CN108121887A - A kind of method that enterprise standardization is handled by machine learning - Google Patents
A kind of method that enterprise standardization is handled by machine learning Download PDFInfo
- Publication number
- CN108121887A CN108121887A CN201810113856.8A CN201810113856A CN108121887A CN 108121887 A CN108121887 A CN 108121887A CN 201810113856 A CN201810113856 A CN 201810113856A CN 108121887 A CN108121887 A CN 108121887A
- Authority
- CN
- China
- Prior art keywords
- design
- machine learning
- parts
- product structure
- handled
- 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]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computer Hardware Design (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a kind of methods that enterprise standardization is handled by machine learning, comprise the steps of：A, the configurable product structure containing grouping is created；B, product design and extension are carried out based on the product structure；C, using machine learning sample training is carried out for passing design；When D, carrying out next secondary design, design parts are predicted；E, selection or the corresponding parts of design；F, continue to optimize training pattern using final design result.The present invention obtains relevant parts using machine learning and configurable product structure design mode the problem of handling enterprise standardization, can solve the problems, such as engineer by way of retrieval.And the problem of can reducing because retrieval information is imperfect, causing recall precision low, i.e., in product design process, the parts of design can be no longer obtained by way of retrieving and by way of machine learning, and be applied to product design.
Description
Technical field
It is specifically a kind of that enterprise standardization is handled by machine learning the present invention relates to manufacturing informatization technical field
Method.
Background technology
The degree of manufacturing enterprise's part-subassemble standard determines the efficiency of enterprise's design, and due to the buying of raw material
Manufacture with parts be all by engineer design end determine, therefore engineer whether can choose or design it is proper
Parts, fundamentally determine the parts of enterprise（Raw material）Inventory problem.Therefore, how enterprise parts mark
Quasi-ization degree, part-subassemble standard are one of manufacturing enterprise's key problems.
Part-subassemble standard is very important content for manufacturing enterprise, thus at present enterprise by many methods come
Solve the problems, such as part-subassemble standard, but at present no matter which kind of mode to be standardized the management of parts using, substantially
It is required for through suitable search method --- corresponding attribute such as is set to each part, passes through attribute retrieval；It is or logical
Cross the methods of parts similitude retrieve etc. --- to realize engineer in the design process for having looking into for parts
It looks for and calls.
But such way is, it is necessary to which engineer is familiar for the content of coordinate indexing, it is thus possible to be present with nothing
Method retrieves the situation of corresponding parts.
The content of the invention
It is an object of the invention to provide a kind of method that enterprise standardization is handled by machine learning, to solve the above-mentioned back of the body
The problem of being proposed in scape technology.
To achieve the above object, the present invention provides following technical solution：
A kind of method that enterprise standardization is handled by machine learning, comprises the steps of：
A, the configurable product structure containing grouping is created；
B, product design and extension are carried out based on the product structure；
C, using machine learning sample training is carried out for passing design；
When D, carrying out next secondary design, design parts are predicted；
E, selection or the corresponding parts of design；
F, continue to optimize training pattern using final design result.
Further technical solution as the present invention：The configurable product structure containing grouping is needed with influencing its
Feature is associated.
Further technical solution as the present invention：The step B is specifically：According to demand, parts are designed,
And the parts after design are extended to by grouping in the configurable product structure.
Further technical solution as the present invention：The step C is specifically：Using with the configurable product structure connection
Feature value, as the input sample of machine learning, using the parts of the configurable product structure of final checked as machine
Output sample in study, and suitable training pattern is chosen, model training is carried out, obtains the training mould for meeting passing demand
Type.
Further technical solution as the present invention：The step D is specifically：In next secondary design, step 3 is utilized
In, the obtained model of training, in configurable product structure, provide the parts in each grouping occur under the demand it is general
Rate.
Compared with prior art, the beneficial effects of the invention are as follows：The present invention utilizes machine learning and configurable product structure
Design method obtains relevant parts the problem of handling enterprise standardization, can solve engineer by way of retrieval
The problem of, and can reduce because retrieval information is imperfect, the problem of causing recall precision low, i.e., in product design process
In, the parts of design can be no longer obtained by way of retrieving and by way of machine learning, and be answered
For product design.
Specific embodiment
The technical solution in the embodiment of the present invention will be clearly and completely described below, it is clear that described implementation
Example is only part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiments obtained without making creative work belong to the model that the present invention protects
It encloses.
A kind of method that enterprise standardization is handled by machine learning, which is characterized in that comprise the steps of：
A, the configurable product structure containing grouping is created.The configurable product structure containing grouping information is created, it can using this
Configuration structure can reach and derive a variety of product structures by a structure.And create relevant options（Feature）With this
Configurable product structure is associated；
B, product design and extension are carried out based on the product structure.According to demand, parts are designed, and will be after design
Parts are added in the configurable product structure suitably grouping；
C, using machine learning sample training is carried out for passing design.Utilize the feature with the configurable product structure connection
Value, as the input sample of machine learning, using the parts of the configurable product structure of final checked as in machine learning
Sample is exported, and chooses suitable training pattern, model training is carried out, obtains the training pattern for meeting passing demand；
When D, carrying out next secondary design, design parts are predicted.In next secondary design, using in step 3, trained
The model arrived in configurable product structure, provides the probability that parts occur under the demand in each grouping；
E, selection or the corresponding parts of design.Parts there are one most only containing at last in product design, in each grouping
It is selected, and it is applied to product design.Therefore, for the parts that contain under each grouping, probability from high to low into
Row sequence, is not required to check for all parts under the classification, it is only necessary to check the higher N number of parts of probability（Such as N
=3 either N=5 or N=10 etc., according to depending on concrete condition difference）, will if there is meeting the parts of current design demand
The parts elect the parts needed for the demand as, if not provided, being redesigned, and add it in relevant classification.
So in product design, it is possible to relevant parts are not searched by retrieving, but are based on by machine learning previous
The model that project training obtains, prediction obtain the probability of parts under each grouping to determine whether meeting product design requirement；
F, continue to optimize training pattern using final design result.By the product structure of final design again by machine learning
It is trained, and passes through training, continue the training pattern of optimization design, instruct next product design.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requirement rather than above description limit, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included within the present invention.
Moreover, it will be appreciated that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
Using specification as an entirety, the technical solutions in each embodiment can also be properly combined, forms those skilled in the art
It is appreciated that other embodiment.
Claims (5)
- A kind of 1. method that enterprise standardization is handled by machine learning, which is characterized in that comprise the steps of：A, the configurable product structure containing grouping is created；B, product design and extension are carried out based on the product structure；C, using machine learning sample training is carried out for passing design；When D, carrying out next secondary design, design parts are predicted；E, selection or the corresponding parts of design；F, continue to optimize training pattern using final design result.
- 2. a kind of method that enterprise standardization is handled by machine learning according to claim 1, which is characterized in that described Configurable product structure containing grouping needs to be associated with influencing its feature.
- 3. a kind of method that enterprise standardization is handled by machine learning according to claim 1, which is characterized in that described Step B is specifically：According to demand, parts are designed, and the parts after design is extended to this by grouping to match somebody with somebody It puts in product structure.
- 4. a kind of method that enterprise standardization is handled by machine learning according to claim 1, which is characterized in that described Step C is specifically：It, will most as the input sample of machine learning using the value of the feature with the configurable product structure connection The parts for the configurable product structure chosen eventually choose suitable training pattern as the output sample in machine learning, Model training is carried out, obtains the training pattern for meeting passing demand.
- 5. a kind of method that enterprise standardization is handled by machine learning according to claim 1, which is characterized in that described Step D is specifically：In next secondary design, using the model that in step 3, training obtains, in configurable product structure, provide The probability that parts in each grouping occur under the demand.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810113856.8A CN108121887A (en) | 2018-02-05 | 2018-02-05 | A kind of method that enterprise standardization is handled by machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810113856.8A CN108121887A (en) | 2018-02-05 | 2018-02-05 | A kind of method that enterprise standardization is handled by machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108121887A true CN108121887A (en) | 2018-06-05 |
Family
ID=62233515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810113856.8A Pending CN108121887A (en) | 2018-02-05 | 2018-02-05 | A kind of method that enterprise standardization is handled by machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108121887A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404073A (en) * | 2008-10-21 | 2009-04-08 | 浙江大学 | Complex product fuzz hierarchy collocation method |
| CN104598569A (en) * | 2015-01-12 | 2015-05-06 | 北京航空航天大学 | Association rule-based MBD (Model Based Definition) data set completeness checking method |
| CN106066907A (en) * | 2016-05-27 | 2016-11-02 | 大连楼兰科技股份有限公司 | The setting loss grading method judged based on many parts multi-model |
| US20170011301A1 (en) * | 2015-07-09 | 2017-01-12 | General Electric Company | Capturing, encoding, and executing knowledge from subject matter experts |
| CN107203678A (en) * | 2017-06-23 | 2017-09-26 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of parts automatic assembly method mapped based on geometric properties |
| CN107273131A (en) * | 2017-06-22 | 2017-10-20 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of machine learning method applied to Configurable BOM |
| US20170316004A1 (en) * | 2016-04-28 | 2017-11-02 | Microsoft Technology Licensing, Llc | Online engine for 3d components |
-
2018
- 2018-02-05 CN CN201810113856.8A patent/CN108121887A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404073A (en) * | 2008-10-21 | 2009-04-08 | 浙江大学 | Complex product fuzz hierarchy collocation method |
| CN104598569A (en) * | 2015-01-12 | 2015-05-06 | 北京航空航天大学 | Association rule-based MBD (Model Based Definition) data set completeness checking method |
| US20170011301A1 (en) * | 2015-07-09 | 2017-01-12 | General Electric Company | Capturing, encoding, and executing knowledge from subject matter experts |
| US20170316004A1 (en) * | 2016-04-28 | 2017-11-02 | Microsoft Technology Licensing, Llc | Online engine for 3d components |
| CN106066907A (en) * | 2016-05-27 | 2016-11-02 | 大连楼兰科技股份有限公司 | The setting loss grading method judged based on many parts multi-model |
| CN107273131A (en) * | 2017-06-22 | 2017-10-20 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of machine learning method applied to Configurable BOM |
| CN107203678A (en) * | 2017-06-23 | 2017-09-26 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of parts automatic assembly method mapped based on geometric properties |
Non-Patent Citations (3)
| Title |
|---|
| SNIGDHA CHATURVEDI,ET AL.: "Automating Pattern Discovery for Rule Based Data Standardization Systems", 《IEEE》 * |
| 徐翔斌 等: "支持产品设计的知识仓库框架研究", 《中国机械工程》 * |
| 徐翔斌: "基于设计知识库的CAD和PDM集成", 《铸造技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2015185104A (en) | Database device | |
| CN106776962A (en) | A kind of general Excel data import multiple database physical table methods | |
| CN105279269A (en) | SQL generating method and system for supporting table free association | |
| CN102737108A (en) | Method and device for processing flow diagram | |
| CN104732041A (en) | Automatic virtual terminal generation method based on multiple SCD templates | |
| US10776313B2 (en) | Converting source objects to target objects | |
| CN116244333A (en) | Database query performance prediction method and system based on cost factor calibration | |
| CN107153469B (en) | Method for searching input data for matching candidate items, database creation method, database creation device and computer program product | |
| CN105404638A (en) | Method for solving correlated query of distributed cross-database fragment table | |
| CN110704430A (en) | Universal tree structure data query method and device | |
| CN103870511B (en) | Information inquiry device and method based on shared drive | |
| CN103942280A (en) | Automatic code generating method based on data structure | |
| CN109741034B (en) | Grid tree organization management method and device | |
| CN114461521A (en) | PLC software test case generation method and system based on state machine | |
| CN108121887A (en) | A kind of method that enterprise standardization is handled by machine learning | |
| US20180189952A1 (en) | Method for processing the lef diagram of a layout | |
| CN105550220A (en) | Fetching method and apparatus for heterogeneous system | |
| CN110928863A (en) | Method for task breakpoint resume applied to data cleaning tool | |
| CN101620415B (en) | Control method of photoetching equipment in semiconductor process and device | |
| CN101272222A (en) | Restriction calibration method and device | |
| CN112783915A (en) | Data transmission object mapping method and unit based on SpringMVC + Mybatis framework | |
| CN113672615B (en) | Data analysis method and system for automatically generating SQL based on relationships among tree tables | |
| CN106933844A (en) | Towards the construction method of the accessibility search index of extensive RDF data | |
| CN104376054B (en) | A kind of processing method and processing device of persisted instances object | |
| CN110488750B (en) | Shortest cutter path generation method facing STEP-NC complex cavity |
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: 20180605 |
|
| RJ01 | Rejection of invention patent application after publication |