CN109785180A - A kind of scene perception system and method towards the twin workshop of number - Google Patents
A kind of scene perception system and method towards the twin workshop of number Download PDFInfo
- Publication number
- CN109785180A CN109785180A CN201910124344.6A CN201910124344A CN109785180A CN 109785180 A CN109785180 A CN 109785180A CN 201910124344 A CN201910124344 A CN 201910124344A CN 109785180 A CN109785180 A CN 109785180A
- Authority
- CN
- China
- Prior art keywords
- data
- information
- module
- lathing
- machine
- 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
- 230000008447 perception Effects 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000013517 stratification Methods 0.000 claims abstract description 13
- 238000005065 mining Methods 0.000 claims abstract description 10
- 238000007418 data mining Methods 0.000 claims abstract description 9
- 230000008094 contradictory effect Effects 0.000 claims abstract description 8
- 230000007613 environmental effect Effects 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013501 data transformation Methods 0.000 claims description 5
- 238000003745 diagnosis Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000005457 optimization Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000004321 preservation Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 210000001520 comb Anatomy 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of scene perception system and methods towards the twin workshop of number, including sequentially connected data acquisition module, scene perception module, data-mining module;Data acquisition module is for obtaining NC lathing information data;Scene perception module is for pre-processing the NC lathing information data that data acquisition module obtains;NC lathing ontology model is constructed, builds the stratification relationship between data, and detect by ontology inference and eliminate contradictory information, by the way that data after the pretreatment being stored in front of are loaded into NC lathing ontology model, realizes the instantiation of NC lathing ontology model;Data-mining module is used to excavate in data and potentially be associated with by mining algorithm needed for operation user.The present invention solves the problem of " big data, small information " present in manufacturing process, the twin plant model of real-time update number using scene perception technology and Ontology Modeling technology, and can be used as the basis of the subsequent operations such as failure predication, objective optimization.
Description
Technical field
It is specifically a kind of high the present invention relates to a kind of scene perception system and method towards the twin workshop of number
Effect, the perceptual strategy for accurately, being automatically acquired to the data in manufacturing environment, analyzing, handle, storing, utilizing, belong to big
Data processing and context-aware technology field.
Background technique
Digital Twin number is twin, is to make full use of the data such as physical model, sensor update, history run, collection
At multidisciplinary, more physical quantitys, the simulation process of multiple dimensioned, more probability, mapping is completed in Virtual Space, to reflect corresponding
Entity equipment lifecycle process technology.
Currently, workshop informationization technology has tended to mature, its development is to pursue process automation, improve product processing
Precision reduces labor intensity of workers.Workshop informationization technology provides a large amount of data source for realization intelligence manufacture, however, by
In the complexity of workshop appliance and environment, the status data of acquisition is usually complexity, couples, time-varying, there is " big data,
The problem of small information ", directly carries out intelligent decision using these data building data set, it is low and effective to be easy to appear treatment effeciency
Acquisition of information difficulty and insufficient phenomenon.Therefore, in order to allow the data information in the twin workshop of number become it is valuable can benefit
With, there is an urgent need to a kind of scene perception methods and device towards the twin workshop of number, processing storage automatically is carried out to data,
To fill up this blank.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of scene perception system towards the twin workshop of number and sides
Method.
Term is explained:
1, ontology inference refers on the basis of the ontology model of building, inference rule is loaded on inference machine, to ontology
The consistency of model is detected, and the contradictory information for wherein repeating to indicate is eliminated, and combs logical relation, and sort out the reality newly introduced
Example.
2, superior context information refers to the letter that people, machine, application program are readable, extract from the scene of workshop
Breath.
3, data cleansing, refer to by acquired original to data handle, eliminate missing therein, repeat, abnormal letter
Breath.
4, data integration refers to and integrates what data collected in different data sources, data warehouse were unified, passes through
Different data is moved into same mode, to provide consistent available data for user.
5, data regularization refers to and deletes original mass data, only retains negligible amounts but can represent original
The data set of beginning data.
6, data convert, and refer to according to using algorithm, carry out dimension processing or the planning again of data area to data,
The common comparison for facilitating different attribute data, improves the utilization efficiency of algorithm.
7, the twin workshop of number refers to that the twin body of number with NC lathing, NC lathing are present in physical world, number
Twin workshop is its accurate mapping in digital space.
The technical solution of the present invention is as follows:
A kind of scene perception system towards the twin workshop of number, including sequentially connected data acquisition module, scene sense
Know module, data-mining module;
The data acquisition module includes personnel's letter for obtaining NC lathing information data, NC lathing information data
Breath, machine information, product information and environmental information, personal information include operating time and personnel position, machine information packet
Machine coordinates, machine speed, machine acceleration and machine temperature are included, product information includes number of packages and surface quality, environmental information
Including environment temperature, ambient humidity;
The NC lathing information data that the scene perception module is used to obtain the data acquisition module is located in advance
Pretreated data are stored in database and used for subsequent applications algorithm and Model instantiation by reason;At the same time, numerical control is constructed
Workshop ontology model builds the stratification relationship between data, and eliminates contradictory information therein by ontology inference detection, leads to
Data are loaded into NC lathing ontology model after crossing the pretreatment that will be stored in front of, the example for realizing NC lathing ontology model
Change, form the superior context information of owl language description, is stored in the calling in database for application program;
The data-mining module passes through operation for utilizing to the data after the scene perception resume module
Mining algorithm needed for user, excavates in data and is potentially associated with.For example, finding machine failure number by neural network algorithm
According to the potential relationship between fault type, to be diagnosed by collected machine tool data, predict failure.
Preferred according to the present invention, the scene perception module includes data preprocessing module, ontology model module, data
Library module;
Personal information that the data preprocessing module is used to obtain the data acquisition module, machine information, product
Information and environmental information successively carry out the operation of data cleansing, data integration, hough transformation, data transformation;The ontology model
Module includes embodying the belonging relation and its packet of data to the stratification statement of personnel, machine, product and environment and corresponding relationship
The attribute contained, and the information and contradictory information for repeating statement, the new introducing member of automatic clustering are removed by ontology inference;The number
It include data and the height after being instantiated by ontology model module after NC lathing information data, pretreatment according to library module
Grade contextual information.
Preferred according to the present invention, the data acquisition module includes different types of data pick-up, including position passes
Sensor, velocity sensor, acceleration transducer, temperature sensor, vibrating sensor.By by sensor arrangement in needing to acquire
The position of data obtains NC lathing newest status information in time.
A kind of scene perception method towards the twin workshop of number, comprises the following steps that
(1) personal information, machine information, product information and environmental information are obtained;
(2) personal information, machine information, product information and environmental information are pre-processed and is saved, while constructing this
The stratification expression of body Model and its corresponding relationship eliminate potential contradiction by ontology inference, and using pre-processing and save
Data carry out instantiation operation, obtain superior context information;Data and height after preservation NC lathing information data, pretreatment
Grade contextual information, for inquiring and calling;
(3) information decoupling is carried out to superior context information by mining algorithm, excavates data and failure, running optimizatin
Potential relationship.
In step (1), personal information, machine information, product information and environmental information are obtained, refers to: being acquired according to workshop
The needs of data pass through workshop using sensor, handheld reader, production equipment, intelligent terminal, human-computer interaction, RFID technique
Bus or wifi network obtain personal information, machine information, product information and environmental information.
It is preferred according to the present invention, the step (2), to personal information, machine information, product information and environmental information into
Row pretreatment, refers to:
Data cleansing, data set are successively carried out to the personal information of acquisition, machine information, product information and environmental information
At, hough transformation, data transformation operation, using existing algorithm and remove the interference information in data, interference information refers to scarce
It loses, abnormal or duplicate data.The degree of redundancy for reducing data improves the operational efficiency of algorithm and accurate using the data simplified
Degree.
Preferred according to the present invention, the step (2) constructs stratification expression and its corresponding relationship of ontology model, is
Refer to:
A, personnel, machine, product, the big parent of environment four and its subclass for being included in NC lathing are constructed, is completed
Class and hierarchical relationship;
B, object properties, i.e. corresponding relationship between inhomogeneity are defined;E.g., including " design " of the personnel to product, personnel
" adjustment " to environment, " operation " of the personnel to machine, " processing " of the machine to product, environment is on " influence " of product etc.;
C, numerical attribute, i.e., the data with specific value that different objects include are defined.E.g., including " position " " is sat
Mark ", " speed ", " acceleration ", " temperature ", " humidity ", " stress " etc., with specific reference to the limitation of workshop needs and acquisition mode
To define.
Preferred according to the present invention, the step (2) eliminates potential contradiction by ontology inference, and simultaneously using pretreatment
The data of preservation carry out instantiation operation, obtain superior context information, refer to:
D, on the basis of ontology model, inference rule is defined, utilizes inference machine discovery patrolling in ontology model building
Volume mistake, eliminates duplicate statement, while simplifying ontology model, part that automatic clustering newly defines;
E, after ontology inference, preprocessed data is loaded onto ontology model, completes the instantiation of ontology model frame,
The superior context information of the owl language description of formation.The calling of model in utilization and different workshops for application program.
Preferred according to the present invention, the step (3) carries out information solution to superior context information by mining algorithm
Coupling is excavated data and failure, the potential relationship of running optimizatin, is referred to:
F, according to user demand selection algorithm, load operating is carried out to data;(running optimizatin is same by taking fault diagnosis as an example
Reason), the convolutional neural networks on multiple bases are defined first as operation algorithm, are input with fault data, fault type is defeated
Basic model is built out.
G, pretreated data are extracted from database, the part 60%-80% is defined as training set, remainder
It is defined as verifying collection;
H, single convolutional neural networks are trained using training set, by adjusting parameter, are obtained not known
Implication relation between data and failure, and verified by verifying collection, until obtaining the parameter value of the highest algorithm of accuracy;
I, by comparing the accuracy of algorithms of different, obtain in whole algorithms to fault diagnosis parameter set the most accurate and
Its respective algorithms frame;
J, the algorithm completed using training is tested new collected data, to judge current data and failure classes
The corresponding relationship of type.
The invention has the benefit that
Scene perception system and method for the present invention overcomes the problem of " big data, small information " present in workshop condition,
The contextual data for obtaining time-varying is acquired by data incessantly;The letter of invalid, interference, redundancy is rejected by the pretreatment of data
Breath, guarantee data consistency and boosting algorithm for data utilization speed;It is hierarchically stated by constructing ontology model
Relationship between data eliminates implicit contradiction, and reusing the instantiation of preprocessed data ontology model, to obtain people, machine, program readable
Superior context information.By the reading and storage to initial data, preprocessed data and superior context data, guarantee
Data can timely, effective, true consersion unit state, personal information and locating workshop condition;By twin to number
Workshop big data is excavated, it can be found that digital control system or engineer are difficult to the rule implied between the data and phenomenon found
With logic, support is provided for advanced technologies such as quality testing, fault pre-alarming, objective optimizations, to realize that intelligence manufacture provides base
Plinth.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of scene perception system of the present invention towards the twin workshop of number;
Fig. 2 is the specific implementation process schematic diagram of scene perception of the present invention;
Fig. 3 is the specific implementation process schematic diagram of data mining of the present invention;
Specific embodiment
The present invention is further qualified with embodiment with reference to the accompanying drawings of the specification, but not limited to this.
Embodiment 1
A kind of scene perception system towards the twin workshop of number, as shown in Figure 1, including sequentially connected data acquisition module
Block, scene perception module, data-mining module;
For data acquisition module for obtaining NC lathing information data, NC lathing information data includes personal information, machine
Device information, product information and environmental information, personal information include operating time and personnel position, and machine information includes machine
Coordinate, machine speed, machine acceleration and machine temperature, product information include number of packages and surface quality, and environmental information includes ring
Border temperature, ambient humidity;
Scene perception module will be located in advance for pre-processing to the NC lathing information data that data acquisition module obtains
Data deposit database after reason is used for subsequent applications algorithm and Model instantiation;At the same time, NC lathing ontology is constructed
Model builds the stratification relationship between data, and eliminates contradictory information therein by ontology inference detection, by by before
Data are loaded into NC lathing ontology model after the pretreatment of deposit, realize the instantiation of NC lathing ontology model, are formed
The superior context information of owl language description is stored in the calling in database for application program;
Data-mining module is for utilizing the data after scene perception resume module, by needed for operation user
Mining algorithm is excavated in data and is potentially associated with.For example, finding machine failure data and failure classes by neural network algorithm
Potential relationship between type, to be diagnosed by collected machine tool data, predict failure.
Scene perception module includes data preprocessing module, ontology model module, database module;
Data preprocessing module is used for personal information, machine information, product information and the ring obtained to data acquisition module
Border information successively carries out the operation of data cleansing, data integration, hough transformation, data transformation;Ontology model module includes to people
Member, machine, product and environment stratification statement and corresponding relationship, embody data belonging relation and it includes attribute, and
The information and contradictory information for repeating statement, the new introducing member of automatic clustering are removed by ontology inference;Database module includes number
Control workshop information data, data and the superior context information after being instantiated by ontology model module after pretreatment.
Data acquisition module includes different types of data pick-up, including position sensor, velocity sensor, acceleration
Sensor, temperature sensor, vibrating sensor.By the way that sensor arrangement in the position for needing to acquire data, is obtained number in time
Control workshop newest status information.The methods such as handheld reader, production equipment, intelligent terminal, human-computer interaction are additionally included, it can be with
Obtain equipment, environment and personnel state information data, data transfer mode by workshop bus, Wifi, bluetooth, RFID,
The composition such as RS232.
Embodiment 2
A kind of scene perception method towards the twin workshop of number, comprises the following steps that
(1) personal information, machine information, product information and environmental information are obtained;
(2) personal information, machine information, product information and environmental information are pre-processed and is saved, while constructing this
The stratification expression of body Model and its corresponding relationship eliminate potential contradiction by ontology inference, and using pre-processing and save
Data carry out instantiation operation, obtain superior context information;Data and height after preservation NC lathing information data, pretreatment
Grade contextual information, for inquiring and calling;As shown in Figure 2.
(3) information decoupling is carried out to superior context information by mining algorithm, excavates data and failure, running optimizatin
Potential relationship.As shown in Figure 3.
In step (1), personal information, machine information, product information and environmental information are obtained, refers to: being acquired according to workshop
The needs of data pass through workshop using sensor, handheld reader, production equipment, intelligent terminal, human-computer interaction, RFID technique
Bus or wifi network obtain personal information, machine information, product information and environmental information.
In steps (2), personal information, machine information, product information and environmental information are pre-processed, referred to:
Data cleansing, data set are successively carried out to the personal information of acquisition, machine information, product information and environmental information
At, hough transformation, data transformation operation, using existing algorithm and remove the interference information in data, interference information refers to scarce
It loses, abnormal or duplicate data.The degree of redundancy for reducing data improves the operational efficiency of algorithm and accurate using the data simplified
Degree.
In steps (2), stratification expression and its corresponding relationship of ontology model are constructed, is referred to:
A, personnel, machine, product, the big parent of environment four and its subclass for being included belonging to NC lathing are constructed, it is complete
At class and hierarchical relationship;
B, object properties, i.e. corresponding relationship between inhomogeneity are defined;E.g., including " design " of the personnel to product, personnel
" adjustment " to environment, " operation " of the personnel to machine, " processing " of the machine to product, environment is on " influence " of product etc..
C, numerical attribute, i.e., the data with specific value that different objects include are defined.E.g., including " position " " is sat
Mark ", " speed ", " acceleration ", " temperature ", " humidity ", " stress " etc., with specific reference to the limitation of workshop needs and acquisition mode
To define.
In step (2), potential contradiction is eliminated by ontology inference, and using pre-processing and the data saved are instantiated
Operation obtains superior context information, refers to:
D, on the basis of ontology model, inference rule is defined, utilizes inference machine discovery patrolling in ontology model building
Volume mistake, eliminates duplicate statement, while simplifying ontology model, part that automatic clustering newly defines;
E, after ontology inference, preprocessed data is loaded onto ontology model, completes the instantiation of ontology model frame,
The superior context information of the owl language description of formation.The calling of model in utilization and different workshops for application program.
In step (3), information decoupling is carried out to superior context information by mining algorithm, excavates data and failure, fortune
The potential relationship of row optimization, refers to:
F, it is based on Weka software, according to user demand selection algorithm, load operating is carried out to data;By taking fault diagnosis as an example
(running optimizatin is similarly) defines the convolutional neural networks on multiple bases as operation algorithm first, is input with fault data, therefore
Barrier type is that basic model is built in output;
G, pretreated data are extracted from database, the part 60%-80% is defined as training set, remainder
It is defined as verifying collection;
H, single convolutional neural networks are trained using training set, by adjusting parameter, are obtained not known
Implication relation between data and failure, and verified by verifying collection, until obtaining the parameter value of the highest algorithm of accuracy;
Training set, adjustment algorithm parameter are loaded in algorithms of different, application verification collection carries out longitudinal comparison to the arithmetic result of generation, really
Determine optimized parameter;
I, by comparing the accuracy of algorithms of different, obtain in whole algorithms to fault diagnosis parameter set the most accurate and
Its respective algorithms frame;The algorithm performance that each training set of across comparison generates obtains the algorithm of best performance and its corresponding
Characteristic parameter forms the mapping of " application scenarios-manufaturing data ";
J, the algorithm completed using training is tested new collected data, to judge current data and failure classes
The corresponding relationship of type.It is quality testing, fault pre-alarming, objective optimization using the variation of generating algorithm real time monitoring manufaturing data
Equal offers support.
For the ordinary skill in the art, introduction according to the present invention, do not depart from the principle of the present invention with
In the case where spirit, changes, modifications that embodiment is carried out, replacement and variant still fall within protection scope of the present invention it
It is interior.
Claims (8)
1. a kind of scene perception system towards the twin workshop of number, which is characterized in that including sequentially connected data acquisition module
Block, scene perception module, data-mining module;
For the data acquisition module for obtaining NC lathing information data, NC lathing information data includes personal information, machine
Device information, product information and environmental information, personal information include operating time and personnel position, and machine information includes machine
Coordinate, machine speed, machine acceleration and machine temperature, product information include number of packages and surface quality, and environmental information includes ring
Border temperature, ambient humidity;
The NC lathing information data that the scene perception module is used to obtain the data acquisition module pre-processes, will
Pretreated data deposit database is used for subsequent applications algorithm and Model instantiation;At the same time, NC lathing is constructed
Ontology model, builds the stratification relationship between data, and eliminates contradictory information therein by ontology inference detection, pass through by
Data are loaded into NC lathing ontology model the pretreatment being stored in front of after, realize the instantiation of NC lathing ontology model,
The superior context information of owl language description is formed, the calling in database for application program is stored in;
The data-mining module is for utilizing the data after the scene perception resume module, by running user
Required mining algorithm, excavates in data and is potentially associated with.
2. a kind of scene perception system towards the twin workshop of number according to claim 1, which is characterized in that the field
Scape sensing module includes data preprocessing module, ontology model module, database module;
Personal information that the data preprocessing module is used to obtain the data acquisition module, machine information, product information
And environmental information successively carries out the operation of data cleansing, data integration, hough transformation, data transformation;The ontology model module
Including to personnel, machine, product and environment stratification statement and corresponding relationship, embody data belonging relation and it includes
Attribute, and the information and contradictory information for repeating statement, the new introducing member of automatic clustering are removed by ontology inference;The database
Module includes after NC lathing information data, pretreatment on data and advanced after being instantiated by ontology model module
Context information.
3. a kind of scene perception system towards the twin workshop of number according to claim 1, which is characterized in that the number
It include different types of data pick-up, including position sensor, velocity sensor, acceleration transducer, temperature according to acquisition module
Spend sensor, vibrating sensor.
4. a kind of scene perception method towards the twin workshop of number, which is characterized in that comprise the following steps that
(1) personal information, machine information, product information and environmental information are obtained;
(2) personal information, machine information, product information and environmental information are pre-processed and is saved, while constructing ontology mould
The stratification expression of type and its corresponding relationship eliminate potential contradiction by ontology inference, and use the data for pre-processing and saving
Instantiation operation is carried out, superior context information is obtained;Save NC lathing information data, after pretreatment data and it is advanced on
Context information, for inquiring and calling;
(3) information decoupling is carried out to superior context information by mining algorithm, excavate data and failure, running optimizatin it is potential
Relationship.
5. a kind of scene perception method towards the twin workshop of number according to claim 4, which is characterized in that the step
Suddenly (2) pre-process personal information, machine information, product information and environmental information, refer to:
Data cleansing, data integration, number are successively carried out to the personal information of acquisition, machine information, product information and environmental information
According to the operation that specification, data convert, and the interference information in data is removed, interference information refers to missing, abnormal or duplicate number
According to.
6. a kind of scene perception method towards the twin workshop of number according to claim 4, which is characterized in that the step
Suddenly (2) construct stratification expression and its corresponding relationship of ontology model, refer to:
A, personnel, machine, product, the big parent of environment four and its subclass for being included belonging to NC lathing are constructed, class is completed
And hierarchical relationship;
B, object properties, i.e. corresponding relationship between inhomogeneity are defined;
C, numerical attribute, i.e., the data with specific value that different objects include are defined.
7. a kind of scene perception method towards the twin workshop of number according to claim 4, which is characterized in that the step
Suddenly (2) eliminate potential contradiction by ontology inference, and carry out instantiation operation using the data for pre-processing and saving, and obtain high
Grade contextual information, refers to:
D, on the basis of ontology model, inference rule is defined, it is wrong using logic of the inference machine discovery in ontology model building
Accidentally, duplicate statement is eliminated, while simplifying ontology model, part that automatic clustering newly defines;
E, after ontology inference, preprocessed data is loaded onto ontology model, completes the instantiation of ontology model frame, is formed
Owl language description superior context information.
8. according to a kind of any scene perception method towards the twin workshop of number of claim 4-7, which is characterized in that
The step (3) carries out information decoupling to superior context information by mining algorithm, excavates data and failure, running optimizatin
Potential relationship, refer to:
F, according to user demand selection algorithm, load operating is carried out to data;
G, pretreated data are extracted from database, the part 60%-80% is defined as training set, remainder definition
For verifying collection;
H, single convolutional neural networks are trained using training set, by adjusting parameter, are obtained hidden between data and failure
It is verified containing relationship, and by verifying collection, until obtaining the parameter value of the highest algorithm of accuracy;
I, it by comparing the accuracy of algorithms of different, obtains in whole algorithms to fault diagnosis parameter set the most accurate and its phase
Answer algorithm frame;
J, the algorithm completed using training tests new collected data, to judge current data and fault type
Corresponding relationship.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910124344.6A CN109785180A (en) | 2019-02-19 | 2019-02-19 | A kind of scene perception system and method towards the twin workshop of number |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910124344.6A CN109785180A (en) | 2019-02-19 | 2019-02-19 | A kind of scene perception system and method towards the twin workshop of number |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109785180A true CN109785180A (en) | 2019-05-21 |
Family
ID=66504667
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910124344.6A Pending CN109785180A (en) | 2019-02-19 | 2019-02-19 | A kind of scene perception system and method towards the twin workshop of number |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109785180A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110187686A (en) * | 2019-06-03 | 2019-08-30 | 济南浪潮高新科技投资发展有限公司 | A kind of Internet of Things industrial processes monitoring method based on the twin technology of number |
CN110276147A (en) * | 2019-06-24 | 2019-09-24 | 广东工业大学 | A kind of manufacture system fault source tracing method, system based on the twin model of number |
CN110442737A (en) * | 2019-07-11 | 2019-11-12 | 北京飞利信电子技术有限公司 | The twin method and system of number based on chart database |
CN110674581A (en) * | 2019-09-27 | 2020-01-10 | 北京航空航天大学 | Method and system for accurately judging consistency of digital twin model |
CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
CN111026063A (en) * | 2019-12-25 | 2020-04-17 | 南方科技大学 | Digital twin construction method and device, computer equipment and storage medium |
CN111061318A (en) * | 2019-12-27 | 2020-04-24 | 清华大学无锡应用技术研究院 | Digital twinning control method for temperature field of silicon carbide coating deposition furnace |
CN112016737A (en) * | 2020-08-05 | 2020-12-01 | 东北大学秦皇岛分校 | Digital twin-based complex product assembly workshop management and control method |
CN112231305A (en) * | 2020-08-23 | 2021-01-15 | 山东翰林科技有限公司 | Digital power grid system and method based on digital twinning |
CN112365167A (en) * | 2020-11-13 | 2021-02-12 | 广西电网有限责任公司南宁供电局 | Dynamic ontology model-based power grid equipment digital twin construction method and device |
CN112418455A (en) * | 2020-11-28 | 2021-02-26 | 北京三维天地科技股份有限公司 | Equipment failure prediction and health management system |
CN112462696A (en) * | 2020-08-18 | 2021-03-09 | 江苏大学 | Intelligent manufacturing workshop digital twin model construction method and system |
CN112947173A (en) * | 2021-02-03 | 2021-06-11 | 北京理工大学 | Method, controller and system for predicting running state of digital twin workshop |
CN113126580A (en) * | 2021-03-24 | 2021-07-16 | 东北大学 | Assembly control method and device based on digital twins and computer equipment |
CN113890831A (en) * | 2021-10-20 | 2022-01-04 | 中国联合网络通信集团有限公司 | Method, device and storage medium for simulating network equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710343A (en) * | 2009-12-11 | 2010-05-19 | 北京中机科海科技发展有限公司 | Body automatic build system and method based on text mining |
CN106530111A (en) * | 2016-12-01 | 2017-03-22 | 东华大学 | CPS architecture oriented to intelligent cotton spinning production |
US20180129941A1 (en) * | 2016-11-10 | 2018-05-10 | General Electric Company | Methods and systems for capturing analytic model authoring knowledge |
CN108107841A (en) * | 2017-12-26 | 2018-06-01 | 山东大学 | A kind of twin modeling method of numerically-controlled machine tool number |
CN108427390A (en) * | 2018-04-16 | 2018-08-21 | 长安大学 | A kind of the workshop level intelligent manufacturing system and its configuration method twin based on number |
EP3376361A2 (en) * | 2017-10-19 | 2018-09-19 | Pure Storage, Inc. | Ensuring reproducibility in an artificial intelligence infrastructure |
CN109062177A (en) * | 2018-06-29 | 2018-12-21 | 无锡易通精密机械股份有限公司 | A kind of Trouble Diagnostic Method of Machinery Equipment neural network based and system |
CN109116751A (en) * | 2018-07-24 | 2019-01-01 | 西安西电电气研究院有限责任公司 | Digitization system and its construction method based on the twin technology of number |
CN109343496A (en) * | 2018-11-14 | 2019-02-15 | 中国电子工程设计院有限公司 | Applied to industrial digital twinned system and forming method thereof |
-
2019
- 2019-02-19 CN CN201910124344.6A patent/CN109785180A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710343A (en) * | 2009-12-11 | 2010-05-19 | 北京中机科海科技发展有限公司 | Body automatic build system and method based on text mining |
US20180129941A1 (en) * | 2016-11-10 | 2018-05-10 | General Electric Company | Methods and systems for capturing analytic model authoring knowledge |
CN106530111A (en) * | 2016-12-01 | 2017-03-22 | 东华大学 | CPS architecture oriented to intelligent cotton spinning production |
EP3376361A2 (en) * | 2017-10-19 | 2018-09-19 | Pure Storage, Inc. | Ensuring reproducibility in an artificial intelligence infrastructure |
CN108107841A (en) * | 2017-12-26 | 2018-06-01 | 山东大学 | A kind of twin modeling method of numerically-controlled machine tool number |
CN108427390A (en) * | 2018-04-16 | 2018-08-21 | 长安大学 | A kind of the workshop level intelligent manufacturing system and its configuration method twin based on number |
CN109062177A (en) * | 2018-06-29 | 2018-12-21 | 无锡易通精密机械股份有限公司 | A kind of Trouble Diagnostic Method of Machinery Equipment neural network based and system |
CN109116751A (en) * | 2018-07-24 | 2019-01-01 | 西安西电电气研究院有限责任公司 | Digitization system and its construction method based on the twin technology of number |
CN109343496A (en) * | 2018-11-14 | 2019-02-15 | 中国电子工程设计院有限公司 | Applied to industrial digital twinned system and forming method thereof |
Non-Patent Citations (2)
Title |
---|
WEICHAO LUO 等: ""Digital twin modeling method for CNC machine tool"", 《2018 IEEE 15TH INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL (ICNSC)》 * |
涂凡 等: ""面向离散车间制造信息本体建模的研究"", 《机械设计与制造》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110187686A (en) * | 2019-06-03 | 2019-08-30 | 济南浪潮高新科技投资发展有限公司 | A kind of Internet of Things industrial processes monitoring method based on the twin technology of number |
CN110276147A (en) * | 2019-06-24 | 2019-09-24 | 广东工业大学 | A kind of manufacture system fault source tracing method, system based on the twin model of number |
CN110276147B (en) * | 2019-06-24 | 2020-02-11 | 广东工业大学 | Manufacturing system fault tracing method and system based on digital twin model |
CN110442737A (en) * | 2019-07-11 | 2019-11-12 | 北京飞利信电子技术有限公司 | The twin method and system of number based on chart database |
CN110674581A (en) * | 2019-09-27 | 2020-01-10 | 北京航空航天大学 | Method and system for accurately judging consistency of digital twin model |
CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
CN111026063B (en) * | 2019-12-25 | 2023-10-03 | 南方科技大学 | Digital twin body construction method, device, computer equipment and storage medium |
CN111026063A (en) * | 2019-12-25 | 2020-04-17 | 南方科技大学 | Digital twin construction method and device, computer equipment and storage medium |
CN111061318A (en) * | 2019-12-27 | 2020-04-24 | 清华大学无锡应用技术研究院 | Digital twinning control method for temperature field of silicon carbide coating deposition furnace |
CN112016737A (en) * | 2020-08-05 | 2020-12-01 | 东北大学秦皇岛分校 | Digital twin-based complex product assembly workshop management and control method |
CN112016737B (en) * | 2020-08-05 | 2022-03-22 | 东北大学秦皇岛分校 | Digital twin-based complex product assembly workshop management and control method |
CN112462696A (en) * | 2020-08-18 | 2021-03-09 | 江苏大学 | Intelligent manufacturing workshop digital twin model construction method and system |
CN112231305A (en) * | 2020-08-23 | 2021-01-15 | 山东翰林科技有限公司 | Digital power grid system and method based on digital twinning |
CN112365167A (en) * | 2020-11-13 | 2021-02-12 | 广西电网有限责任公司南宁供电局 | Dynamic ontology model-based power grid equipment digital twin construction method and device |
CN112418455A (en) * | 2020-11-28 | 2021-02-26 | 北京三维天地科技股份有限公司 | Equipment failure prediction and health management system |
CN112947173A (en) * | 2021-02-03 | 2021-06-11 | 北京理工大学 | Method, controller and system for predicting running state of digital twin workshop |
CN113126580A (en) * | 2021-03-24 | 2021-07-16 | 东北大学 | Assembly control method and device based on digital twins and computer equipment |
CN113890831A (en) * | 2021-10-20 | 2022-01-04 | 中国联合网络通信集团有限公司 | Method, device and storage medium for simulating network equipment |
CN113890831B (en) * | 2021-10-20 | 2024-02-13 | 中国联合网络通信集团有限公司 | Method, device and storage medium for simulating network equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109785180A (en) | A kind of scene perception system and method towards the twin workshop of number | |
Chen et al. | The framework design of smart factory in discrete manufacturing industry based on cyber-physical system | |
CN112085261B (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
CN101093559B (en) | Method for constructing expert system based on knowledge discovery | |
CN116578040B (en) | Digital twin model construction method, system and terminal for machine tool fault diagnosis | |
Liu et al. | Dynamic design method of digital twin process model driven by knowledge-evolution machining features | |
CN112462696A (en) | Intelligent manufacturing workshop digital twin model construction method and system | |
CN105807628B (en) | Robot flexibility controller and its implementation for complicated CPS | |
CN109636139A (en) | A kind of smart machine method for diagnosing faults based on semantic reasoning | |
CN112487058A (en) | Numerical control machine tool fault monitoring and diagnosing system based on data mining | |
CN114746815A (en) | Method for creating a digital twin of a facility or device | |
Liu et al. | CNC machine tool fault diagnosis integrated rescheduling approach supported by digital twin-driven interaction and cooperation framework | |
CN115544775A (en) | Digital twin workshop multi-dimensional multi-level model construction and dynamic configuration method | |
CN117270482A (en) | Automobile factory control system based on digital twin | |
CN117709185A (en) | Digital twin architecture design method for process industry | |
CN114818361A (en) | Digital twin model construction method based on application scene | |
Pulikottil et al. | Big data life cycle in shop-floor–trends and challenges | |
Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
Li et al. | Digital twin technology in intelligent manufacturing | |
Bretones Cassoli et al. | Knowledge Graphs for Data And Knowledge Management in Cyber-Physical Production Systems | |
Lin et al. | Design and implementation of a CPS‐based predictive maintenance and automated management platform | |
Thirupathieswaran et al. | IoT Enabled Waste Management Optimization Framework (IWMOF) | |
CN116771576B (en) | Comprehensive fault diagnosis method for hydroelectric generating set | |
Hou et al. | Monitoring System of Robot Based on Digital Twin | |
Babic | Digital twins in smart manufacturing |
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: 20190521 |
|
RJ01 | Rejection of invention patent application after publication |