CN109670227A - A kind of methods of evaluation of the simulation mathematical model parameter pair based on big data - Google Patents
A kind of methods of evaluation of the simulation mathematical model parameter pair based on big data Download PDFInfo
- Publication number
- CN109670227A CN109670227A CN201811503393.2A CN201811503393A CN109670227A CN 109670227 A CN109670227 A CN 109670227A CN 201811503393 A CN201811503393 A CN 201811503393A CN 109670227 A CN109670227 A CN 109670227A
- Authority
- CN
- China
- Prior art keywords
- big data
- data
- module
- mathematical model
- model parameter
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to simulation technical fields, a kind of methods of evaluation of simulation mathematical model parameter pair based on big data is disclosed, the appraisal system of the simulation mathematical model parameter pair based on big data includes: big data acquisition module, main control module, parameter setting module, optimization module, estimation block, data memory module, display module.The present invention can guarantee that industrial big data can be transmitted in real time and safely by big data acquisition module, to alleviate the pressure of network transmission；Most distortion data can be filtered out by estimation block, improves the unbiasedness of parameter estimation result；Simultaneously, industrial big data is stored by row by the line unit that data memory module designs measuring point ID and time series composition, to make in service logic with temporal correlation, measuring point correlation data in physical store by row arranged adjacent, optimize readwrite performance simultaneously, realizes the balance of search efficiency and write efficiency.
Description
Technical field
The invention belongs to simulation technical field more particularly to a kind of simulation mathematical model parameters based on big data to estimating
Amount method.
Background technique
Simulation mathematical model is in specific industrial production equipment in application, needing to do targetedly parameter Estimation.Emulation
(Simulation), i.e., their shadows to target will be converted into specific to the uncertainty of a certain specific level using project model
It rings, which indicated on the level of project simulation project entirety.Project simulation utilizes computer model and a certain specific
The evaluation of risk of level is generally emulated using Monte Carlo method.Utilize the essential mistake occurred in model reproduction real system
Journey, and by studying the experiment of system model the system in existing or design, also known as simulate.Model packet referred herein
Include physics and mathematics, static and dynamic, continuous and discrete various models.Signified system also very extensively, is wrapped
The systems such as electrical, mechanical, chemical industry, waterpower, heating power are included, also include the systems such as society, economic, ecology, management.When what is studied is
System involves great expense, risk test is greatly or when needing long time just and will appreciate that consequence caused by system parameter variations,
Emulation is a kind of particularly effective research means.The important tool of emulation is computer.Emulation calculates with numerical value, method for solving
It is a kind of experimental technique that difference, which is it first,.The process of emulation includes establishing simulation model and carrying out emulation experiment two mainly
Step.However, the data volume that existing simulation data source generates in real time is huge, the data of industrial control system or intelligence sensor are several
Second grade variation, data packet is small, more than quantity and in the case that frequency is high, it is non-to the pressure of acquisition server and transmission network
Chang great, collecting efficiency are low；And industrial production data has usually contained various noise errors, partial data may be distortion；
The interference that residual error larger data calculates parameter is increased, calculated result at this moment has inclined；Meanwhile the number in industrial process
Increasing according to scale, data volume is more and more, and acquisition, the storage of magnanimity big data face immense pressure, traditional relationship type
Database or real-time data base can no longer meet the application demand of industrial big data.
In conclusion problem of the existing technology is: the data volume that existing simulation data source generates in real time is huge, data
Carrying cost is high, and data management and dispatching be not high；The data of industrial control system or intelligence sensor are almost second grade
Variation, data packet is small, more than quantity and in the case that frequency is high, it is very big to the pressure of acquisition server and transmission network, adopt
Collect low efficiency；And industrial production data has usually contained various noise errors, partial data may be distortion；It increases
The interference that residual error larger data calculates parameter, calculated result at this moment have inclined；Meanwhile the data scale in industrial process
Increasing, data volume is more and more, and acquisition, the storage of magnanimity big data face immense pressure, traditional relevant database
Or real-time data base can no longer meet the application demand of industrial big data；Display shows that picture noise is big, and image texture is aobvious
Show ineffective.
Summary of the invention
In view of the problems of the existing technology, the simulation mathematical model parameter pair based on big data that the present invention provides a kind of
Methods of evaluation.
The invention is realized in this way a kind of methods of evaluation of the simulation mathematical model parameter pair based on big data, described
The methods of evaluation of simulation mathematical model parameter pair based on big data includes:
Step 1 acquires industrial big data information using data acquisition interface；
Simulation mathematical model parameter pair is arranged using simulation software by parameter setting module in step 2；
Step 3 optimizes place to the big data of acquisition using the big data optimization algorithm based on optimization particle swarm algorithm
Reason；The estimation of simulation mathematical model parameter pair is operated using simulation software；
Step 4 utilizes the industrial big data of memory storage acquisition；
Step 5, it is aobvious using the display for carrying out image denoising based on global adaptive fractional rank integral image Denoising Algorithm
Show the industrial big data and estimation result of acquisition.
Further, the big data optimization algorithm based on optimization particle swarm algorithm in the step 5 is as follows:
In D dimension big data cloud storage cluster feature space, a population is formed by m particle, data clusters problem
It is converted into a multi-objective optimization question, big data clusters in cloud storage:
MinF (x)=[f1(x), f2(x) ..., fn(x)]
s.t.gi(x)≤0 (or >=0) i=1,2 ... n
hj(x)=0j=1,2 ..., m；
Wherein, fi(x) (i=1,2 ..., n) be objective function, gi(x) there are two 1 unstable periodic point x=0 for system
With x=1-1/ μ, hjIt (x) is equality constraint；It introduces Chaos-Particle Swarm Optimization and disturbs concept, obtain in the cluster of decision variable x* domination
The characteristic solution of the heart are as follows:
For each big data information characteristics vector XiIt is achieved:
li(k)=(1- ρ) li(k-1)+γf(xi(k))；
Wherein, fiIt is Pareto optimal solution, Pij(k) i-th of decision variable of k moment, inequality f are indicatedi(X*)≤fi(X)
It sets up, wherein i=1,2 ..., n, are arranged the threshold value N of clusterth, work as Neff< NthWhen, the O of region of searchαAnd OβTwo sections
Cluster correct probability are as follows:
The particle carried out in repository that improved mechanism using population hop count is updated；
Update the spatial position of each particle in population:
Wherein, xkFor the inertia weight searched in the region, a is the noninferior solution of cluster centre, deFor extreme point to noninferior solution
Distance, assess disaggregation distribution uniformity coefficient when, calculate press Optimal cluster centers phasor function q (xi k/xi k-1), according to mould
Because of the update iteration sequence in group, obtain:
∑τ=diag (max (σi- τ, 0)；
Thus the particle fitness function that big data clusters in cloud storage is obtained are as follows:
Wherein, { α, β } is that diversity is amassed wealth by heavy taxation objective function.
Further, include: based on global adaptive fractional rank integral image Denoising Algorithm in the step 5
If the average value of the gradient magnitude in image f (i, j) on 8 directions of each pixel is M (i, j), and is carried out
Normalization, finds out integral order corresponding with the pixel；The maximum value for taking M (i, j) is Y, minimum value X, by pixel
After gradient magnitude is normalized, dynamic fractional order integration order is found out:
Another object of the present invention is to provide the simulation mathematical model parameters pair described in a kind of application based on big data
The appraisal system of the simulation mathematical model parameter pair based on big data of methods of evaluation, the emulation mathematical modulo based on big data
The appraisal system of shape parameter pair includes:
Big data acquisition module, connect with main control module, for acquiring industrial big data information by data acquisition interface；
Main control module stores mould with big data acquisition module, parameter setting module, optimization module, estimation block, data
Block, display module connection, work normally for controlling modules by single-chip microcontroller；
Parameter setting module is connect with main control module, for simulation mathematical model parameter pair to be arranged by simulation software；
Optimization module is connect with main control module, for optimizing processing by big data of the optimization algorithm to acquisition；
Estimation block is connect with main control module, for being grasped by simulation software to the estimation of simulation mathematical model parameter pair
Make；
Data memory module is connect with main control module, for the industrial big data by memory storage acquisition；
Display module is connect with main control module, for the industrial big data and estimation result by display display acquisition.
Another object of the present invention is to provide the simulation mathematical model parameters pair described in a kind of application based on big data
The information data processing terminal of methods of evaluation.
Advantages of the present invention and good effect are as follows: the present invention is adopted by big data acquisition module according to multi-course concurrency form
Collect industrial big data, it can be achieved that second frequency real-time data acquisition, to alleviate the pressure of data acquisition interface；By to described
Industrial big data carries out unified protocol conversion and package and uploads, it is ensured that and industrial big data can be transmitted in real time and safely,
To alleviate the pressure of network transmission；The precision of parameter Estimation can be improved in varying degrees by estimation block.Precision can improve
Number still cause data distortion situation related with noise in data.This method can filter out most distortion data, mention
The high unbiasedness of parameter estimation result；Meanwhile the line unit of measuring point ID and time series composition are designed by data memory module
By industrial big data by row store, thus make in service logic with temporal correlation, measuring point correlation data in object
Row arranged adjacent is pressed in reason storage, while optimizing readwrite performance, realizes the balance of search efficiency and write efficiency；Certainly using the overall situation
It adapts to fractional order integration Image denoising algorithm to be conducive to reduce picture noise, retains enhancing image texture；Based on optimization population
The big data optimization algorithm of algorithm is conducive to optimize data, reduces storage overhead, improves data management and dispatching.
Detailed description of the invention
Fig. 1 is the methods of evaluation process of the simulation mathematical model parameter pair provided in an embodiment of the present invention based on big data
Figure.
Fig. 2 is that the appraisal system structure of the simulation mathematical model parameter pair provided in an embodiment of the present invention based on big data is shown
It is intended to；
In figure: 1, big data acquisition module；2, main control module；3, parameter setting module；4, optimization module；5, mould is estimated
Block；6, data memory module；7, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, the methods of evaluation of the simulation mathematical model parameter pair provided by the invention based on big data include with
Lower step:
Step S101 acquires industrial big data information using data acquisition interface；
Simulation mathematical model parameter pair is arranged using simulation software by parameter setting module in step S102；
Step S103 optimizes the big data of acquisition using the big data optimization algorithm based on optimization particle swarm algorithm
Processing；The estimation of simulation mathematical model parameter pair is operated using simulation software；
Step S104 utilizes the industrial big data of memory storage acquisition；
Step S105 utilizes the display that image denoising is carried out based on global adaptive fractional rank integral image Denoising Algorithm
Show the industrial big data and estimation result of acquisition.
In step S105, the big data optimization algorithm provided in an embodiment of the present invention based on optimization particle swarm algorithm is as follows:
Assuming that a population is formed by m particle in D dimension big data cloud storage cluster feature space, when disturbance sequence
It is added in population, affects clustering precision, in this regard, data clusters problem is converted into a multi-objective optimization question by the present invention,
The mathematical description that big data clusters in cloud storage is as follows:
Min F (x)=[f1(x), f2(x) ..., fn(x)]
s.t.gi(x)≤0 (or >=0) i=1,2 ... n
hj(x)=0j=1,2 ..., m
Wherein, fi(x) (i=1,2 ..., n) be objective function, gi(x) there are two 1 unstable periodic point x=0 for system
With x=1-1/ μ, hjIt (x) is equality constraint.Here, it introduces Chaos-Particle Swarm Optimization and disturbs concept, obtain the poly- of decision variable x* domination
The characteristic solution at class center are as follows:
In order to avoid particle falls into local optimum, for each big data information characteristics vector XiIt is achieved, are as follows:
li(k)=(1- ρ) li(k-1)+γf(xi(k))
Wherein, fiIt is Pareto optimal solution, Pij(k) i-th of decision variable of k moment, inequality f are indicatedi(X*)≤fi(X)
It sets up, wherein i=1,2 ..., n, are arranged the threshold value N of clusterth, work as Neff<NthWhen, the O of region of searchαAnd OβTwo sections it is poly-
The correct probability of class are as follows:
The particle carried out in repository that improved mechanism using population hop count is updated；
Update the spatial position of each particle in population:
Wherein, xkFor the inertia weight searched in the region, a is the noninferior solution of cluster centre, deFor extreme point to noninferior solution
Distance, assess disaggregation distribution uniformity coefficient when, calculate press Optimal cluster centers vector
Function q (xi k/xi k-1), according to mould because of the update iteration sequence in group, obtain:
∑ τ=diag (max (σi- τ, 0)
Thus the particle fitness function that big data clusters in cloud storage is obtained are as follows:
Wherein, { α, β } is that diversity is amassed wealth by heavy taxation objective function.
Big data optimization algorithm based on optimization particle swarm algorithm is conducive to optimize data, reduces storage overhead, improves number
According to management and dispatching.
It is provided in an embodiment of the present invention based on global adaptive fractional rank integral image Denoising Algorithm in step S105, such as
Under:
If the average value of the gradient magnitude in image f (i, j) on 8 directions of each pixel is M (i, j), and is carried out
Normalization, so as to find out integral order corresponding with the pixel.The maximum value for taking M (i, j) is Y, minimum value X, by pixel
After the gradient magnitude of point is normalized, dynamic fractional order integration order can be found out:
So as to realize, there is lesser negative order, point of the order in gradient mean value larger part (regarding noise spot as)
Number rank integral has biggish attenuation to noise；Medium for gradient magnitude and smaller part (regarding image texture point as) has
Integral order of corresponding size has certain enhancing and stick effect to image texture.
As shown in Fig. 2, the appraisal system of the simulation mathematical model parameter pair provided by the invention based on big data includes: big
Data acquisition module 1, main control module 2, parameter setting module 3, optimization module 4, estimation block 5, data memory module 6, display
Module 7.
Big data acquisition module 1 is connect with main control module 2, for acquiring industrial big data letter by data acquisition interface
Breath；
Main control module 2 is deposited with big data acquisition module 1, parameter setting module 3, optimization module 4, estimation block 5, data
Module 6, the connection of display module 7 are stored up, controls modules normal work for passing through single-chip microcontroller；
Parameter setting module 3 is connect with main control module 2, for simulation mathematical model parameter pair to be arranged by simulation software；
Optimization module 4 is connect with main control module 2, for optimizing processing by big data of the optimization algorithm to acquisition；
Estimation block 5 is connect with main control module 2, for passing through estimation of the simulation software to simulation mathematical model parameter pair
Operation；
Data memory module 6 is connect with main control module 2, for the industrial big data by memory storage acquisition；
Display module 7 is connect with main control module 2, for being tied by the industrial big data and estimation of display display acquisition
Fruit.
1 acquisition method of big data acquisition module provided by the invention is as follows:
1) at data acquisition interface, the industrial big data is acquired by multi-course concurrency form, and to the industry
Big data carries out protocol conversion and package uploads for the first time；
2) in data receiver interface, receive the industrial big data that package for the first time uploads, to the industry big data into
The parsing of row data and the processing of magnitude compression, and database is written in the industrial big data by treated.
The reception provided by the invention industrial big data that package uploads for the first time, carries out data solution to the industry big data
Analysis and the processing of magnitude compression, and the industrial big data write-in database includes: by treated
Interface is converged in data, the industrial big data that the package for the first time uploads is received, to the industry big data
Data summarization, data compression, data encryption and secondary package is carried out to upload；
In the data receiver interface, the industrial big data that secondary package uploads is received, to the industry big data
Data deciphering, data decompression, data parsing and the processing of magnitude compression are carried out, and the industrial big data is write by treated
Enter database.
Collecting method provided by the invention further include: big acquiring the industry by the multi-course concurrency form
After data, data filtering is carried out to the industrial big data, the data that only timestamp and data value change simultaneously could be stored in
The first shared section key in the data acquisition interface.
Collecting method provided by the invention further include: use breakpoint transmission technical transmission data, the breakpoint transmission skill
Art includes:
When the communication failure of data acquisition interface and data convergence interface, the data that do not transmit are marked；And when this is logical
When news restore normal, the data are uploaded in the case where not influencing normal data upload, then by the data that do not transmit
Interface is converged, and/or when the communication failure of data convergence interface and data receiver interface, marks the data that do not transmit；
And when the communication restores normal, uploaded in the case where not influencing normal data upload, then by the data that do not transmit
To the data receiver interface.
At data acquisition interface provided by the invention, the institute that is uploaded the package for the first time by the UDP network transmission protocol
It states industrial big data and is uploaded to the data convergence interface；Interface is converged in the data, it will by the TCP network transmission protocol
The industrial big data that the secondary package uploads is uploaded to the data receiver interface.
5 evaluation method of estimation block provided by the invention is as follows:
If dependent variable y and p independent variable x1,x2,…,xpThere is functional relation: y=β0+β1x1+…+βpxp, wherein β0,
β1,…,βpIt is the parameter to be estimated, it is characterised in that carry out in the following manner:
(1) setting the data sample for participating in least-squares calculation has n: xi1,xi2,…,xip,yi, i=1,2 ..., n are used
Weighted least squares regression is calculatedWhereinIt is β0,β1,…,βp's
Estimated value；
(2) sample data average deviation is calculated:
(3) following processing is recycled from i=1 ... n:
Calculate εi=abs (yi-β0-β1xi1-…-βpxip)；
If εiIt is excessive, distortion data is determine whether, if it is distortion data, is then filtered out；
Wherein distortion determines to carry out in the following manner:
εi>ε*xs,
Wherein xsIt can be empirical, can also be automatically adjusted with program, xs>1；
(4) filtered data sample number n is obtained1If the initial total number of samples calculated that participates in is n0
Work as n1< 0.67*n0 or n=n1When, then parameter Estimation calculating terminates；
Otherwise: enabling n=n1And (1) is returned, with this n1A data sample re-starts least-squares calculation
6 storage method of data memory module provided by the invention is as follows:
Firstly, obtaining measuring point title and the measuring point time of the industrial big data；
Secondly, obtaining corresponding measuring point ID and time series respectively according to the measuring point title and the measuring point time；
Then, the industrial big data is stored by row according to the measuring point ID and the time series.
It is provided by the invention to include: according to the corresponding time series of measuring point time acquisition
Date-time is converted by the character string of the measuring point time；
The time interval of the measuring point time and preset time are obtained, when hourage corresponding to the time interval is described
Between sequence.
It is provided by the invention to be stored the industrial big data by row according to the measuring point ID and the time series
It include: to be stored the industrial big data from same observation station ID by row according to the time series.
Storage method provided by the invention further include:
Industrial big data from same observation station ID is merged into same data area；
Industrial big data in the same data area from same time series is merged into same data file.
Storage method provided by the invention further include: to the industrial big data from same observation station ID and same observation station time
Automatic fitration is carried out to be stored if the industry big data is not stored；If the industry big data is stored, give up.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (5)
1. a kind of methods of evaluation of the simulation mathematical model parameter pair based on big data, which is characterized in that described to be based on big data
The methods of evaluation of simulation mathematical model parameter pair include:
Step 1 acquires industrial big data information using data acquisition interface；
Simulation mathematical model parameter pair is arranged using simulation software by parameter setting module in step 2；
Step 3 optimizes processing to the big data of acquisition using the big data optimization algorithm based on optimization particle swarm algorithm；
The estimation of simulation mathematical model parameter pair is operated using simulation software；
Step 4 utilizes the industrial big data of memory storage acquisition；
Step 5 is shown using the display for carrying out image denoising based on global adaptive fractional rank integral image Denoising Algorithm and is adopted
The industrial big data and estimation result of collection.
2. the methods of evaluation of the simulation mathematical model parameter pair based on big data as described in claim 1, which is characterized in that institute
The big data optimization algorithm based on optimization particle swarm algorithm in step 5 is stated, as follows:
In D dimension big data cloud storage cluster feature space, a population is formed by m particle, data clusters problem is converted
For a multi-objective optimization question, big data cluster in cloud storage:
MinF (x)=[f1(x), f2(x) ..., fn(x)]
s.t.gi(x)≤0 (or >=0) i=1,2 ... n
hj(x)=0 j=1,2 ..., m；
Wherein, fi(x) (i=1,2 ..., n) be objective function, gi(x) there are two 1 unstable periodic point x=0 and x=for system
1-1/ μ, hjIt (x) is equality constraint；It introduces Chaos-Particle Swarm Optimization and disturbs concept, obtain the spy of the cluster centre of decision variable x* domination
Sign solution are as follows:
For each big data information characteristics vector XiIt is achieved:
li(k)=(1- ρ) li(k-1)+γf((xi(k))；
Wherein, fiIt is Pareto optimal solution, Pij(k) i-th of decision variable of k moment, inequality f are indicatedi(X*)≤fi(X) it sets up,
The threshold value N of cluster is arranged in wherein i=1,2 ..., nth, work as Neff< NthWhen, the O of region of searchαAnd OβThe cluster in two sections is just
True probability are as follows:
The particle carried out in repository that improved mechanism using population hop count is updated；
Update the spatial position of each particle in population:
Wherein, xkFor the inertia weight searched in the region, a is the noninferior solution of cluster centre, deFor extreme point to noninferior solution away from
From when assessing the uniformity coefficient of disaggregation distribution, Optimal cluster centers phasor function q (x is pressed in calculatingi k/xi k-1), according to mould because of group
In update iteration sequence, obtain:
∑τ=diag (max (σi- τ, 0)；
Thus the particle fitness function that big data clusters in cloud storage is obtained are as follows:
Wherein, { α, β } is that diversity is amassed wealth by heavy taxation objective function.
3. the methods of evaluation of the simulation mathematical model parameter pair based on big data as described in claim 1, which is characterized in that institute
It states in step 5 and includes: based on global adaptive fractional rank integral image Denoising Algorithm
If the average value of the gradient magnitude in image f (i, j) on 8 directions of each pixel is M (i, j), and carries out normalizing
Change, finds out integral order corresponding with the pixel；The maximum value for taking M (i, j) is Y, minimum value X, by the gradient of pixel
After amplitude is normalized, dynamic fractional order integration order is found out:
4. a kind of methods of evaluation using the simulation mathematical model parameter pair described in claim 1 based on big data is counted based on big
According to simulation mathematical model parameter pair appraisal system, which is characterized in that the simulation mathematical model parameter based on big data
Pair appraisal system include:
Big data acquisition module, connect with main control module, for acquiring industrial big data information by data acquisition interface；
Main control module, with big data acquisition module, parameter setting module, optimization module, estimation block, data memory module, aobvious
Show that module connects, is worked normally for controlling modules by single-chip microcontroller；
Parameter setting module is connect with main control module, for simulation mathematical model parameter pair to be arranged by simulation software；
Optimization module is connect with main control module, for optimizing processing by big data of the optimization algorithm to acquisition；
Estimation block is connect with main control module, for being operated by simulation software to the estimation of simulation mathematical model parameter pair；
Data memory module is connect with main control module, for the industrial big data by memory storage acquisition；
Display module is connect with main control module, for the industrial big data and estimation result by display display acquisition.
5. a kind of appraisal side using the simulation mathematical model parameter pair described in claims 1 to 3 any one based on big data
The information data processing terminal of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811503393.2A CN109670227B (en) | 2018-12-10 | 2018-12-10 | Method for estimating parameter pairs of simulation mathematical model based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811503393.2A CN109670227B (en) | 2018-12-10 | 2018-12-10 | Method for estimating parameter pairs of simulation mathematical model based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109670227A true CN109670227A (en) | 2019-04-23 |
| CN109670227B CN109670227B (en) | 2023-04-07 |
Family
ID=66143583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811503393.2A Active CN109670227B (en) | 2018-12-10 | 2018-12-10 | Method for estimating parameter pairs of simulation mathematical model based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670227B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112953913A (en) * | 2021-01-29 | 2021-06-11 | 江苏提米智能科技有限公司 | Method for realizing rapid access, aggregation, storage and release of industrial Internet of things intelligent equipment data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040040000A1 (en) * | 2002-08-20 | 2004-02-26 | Kunal Taravade | Device parameter and gate performance simulation based on wafer image prediction |
| CN103105778A (en) * | 2013-02-05 | 2013-05-15 | 中原工学院 | Estimation method for industrial process simulation mathematical model parameters |
| CN107480394A (en) * | 2017-08-28 | 2017-12-15 | 河南科技学院 | A kind of methods of evaluation of simulation mathematical model parameter pair |
| US20180004880A1 (en) * | 2016-06-29 | 2018-01-04 | Oracle International Corporation | Variation-aware design analysis |
-
2018
- 2018-12-10 CN CN201811503393.2A patent/CN109670227B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040040000A1 (en) * | 2002-08-20 | 2004-02-26 | Kunal Taravade | Device parameter and gate performance simulation based on wafer image prediction |
| CN103105778A (en) * | 2013-02-05 | 2013-05-15 | 中原工学院 | Estimation method for industrial process simulation mathematical model parameters |
| US20180004880A1 (en) * | 2016-06-29 | 2018-01-04 | Oracle International Corporation | Variation-aware design analysis |
| CN107480394A (en) * | 2017-08-28 | 2017-12-15 | 河南科技学院 | A kind of methods of evaluation of simulation mathematical model parameter pair |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112953913A (en) * | 2021-01-29 | 2021-06-11 | 江苏提米智能科技有限公司 | Method for realizing rapid access, aggregation, storage and release of industrial Internet of things intelligent equipment data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109670227B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Probabilistic solar irradiation forecasting based on variational Bayesian inference with secure federated learning | |
| CN112054943B (en) | Traffic prediction method for mobile network base station | |
| CN105791051A (en) | WSN (Wireless Sensor Network) abnormity detection method and system based on artificial immunization and k-means clustering | |
| CN112733417A (en) | Abnormal load data detection and correction method and system based on model optimization | |
| CN112329997A (en) | Power demand load prediction method and system, electronic device, and storage medium | |
| CN116992399A (en) | Power equipment operation and maintenance assessment method based on power data analysis | |
| CN115795329B (en) | Power utilization abnormal behavior analysis method and device based on big data grid | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN111163487A (en) | Method and system for evaluating comprehensive transmission performance of communication waveform | |
| CN116308883A (en) | Regional power grid data overall management system based on big data | |
| CN116933318A (en) | Power consumption data privacy protection method based on federal learning | |
| CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
| CN109670227A (en) | A kind of methods of evaluation of the simulation mathematical model parameter pair based on big data | |
| CN116738354B (en) | Method and system for detecting abnormal behavior of electric power Internet of things terminal | |
| CN117010483A (en) | Federal learning security aggregation method and system for distributed load prediction | |
| CN110264010B (en) | Novel rural power saturation load prediction method | |
| WO2023061303A1 (en) | Large-scale fading modeling and estimation method, system, and device, and storage medium | |
| CN116885702A (en) | Power grid state analysis method and system based on random matrix theory principal component analysis | |
| CN115099385B (en) | Spectrum map construction method based on sensor layout optimization and self-adaptive Kriging model | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| CN109493065A (en) | A kind of fraudulent trading detection method of Behavior-based control incremental update | |
| CN118484566B (en) | Distributed time sequence data analysis processing method and system | |
| CN117834455B (en) | Electric power Internet of things data transmission simulation method and system | |
| CN118300104B (en) | Distributed photovoltaic power prediction method, system, electronic equipment and storage medium based on graph neural network | |
| CN116911414A (en) | Power consumption prediction method, device, equipment and computer storage medium |
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 |