CN109685316A - Life cycle autoknowledge evaluation system towards product quality - Google Patents
Life cycle autoknowledge evaluation system towards product quality Download PDFInfo
- Publication number
- CN109685316A CN109685316A CN201811393527.XA CN201811393527A CN109685316A CN 109685316 A CN109685316 A CN 109685316A CN 201811393527 A CN201811393527 A CN 201811393527A CN 109685316 A CN109685316 A CN 109685316A
- Authority
- CN
- China
- Prior art keywords
- data
- product quality
- product
- module
- subsystem
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 31
- 238000013461 design Methods 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 28
- 238000004519 manufacturing process Methods 0.000 claims description 24
- 238000013441 quality evaluation Methods 0.000 claims description 21
- 230000004927 fusion Effects 0.000 claims description 19
- 238000004140 cleaning Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000005065 mining Methods 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 136
- 238000000034 method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/046—Forward inferencing; Production systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to uniform data acess technical fields, more particularly to a kind of Life cycle autoknowledge evaluation system towards product quality, aim to solve the problem that how analysis mining and Knowledge Discovery are carried out to product lifecycle data, the technical issues of with overall merit product quality, for this purpose, Life cycle autoknowledge evaluation system provided by the invention towards product quality includes product quality forecast subsystem and product quality feedback subsystem, product quality forecast subsystem is configured to the R & D design data according to product and manufactures the credit rating of data prediction product；Product quality feedback subsystem is configured to physical state data and O&M detection data upgrading products prediction of quality module according to product, so that updated product quality forecast module is predicted to obtain the real quality grade of product.Based on above structure, the present invention can comprehensively utilize product lifecycle data preferably to predict the credit rating of product.
Description
Technical field
The present invention relates to uniform data acess technical fields, and in particular to a kind of full life towards product quality
Period autoknowledge evaluation system.
Background technique
The development of artificial intelligence pushes various industries to be changed, in a manner of the production and operation of data and Knowledge driving
It gradually rises, autoknowledge aims at the automation of knowledge work, just becomes the trend of industrial development.
Currently, the magnanimity that product is generated from Life cycle such as R & D design, the manufacturing, logistics sale and O&M services
Data, which carry out Knowledge Discovery, has a great potentiality to Improving The Quality of Products, and how using Life cycle data to be still one
Bigger challenge.For example, in the production and operation of lithium battery, each link is to production in the design of product, production process
The quality of product has certain influence, how to carry out analysis mining and Knowledge Discovery to the Life cycle data of product, obtains one
The synthesis accurate evaluation of product is a biggish challenge.
Correspondingly, this field needs a kind of new autoknowledge evaluation system to solve the above problems.
Summary of the invention
In order to solve the above problem in the prior art, in order to solve how to divide product lifecycle data
Analysis is excavated and Knowledge Discovery, and the technical issues of with overall merit product quality, the present invention provides a kind of towards product quality
Life cycle autoknowledge evaluation system, the autoknowledge evaluation system include:
Product quality forecast subsystem and product quality feedback subsystem, the product quality forecast subsystem include first
Feature obtains module and product quality forecast module；
The fisrt feature obtains module and is configured to the R & D design data and life to the product obtained in advance respectively
It produces manufaturing data to carry out extraction of semantics and carry out data fusion to extraction of semantics result, obtains primary semantic knowledge；
The product quality forecast module is configured to predict the credit rating of the product according to the primary semantic knowledge；
The product quality feedback subsystem is configured to physical state data and fortune according to the product obtained in advance
It ties up detection data and updates the product quality forecast module, so that the updated product quality forecast module is predicted to obtain institute
State the real quality grade of product.
Further, a preferred embodiment provided by the invention are as follows:
The fisrt feature obtains module and includes the first data prediction submodule and the second data prediction submodule,
The pre- virgin of first data manage module be configured to respectively to the R & D design data and manufacture data into
Row data cleansing, so that the fisrt feature obtains module according to the R & D design data after the data cleansing and manufactures
Data carry out extraction of semantics；
The second data prediction submodule is configured to obtain primary to extraction of semantics result progress data fusion
Semantic knowledge.
Further, a preferred embodiment provided by the invention are as follows:
The product quality forecast module includes product quality knowledge reasoning model, and the system also includes knowledge bases and mould
Type training module,
The knowledge base is configured to store preset data training set, and the data training set includes multiple preset products
Primary semantic knowledge；
The model training module be configured to according to the data training set to the product quality knowledge reasoning model into
Row training, so that the product quality knowledge reasoning model after the training can be predicted according to the primary semantic knowledge of current production
The credit rating of the product.
Further, a preferred embodiment provided by the invention are as follows:
The product quality feedback subsystem includes that second feature obtains module, Product Quality Evaluation module and product quality
Feedback module,
The second feature obtains module and is configured to respectively propose physical state data and O&M detection data progress semanteme
It takes and data fusion is carried out to extraction of semantics result；
The Product Quality Evaluation module is configured to obtain the data fusion result of module to institute according to the second feature
It states product and carries out quality evaluation, obtain the quality evaluation result of the product；
The product quality feedback module is configured to be updated in the knowledge base according to the quality evaluation result of the product
Data training set, the product quality is corrected according to the updated data training set so as to the model training module and is known
Know inference pattern.
Further, a preferred embodiment provided by the invention are as follows:
It includes third data prediction mould block and the 4th data prediction submodule that the second feature, which obtains module,
The pre- virgin of the third data manage module be configured to respectively to the physical state data and O&M detection data into
Row data cleansing, so that the second feature obtains module according to the physical state data and O&M detection after the data cleansing
Data carry out extraction of semantics；
The 4th data prediction submodule is configured to carry out data fusion to the extraction of semantics result.
Further, a preferred embodiment provided by the invention are as follows:
The system also includes data acquisition subsystem,
The data acquisition subsystem is configured to acquire the R & D design data of the product, manufactures data, logistics
Status data and O&M detection data, and
It by the R & D design data and manufactures data and is sent to the product quality forecast subsystem, and by institute
It states physical state data and O&M detection data is sent to the product quality feedback subsystem.
Compared with the immediate prior art, above-mentioned technical proposal is at least had the following beneficial effects:
A kind of Life cycle autoknowledge evaluation system towards product quality provided by the invention mainly includes such as
Flowering structure: product quality forecast subsystem and product quality feedback subsystem, product quality forecast subsystem include fisrt feature
Obtain module and product quality forecast module；Fisrt feature obtains module and is configured to respectively set the research and development of the product obtained in advance
It counts and manufactures data to carry out extraction of semantics and carry out data fusion to extraction of semantics result, obtain primary semanteme and know
Know；Product quality forecast module is configured to predict the credit rating of product according to primary semantic knowledge；Product quality feeds back subsystem
Under unified central planning be set to updates the product quality forecast mould according to the physical state data and O&M detection data of the product obtained in advance
Block, so that updated product quality forecast module is predicted to obtain the real quality grade of product.It, can be comprehensive based on above structure
It closes and quality evaluation is carried out to product using the data of product lifecycle, improve the accuracy of product quality forecast.
Detailed description of the invention
Fig. 1 is a kind of master of the Life cycle autoknowledge evaluation system towards product quality in the embodiment of the present invention
Want structural schematic diagram；
Fig. 2 is a kind of primary structure schematic diagram of fisrt feature acquisition module in the embodiment of the present invention；
Fig. 3 is a kind of primary structure schematic diagram of product quality feedback subsystem in the embodiment of the present invention；
Fig. 4 is a kind of primary structure schematic diagram of second feature acquisition module in the embodiment of the present invention；
Fig. 5 is a kind of Life cycle autoknowledge evaluation system towards product quality in another embodiment of the present invention
Primary structure schematic diagram；
Fig. 6 is a kind of Life cycle autoknowledge evaluation system towards product quality in another embodiment of the present invention
Main working process schematic diagram.
Specific embodiment
The preferred embodiment of the present invention described with reference to the accompanying drawings.It will be apparent to a skilled person that this
A little embodiments are used only for explaining technical principle of the invention, it is not intended that limit the scope of the invention.
The quality evaluation of product is an important index for product sale.One product quality grade of accurate evaluation
It is possible to prevente effectively from product in transport, storage, the security risk in links such as use, for example, lithium ion battery enterprise, accurately comments
The credit rating of valence battery can be effectively prevented that transport, storage, there is a situation where generations of exploding in use process.For this purpose, this hair
A kind of Life cycle autoknowledge evaluation system towards product quality of bright offer being capable of the full life of integrated use product
The data in period, to improve the accuracy of product quality forecast.With reference to the accompanying drawing to provided by the invention towards product quality
Life cycle autoknowledge evaluation system be described in detail.
Refering to attached drawing 1, Fig. 1 illustrates the Life cycle autoknowledge evaluation system towards product quality
Primary structure, the Life cycle autoknowledge evaluation system towards product quality may include product quality as shown in Figure 1
Predicting subsystem 1 and product quality feedback subsystem 2, product quality forecast subsystem 1 include that fisrt feature obtains 11 He of module
Product quality forecast module 12.
Fisrt feature obtains module 11 and is configured to respectively to the R & D design data of the product obtained in advance and the manufacturing
Data carry out extraction of semantics and carry out data fusion to extraction of semantics result, obtain primary semantic knowledge；Product quality forecast
Module 12 is configured to predict the credit rating of product according to primary semantic knowledge；Product quality feedback subsystem 2 is configured to basis
The physical state data and O&M detection data upgrading products prediction of quality module of the product obtained in advance, so as to updated production
The prediction of quality prediction module 12 obtains the real quality grade of product.
Specifically, fisrt feature, which obtains module 11, can pass through preset knowledge fusion algorithm (such as deepness belief network)
Data fusion is carried out to extraction of semantics result.Primary semantic knowledge can show as a feature and its corresponding attribute, the category
Property can be the corresponding class label of this feature.R & D design data can be research and development of products design process generation structuring,
Semi-structured and unstructured data, such as product design drawing, formula etc..Manufacturing data can be production manufacture
Structuring caused by process, semi-structured and unstructured data, such as raw material data, process flow data, business datum
Deng.Physical state data can be structuring caused by product stream transportational process, semi-structured and unstructured data, packet
Including abrasion, failure etc. influences the related data of product quality.O&M detection data can be the generation of product O&M service process
Structuring, semi-structured and unstructured data, service condition, life situations including product use the product qualities such as failure
Related data.The credit rating of product can be the evaluation to product quality, can show as it is excellent, good, in, poor or enterprise from
The quality grade compartmentalization of definition.
Refering to attached drawing 2, Fig. 2 illustrates the primary structure that fisrt feature obtains module, fisrt feature as shown in Figure 2
Obtaining module 11 may include the first data prediction submodule 111 and the second data prediction submodule 112, and the first data are pre-
Virgin manages module 111 and is configured to carry out data cleansing to R & D design data and manufacturing data respectively, so as to fisrt feature
Module 11 is obtained according to the R & D design data after data cleansing and manufactures data progress extraction of semantics；Second data are located in advance
Reason submodule 112 is configured to obtain primary semantic knowledge to extraction of semantics result progress data fusion.
Further, product quality forecast module 12 may include that product quality knowledge reasoning model is in the case
System can also include knowledge base and model training module.Knowledge base is configured to store preset data training set, data training set
Primary semantic knowledge including multiple preset products；Model training module is configured to know product quality according to data training set
Know inference pattern to be trained, so that the product quality knowledge reasoning model after training can be semantic according to the primary of current production
Knowledge predicts the credit rating of the product.Product quality inference pattern can be a knowledge reasoning algorithm model, such as convolution
Neural network, Bayesian probability deduction etc..
Refering to attached drawing 3, Fig. 3 illustrates the primary structure of product quality feedback subsystem, product matter as shown in Figure 3
Amount feedback subsystem 2 may include that second feature obtains module 21, Product Quality Evaluation module 22 and product quality feedback module
23, second feature obtains module 21 and is configured to respectively to physical state data and O&M detection data progress extraction of semantics and right
Extraction of semantics result carries out data fusion；The data that Product Quality Evaluation module 22 is configured to obtain module according to second feature are melted
It closes result and quality evaluation is carried out to product, obtain the quality evaluation result of product；Product quality feedback module 23 is configured to basis
Data training set in the quality evaluation result of product more new knowledge base, so that model training module is instructed according to updated data
Practice collection amendment product quality knowledge reasoning model.Specifically, product quality feedback subsystem 2 be using product in logistics transportation and
Generated data carry out Feedback Evaluation to product quality in O&M service process, to feed back the actual use feelings of product quality
Condition, thus more new knowledge base and product quality knowledge reasoning model, to predict more accurate product quality grade.
Refering to attached drawing 4, Fig. 4 illustrates the primary structure that second feature obtains module, second feature as shown in Figure 4
Obtaining module 21 may include third data prediction mould block 211 and the 4th data prediction submodule 212, and third data are pre-
Virgin manages module 211 and is configured to carry out data cleansing to physical state data and O&M detection data respectively, so as to second feature
Module 21 is obtained according to the physical state data and O&M detection data progress extraction of semantics after data cleansing；4th data are located in advance
Reason submodule 212 is configured to carry out data fusion to extraction of semantics result.
Refering to attached drawing 5, the Life cycle knowledge towards product quality that Fig. 5 illustrates another embodiment is automatic
Change the primary structure of evaluation system, the Life cycle Assessment system towards product quality can also wrap as shown in Figure 5
Data acquisition subsystem 3 is included, data acquisition subsystem 3 is configured to the R & D design data of acquisition product, manufactures data, object
Stream mode data and O&M detection data, and R & D design data and manufacturing data are sent to product quality forecast
System 1, and physical state data and O&M detection data are sent to product quality feedback subsystem 2.Data acquisition system
System 3 may include the server cluster being made of multiple data acquisition servers, such as relational database cluster, Cloudera big
Data cluster etc..
Refering to attached drawing 6, the Life cycle knowledge towards product quality that Fig. 6 illustrates another embodiment is automatic
Change the main working process of evaluation system, as shown in Figure 6 the Life cycle autoknowledge evaluation system towards product quality
Including data acquisition subsystem 3, product quality forecast subsystem 1, product quality feedback subsystem 2, the packet of data acquisition subsystem 3
The service centre being made of multiple data acquisition servers is included, product quality forecast subsystem 1 includes knowledge base and product quality
Knowledge reasoning model, Product Quality Evaluation subsystem 2 include Product Quality Evaluation model.Specifically, product lifecycle mistake
Journey includes R & D design, the manufacturing, logistics sale and O&M service.Data center is to R & D design, the manufacturing, logistics pin
Sell with O&M service structuring, semi-structured and unstructured data that each stage generates be acquired, transimission and storage etc.,
Wherein, R & D design data and manufacturing data are sent to product quality forecast subsystem 1 by data center, by physical state
Data and O&M detection data are sent to product quality feedback subsystem 2.Product quality forecast subsystem 1 is respectively to receiving
R & D design data and the extraction that data carry out data prediction and primary semantic knowledge is manufactured, and by the primary of extraction
Semantic knowledge carries out knowledge fusion, obtains primary semantic knowledge.Knowledge base is constructed based on obtained primary semantic knowledge, using knowing
Know library training product quality knowledge reasoning model, carries out product quality grade using trained product quality knowledge reasoning model
Prediction.It is pre- that product quality feedback subsystem 2 carries out data to the physical state data and O&M detection data received respectively
Processing, and pretreated physical state data and O&M detection data are subjected to data fusion, Product Quality Evaluation model root
Quality evaluation is carried out according to the fused data of physical state data and O&M detection data, obtains evaluation result, is based on the evaluation knot
Fruit more new knowledge base, to utilize updated knowledge base re -training product quality inference pattern.
Those skilled in the art should be able to recognize that, mould described in conjunction with the examples disclosed in the embodiments of the present disclosure
Block and system, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate electronic hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are executed actually with electronic hardware or software mode, the specific application and design constraint item depending on technical solution
Part.Those skilled in the art can use different methods to achieve the described function each specific application, but this
Kind is realized and be should not be considered as beyond the scope of the present invention.
Term " first ", " second " etc. are to be used to distinguish similar objects, rather than be used to describe or indicate specific suitable
Sequence or precedence.
Term " includes " or any other like term are intended to cover non-exclusive inclusion, so that including a system
Process, method, article or equipment/device of column element not only includes those elements, but also including being not explicitly listed
Other elements, or further include the intrinsic element of these process, method, article or equipment/devices.
So far, it has been combined preferred embodiment shown in the drawings and describes technical solution of the present invention, still, this field
Technical staff is it is easily understood that protection scope of the present invention is expressly not limited to these specific embodiments.Without departing from this
Under the premise of the principle of invention, those skilled in the art can make equivalent change or replacement to the relevant technologies feature, these
Technical solution after change or replacement will fall within the scope of protection of the present invention.
Claims (7)
1. a kind of Life cycle autoknowledge evaluation system towards product quality, which is characterized in that the system comprises
Product quality forecast subsystem and product quality feedback subsystem, the product quality forecast subsystem include that fisrt feature obtains
Module and product quality forecast module；
The fisrt feature obtains module and is configured to respectively make the R & D design data of the product obtained in advance and production
It makes data to carry out extraction of semantics and carry out data fusion to extraction of semantics result, obtains primary semantic knowledge；
The product quality forecast module is configured to predict the credit rating of the product according to the primary semantic knowledge；
The product quality feedback subsystem is configured to be examined according to the physical state data and O&M of the product obtained in advance
Measured data updates the product quality forecast module, so that the updated product quality forecast module is predicted to obtain the production
The real quality grade of product.
2. the Life cycle autoknowledge evaluation system according to claim 1 towards product quality, feature exist
In, the fisrt feature obtains module and includes the first data prediction submodule and the second data prediction submodule,
The pre- virgin of first data manages module and is configured to respectively count the R & D design data and manufacturing data
According to cleaning, so that the fisrt feature obtains module according to the R & D design data after the data cleansing and manufactures data
Carry out extraction of semantics；
The second data prediction submodule is configured to obtain primary semanteme to extraction of semantics result progress data fusion
Knowledge.
3. the Life cycle autoknowledge evaluation system according to claim 1 towards product quality, feature exist
In the product quality forecast module includes product quality knowledge reasoning model, and the system also includes knowledge bases and model to instruct
Practice module,
The knowledge base is configured to store preset data training set, and the data training set includes the first of multiple preset products
Grade semantic knowledge；
The model training module is configured to instruct the product quality knowledge reasoning model according to the data training set
Practice, so that the product quality knowledge reasoning model after the training can predict the production according to the primary semantic knowledge of current production
The credit rating of product.
4. the Life cycle autoknowledge evaluation system according to claim 3 towards product quality, feature exist
In the product quality feedback subsystem includes that second feature obtains module, Product Quality Evaluation module and product quality feedback
Module,
The second feature obtains module and is configured to carry out extraction of semantics simultaneously to physical state data and O&M detection data respectively
And data fusion is carried out to extraction of semantics result；
The Product Quality Evaluation module is configured to obtain the data fusion result of module to the production according to the second feature
Product carry out quality evaluation, obtain the quality evaluation result of the product；
The product quality feedback module is configured to update the number in the knowledge base according to the quality evaluation result of the product
According to training set, the product quality knowledge is corrected according to the updated data training set so as to the model training module and is pushed away
Manage model.
5. the Life cycle autoknowledge evaluation system according to claim 4 towards product quality, feature exist
Obtaining module in, the second feature includes third data prediction mould block and the 4th data prediction submodule,
The pre- virgin of third data manages module and is configured to respectively count the physical state data and O&M detection data
According to cleaning, so that the second feature obtains module according to the physical state data and O&M detection data after the data cleansing
Carry out extraction of semantics；
The 4th data prediction submodule is configured to carry out data fusion to the extraction of semantics result.
6. the Life cycle autoknowledge according to any one of claim 1 to 5 towards product quality evaluates system
System, which is characterized in that the system also includes data acquisition subsystem,
The data acquisition subsystem is configured to acquire the R & D design data of the product, manufactures data, physical state
Data and O&M detection data, and
It by the R & D design data and manufactures data and is sent to the product quality forecast subsystem, and by the object
Stream mode data and O&M detection data are sent to the product quality feedback subsystem.
7. the Life cycle autoknowledge evaluation system according to claim 6 towards product quality, feature exist
In the data acquisition subsystem includes the server cluster being made of multiple data acquisition servers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811393527.XA CN109685316A (en) | 2018-11-21 | 2018-11-21 | Life cycle autoknowledge evaluation system towards product quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811393527.XA CN109685316A (en) | 2018-11-21 | 2018-11-21 | Life cycle autoknowledge evaluation system towards product quality |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109685316A true CN109685316A (en) | 2019-04-26 |
Family
ID=66185406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811393527.XA Pending CN109685316A (en) | 2018-11-21 | 2018-11-21 | Life cycle autoknowledge evaluation system towards product quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109685316A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198524A (en) * | 2019-12-27 | 2020-05-26 | 苏州数设科技有限公司 | Product data processing method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303296A (en) * | 2015-09-29 | 2016-02-03 | 国网浙江省电力公司电力科学研究院 | Electric power equipment full-life state evaluation method |
-
2018
- 2018-11-21 CN CN201811393527.XA patent/CN109685316A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303296A (en) * | 2015-09-29 | 2016-02-03 | 国网浙江省电力公司电力科学研究院 | Electric power equipment full-life state evaluation method |
Non-Patent Citations (5)
| Title |
|---|
| KAI ZHANG ET AL.: "Research on Assembly Data Mining Technology of Complex Mechanical System", 《6TH CIRP CONFERENCE ON ASSEMBLY TECHNOLOGIES AND SYSTEMS (CATS)》 * |
| 江宜春: "面向产品全生命周期的质量管理关键技术及系统研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
| 郑院生等: "基于ETL思想的产品全生命周期质量数据整合", 《成组技术与生产现代化》 * |
| 郭钧: "数据挖掘技术在光电子企业产品质量管理中的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 高建荣等: "基于产品生命周期的质量数据分析与数据挖掘", 《智能制造》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198524A (en) * | 2019-12-27 | 2020-05-26 | 苏州数设科技有限公司 | Product data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kannan et al. | A hybrid approach using ISM and fuzzy TOPSIS for the selection of reverse logistics provider | |
| Azadnia et al. | Order batching in warehouses by minimizing total tardiness: a hybrid approach of weighted association rule mining and genetic algorithms | |
| CN102016730B (en) | Autonomous adaptive semiconductor manufacturing | |
| CN111401808A (en) | Material agreement inventory demand prediction method based on hybrid model | |
| Tombido et al. | A systematic review of 3pls’ entry into reverse logistics | |
| Munirathinam et al. | Big data predictive analtyics for proactive semiconductor equipment maintenance | |
| Ma et al. | A big data-driven root cause analysis system: Application of Machine Learning in quality problem solving | |
| CN102449623A (en) | Method and system for detection of tool performance degradation and mismatch | |
| CN108197737A (en) | A kind of method and system for establishing medical insurance hospitalization cost prediction model | |
| CN104246798A (en) | Problem analysis and priority determination based on fuzzy expert systems | |
| CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
| US20230123527A1 (en) | Distributed client server system for generating predictive machine learning models | |
| CN112712314A (en) | Logistics data recommendation method based on sensor of Internet of things | |
| CN116540584A (en) | Intelligent management and control system of unmanned production line of fusion-cast charging | |
| Velmurugan et al. | SME 4.0: Machine learning framework for real-time machine health monitoring system | |
| Lyu et al. | A data-driven approach for identifying possible manufacturing processes and production parameters that cause product defects: A thin-film filter company case study | |
| Yang et al. | Development of a predictive maintenance platform for cyber-physical systems | |
| CN109685316A (en) | Life cycle autoknowledge evaluation system towards product quality | |
| CN117319452B (en) | Safety inspection method and system applied to barium sulfate preparation | |
| Chen et al. | Artificial Intelligence and Lean Manufacturing | |
| Heydarbakian et al. | Interpretable machine learning to improve supply chain resilience, an industry 4.0 Recipe | |
| Bahrampour et al. | Designing a Scenario‐Based Fuzzy Model for Sustainable Closed‐Loop Supply Chain Network considering Statistical Reliability: A New Hybrid Metaheuristic Algorithm | |
| Bazargan-Lari et al. | A hybrid data-driven approach for forecasting the characteristics of production disruptions and interruptions | |
| Iqbal et al. | Selecting a Multicriteria Inventory Classification Model to Improve Customer Order Fill Rate. | |
| Lau et al. | Monitoring the supply of products in a supply chain environment: a fuzzy neural approach |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |