Each node passes through other node phases of the line and several between node in product form idiotype network
Connection, the bar number of this node line had both been node viDegree, be designated as ki, the distribution situation distribution function P of the degree of nodes
(k) describe, P (k) represents the probability when degree of a node selected at random is exactly K.Accumulation degree in calculating network model
Distribution function：
If accumulated degree distribution function meets the power-law distribution that power exponent is γ -1, i.e.,：
Then degree distribution meets power-law distribution feature, that is, the K-FGN networks built are scales-free network.It is wherein big in network
The degree of part of nodes is relatively low, but there is a small amount of degree very high Hub nodes, i.e. image target gene relatively.
Step 7: carrying out the preferred of target gene group as analysis object using the cluster coefficient in network topology structure.Collection
Also the perfect degree of the ratio of adjoint point, i.e. clique's structure each other between adjoint point of group's coefficient to describe nodes.
Step 8: to K-FGN networks carry out topological analysis, it is necessary in statistics network each node degree and CCiValue.
Thus, image degree of correlation highest image target gene and target gene group are determined, visual set is provided for subsequent product design
Count auxiliary information.
The beneficial effects of the invention are as follows：This method annotates product gene net using the scales-free network based on power-law distribution
Network, image target gene concept, effect of the analysis image target gene in product form structure are introduced from the angle of bioinformatics
Mechanism, builds the product form idiotype network K-FGN driven by the image of some image target gene interactions, understands product shape
The topological structure of state idiotype network, recognizes and predicts the Hub genes and preferred base in the product form idiotype network that image drives
Because of combination, concrete proposals are provided for follow-up Design Stage, practicality is good.
The present invention is elaborated with reference to the accompanying drawings and detailed description.
Brief description of the drawings
Fig. 1 is the flow chart of the product form gene network model construction method of image driving of the present invention.
Fig. 2 is the configuration gene network of automobile side profile in the inventive method.
Fig. 3 is seven grades of scales of Likert of " gracefulness " index in the inventive method.
Fig. 4 is " gracefulness " image cognitive experiment scale in the inventive method.
Fig. 5 is the K-FGN network models of automobile side profile in the inventive method.
Fig. 6 is the accumulated degree distribution curve of network in the inventive method.
Fig. 7 is automobile side outline shape composition curve and extreme coordinates in the inventive method.
Fig. 8 is Optimization Solution precedence diagram in the inventive method.
Fig. 9 is Optimizing Flow and result figure in the inventive method.
Embodiment
Reference picture 1-9.The product form gene network model construction method of image driving of the present invention is comprised the following steps that：
Step 1: using the broadside lines of three railway carriage or compartment automobiles as instance objects, verifying that the technology of K-FGN network models is real
Now with application.The example has the advantage that：1. for general user, the brand identification of automobile side contour line is relatively low,
The problem of user gets sth into one's head according to brand image can largely be avoided；2. modality curves are more free, it is ensured that sample
Diversity, connective stronger between parameters, single parameter does not have characteristic；3. automobile side contour line is covered
Design considerations is more, belongs to typical somewhat complex design problem.
Step 2: linked up by early stage and Automobile Design teacher, it is determined that by automobile side Contour segmentation into interconnection
21 line segments, wherein every curved section can be by two endpoint curve P (Pi, i=1,2 ..., n) with an anchor point C (Ci, i=1,
2 ..., n) accurate expression：
l(Li)=(Pi,Pj,Ci), j=i+1,1≤i≤n (1)
The mathematic(al) representation of 3 power Beziers is：
B (t)=P0(1-t)3+3P1t(1-t)2+3P2 2t(1-t)+P3 3t,t∈[0,1] (2)
Thus 21 configuration gene parameters using define its morphological feature, including 16 outline parameters and
5 Internal periphery parameters.
Step 3: to analyze and confirming to whether there is interaction between 21 configuration gene parameters, to the sub- still work in Shanghai
Professional Automobile Design teacher of 10, industry product design Co., Ltd is investigated, and investigation uses expert graded, it is desirable to 10 automobiles
Designer scores the power of design relation between two two parameters according to the experience during Automobile Design, and score value is interval
[1-10], the two of relation between to investigation structure can obtain after statistical analysis, normalized 21 parameters with Matlab
Two weight coefficients：
The weight coefficient two-by-two of relation between 1 21 parameters of table
Weight threshold is set, Relation Parameters group of the weight more than 0.4 is filtered out, these parameters have interaction between any two
Relation：
The Relation Parameters that table 2 is filtered out
Step 4: according to the building mode of configuration gene network, the configuration gene network of above-mentioned automobile side profile is taken out
As scheming the line representative products form base between M, wherein 21 automobile form genes of the node on behalf of network, each node into one
Therefore the interaction relationship between.
Step 5: according to the automobile market feedback information in the first half of the year in 2016, selection market sales volume is preferable 15 sections medium-sized
Automobile, comprising the domestic and international different automobile vendors such as masses, BMW, benz, Honda, Toyota, Ford, lucky, sample has certain
Generality.Programing work has been carried out using Matlab gui tool, it is therefore intended that obtained with Canny operators for the case
Take the side profile feature of automobile.The automobile side contour feature that above-mentioned steps are obtained is entered with Coreldraw vectors software
Row amendment and refine, obtain 15 contour line feature samples, from carrying out case verification exemplified by " graceful " kansei image index,
Other kansei image indexs can equally apply the inventive method.
Step 6: building seven grades of scales of Likert of " gracefulness " index to users' expectation, local 4 S auto shop is visited,
15 domestic consumers are randomly selected in the customer for choosing compact car and investigation questionnaire is provided, 15 samples are given a mark, most
5 sections of higher contour line samples of score are selected afterwards as the contour line sample of " gracefulness " index.
Step 7: 10 professional Automobile Design teacher of Shanghai Ya Shang Design of Industrial Product Co., Ltd are investigated, it is desirable to
Every designer 21 configuration genes respective to 5 sections of contour line samples carry out image scoring, and 21 are calculated according to appraisal result
Configuration gene for " gracefulness " image weighted value, set weight threshold, according to weight by 21 configuration genes be divided into strong correlation,
Weak related, unrelated three types, obtain the cdna sample that " gracefulness " image is best embodied in 21 configuration genes.
Step 8: useless node 7,14,15,16,17,18,21 is rejected from idiotype network, kansei image can must be directed to
The fuzzy image gene sets Geneset of " gracefulness ".
Step 9: finding out each element g in Geneset firstiNeighborhood G in product form structurei={ gi1,
gi2,gi3,...,gik}.Specific algorithm is：For each gi, initialize gi=gi0.For in product form idiotype network figure M
Any a line ei=(vi,vi+1), if gi=vi, then Gi=Gi∪{vi+1}；If gi=vi+1, then Gi=Gi∪{vi+1, otherwise
GiIt is constant, so repeat, until all sides in M all check and finished.Calculate the possible gene sets V of image Dd'.Specific algorithm
For：Vd'=Geneset ∪ G1∪G2∪G3∪...∪Gn.Build the line set E of the related product form idiotype networks of image Dd。
Specific algorithm is：Initial Ed=e0, for any a line e in product form idiotype network figure Mi=(vi,vi+1), check vi
With vi+1Whether V is belonged to simultaneouslydIf belonged to simultaneously, Ed=Ed∪{ei}；If do not met, EdIt is constant.So repeat, directly
All sides into M, which are all checked, to be finished.Finally construct the K-FGN networks of the case.
Step 10: using the shortest path bar number in scales-free network as topological analysis object, obtaining the topology point of node
Analyse statistical form：
The topological analysis statistical form of table 3
The accumulated degree distribution curve of K-FGN networks is drawn in MATLAB.Accumulated degree distribution letter in calculating network model
Number：
If accumulated degree distribution function meets the power-law distribution that power exponent is γ -1, i.e.,：
Then degree distribution meets power-law distribution feature, that is, the K-FGN networks built are a small-sized scales-free network, can be obtained
The image target gene of the Hub nodes that a small amount of degree of distribution is higher, i.e. this research is taken, the topological structure of K-FGN networks is drawn.
Step 11: the statistics to K-FGN networks is described as follows：1. 3 image target genes are eutectoid out：L2、L5、L8；②
Separate out two more independent gene sets, respectively M1 { L2, L1, L3, L4, L12, L13 } and M2 L5, L8, L6, L9,
L19,L20,L10,L11,L17}；3. there is the target gene group N1 of two mutual relations closely in two gene sets
{ L2, L3, L4 } and N2 { L5, L8, L9, L19, L20 }；4. exist 7 with image target gene related minor gene L1,
L12,L13,L6,L10,L11,L17}；5. there are 6 independent minor genes { L7, L14, L15, L16, L18, L21 }.Separate out
The recessive information of Computer Aided Design is as follows：
(1) 1 independent image target gene (L2) surrounds moulding before representing, wherein be closely related with preceding encirclement moulding
Two sensitive genes represent bumper (L3) adjacent thereto and air-inlet grille form (L4) respectively, and these three genes constitute one
Close ternary genome, belongs to the crucial morphology factor of automobile front face, it is necessary to collaborative design；
The interrelated degree of (2) two crucial image target genes for representing bonnet radian (L5) and vehicle rear window radian (L8) compared with
Height, belongs to the crucial morphology factor on car top, it is necessary to while carry out in the lump with 3 genes (L9, L19, L20) associated therewith
Optimization design.
(3) gene (L1) and represent tailstock bottom gene (L12, L13) it is relevant with the form moulding of automobile front face, with
There is concord relation in image target gene (L2), belong to minor gene, can optionally take into consideration；In the presence of four and the moulding of car top
Form has the minor gene of certain degree of association, can optionally take into consideration；
(4) there are 6 more independent minor genes, universality is stronger in the shape-designing of automobile side profile, represent
Difference degree of 6 sections of curves in different automobiles less, can not be deeply considered in specific design.
Step 12: the initial configuration to automobile side profile is encoded, objective contour by outline collection of curves L1,
L2, L3, L4 ..., L16 } and inner profile curve set { L17, L18, L19, L20, L21 } composition.Randomly choose a automotive wheels
Wide Cx is used as initial configuration.The product form gene code method of foundation is with initial shape of 3 Bezier models to selection
State is encoded.Feature coding information is carried out to simplify processing using the aided design information of above-mentioned precipitation, first by 7 and meaning
As the related minor gene of target gene and 6 independent minor genes carry out dimension constraint, it is ensured that its shape invariance, it is not involved in
Interaction design process.Remaining 3 image target genes and 5 slave genes are placed in coordinate system, line discipline of going forward side by side constraint, limit
Its fixed excursion, obtains automobile side outline shape and constitutes curve and extreme coordinates.
Step 13: carrying out secondary development using VBA language in vector graphics software CorelDRAW X6, intelligence is built
Interaction design engine, modality curves are obtained according to preceding 15 sample statistics, limit shape reasoning rule using coordinate fine setting, scaling
Cut operation with mistake, to initial configuration optimize design.
Step 14: being solved using sequential system：3 tuples are first sought, then the second group is solved.
Man-machine interactively scoring optimization is carried out between solution procedure, the optimum after optimization proceeds next step solution,
Until 4 wheel Optimization Solutions are finished, result after optimization is finally given.
Claims (1)
1. a kind of product form gene network model construction method of image driving, it is characterised in that comprise the following steps：
Step 1: carrying out gene code to target morphology using follow-on curve controlled method, calculated using the Canny of characteristic synthetic
Son carries out morphological feature edge extracting to target product, and this step is based on programming realization in Matlab, and is made with gui tool
View plug-ins；
Step 2: being encoded using 3 power Beziers to product form gene, if product form characteristic curve is divided into
The set that main section is collectively constituted, wherein every curved section L is by two endpoint curve P (Pi, i=1,2 ..., n) with an anchor
Point C (Ci, i=1,2 ..., n) express：
l(Li)=(Pi,Pj,Ci), j=i+1,1≤i≤n (1)
The mathematic(al) representation of 3 power Beziers is：
B (t)=P0(1-t)3+3P1t(1-t)2+3P2 2t(1-t)+P3 3t,t∈[0,1] (2)
In formula, P0, P1, P2, P3It is respectively defined as 4 nodes of 3 power Beziers；By the way that product gene is carried out into form plan
Code is compiled in collaboration with, the function expression of product form gene is obtained；
Step 3: product form idiotype network is abstracted into a figure M, wherein, each node viRepresent a product form base
The interaction relationship e between line representative products configuration gene between cause, nodei, i.e. ei=(vi,vi+1) represent node vi
With vi+1Between interaction；Remember any kansei image D={ d1,d2,d3,...,dk, the production related to any kansei image D
Product configuration gene network is a M subgraph, is designated as Gd(Vd,Vd)；Wherein,It is GdIn any node, represent any one
The product form gene related to kansei image；It is figure GdIn any a line, represent nodeWithBetween
Interaction relationship；
Step 4: according to specific kansei image D, analysis is investigated with reference to scaling method using experiment, its fuzzy image base is found out
Because of set Geneset={ g1,g2,g3,...,gm}；Specific method is that organizing user is anticipated to several target product forms
As investigation, according to the corresponding product form of some specific kansei images of Weight Acquisition, and pass through to decompose and obtain specific kansei image
Corresponding product form gene；Find out each element g in GenesetiNeighborhood G in product form structurei={ gi1,
gi2,gi3,...,gik}；Specific algorithm is, for each gi, initialize gi=gi0；For in product form idiotype network figure M
Any a line ei=(vi,vi+1), if gi=vi, then Gi=Gi∪{vi+1}；If gi=vi+1, then Gi=Gi∪{vi+1, otherwise
GiIt is constant, so repeat, until all sides in M all check and finished；Calculate the possible gene sets V of image Dd'；Specific algorithm
It is, Vd'=Geneset ∪ G1∪G2∪G3∪...∪Gn；
Step 5: building the line set E of the related product form idiotype networks of image Dd；Specific algorithm is, initial Ed=e0, it is right
Any a line e in product form idiotype network figure Mi=(vi,vi+1), check viWith vi+1Whether V is belonged to simultaneouslydIf,
Belong to simultaneously, then Ed=Ed∪{ei}；If do not met, EdIt is constant；So repeat, until all sides in M are all checked out
Finish；
Step 6: excavating in gene as analysis object using the degree in complex network and degree distribution and contacting close Hub the most
Node；By the line and several between node, other nodes are connected each node in product form idiotype network,
The bar number of this node line had both been node viDegree, be designated as ki, the distribution situation of the degree of nodes retouched with distribution function P (k)
State, P (k) represents the probability when degree of a node selected at random is exactly K；Accumulated degree distribution letter in calculating network model
Number：
<mrow>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msup>
<mi>k</mi>
<mo>&prime;</mo>
</msup>
<mo>=</mo>
<mi>k</mi>
</mrow>
<mi>&infin;</mi>
</munderover>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msup>
<mi>k</mi>
<mo>&prime;</mo>
</msup>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
If accumulated degree distribution function meets the power-law distribution that power exponent is γ -1, i.e.,：
<mrow>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<mo>&Proportional;</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msup>
<mi>k</mi>
<mo>&prime;</mo>
</msup>
<mo>=</mo>
<mi>k</mi>
</mrow>
<mi>&infin;</mi>
</munderover>
<mo>&Proportional;</mo>
<msup>
<mi>k</mi>
<mrow>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mi>r</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Then degree distribution meets power-law distribution feature, that is, the K-FGN networks built are scales-free network；Major part wherein in network
The degree of node is relatively low, but there is a small amount of degree very high Hub nodes, i.e. image target gene relatively；
Step 7: carrying out the preferred of target gene group as analysis object using the cluster coefficient in network topology structure；Cluster system
Also the perfect degree of the ratio of adjoint point, i.e. clique's structure each other between adjoint point of the number to describe nodes；
Step 8: to K-FGN networks carry out topological analysis, it is necessary in statistics network each node degree and CCiValue；Thus,
Image degree of correlation highest image target gene and target gene group are determined, visual Design assistant is provided for subsequent product design
Information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710381753.5A CN107220435A (en) | 2017-05-26 | 2017-05-26 | The product form gene network model construction method of image driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710381753.5A CN107220435A (en) | 2017-05-26 | 2017-05-26 | The product form gene network model construction method of image driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107220435A true CN107220435A (en) | 2017-09-29 |
Family
ID=59945242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710381753.5A Pending CN107220435A (en) | 2017-05-26 | 2017-05-26 | The product form gene network model construction method of image driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220435A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109003142A (en) * | 2018-08-03 | 2018-12-14 | 贵州大学 | The product form gene network model construction method of multiple target driving |
| CN109919646A (en) * | 2017-12-12 | 2019-06-21 | 财团法人工业技术研究院 | Data analysis device and data analysis method |
| CN109992612A (en) * | 2019-04-19 | 2019-07-09 | 吉林大学 | A kind of development approach in fascia modeling formation elemental characteristic library |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719194A (en) * | 2009-12-03 | 2010-06-02 | 上海大学 | Artificial gene regulatory network simulation method |
-
2017
- 2017-05-26 CN CN201710381753.5A patent/CN107220435A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719194A (en) * | 2009-12-03 | 2010-06-02 | 上海大学 | Artificial gene regulatory network simulation method |
Non-Patent Citations (3)
| Title |
|---|
| CHRISTOPH MEIER 等: "Design process sequencing with competent genetic algorithms", 《JOURNAL OF MECHANICAL DESIGN》 * |
| 刘肖健 等: "产品基因调控网络模型及其对设计过程的辅助", 《计算机集成制造系统》 * |
| 李雪瑞 等: "意象驱动的产品形态基因网络模型构建与应用", 《计算机集成制造系统》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919646A (en) * | 2017-12-12 | 2019-06-21 | 财团法人工业技术研究院 | Data analysis device and data analysis method |
| CN109003142A (en) * | 2018-08-03 | 2018-12-14 | 贵州大学 | The product form gene network model construction method of multiple target driving |
| CN109003142B (en) * | 2018-08-03 | 2021-11-19 | 贵州大学 | Multi-target driven product morphological gene network model construction method |
| CN109992612A (en) * | 2019-04-19 | 2019-07-09 | 吉林大学 | A kind of development approach in fascia modeling formation elemental characteristic library |
| CN109992612B (en) * | 2019-04-19 | 2022-03-04 | 吉林大学 | Development method of automobile instrument board modeling form element feature library |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Humanlike driving: Empirical decision-making system for autonomous vehicles | |
| WO2020034632A1 (en) | Mbd-based three-dimensional process designing method and platform for typical automobile machined part | |
| AlGeddawy et al. | Optimum granularity level of modular product design architecture | |
| CN110957002B (en) | Drug target interaction relation prediction method based on synergistic matrix decomposition | |
| CN107220435A (en) | The product form gene network model construction method of image driving | |
| CN107563426A (en) | A kind of learning method of locomotive operation temporal aspect | |
| CN101576604A (en) | Method for diagnosing failures of analog circuit based on heterogeneous information fusion | |
| CN111783826B (en) | Driving style classification method based on pre-classification and ensemble learning | |
| CN108229728A (en) | A kind of recommendation method of information of freight source and a kind of computer equipment | |
| CN106845536B (en) | Parallel clustering method based on image scaling | |
| CN110866332A (en) | Complex cable assembly assembling method and system | |
| CN110991532A (en) | Scene graph generation method based on relational visual attention mechanism | |
| Liu et al. | A semantic feature model in concurrent engineering | |
| Wang et al. | Understanding v2v driving scenarios through traffic primitives | |
| CN109344498B (en) | Design implementation method of wedge module | |
| Wang et al. | Energy consumption characteristics based driving conditions construction and prediction for hybrid electric buses energy management | |
| Chen et al. | A feature-based CAD-LCA software integration approach for eco-design | |
| CN114912195B (en) | Aerodynamic sequence optimization method for commercial vehicle | |
| CN108595631A (en) | Three-dimensional CAD model bilayer search method based on Graph Spectral Theory | |
| Cong et al. | Conceptual design of a user-centric smart product-service system using self-organizing map | |
| Usama et al. | A data-driven interactive system for aerodynamic and user-centred generative vehicle design | |
| Zhang et al. | Research on flexible transfer line schematic design using hierarchical process planning | |
| Hua et al. | GA-based synthesis approach for machining scheme selection and operation sequencing optimization for prismatic parts | |
| CN115374498B (en) | Road scene reconstruction method and system considering road attribute characteristic parameters | |
| Fanoiki et al. | Case-based reasoning retrieval and reuse using case resemblance hypergraphs |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170929 |
|
| WD01 | Invention patent application deemed withdrawn after publication |