CN108388676A - A kind of mold data matching process, apparatus and system based on simulated annealing - Google Patents
A kind of mold data matching process, apparatus and system based on simulated annealing Download PDFInfo
- Publication number
- CN108388676A CN108388676A CN201810258231.0A CN201810258231A CN108388676A CN 108388676 A CN108388676 A CN 108388676A CN 201810258231 A CN201810258231 A CN 201810258231A CN 108388676 A CN108388676 A CN 108388676A
- Authority
- CN
- China
- Prior art keywords
- mold data
- history
- characteristic information
- mold
- data
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of mold data matching process, including:Extract the characteristic information of target mold data;Similarity mode is carried out using the characteristic information of each history mold data in characteristic information and knowledge base, obtains the similarity of each history mold data and target mold data;Using similarity be more than predetermined threshold history mold data as with the matched history mold data of target mold data.It can be seen that, this programme carries out similarity calculation by the characteristic information of target mold data and the characteristic information of history mold data, history mold data case similar with target mold data can be searched out from knowledge base, to provide most similar case data for mold design, design considerations is provided for mold design, the accuracy and efficiency for promoting mold to redesign;The invention also discloses a kind of mold data coalignment, equipment, system and computer readable storage mediums, equally can realize above-mentioned technique effect.
Description
Technical field
The present invention relates to more specifically to a kind of mold data matching process, dress based on simulated annealing
It sets, equipment, system and computer readable storage medium.
Background technology
Die industry is typical single product custom model, the spy with labyrinth and difference in height engineering demand
Point.Due to the complexity of mold parting surface, the diversification of structure and condition of molding, even if following all mold design and manufacture
Principle, when beginning, are still difficult to ensure successful die test.Further, since the characteristics of irreplaceability of critical component, height
The knowledge experience for relying on engineer needs to formulate solution, ensures the accuracy and rapidity of entire design activity.In turn,
Since die industry has the features such as precision is high, efficient, durability is high, it is widely used to various fields.Molded part accounts for electricity
Brain, household electrical appliance, medical instrument, 70% or more of the consumer goods such as automobile.With flourishing for die industry, cause
Time of product development is shortened in extensive concern, reinforces enterprise competitiveness.However, due to design mistake and complicated manufacturing process,
Enterprise be frequently necessary to redesign and change mold, cause mold manufacturing and molding product it is bad, to waste time, money and
Manpower.The experience dependence of mold design tool is high, and has the characteristics that directly related with die manufacture, and manufacturer is often with tool
Body reference record case provides huge potential value to improve design activity.
Therefore, how for mold design most similar case data is provided, provides design considerations for mold design, is ability
Field technique personnel's problem to be solved.
Invention content
The mold data matching process that the purpose of the present invention is to provide a kind of based on simulated annealing, device, equipment,
System and computer readable storage medium provide design to provide most similar case data for mold design for mold design
Foundation.
To achieve the above object, an embodiment of the present invention provides following technical solutions:
A kind of mold data matching process, including:
Extract the characteristic information of target mold data;
Similarity mode is carried out using the characteristic information of each history mold data in the characteristic information and knowledge base, is obtained
To the similarity of each history mold data and the target mold data;
Judge whether that similarity is more than the history mold data of predetermined threshold;
If in the presence of the history mold data that similarity is more than to predetermined threshold is matched as with the target mold data
History mold data.
Wherein, the generation method of the knowledge base includes:
Extract the characteristic information of history mold data;
Using latent semantic analysis technology, and characteristic information corresponding with each history mold data, know described in structure
Know library.
Wherein, described similar to each characteristic information progress of history mold data in knowledge base using the characteristic information
Degree matching, obtains the similarity of each history mold data and the target mold data, including:
By the characteristic information of each history mold data in simulated annealing calculation knowledge library, with the target mold
The similarity of the corresponding characteristic information of data;
Using the characteristic information of each history mold data, characteristic information corresponding with the target mold data it is similar
Degree, and each selection weight of characteristic information, calculate the similarity of each history mold data and the target mold data.
A kind of mold data coalignment, including:
Characteristic extracting module, the characteristic information for extracting target mold data;
Similarity calculation module, for being believed using the characteristic information and the feature of each history mold data in knowledge base
Breath carries out similarity mode, obtains the similarity of each history mold data and the target mold data;
Judgment module, for judging whether that similarity is more than the history mold data of predetermined threshold;
Module is chosen, for there are when the history mold data that similarity is more than predetermined threshold, similarity being more than predetermined
The history mold data of threshold value as with the matched history mold data of the target mold data.
Wherein, further include construction of knowledge base module;The construction of knowledge base module includes:
Feature extraction unit, the characteristic information for extracting history mold data;
Construction unit, for utilizing latent semantic analysis technology, and feature corresponding with each history mold data to believe
Breath, builds the knowledge base.
Wherein, the similarity calculation module includes:
First computing unit, for the feature letter by each history mold data in simulated annealing calculation knowledge library
Breath, the similarity of characteristic information corresponding with the target mold data;
Second computing unit, for the characteristic information using each history mold data, with the target mold data pair
The similarity for the characteristic information answered, and each selection weight of characteristic information, calculate each history mold data and the mesh
Mark the similarity of mold data.
A kind of mold data matching unit, including:
Memory, for storing computer program;
Processor is realized when for executing the computer program such as the step of above-mentioned mold data matching process.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
It is realized such as the step of above-mentioned mold data matching process when computer program is executed by processor.
A kind of mold data matching system, including:The mold data coalignment of input layer, above-mentioned any one, and
Output layer;
The input layer is input to mold data for obtaining target mold data, and by the target mold data
With device;
The output layer, for the selection of output mask data matching device and the matched history of target mold data
Mold data.
By above scheme it is found that a kind of mold data matching process provided in an embodiment of the present invention, including:Extract target
The characteristic information of mold data;Phase is carried out using the characteristic information and the characteristic information of each history mold data in knowledge base
It is matched like degree, obtains the similarity of each history mold data and the target mold data;Judge whether that similarity is big
In the history mold data of predetermined threshold, and if it exists, then using similarity be more than predetermined threshold history mold data as with institute
State the matched history mold data of target mold data.As it can be seen that characteristic information and history that this programme passes through target mold data
The characteristic information of mold data carries out similarity calculation, and history similar with target mold data can be searched out from knowledge base
Mold data case provides design considerations for mold design, promotes mould to provide most similar case data for mold design
Has the accuracy and efficiency redesigned;The invention also discloses a kind of mold data coalignment, equipment and computer-readable
Storage medium equally can realize above-mentioned technique effect.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of mold data matching process flow signal based on simulated annealing disclosed by the embodiments of the present invention
Figure;
Fig. 2 is a kind of mold data coalignment structural representation based on simulated annealing disclosed by the embodiments of the present invention
Figure;
Fig. 3 is a kind of mold data matching system structural representation based on simulated annealing disclosed by the embodiments of the present invention
Figure.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
The mold data matching process that the embodiment of the invention discloses a kind of based on simulated annealing device, equipment, is
System and computer readable storage medium, to provide most similar case data for mold design, for mold design provide design according to
According to.
Referring to Fig. 1, a kind of mold data matching process provided in an embodiment of the present invention, including:
S101, the characteristic information for extracting target mold data;
Specifically, in the present embodiment, target mold data is the design problem of input system, asked with design for each
The reason of topic, it includes four representative aspects, including name of product, existing issue, problem and auxiliary information.Namely
It says, the reason of characteristic information of target mold data includes at least name of product, existing issue, problem and auxiliary information etc..
S102, similarity is carried out using the characteristic information of each history mold data in the characteristic information and knowledge base
Match, obtains the similarity of each history mold data and the target mold data;
Knowledge base in this programme was generated in the study stage, and specifically, the generation method of knowledge base includes:Extraction
The characteristic information of history mold data;Using latent semantic analysis technology, and feature corresponding with each history mold data
Information builds the knowledge base.
It is understood that learning the content in the knowledge base that the stage is established, it is easy for the inspection of subsequent application stage
The most matched data of design problem with input are retrieved during rope.Specifically, the structure of knowledge base is by history
Change feature extraction and the latent semantic analysis of mould case to complete.
Wherein, feature extraction is for extracting the existing important feature changed in mould case.For example, there are one redesigns
Case, wherein including following information:" there is slight edge (injection-moulded plastic mould product) on glove box separation surface.The reason is that point
Precision from face is not good enough.Solution is grinding die joint to improve the precision of die joint.Then obtained after feature extraction
Each characteristic information be:The information provided is that name of product is " glove box ";Existing issue is that " separating surface has slight side
Edge ";The reason is that " precision of parting surface is not good enough ";Solution is " grinding die joint ", without auxiliary information.
Further, after feature extraction, latent semantic analysis (Latent Semantic are carried out to each feature
Analysis, LSA) each feature of processing, specifically, before carrying out latent semantic analysis, to history change mould case into
Feature extraction is gone, these are characterized in a series of words, and word often has one justice of polysemy or more words in use
Problem, and latent semantic analysis can excavate the potential applications corresponding to word, other meaningless semantemes be rejected, to reach
Data are carried out with the purpose of noise reduction and dimensionality reduction, and generates final knowledge base.It should be noted that potential used in this programme
Compared with traditional vector space model, the feature that LSA has precision high, small can greatly simplify semantic analysis technology
The computation complexity of file retrieval algorithm.And after cluster process, what the average value acquisition based on each feature each clustered
Barycenter.
S103, judge whether that similarity is more than the history mold data of predetermined threshold;If in the presence of similarity is big
In predetermined threshold history mold data as with the matched history mold data of the target mold data.
Specifically, needing extraction to redesign the feature of case, and pass through potential applications in the study stage in this programme
Knowledge base is generated after analysis;In the application stage, then the characteristic value of matched target mold data as needed, and passes through simulation
Annealing algorithm SAA calculates the similarity of target mold data and the history mold data in knowledge base, when target mold data with
The similarity of history mold data in knowledge base is more than predetermined threshold, then extracts the history mold data as case, also
It is the matched history mold data in this programme.
In turn, after all having matched, it can be determined that whether the quantity for extracting case is zero, if zero, is then illustrated not
It is matched to case, then is redesigned based on traditional method;If the quantity for extracting case is more than zero, based on extracted
Case redesigns;After redesign, need to extract solution from the scheme of redesign, and carry out CAE simulations, such as
Fruit is unqualified, then redesigns;If qualified, judge whether the scheme of the redesign is improvement project, if not changing
Into scheme, then terminate flow;If it is improvement project, then knowledge base is added in the related data of the case.
As can be seen that this programme is carried out by the characteristic information of target mold data and the characteristic information of history mold data
Similarity calculation can search out history mold data case similar with target mold data from knowledge base, to be mould
Tool design provides most similar case data, design considerations is provided for mold design, in this way by history injection mold
Data analysis and re-using are changed, the accuracy and efficiency of mold redesign is promoted.
Based on above-described embodiment, in the present embodiment, each history mold number in the characteristic information and knowledge base is utilized
According to characteristic information carry out similarity mode, obtain the similarity of each history mold data and the target mold data, packet
It includes:
By the characteristic information of each history mold data in simulated annealing calculation knowledge library, with the target mold
The similarity of the corresponding characteristic information of data;
Using the characteristic information of each history mold data, characteristic information corresponding with the target mold data it is similar
Degree, and each selection weight of characteristic information, calculate the similarity of each history mold data and the target mold data.
Specifically, the application stage in the present embodiment, particular by simulated annealing (Simulated
Annealing Algorithm, SAA) matching and the higher history mould of target mold data similarity inputted from knowledge base
Have data.SAA is a kind of typical global optimization method, has the characteristics that receive worse solution once in a while, probability helps
In jumping out any local optimum.In order to realize effective and efficient retrieval, following two calculating can be passed through in the application stage
Mode determines final history mold data.
First way is to be applied to case by traditional simulated annealing Class-SAA, the SAA of this classics
Center has the case of highest similitude with the design problem sought and inputted.Algorithm is with random initial point S0With temperature T0It opens
Begin.In order to preferably explore entire case space, it is contemplated that the pervious discrete certainty feature for changing mould design, initial T0It is one
A constant.The mechanism moved from case space is randomly selected from previous neighborhood of a point.Assuming that SiIt is that there is mesh in iteration k
Scalar functions F (Si) selected element, then next point Si+1With object function F (Si+1) value.If F (Si+1)≥F(Si), point
Si+1It is accepted as new estimation solution.On the other hand, if F (Si+1)<F(Si), then point Si+1It is (general as the receiving station that has an opportunity
Standard).Therefore, uniform random number U is generatedk~U [0,1] (is evenly distributed on section [0,1]).If Uk< exp [- [F (Si-
F(Si+1))]/T0], point Si+1With probability exp [- [F (Si-F(Si+1))]/T0] it is accepted as optimal approximate solution;Otherwise SiStill
It is optimal approximate solution.When the optimal value of algorithm remains unchanged in 10 consecutive steps, algorithm terminates.
Second method improves generation by this programme based on traditional simulated annealing Class-SAA, specially
Simulated annealing Individual-SAA, for Individual-SAA, it is solved for searching for for realizing global optimization
Situation in the best case of scheme.Similar program carries out in Individual-SAA.In addition, Individual-SAA is
Finding out has the case where similitude than threshold value bigger.Therefore, once the case of Individual-SAA extractions obtains similitude,
Just there are one compare.End condition is the case where reaching desired amt or the optimal value of algorithm is protected in 10 consecutive steps
It holds constant.
If the input in this programme is:The problem of changing mould design;Similarity threshold Ts;Output is:Possess and changes with input
Modulus problem similarity changes mould case more than threshold value;Then in the present embodiment simulated annealing Individual-SAA specific step
It is rapid as follows:
Step 1:Initial temperature T0, initial solution state S0(starting point of iterative algorithm);
Step 2:Another k=0, and generate a new solution Sk+1;
Step 3:Calculate t=C (Sk+1)-C(Sk) and t'=C (Sk+1)-TSIncrement, wherein C (S) counts by formula 1 hereafter
It acquires;
Step 4:If t < 0 and t'< 0, SkIt is still optimal approximate solution;
If t < 0 and t' >=0, S is received based on Metropolis criterionk+1, and it is regarded as output situation;
If t >=0 and t'< 0, S is received based on Metropolis criterionk+1;
If t >=0 and t' >=0, Sk+1It is received and exports.
Step 5:If meeting end condition, current optimal solution is exported.If it is not, enabling k=i+1, and repeat to hold
Row step 2~step 5.
Specifically, it is assumed that best similarity selection criteria is { name of product, existing issue, reason, structure and mold essence
Degree }.Experienced mold worker can express actual preference by distributing the relative weighting of selection criteria.For example, if
Worker thinks that name of product is then can higher value to be distributed to name of product problem an important factor for finding similar situation.
Name of product and existing issue are considered as prior factor, the relative weighting of selection criteria be 0.300,0.300,
0.200,0.200 }.Therefore, the C (S) in similarity namely above-mentioned steps can be calculated as in equationi:
Wherein Sim (Pa, Pb) it is similitude in In-put design problem and knowledge base between existing case;ωkIt is k-th
The relative weighting of selection criteria;In the present solution, selection criteria is the characteristic information in above-described embodiment;Sim(Pak,Pbk)
It is the similitude of k-th of selection criteria between input problem and existing situation.Using TF-IDF (term frequency-
Inverse document frequency, weighting technique), using the probability distribution of the contextual information of vocabulary as between word
Semantic Similarity calculate reference.According to word frequency statistics, all words in each selection criteria in corpus are appeared in
All n-dimensional vector is expressed as with word frequency:More specifically, k-th of selection criteria repository P in knowledge can be presented in weak=
< Pak 1,Pak 2,......,Pak n>.Similarly, the n-dimensional vector P of target searchbk=< Pbk 1,Pbk 2,......,Pbk n>.Phase
It is indicated by the cosine of the angle between two vectors like property, as shown in equation 2:
Wherein PakIt is the n-dimensional vector of k-th of selection criteria of situation a in knowledge base, and PbkIt is the of In-put design problem
K selection criteria.
Mold data coalignment provided in an embodiment of the present invention is introduced below, mold data described below
It can be cross-referenced with device and above-described mold data matching process.
Referring to Fig. 2, a kind of mold data coalignment provided in an embodiment of the present invention, including:
Characteristic extracting module 110, the characteristic information for extracting target mold data;
Similarity calculation module 120, for the spy using the characteristic information and each history mold data in knowledge base
Reference breath carries out similarity mode, obtains the similarity of each history mold data and the target mold data;
Judgment module 130, for judging whether that similarity is more than the history mold data of predetermined threshold;
Module 140 is chosen, for there are when the history mold data that similarity is more than predetermined threshold, similarity being more than pre-
Determine the history mold data of threshold value as with the matched history mold data of the target mold data.
Wherein, this programme further includes construction of knowledge base module;The construction of knowledge base module includes:
Feature extraction unit, the characteristic information for extracting history mold data;
Construction unit, for utilizing latent semantic analysis technology, and feature corresponding with each history mold data to believe
Breath, builds the knowledge base.
Wherein, the similarity calculation module includes:
First computing unit, for the feature letter by each history mold data in simulated annealing calculation knowledge library
Breath, the similarity of characteristic information corresponding with the target mold data;
Second computing unit, for the characteristic information using each history mold data, with the target mold data pair
The similarity for the characteristic information answered, and each selection weight of characteristic information, calculate each history mold data and the mesh
Mark the similarity of mold data.
The embodiment of the invention also discloses a kind of mold data matching units, including:Memory, for storing computer journey
Sequence;Processor, when for executing the computer program in realization the step of institute's mold data matching process.
Specifically, the storage medium may include:USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. are various can store program
The medium of code.
The embodiment of the invention also discloses a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is contained, is realized such as the step of above-mentioned mold data matching process when the computer program is executed by processor.
Referring to Fig. 3, for the embodiment of the invention also discloses a kind of mold data matching systems, including:Input layer 200, on
State the mold data coalignment 100 and output layer 300 described in embodiment;
The input layer 200 is input to mold data for obtaining target mold data, and by the target mold data
Coalignment;
The output layer 300 is chosen matched with the target mold data for output mask data matching device
History mold data.
Specifically, this system one has three layers, i.e. input layer, the injection mold based on simulated annealing changes knowledge
(SAA-based IMMK) system, i.e. die described above Data Matching and output layer.Input layer:For In-put design
Problem is made of design problem, for each problem, it includes four representative aspects, including name of product, existing to ask
The reason of topic, problem and auxiliary information.
IMMK systems:By feature extraction, latent semantic analysis (LSA), knowledge base, SAA and redesign retrieval etc. five
Part forms.In order to reuse modification mold case, it is necessary to be carried out to text on the basis of ensuring the meaning of original text pre-
Processing.In order to solve this problem, most efficient method is to reduce dimension.LSA is the allusion quotation for analyzing the relationship between one group of term
Type technology, for clustering the feature of extraction to establish knowledge base.SAA is an outstanding global optimization and Fast Convergent Algorithm,
It can be used to implement the efficient retrieving to knowledge base.
Output layer:The problem of according to being obtained in input layer, then similarity is carried out to the case in knowledge base by SAA algorithms
Matching, is optionally changed mould case, and output layer is exactly to be made of these cases.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (9)
1. a kind of mold data matching process, which is characterized in that including:
Extract the characteristic information of target mold data;
Similarity mode is carried out using the characteristic information of each history mold data in the characteristic information and knowledge base, is obtained every
The similarity of a history mold data and the target mold data;
Judge whether that similarity is more than the history mold data of predetermined threshold;
If in the presence of, using similarity be more than the history mold data of predetermined threshold as with the target mold data is matched goes through
History mold data.
2. mold data matching process according to claim 1, which is characterized in that the generation method packet of the knowledge base
It includes:
Extract the characteristic information of history mold data;
Using latent semantic analysis technology, and characteristic information corresponding with each history mold data, build the knowledge base.
3. mold data matching process according to claim 2, which is characterized in that described to utilize the characteristic information and know
The characteristic information for knowing each history mold data in library carries out similarity mode, obtains each history mold data and the target
The similarity of mold data, including:
By the characteristic information of each history mold data in simulated annealing calculation knowledge library, with the target mold data
The similarity of corresponding characteristic information;
Using the characteristic information of each history mold data, the similarity of characteristic information corresponding with the target mold data,
And the selection weight of each characteristic information, calculate the similarity of each history mold data and the target mold data.
4. a kind of mold data coalignment, which is characterized in that including:
Characteristic extracting module, the characteristic information for extracting target mold data;
Similarity calculation module, for the characteristic information using each history mold data in the characteristic information and knowledge base into
Row similarity mode obtains the similarity of each history mold data and the target mold data;
Judgment module, for judging whether that similarity is more than the history mold data of predetermined threshold;
Module is chosen, for there are when the history mold data that similarity is more than predetermined threshold, similarity to be more than predetermined threshold
History mold data as with the matched history mold data of the target mold data.
5. mold data coalignment according to claim 4, which is characterized in that further include construction of knowledge base module;Institute
Stating construction of knowledge base module includes:
Feature extraction unit, the characteristic information for extracting history mold data;
Construction unit, for utilizing latent semantic analysis technology, and characteristic information corresponding with each history mold data, structure
Build the knowledge base.
6. mold data coalignment according to claim 5, which is characterized in that the similarity calculation module includes:
First computing unit, the characteristic information for passing through each history mold data in simulated annealing calculation knowledge library,
The similarity of characteristic information corresponding with the target mold data;
Second computing unit, it is corresponding with the target mold data for the characteristic information using each history mold data
The similarity of characteristic information, and each selection weight of characteristic information, calculate each history mold data and the target mould
Has the similarity of data.
7. a kind of mold data matching unit, which is characterized in that including:
Memory, for storing computer program;
Processor realizes the mold data match party as described in any one of claims 1 to 3 when for executing the computer program
The step of method.
8. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the mold data matching process as described in any one of claims 1 to 3 when the computer program is executed by processor
The step of.
9. a kind of mold data matching system, which is characterized in that including:Input layer, as described in claim 4-6 any one
Mold data coalignment and output layer;
The input layer is input to mold data matching dress for obtaining target mold data, and by the target mold data
It sets;
The output layer, for the selection of output mask data matching device and the matched history mold of the target mold data
Data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810258231.0A CN108388676A (en) | 2018-03-27 | 2018-03-27 | A kind of mold data matching process, apparatus and system based on simulated annealing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810258231.0A CN108388676A (en) | 2018-03-27 | 2018-03-27 | A kind of mold data matching process, apparatus and system based on simulated annealing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108388676A true CN108388676A (en) | 2018-08-10 |
Family
ID=63072649
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810258231.0A Pending CN108388676A (en) | 2018-03-27 | 2018-03-27 | A kind of mold data matching process, apparatus and system based on simulated annealing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108388676A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110866317A (en) * | 2019-11-23 | 2020-03-06 | 广东科龙模具有限公司 | Design tool kit reconstruction method based on product historical information and design behavior analysis |
CN115354144A (en) * | 2022-08-29 | 2022-11-18 | 湖南华菱涟源钢铁有限公司 | Roller type quenching process operation parameter setting method based on case matching |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102193948A (en) * | 2010-03-16 | 2011-09-21 | 华为技术有限公司 | Feature matching method and device |
CN102663367A (en) * | 2012-04-16 | 2012-09-12 | 电子科技大学 | Three-dimensional face identification method on basis of simulated annealing algorithm |
CN103810306A (en) * | 2012-11-07 | 2014-05-21 | 北京有色金属研究总院 | Efficient design method of profile extrusion mould |
CN103838821A (en) * | 2013-12-31 | 2014-06-04 | 中国传媒大学 | Characteristic vector optimization method for interactive image retrieval |
CN104408161A (en) * | 2014-12-08 | 2015-03-11 | 周理 | Mould CAD drawing query based on similarity query and management method |
US20150310088A1 (en) * | 2014-04-28 | 2015-10-29 | Emlab P&K, Llc | System and method for searching for, collecting and generating mold spore data for mold reports using climate codes |
CN106295032A (en) * | 2016-08-16 | 2017-01-04 | 佛山市石湾陶瓷工业研究所有限公司 | A kind of ceramic tile Design of Dies software system and method for designing thereof |
-
2018
- 2018-03-27 CN CN201810258231.0A patent/CN108388676A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102193948A (en) * | 2010-03-16 | 2011-09-21 | 华为技术有限公司 | Feature matching method and device |
CN102663367A (en) * | 2012-04-16 | 2012-09-12 | 电子科技大学 | Three-dimensional face identification method on basis of simulated annealing algorithm |
CN103810306A (en) * | 2012-11-07 | 2014-05-21 | 北京有色金属研究总院 | Efficient design method of profile extrusion mould |
CN103838821A (en) * | 2013-12-31 | 2014-06-04 | 中国传媒大学 | Characteristic vector optimization method for interactive image retrieval |
US20150310088A1 (en) * | 2014-04-28 | 2015-10-29 | Emlab P&K, Llc | System and method for searching for, collecting and generating mold spore data for mold reports using climate codes |
CN104408161A (en) * | 2014-12-08 | 2015-03-11 | 周理 | Mould CAD drawing query based on similarity query and management method |
CN106295032A (en) * | 2016-08-16 | 2017-01-04 | 佛山市石湾陶瓷工业研究所有限公司 | A kind of ceramic tile Design of Dies software system and method for designing thereof |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110866317A (en) * | 2019-11-23 | 2020-03-06 | 广东科龙模具有限公司 | Design tool kit reconstruction method based on product historical information and design behavior analysis |
CN115354144A (en) * | 2022-08-29 | 2022-11-18 | 湖南华菱涟源钢铁有限公司 | Roller type quenching process operation parameter setting method based on case matching |
CN115354144B (en) * | 2022-08-29 | 2024-01-30 | 湖南华菱涟源钢铁有限公司 | Roller quenching process operation parameter setting method based on case matching |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106815244B (en) | Text vector representation method and device | |
CN102129451A (en) | Method for clustering data in image retrieval system | |
Tan | An improved KNN text classification algorithm based on K-medoids and rough set | |
CN111177438B (en) | Image characteristic value searching method and device, electronic equipment and storage medium | |
Kiktova-Vozarikova et al. | Feature selection for acoustic events detection | |
KR20150037924A (en) | Information classification based on product recognition | |
CN107291895B (en) | Quick hierarchical document query method | |
CN110134777B (en) | Question duplication eliminating method and device, electronic equipment and computer readable storage medium | |
CN107784110A (en) | A kind of index establishing method and device | |
CN108875065B (en) | Indonesia news webpage recommendation method based on content | |
CN107357895B (en) | Text representation processing method based on bag-of-words model | |
CN112329460A (en) | Text topic clustering method, device, equipment and storage medium | |
CN112632261A (en) | Intelligent question and answer method, device, equipment and storage medium | |
CN111859004A (en) | Retrieval image acquisition method, device, equipment and readable storage medium | |
CN113722512A (en) | Text retrieval method, device and equipment based on language model and storage medium | |
Li et al. | Computer aided design (CAD) model search and retrieval using frequency domain file conversion | |
CN108388676A (en) | A kind of mold data matching process, apparatus and system based on simulated annealing | |
CN112925912B (en) | Text processing method, synonymous text recall method and apparatus | |
CN104598599A (en) | Method and system for removing name ambiguity | |
CN111125329B (en) | Text information screening method, device and equipment | |
CN111259975B (en) | Method and device for generating classifier and method and device for classifying text | |
CN111767419B (en) | Picture searching method, device, equipment and computer readable storage medium | |
Golzari et al. | Question classification in question answering system using combination of ensemble classification and feature selection | |
CN103793466A (en) | Image retrieval method and image retrieval device | |
CN110457455B (en) | Ternary logic question-answer consultation optimization method, system, medium and equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180810 |
|
RJ01 | Rejection of invention patent application after publication |