CN109299528A - A kind of digital aircraft emulation data artificial intelligence statistical analysis technique and device - Google Patents
A kind of digital aircraft emulation data artificial intelligence statistical analysis technique and device Download PDFInfo
- Publication number
- CN109299528A CN109299528A CN201811057968.2A CN201811057968A CN109299528A CN 109299528 A CN109299528 A CN 109299528A CN 201811057968 A CN201811057968 A CN 201811057968A CN 109299528 A CN109299528 A CN 109299528A
- Authority
- CN
- China
- Prior art keywords
- analysis
- data
- matlab
- library
- definition
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Abstract
The invention discloses a kind of digital aircraft emulation data artificial intelligence statistical analysis technique and devices, the method comprise the steps that knowledge base is established, definition emulation data analysis relevant fact and basic conception in the knowledge base；Method for building up library defines the decision rule according to fact selection corresponding with the basic conception in the method library；Algorithms library is established, analysis method defined in the knowledge base is associated with corresponding parser；Emulation operating condition is obtained, data analysis is carried out according to the knowledge base, the method library and the algorithms library, obtains analysis result；Analysis report is automatically generated according to the analysis result, realizes and aerial vehicle simulation data is screened and analyzed automatically, simulation analysis report is write, greatly reduces the workload of people.
Description
Technical field
The present invention relates to artificial intelligence analysis technical field, more particularly to a kind of digital aircraft emulates data
Artificial intelligence statistical analysis technique and device.
Background technique
Emulation technology is a kind of technology simulated using digital world to real world, has controllability height, without broken
Bad property allows to be repeated several times, limit by current conditions small etc. excellent, is able to ascend product development efficiency and quality, shortens and research and develop
Period.
Since 20th century mid-term, with the development of space industry, emulation technology is provided for space flight and is effectively assisted.Especially
Its nearly more than 20 years again, with computer, visualization technology rapid development with merge, emulation technology was developed in space product
Large-scale application is obtained in journey, is especially played very important effect in key links such as designs, is become space product
Digitize the chief component of development mode.
And emulating data analysis is the direct approach of Pre-Evaluation of testing to emulation technology.It is analyzed by emulation data,
The inherent law that analogue system can be extracted from simulation result, converts information and knowledge for it, provides support for people's decision.
But currently, the emulation data of Complex simulation systems have the characteristics that scale is big, latitude is high, dynamic is strong, analytic process is basic
By being accomplished manually, larger workload is taken time and effort.
Therefore, how to provide a kind of analysis method of workload for reducing people is asking for those skilled in the art's urgent need to resolve
Topic.
Summary of the invention
In view of this, the present invention provides a kind of digital aircraft emulation data artificial intelligence statistical analysis technique and dresses
It sets, aerial vehicle simulation data can be screened and be analyzed automatically, write simulation analysis report, greatly reduce the work of people
Amount.
To achieve the goals above, the present invention adopts the following technical scheme:
A kind of digital aircraft emulation data artificial intelligence statistical analysis technique, comprising:
Knowledge base is established, definition emulation data analysis relevant fact and basic conception in the knowledge base；
Method for building up library defines determining according to fact selection corresponding with the basic conception in the method library
Plan rule；
Algorithms library is established, analysis method defined in the knowledge base is associated with corresponding parser；
Emulation operating condition is obtained, data analysis is carried out according to the knowledge base, the method library and the algorithms library, is divided
Analyse result；
Analysis report is automatically generated according to the analysis result.
Preferably, the knowledge base of establishing includes at least: to emulation operating condition define, to the definition of data, to the parameter
The definition of analysis method and definition to expression way.
Preferably, the method for building up library includes at least: analysis parameter selection decision, analysis method choice decision and analysis
Results expression mode decision；
The analysis parameter selection decision includes: according to task definition, emulation granularity and data analysis dynamics selection parameter；
The analysis method choice decision includes: to determine analysis method according to working condition requirement and data characteristics；
The analysis results expression mode decision includes: to determine analysis knot according to the combination of the data analysing method of selection
The expression way of fruit.
Preferably, the algorithms library of establishing specifically includes: establishing algorithms library using Matlab, the algorithms library includes:
Matlab scheduler program, Matlab data analysis algorithm and Matlab database interface；
The Matlab scheduler program calls the Matlab database interface to read number for reading the result of decision
According to calling the Matlab data analysis algorithm to analyze data, and Matlab database interface is called to be saved in
Result database；
The Matlab database interface with the database for interacting, completing to read data and saving data function
Energy；
The Matlab data analysis algorithm establishes corresponding analysis for the parameters analysis method according to knowledge base
Algorithm.
A kind of digital aircraft emulation data artificial intelligence statistical analysis device, comprising:
Base module, for establishing knowledge base, definition emulation data analysis relevant fact and base in the knowledge base
This concept；
Method library module is used for method for building up library, and definition is according to described true and described substantially general in the method library
Read the decision rule of corresponding selection；
Algorithm library module calculates analysis method defined in the knowledge base with corresponding analysis for establishing algorithms library
Method is associated；
Data analysis module, for obtain emulation operating condition, according to the knowledge base, the method library and the algorithms library into
The analysis of row data obtains analysis result；
Reporting modules are generated, for automatically generating analysis report according to the analysis result.
Preferably, it is fixed to be at least used to emulate operating condition definition, data definition, the parameters analysis method for the base module
Justice and expression way definition.
Preferably, the method library module be at least used for defined analysis parameter selection decision, analysis method choice decision and
Analyze results expression mode decision；
The analysis parameter selection decision includes: according to task definition, emulation granularity and data analysis dynamics selection parameter；
The analysis method choice decision includes: to determine analysis method according to working condition requirement and data characteristics；
The analysis results expression mode decision includes: to determine analysis knot according to the combination of the data analysing method of selection
The expression way of fruit.
Preferably, the algorithm library module is specifically used for establishing algorithms library using Matlab, and the algorithms library includes:
Matlab scheduler program, Matlab data analysis algorithm and Matlab database interface；
The Matlab scheduler program calls the Matlab database interface to read number for reading the result of decision
According to calling the Matlab data analysis algorithm to analyze data, and Matlab database interface is called to be saved in
Result database；
The Matlab database interface with the database for interacting, completing to read data and saving data function
Energy；
The Matlab data analysis algorithm establishes corresponding analysis for the parameters analysis method according to knowledge base
Algorithm.
It can be seen via above technical scheme that compared with prior art, the present disclosure provides a kind of digital aircrafts
The artificial intelligence statistical analysis technique and device for emulating data are established knowledge base definition emulation data using descriptive language and are analyzed
Relevant fact and basic conception, method for building up library describe decision rule, establish algorithms library association analysis algorithm, pass through inductive decision
Method determines the corresponding data analysis of emulation operating condition, and automatically generates analysis report.The present invention uses artificial intelligence language module
The process that people analyzes data realizes that the intellectual analysis of aerial vehicle simulation result and result are shown, improves simulation result
The efficiency and correctness of analysis.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 attached drawing is the stream for the artificial intelligence statistical analysis technique that a kind of digital aircraft provided by the invention emulates data
Cheng Tu.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a kind of digital aircrafts to emulate data artificial intelligence statistical analysis technique, utilizes description
Language establishes knowledge base definition emulation data analysis relevant fact and basic conception, method for building up library describe decision rule, build
Vertical algorithms library association analysis algorithm determines that the corresponding data of emulation operating condition are analyzed by inductive decision method, and automatically generates point
Analysis report.The process that the present invention analyzes data using artificial intelligence language module people realizes aerial vehicle simulation result
Intellectual analysis and result are shown, improve the efficiency and correctness of analysis of simulation result.
Referring to attached drawing 1, the present invention provides a kind of digital aircrafts to emulate data artificial intelligence statistical analysis technique, packet
It includes:
S1: establishing knowledge base, definition emulation data analysis relevant fact and basic conception in knowledge base；
S2: method for building up library defines the decision rule according to true selection corresponding with basic conception in method base；
S3: establishing algorithms library, and analysis method defined in knowledge base is associated with corresponding parser；
S4: obtaining emulation operating condition, carries out data analysis according to knowledge base, method base and algorithms library, obtains analysis result；
S5: analysis report is automatically generated based on the analysis results.
In order to further optimize the above technical scheme, knowledge base is established to include at least: emulation operating condition definition, data definition,
Analysis method definition and expression way definition.
In order to further optimize the above technical scheme, method for building up library includes at least: analysis parameter selection decision, analysis side
Method trade-off decision and analysis results expression mode decision；
Analysis parameter selection decision includes: according to task definition, emulation granularity and data analysis dynamics selection parameter；
Analysis method choice decision includes: to determine analysis method according to working condition requirement and data characteristics；
Analysis results expression mode decision includes: to determine analysis result according to the combination of the data analysing method of selection
Expression way.
In order to further optimize the above technical scheme, it establishes algorithms library to specifically include: establishing algorithms library using Matlab, calculate
Faku County includes: Matlab scheduler program, Matlab data analysis algorithm and Matlab database interface；
Matlab scheduler program calls Matlab database interface to read data, calls for reading the result of decision
Matlab data analysis algorithm analyzes data, and Matlab database interface is called to be saved in result database；
Matlab database interface with database for interacting, completing to read data and saving data function；
Matlab data analysis algorithm is used to establish corresponding parser according to parameters analysis method in knowledge base.
In addition, the present invention also provides a kind of digital aircraft emulation data artificial intelligence to statistically analyze device, comprising:
Base module, for establishing knowledge base, the definition emulation data analysis relevant fact and substantially general in knowledge base
It reads；Including the defined parameters analysis method in knowledge base；
Method library module is used for method for building up library, and definition is according to true selection corresponding with basic conception in method base
Decision rule；
Parameters analysis method is associated by algorithm library module for establishing algorithms library with corresponding parser；
Data analysis module carries out data analysis according to knowledge base, method base and algorithms library for obtaining emulation operating condition,
Obtain analysis result；
Reporting modules are generated, for automatically generating analysis report based on the analysis results.
In order to further optimize the above technical scheme, base module is at least used to emulate operating condition definition, data definition, divides
The definition of analysis method and expression way definition.
In order to further optimize the above technical scheme, method library module is at least used for defined analysis parameter selection decision, divides
Analyse method choice decision and analysis results expression mode decision；
Analysis parameter selection decision includes: according to task definition, emulation granularity and data analysis dynamics selection parameter；
Analysis method choice decision includes: to determine analysis method according to working condition requirement and data characteristics；
Analysis results expression mode decision includes: to determine analysis result according to the combination of the data analysing method of selection
Expression way.
In order to further optimize the above technical scheme, algorithm library module is specifically used for establishing algorithms library using Matlab, calculates
Faku County includes: Matlab scheduler program, Matlab data analysis algorithm and Matlab database interface；
Matlab scheduler program calls Matlab database interface to read data, calls for reading the result of decision
Matlab data analysis algorithm analyzes data, and Matlab database interface is called to be saved in result database；
Matlab database interface with database for interacting, completing to read data and saving data function；
Matlab data analysis algorithm is used to establish corresponding parser according to parameters analysis method in knowledge base.
The technical solution that present invention is further explained below provides:
Establish the particular content of knowledge base realization are as follows:
(1) environment: the artificial intelligence programmings language such as Prolog, LISP, Smalltalk.
(2) function: definition emulation operating condition, data characteristics, data analysing method, data analysis result methods of exhibiting
The particular content that method for building up library is realized are as follows:
(1) environment: the artificial intelligence programmings language such as Prolog, LISP, Smalltalk.
(2) function: definition selects the rule of analyzed data according to emulation operating condition, according to data characteristics and emulation operating condition
The rule of selection analysis algorithm, the rule that template is shown according to the analysis result of data analysing method selection.
Establish the particular content of Matlab algorithms library realization are as follows:
(1) environment: Matlab
(2) function: the need analysis data and method gone out according to descriptive language decision read emulation data, call corresponding
Parser completes data analysis.
(3) is formed: Matlab scheduler program, Matlab data analysis algorithm, Matlab database interface
The particular content that inductive decision method is realized are as follows:
(1) environment: C#, artificial intelligence language
(2) function: emulation operating condition is obtained from simulation configuration file and task input, is protected according in knowledge base and method base
The knowledge and method deposited make data analysis-decision system, and Calling MATLAB algorithms library carries out data analysis, and analysis result automatically generates
Analysis report.
Automatically generate the particular content of analysis report function realization are as follows:
(1) environment: Access, C#, Matlab
(2) function: subtype is shown according to the data that decision-making mechanism is selected, Matlab is called to draw and according to report
Slide former is combined into data analysis report automatically.
(3) is formed: Word report template library, report content database of record, chart automatically generating program, report are automatic
Generate program.
Present invention is further described in detail With reference to embodiment.
One, knowledge base
Definition emulation data analyze relevant fact in knowledge base, establish basic conception.Knowledge base mainly includes emulation work
Condition definition, data definition, analysis method definition, expression way definition, can use Prolog, LISP and Smalltalk et al.
Work intelligently becomes language realization.
1. emulating operating condition definition:
The concept of definition emulation operating condition, the emulation operating condition of this place definition include task and index demand, imitate in knowledge base
The describing modes such as true granularity, data analysis granularity.The different facts are defined in knowledge base, it is true comprising task and index demand,
It is true to emulate granularity, data analyze granularity fact etc..
(1) task and the definition of the index demand fact.The task and index demand of definition emulation operating condition, including satellite type,
Review is retried, parameter is than equity.
(2) emulates size definition.The configuration of definition emulation operating condition, definition, satellite simulation granularity including satellite environment are fixed
Justice.
Satellite simulation size definition defines simulated program granularity, including Kinematics Simulation, dynamics simulation.Definition emulation
The subsystem that program includes, including attitude and orbit control subsystem, propulsion subsystem, power supply subsystem, thermal control subsystem, observing and controlling subsystem
System, payload subsystem.
The definition of satellite environment defines satellite perturbance motion item and combinations thereof, including but not limited to two body motion, the consideration J2 earth
Perturbation considers the perturbation of J2, J3, J4 earth, considers that group shot is dynamic.Satellite noise is defined, including but not limited to satellite earth magnetic field is strong
Spend the common interferences such as noise, torque noise, remanent magnetism torque noise, component noise.
(3) data analyze size definition.By the importance of parameter, simulation parameter is classified not, main simulation parameter is defined
And auxiliary parameter.
2. data and characterizing definition:
The concept of data is defined in knowledge base, the data of this place definition include simulation parameter and the corresponding number of simulation parameter
According to feature.The different facts are defined in knowledge base, include simulation parameter and data characteristics.
(1) emulates data definition: defining simulation parameter according to simulated program.Define whole star parameter, including environmental parameter,
Orbit parameter, attitude parameter.Define parameter of any subsystem, including attitude and orbit control subsystem, propulsion subsystem, power supply subsystem, thermal control
Subsystem, communication subsystem, payload subsystem.Definition component parameter, including each component measured value etc..
(2) data characteristics defines: the type of defined parameters first, including digital quantity and analog quantity.According to Parameters variation spy
Point definition is fast to be become analog quantity, becomes analog quantity slowly.According to whether having the characteristics that mechanical periodicity delimiting period.
3. analysis method defines:
The concept of defined parameters analysis method in knowledge base.
Defined parameters statistical analysis technique, including but not limited to equal Data-Statistics, variance statistic, median statistics, maximum value are most
Small Data-Statistics, threshold statistical etc..
Defined parameters inspection by attributes analysis method includes but is not limited to periodic survey, test of normality, stationary test.
Define complicated analysis method, including but not limited to clustering, regression analysis, machine learning analysis etc..
It defines data and picks wild method.
Define comparing analysis method, including independence test, residual computations, correlation analysis.
Analysis method fact specific definition is corresponding by the corresponding parser that Matlab algorithms library includes.
4. expression way defines:
Definition tables form, including row, column.
Define image type, including but not limited to distribution map, spectrogram, radar map, column diagram, scatter plot, line chart.
Define Word report template.
Two, method base
Method base mainly stores a kind of method or technology for completing reasoning from logic.For emulation data analysis process, side
Faku County mainly includes analysis parameter selection decision, analysis method choice decision, analysis results expression mode decision, be can use
The artificial intelligence such as Prolog, LISP and Smalltalk become language realization.
1. data trade-off decision:
(1) selects major parameter according to task definition
The data that analysis is determined according to satellite task, including but not limited to Types Below.Subsystem is checked and is retried, choosing
Take corresponding parameter of any subsystem.For remotely sensed image, track, posture and imaging effect relevant parameter are chosen.For track/posture control
System chooses the parameters such as parameters, control force and the torques such as control precision, stability, posture orbit maneuver time.It is imitative for failure
Very, it chooses and is analyzed with fault related data.
(2) is according to emulation granularity selection parameter
Parameter selection decision is made according to satellite simulation granularity.Differentiate simulated program granularity, for Kinematics Simulation, chooses
Orbit parameter is analyzed.For dynamics simulation, Selecting All Parameters should include satellite orbit and attitude parameter.Differentiate simulated program
The subsystem for including, for attitude and orbit control subsystem, weight analysis track keep precision, pointing accuracy, control precision, stability,
Posture orbit maneuver time etc..For promoting subsystem, the duration of ignition, fuel consumption etc. are analyzed emphatically.For power subsystem,
Weight analysis solar cell output power, accumulator cell charging and discharging power, busbar voltage, shunt efficiency, energy utilization efficiency etc..It is right
In thermal control subsystem, hot-fluid, part temperatures inside and outside weight analysis.For observing and controlling number pass subsystem, weight analysis storage time, survey
Control station SEE time etc..For payload subsystem, analyze imaging resolution, image coverage emphatically, revisit characteristic etc..
Differentiate that satellite environment need to analyze disturbance torque suffered by satellite and each component is disturbed for noise circumstance.
(3) analyzes granularity selection parameter according to data
Granularity, which is analyzed, according to data makes parameter selection decision.Differentiate that data analyze granularity, for preliminary analysis, only chooses
The highest data of importance information are analyzed.Deepen with data analysis granularity, weight is successively increased in selected analysis data
The weaker data of the property wanted rank.
2. analysis method choice decision
(1) determines method according to working condition requirement
According to working condition requirement, analysis method is determined.
For single operating condition, single group floor data is analyzed.
Operating condition is emulated for batch, also needs the difference between the statistical result and data of analysis multiple groups floor data.For
The different stochastic variable of multiple result as caused by randomness, determines data estimated value using statistical method.For being matched by emulation
Set the variation of data result caused by difference, the relationship of analysis analysis emulation data variation rule and configuration information variation.
Comparison for two groups of separate sources data need to calculate residual error to two groups of data, carry out data analysis to residual error.Point
Analysis content includes but is not limited to time series consistency treatment, residual error statistical analysis, data dependence analysis, Remanent Model foundation
With inspection.
(2) determines method according to data characteristics
According to simulation parameter data characteristics, parameters analysis method is determined.
Data variation speed is considered, for changing slow digital quantity and becoming analog quantity slowly, using statistical method to data
It is analyzed, statistical result includes but is not limited to mean value, variance, intermediate value, max min, whether exceeds threshold value etc..For
The faster fast change analog quantity of variation, carries out periodic survey, and analyzed using complicated analysis method.
For cyclically-varying data, the data period is extracted, analyzes frequency domain characteristic, and data are carried out in a data
Time-domain analysis.For the data in no significant change period, data analysis is carried out to full time-domain.
3. result describes method choice decision
According to the combination of the data analysing method of selection, analysis results expression mode is determined.
For data only for statistical analysis, the statistic analysis result of data is indicated using table.Grid column coordinates table
Show which data counted, the data characteristics of table row coordinate representation statistics.According to the data source of statistics, table columns is determined,
According to statistical result, the line number and content of table are determined.
For carrying out the data of parameter attribute check analysis, inspection result is drawn using chart.For carrying out normality inspection
The data tested, draw distribution map.For carrying out periodic data, spectrogram is drawn.
For the data analyzed using complicated analysis method, go out to analyze result using picture.For carrying out cluster point
The data of analysis draw cluster result using radar map.
For carrying out the data of classification analysis, classification results are drawn using column diagram.For in the time domain using recurrence point
The data of analysis and machine learning analysis are drawn initial data using scatter plot, are drawn back using line chart using the time as abscissa
Return analysis or machine learning modeling result.
Three, algorithms library
Data and method are analyzed according to the need of decision, emulation data is read, calls corresponding analysis algorithm, complete data point
Analysis is realized using Matlab language.
Algorithms library analyzes data and method according to the need of decision, reads emulation data, calls corresponding analysis algorithm, completes number
According to analysis.Algorithms library is divided into Matlab scheduler program, Matlab data analysis algorithm, Matlab database interface three
Point.
Matlab scheduler program reads the result of decision, and Matlab database interface is called to read data, calls corresponding
Matlab data analysis algorithm analyzes data, analyzes result using database interface and is saved in result database.
Matlab database interface is interacted with database, is completed to read data and is saved data function.
Matlab data analysis algorithm establishes corresponding analysis algorithm according to analysis method definition in knowledge base, including but unlimited
In data preprocessing method, statistical analysis technique, parameter attribute check analysis method etc..
Four, data analysis-decision system process
Emulation operating condition is obtained from simulation configuration file and task input, is done according to the knowledge that descriptive language saves with method
Data analysis-decision system out, Calling MATLAB algorithms library carry out data analysis, and analysis result automatically generates analysis report.
Five, is reported
(1) figure automatically generates
The allocation plan for making bitmap-format according to the result of decision determines the initial data of mapping according to data analysis result, presses
Image automatically generates specification and determines mapping configuration file.Image automatically generating program is called, program is configured according to format and data
Source-information generates corresponding Matlab plotting program.Matlab plotting program is called to draw required image.
Image path will be generated to automatically generate in specification write-in report automatically generated data library by report, calling automatically generates
Image is inserted into Word by program.
(2) table automatically generates
The ranks of table and the meaning of the put content of each lattice are determined according to the result of decision, and table is determined according to data analysis result
The value of middle content automatically generates specification by table and form data is written in report automatically generated data library, and calling automatically generates
Table is inserted into Word by program.
(3) report automatically generates
According to the data of decision process selection analysis and results expression mode, corresponding Word template is determined, in conjunction with automatic
Table technique is generated, data analysis report is generated.
The step of automatically generating report above is realized using language such as Access, C#, Matlab in specific implementation.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (8)
1. a kind of digital aircraft emulates data artificial intelligence statistical analysis technique characterized by comprising
Knowledge base is established, definition emulation data analysis relevant fact and basic conception in the knowledge base；
Method for building up library, definition is advised according to the decision of fact selection corresponding with the basic conception in the method library
Then；
Algorithms library is established, analysis method defined in the knowledge base is associated with corresponding parser；
Emulation operating condition is obtained, data analysis is carried out according to the knowledge base, the method library and the algorithms library, obtains analysis knot
Fruit；
Analysis report is automatically generated according to the analysis result.
2. a kind of digital aircraft according to claim 1 emulates data artificial intelligence statistical analysis technique, feature exists
In the knowledge base of establishing includes at least: defining, emulation operating condition to the definition of data, determine the parameters analysis method
Justice and the definition to expression way.
3. a kind of digital aircraft according to claim 1 emulates data artificial intelligence statistical analysis technique, feature exists
In the method for building up library includes at least: analysis parameter selection decision, analysis method choice decision and analysis results expression mode
Decision；
The analysis parameter selection decision includes: according to task definition, emulation granularity and data analysis dynamics selection parameter；
The analysis method choice decision includes: to determine analysis method according to working condition requirement and data characteristics；
The analysis results expression mode decision includes: to determine analysis result according to the combination of the data analysing method of selection
Expression way.
4. a kind of digital aircraft according to claim 1 emulates data artificial intelligence statistical analysis technique, feature exists
In the algorithms library of establishing specifically includes: establish algorithms library using Matlab, the algorithms library include: Matlab scheduler program,
Matlab data analysis algorithm and Matlab database interface；
The Matlab scheduler program is used to read the result of decision, and the Matlab database interface is called to read data,
It calls the Matlab data analysis algorithm to analyze data, and Matlab database interface is called to be saved in result
Database；
The Matlab database interface with the database for interacting, completing to read data and saving data function；
The Matlab data analysis algorithm establishes corresponding parser for the parameters analysis method according to knowledge base.
5. a kind of digital aircraft emulation data artificial intelligence statisticallys analyze device characterized by comprising
Base module, for establishing knowledge base, the definition emulation data analysis relevant fact and substantially general in the knowledge base
It reads；
Method library module is used for method for building up library, and definition is according to the true and basic conception pair in the method library
The decision rule for the selection answered；
Algorithm library module, for establishing algorithms library, by analysis method defined in the knowledge base and corresponding parser into
Row association；
Data analysis module is counted for obtaining emulation operating condition according to the knowledge base, the method library and the algorithms library
According to analysis, analysis result is obtained；
Reporting modules are generated, for automatically generating analysis report according to the analysis result.
6. a kind of digital aircraft according to claim 5 emulates data artificial intelligence statistical analysis technique, feature exists
In the base module is at least used to emulate operating condition definition, data definition, parameters analysis method definition and expression way
Definition.
7. a kind of digital aircraft according to claim 5 emulates data artificial intelligence statistical analysis technique, feature exists
In the method library module is at least used for defined analysis parameter selection decision, analysis method choice decision and analysis results expression
Mode decision；
The analysis parameter selection decision includes: according to task definition, emulation granularity and data analysis dynamics selection parameter；
The analysis method choice decision includes: to determine analysis method according to working condition requirement and data characteristics；
The analysis results expression mode decision includes: to determine analysis result according to the combination of the data analysing method of selection
Expression way.
8. a kind of digital aircraft according to claim 5 emulates data artificial intelligence statistical analysis technique, feature exists
Be specifically used for establishing algorithms library using Matlab in, the algorithm library module, the algorithms library include: Matlab scheduler program,
Matlab data analysis algorithm and Matlab database interface；
The Matlab scheduler program is used to read the result of decision, and the Matlab database interface is called to read data,
It calls the Matlab data analysis algorithm to analyze data, and Matlab database interface is called to be saved in result
Database；
The Matlab database interface with the database for interacting, completing to read data and saving data function；
The Matlab data analysis algorithm establishes corresponding parser for the parameters analysis method according to knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811057968.2A CN109299528B (en) | 2018-09-11 | 2018-09-11 | Artificial intelligence statistical analysis method and device for simulation data of digital aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811057968.2A CN109299528B (en) | 2018-09-11 | 2018-09-11 | Artificial intelligence statistical analysis method and device for simulation data of digital aircraft |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109299528A true CN109299528A (en) | 2019-02-01 |
| CN109299528B CN109299528B (en) | 2023-04-18 |
Family
ID=65166459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811057968.2A Active CN109299528B (en) | 2018-09-11 | 2018-09-11 | Artificial intelligence statistical analysis method and device for simulation data of digital aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109299528B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112559477A (en) * | 2020-12-18 | 2021-03-26 | 湖南航天机电设备与特种材料研究所 | Quantitative evaluation method, system, equipment and medium based on unmanned aerial vehicle flight log |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480389A (en) * | 2017-08-23 | 2017-12-15 | 广东电网有限责任公司电力科学研究院 | A kind of intelligent alarm test emulation system and method towards scheduling station |
| CN107516452A (en) * | 2017-08-17 | 2017-12-26 | 北京航空航天大学 | A kind of general flight simulation simulated environment evaluation system |
| US20180096252A1 (en) * | 2016-10-05 | 2018-04-05 | International Business Machines Corporation | Database-management system with artificially intelligent virtual database administration |
| CN108399273A (en) * | 2018-01-15 | 2018-08-14 | 北京航空航天大学 | Artificial intelligence program person writes the decision decomposition method of digital aircraft source code |
-
2018
- 2018-09-11 CN CN201811057968.2A patent/CN109299528B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180096252A1 (en) * | 2016-10-05 | 2018-04-05 | International Business Machines Corporation | Database-management system with artificially intelligent virtual database administration |
| CN107516452A (en) * | 2017-08-17 | 2017-12-26 | 北京航空航天大学 | A kind of general flight simulation simulated environment evaluation system |
| CN107480389A (en) * | 2017-08-23 | 2017-12-15 | 广东电网有限责任公司电力科学研究院 | A kind of intelligent alarm test emulation system and method towards scheduling station |
| CN108399273A (en) * | 2018-01-15 | 2018-08-14 | 北京航空航天大学 | Artificial intelligence program person writes the decision decomposition method of digital aircraft source code |
Non-Patent Citations (1)
| Title |
|---|
| 焦松等: "仿真实验数据一体化分析工具研究", 《系统仿真学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112559477A (en) * | 2020-12-18 | 2021-03-26 | 湖南航天机电设备与特种材料研究所 | Quantitative evaluation method, system, equipment and medium based on unmanned aerial vehicle flight log |
| CN112559477B (en) * | 2020-12-18 | 2022-09-13 | 湖南航天机电设备与特种材料研究所 | Quantitative evaluation method, system, equipment and medium based on unmanned aerial vehicle flight log |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109299528B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guan et al. | An artificial-neural-network-based, constrained CA model for simulating urban growth | |
| CN110516539A (en) | Remote sensing image building extracting method, system, storage medium and equipment based on confrontation network | |
| CN111199270A (en) | Regional wave height forecasting method and terminal based on deep learning | |
| CN109508360A (en) | A kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata | |
| CN108664690A (en) | Long-life electron device reliability lifetime estimation method under more stress based on depth belief network | |
| CN109816032A (en) | Zero sample classification method and apparatus of unbiased mapping based on production confrontation network | |
| CN113609596B (en) | Aircraft aerodynamic characteristic prediction method based on neural network | |
| CN103268607B (en) | A kind of common object detection method under weak supervision condition | |
| CN109543905A (en) | Rolling bearing method for predicting residual useful life based on improved two dimension CNN model | |
| CN105989336A (en) | Scene identification method based on deconvolution deep network learning with weight | |
| CN108879732A (en) | Transient stability evaluation in power system method and device | |
| CN113255900A (en) | Impulse load prediction method considering improved spectral clustering and Bi-LSTM neural network | |
| Liu et al. | Wind power short-term forecasting based on LSTM neural network with dragonfly algorithm | |
| CN111353391A (en) | Radar interference effect evaluation method and device, electronic equipment and storage medium thereof | |
| CN109299528A (en) | A kind of digital aircraft emulation data artificial intelligence statistical analysis technique and device | |
| CN109919099A (en) | A kind of user experience evaluation method and system based on Expression Recognition | |
| Shi | Application of artificial neural network in college-level music teaching quality evaluation | |
| Kulkarni et al. | Learning and real-time classification of hand-written digits with spiking neural networks | |
| He et al. | Analysis of concentration in English education learning based on CNN model | |
| Zhang | Deep learning-based hybrid short-term solar forecast using sky images and meteorological data | |
| CN109002661A (en) | The artificial intelligence modification method of digital aircraft simulation model | |
| Qin et al. | Construction of big data monitoring platform for teaching quality under intelligent education | |
| Sinitsyn et al. | Success predicting for students of online courses using neural networks | |
| Ji et al. | Multi-model fusion short-term power load forecasting based on improved WOA optimization | |
| Xi et al. | Mondrian Conformal Prediction of boosting for swarm behavior recognition |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |