CN109034250A - A kind of information representation system of spacecraft monitoring big data - Google Patents
A kind of information representation system of spacecraft monitoring big data Download PDFInfo
- Publication number
- CN109034250A CN109034250A CN201810857938.3A CN201810857938A CN109034250A CN 109034250 A CN109034250 A CN 109034250A CN 201810857938 A CN201810857938 A CN 201810857938A CN 109034250 A CN109034250 A CN 109034250A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- monitoring
- wavelet
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a kind of information representation systems of spacecraft monitoring big data, improve module, signal resolution module and characterization module including multi-source information acquiring module, data, wherein: multi-source information acquiring module acquires monitoring information, and is input in data improvement module;Data improve module and preset foreign peoples's function, determine the reliability of monitoring information according to the absolute difference of foreign peoples's functional value of monitoring signals and monitoring result, and screen reliable data, are transmitted separately to signal resolution module and characterization module;Signal resolution module receives reliable data, establishes deconvolution network, improves the accuracy of data;Characterization module establishes big data sparse network, realizes the quick classification of monitoring data.It by building foreign peoples's function, deconvolution network and big data sparse network, screened, parsed and is characterized to from multiple heterologous monitoring informations, improve the accuracy of monitoring data, improve monitoring quality and monitoring efficiency.
Description
Technical field
The invention belongs to the information representation systems of spacecraft monitoring technical field more particularly to a kind of spacecraft monitoring big data
System.
Background technique
With the progress of Information technology, large-scale intelligent information system is in communication, finance, military affairs, logistics, business administration etc.
Field is commonly used.Spacecraft is monitored, usually with floor control system to the measurement data of sensor filled on spacecraft
To judge the state in orbit of spacecraft.And it is generally equipped with a plurality of types of sensors on spacecraft, obtain and screens is useful
Information, be to obtain accurate determining result basis.In addition it is also necessary to will be carried out from multiple heterologous information data parsing and
Characterization, and be re-organized in the data storage of semantic congruence, for supporting management decision-making process and complicated multi-dimensional query.It is right
This, there is no relevant reports for the prior art.
Summary of the invention
For the above-mentioned deficiency of the prior art, the present invention provides a kind of information representation system of spacecraft monitoring big data,
It include: multi-source information acquiring module, data improvement module, signal resolution module and characterization module, in which: multi-source information is adopted
Collect module and acquire monitoring information, and is input to data to improve in module;Data improve module and preset foreign peoples's function, are believed according to monitoring
Number foreign peoples's functional value and the absolute difference of monitoring result determine the reliability of monitoring information, and screen reliable data, point
Supplementary biography transports to signal resolution module and characterization module;Signal resolution module receives reliable data, establishes deconvolution network,
Improve the accuracy of data;Characterization module establishes big data sparse network, realizes the quick classification of monitoring data.
Preferably, acquisition monitoring information includes power, temperature, light, electric current, voltage and electromagnetic signal.
Preferably, multi-source information acquiring module further includes signal conversion module, and it is defeated to convert analog signals into digital signal
Improve module to data out.
Preferably, the foreign peoples function f (x) is as shown in formula (1):
In formula, x is the absolute difference of foreign peoples's functional value and monitoring result, [0, x0] it is the intensive section of x value, X0It is x
The maximum value being likely to occur, ω ∈ (0,1) are overall coefficients, and n > 1 is radical exponent.Further, ω >=0.6, n≤5.
Preferably, using nerual network technique, desired output is provided according to wavelet automatically, obtain anti-wavelet and deconvolution because
Son.
Further, anti-wavelet is obtained by following steps:
(S11) using wavelet as input, sharp pulse is desired output, and anti-wavelet is network weight, using lowest mean square
Algorithm training network is practised, reality output result is obtained;
(S12) new desired output is provided according to reality output result, re -training network obtains anti-wavelet.
Neural network deconvolution is realized by following steps:
(S21) the super averaged power spectrum wavelet amplitude of multiple tracks is used;
(S22) by constant phase correction technology estimation sub-wave phase spectrum;
(S23) wavelet is sought with anti-Fourier transform;
(S24) anti-wavelet is sought using neural network;
(S25) deconvolution.
Preferably, big data sparse network is obtained according to the iterative calculation of DCT dictionary and sparse decomposition algorithm.
Beneficial effects of the present invention: by building foreign peoples's function, deconvolution network and big data sparse network, to from more
A heterologous monitoring information is screened, parsed and is characterized, and the accuracy of monitoring data is improved, and improves monitoring quality and prison
Survey efficiency.
Specific embodiment
The present invention will be described in detail With reference to embodiment.
The present invention provides a kind of information representation system of spacecraft monitoring big data, comprising: multi-source information acquiring module, number
According to improvement module, signal resolution module and characterization module, in which:
Multi-source information acquiring module acquires the monitoring information including power, temperature, light, electric current, voltage and electromagnetic signal,
And be input in data improvement module, it further include the signal conversion module for converting analog signals into digital signal.
Data improve module and preset foreign peoples's function, and the difference according to foreign peoples's functional value of monitoring signals and monitoring result is absolute
It is worth the reliability for determining monitoring information, and screens reliable data, is transmitted separately to signal resolution module and characterization module.
The foreign peoples function f (x) is as shown in formula (1):
In formula, x is the absolute difference of foreign peoples's functional value and monitoring result, [0, x0] it is the intensive section of x value, X0It is x
The maximum value being likely to occur, W ∈ (0,1) are overall coefficients, and n > 1 is radical exponent.Wherein, ω is weighted to x value, works as ω
Too small or mistake mostly shows that data reliability is bad, x0Be difference it is sparse define value, n adjusts curvature.Comprehensively consider instrument prison
Survey the influence of error and environment to monitoring result, ω >=0.6, n≤5.
Signal resolution module receives reliable data, establishes deconvolution network, improves the accuracy of data.Utilize nerve net
Network technology provides desired output according to wavelet automatically, then using this desired output training network obtain anti-wavelet, can obtain compared with
Reasonable deconvolution operator keeps preferable data SNR.In the ideal case, wavelet is with the output after anti-wavelet convolution
Sharp pulse, wavelet of negating in this way are divided into two steps:
(S11) using wavelet as input, sharp pulse is desired output, and anti-wavelet is network weight, using lowest mean square
Algorithm training network is practised, reality output result is obtained;
(S12) new desired output is provided according to reality output result, re -training network obtains anti-wavelet.
Neural network deconvolution realizes that steps are as follows:
(S21) the super averaged power spectrum wavelet amplitude of multiple tracks is used;
(S22) by constant phase correction technology estimation sub-wave phase spectrum;
(S23) wavelet is sought with anti-Fourier transform;
(S24) anti-wavelet is sought using neural network;
(S25) deconvolution.
Characterization module establishes big data sparse network, realizes the quick classification of monitoring data.Select the DCT word of redundancy
Allusion quotation is initialized, and the iterative calculation of sparse decomposition algorithm is carried out, and realizes the whole average treatment to part, it is quick to reach data
The purpose of classification.
By building foreign peoples's function, deconvolution network and big data sparse network, to from multiple heterologous monitoring informations
It screened, parsed and is characterized, improve the accuracy of monitoring data, improve monitoring quality and monitoring efficiency.
The above embodiments are merely illustrative of the technical solutions of the present invention and is not intended to limit it, all without departing from the present invention
Any modification of spirit and scope or equivalent replacement should all cover in the protection scope of technical solution of the present invention.
Claims (9)
1. a kind of information representation system of spacecraft monitoring big data, which is characterized in that including multi-source information acquiring module, data
Improve module, signal resolution module and characterization module, in which: multi-source information acquiring module acquires monitoring information, and inputs
Improve in module to data;Data improve module and preset foreign peoples's function, according to the foreign peoples's functional value and monitoring result of monitoring signals
Absolute difference determine the reliability of monitoring information, and screen reliable data, be transmitted separately to signal resolution module and letter
Number characterization module;Signal resolution module receives reliable data, establishes deconvolution network, improves the accuracy of data;Signal table
Sign module establishes big data sparse network, realizes the quick classification of monitoring data.
2. information representation system according to claim 1, which is characterized in that acquisition monitoring information include power, temperature, light,
Electric current, voltage and electromagnetic signal.
3. information representation system according to claim 1, which is characterized in that multi-source information acquiring module further includes that signal turns
Block is changed the mold, converting analog signals into digital signal and exporting to data improves module.
4. information representation system according to claim 1, which is characterized in that the foreign peoples function f (x) is as shown in formula (1):
In formula, x is the absolute difference of foreign peoples's functional value and monitoring result, [0, x0] it is the intensive section of x value, X0It is that x may
The maximum value of appearance, ω ∈ (0,1) are overall coefficients, and n > 1 is radical exponent.
5. information representation system according to claim 4, which is characterized in that ω >=0.6, n≤5.
6. information representation system according to claim 1, which is characterized in that utilize nerual network technique, certainly according to wavelet
It is dynamic to provide desired output, obtain anti-wavelet and deconvolution operator.
7. information representation system according to claim 6, which is characterized in that anti-wavelet is obtained by following steps:
(S11) using wavelet as input, sharp pulse is desired output, and anti-wavelet is network weight, learns to calculate using lowest mean square
Method trains network, obtains reality output result;
(S12) new desired output is provided according to reality output result, re -training network obtains anti-wavelet.
8. information representation system according to claim 6, which is characterized in that neural network deconvolution passes through following steps reality
It is existing:
(S21) the super averaged power spectrum wavelet amplitude of multiple tracks is used;
(S22) by constant phase correction technology estimation sub-wave phase spectrum;
(S23) wavelet is sought with anti-Fourier transform;
(S24) anti-wavelet is sought using neural network;
(S25) deconvolution.
9. information representation system according to claim 1, which is characterized in that big data sparse network according to DCT dictionary and
The iterative calculation of sparse decomposition algorithm obtains.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810857938.3A CN109034250A (en) | 2018-07-31 | 2018-07-31 | A kind of information representation system of spacecraft monitoring big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810857938.3A CN109034250A (en) | 2018-07-31 | 2018-07-31 | A kind of information representation system of spacecraft monitoring big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109034250A true CN109034250A (en) | 2018-12-18 |
Family
ID=64647979
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810857938.3A Pending CN109034250A (en) | 2018-07-31 | 2018-07-31 | A kind of information representation system of spacecraft monitoring big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109034250A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040263386A1 (en) * | 2003-06-26 | 2004-12-30 | King Thomas M. | Satellite positioning system receivers and methods |
CN102542291A (en) * | 2011-12-23 | 2012-07-04 | 国网电力科学研究院 | Hyperspectral remote sensing image classification method based on binary decision tree |
US20140072209A1 (en) * | 2012-09-13 | 2014-03-13 | Los Alamos National Security, Llc | Image fusion using sparse overcomplete feature dictionaries |
CN104569694A (en) * | 2015-01-28 | 2015-04-29 | 北京空间飞行器总体设计部 | Electric signal feature extraction and recognition system oriented to aircraft flying process |
CN105608692A (en) * | 2015-12-17 | 2016-05-25 | 西安电子科技大学 | PolSAR image segmentation method based on deconvolution network and sparse classification |
CN106446965A (en) * | 2016-10-21 | 2017-02-22 | 西北工业大学 | Spacecraft visible light image classification method |
CN108022222A (en) * | 2017-12-15 | 2018-05-11 | 西北工业大学 | A kind of thin cloud in remote sensing image minimizing technology based on convolution-deconvolution network |
-
2018
- 2018-07-31 CN CN201810857938.3A patent/CN109034250A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040263386A1 (en) * | 2003-06-26 | 2004-12-30 | King Thomas M. | Satellite positioning system receivers and methods |
CN102542291A (en) * | 2011-12-23 | 2012-07-04 | 国网电力科学研究院 | Hyperspectral remote sensing image classification method based on binary decision tree |
US20140072209A1 (en) * | 2012-09-13 | 2014-03-13 | Los Alamos National Security, Llc | Image fusion using sparse overcomplete feature dictionaries |
CN104569694A (en) * | 2015-01-28 | 2015-04-29 | 北京空间飞行器总体设计部 | Electric signal feature extraction and recognition system oriented to aircraft flying process |
CN105608692A (en) * | 2015-12-17 | 2016-05-25 | 西安电子科技大学 | PolSAR image segmentation method based on deconvolution network and sparse classification |
CN106446965A (en) * | 2016-10-21 | 2017-02-22 | 西北工业大学 | Spacecraft visible light image classification method |
CN108022222A (en) * | 2017-12-15 | 2018-05-11 | 西北工业大学 | A kind of thin cloud in remote sensing image minimizing technology based on convolution-deconvolution network |
Non-Patent Citations (2)
Title |
---|
朱宝山: "子波整形反褶积在提高地震资料分辨率中的研究与应用", 《中国优秀硕士学位论文全文数据库》 * |
李海山: "基于稀疏表示理论的地震信号处理方法研究", 《中国博士学位论文全文数据库》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10565684B2 (en) | Super-resolution method and system, server, user device and method therefor | |
CN108281177B (en) | Internet of things intensive care system | |
CN114692665B (en) | Radiation source open set individual identification method based on metric learning | |
CN109241941A (en) | A method of the farm based on deep learning analysis monitors poultry quantity | |
CN104200441B (en) | Higher-order singular value decomposition based magnetic resonance image denoising method | |
CN110210468A (en) | A kind of character recognition method based on the migration of convolutional neural networks Fusion Features | |
CN115965579B (en) | Substation inspection three-dimensional defect identification and positioning method and system | |
CN109408945A (en) | A kind of non-aircraft noise filter method | |
Pan et al. | DenseNetFuse: A study of deep unsupervised DenseNet to infrared and visual image fusion | |
CN113780160B (en) | Electric energy quality disturbance signal classification method and system | |
CN115376526A (en) | Power equipment fault detection method and system based on voiceprint recognition | |
Aishwarya et al. | An image fusion framework using novel dictionary based sparse representation | |
CN109034250A (en) | A kind of information representation system of spacecraft monitoring big data | |
CN109361484A (en) | A kind of transmission method of electric system time synchronization data | |
Li et al. | An EEMD-SVD method based on gray wolf optimization algorithm for lidar signal noise reduction | |
CN110751201B (en) | SAR equipment task failure cause reasoning method based on textural feature transformation | |
CN106646631B (en) | Intelligent human-body inducing method | |
CN114882139B (en) | End-to-end intelligent generation method and system for multi-level map | |
CN107272048B (en) | A kind of complicated nuclide identification method based on fuzzy decision-tree | |
CN107204741B (en) | Method and device for determining environmental parameters | |
CN106845763B (en) | Power grid reliability analysis method and device | |
CN109596165A (en) | A kind of intelligence geography information dynamic early-warning is deployed to ensure effective monitoring and control of illegal activities system and method | |
Li et al. | Image quality assessment based on the correlation coefficient and the 2-D discrete wavelet transform | |
CN113822833B (en) | Infrared and visible light image frequency domain fusion method based on convolutional neural network and regional energy | |
Wang et al. | Frequency domain fusion algorithm of infrared and visible image based on compressed sensing for video surveillance forensics |
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: 20181218 |
|
RJ01 | Rejection of invention patent application after publication |