CN108983183A - A kind of adaptive radar sea clutter forecast system - Google Patents
A kind of adaptive radar sea clutter forecast system Download PDFInfo
- Publication number
- CN108983183A CN108983183A CN201810691874.4A CN201810691874A CN108983183A CN 108983183 A CN108983183 A CN 108983183A CN 201810691874 A CN201810691874 A CN 201810691874A CN 108983183 A CN108983183 A CN 108983183A
- Authority
- CN
- China
- Prior art keywords
- layer
- sea clutter
- output
- radar
- wavelet
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/414—Discriminating targets with respect to background clutter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of adaptive radar sea clutter forecast systems, including radar, database and host computer;Radar, database and host computer are sequentially connected, and radar is irradiated detected sea area, and by radar sea clutter data storage into database, and host computer carries out Modeling and Prediction to the sea clutter data in database;The host computer includes data preprocessing module, Fuzzy Wavelet Network modeling module, sea clutter forecast module, discrimination model update module and result display module.And propose a kind of radar sea clutter forecasting procedure based on Fuzzy Wavelet Network.The present invention provides the radar sea clutter forecast system and method that a kind of structural parameters are adaptive, model automatically updates, noise resistance interference performance is strong.
Description
Technical field
The present invention relates to radar data process fields, particularly, are related to a kind of adaptive radar sea clutter forecast system.
Background technique
Sea clutter, the i.e. backscattering echo from a piece of sea irradiated by radar emission signal.Due to sea clutter
To from sea or close to " point " target on sea, such as maritime buoyage and the radar return of the afloat ice cube target of floating
Detectability forms serious restriction, therefore the research of sea clutter has very the detection performance of the targets such as steamer in marine background
Important influence is to have most important theories meaning and practical value.
Traditionally sea clutter is considered as single random process, such as logarithm normal distribution, K distribution.However these models exist
There is its specific limitation in practical application, one of major reason is that sea clutter seems random waveform, actually simultaneously
Without random distribution nature.
Summary of the invention
In order to overcome influence, the system noise resistance interference performance of the artificial selection parameter of conventional radar sea clutter forecasting procedure weak
Deficiency, the present invention provides the radar sea clutter that a kind of structural parameters are adaptive, model automatically updates, noise resistance interference performance is strong
Forecast system.
The technical solution adopted by the present invention to solve the technical problems is: a kind of adaptive pre- syndicate of radar sea clutter
System, including radar, database and host computer;The host computer includes that data preprocessing module, Fuzzy Wavelet Network are built
Mould module, sea clutter forecast module, discrimination model update module and result display module, in which:
Data preprocessing module: pre-processing the radar sea clutter data of database input, complete using following process
At:
(1) N number of radar sea clutter echo-signal amplitude x is acquired from databaseiAs training sample, i=1,2 ..., N;
(2) training sample is normalized, obtains normalization amplitude
Wherein, min x indicates the minimum value in training sample, and max x indicates the maximum value in training sample;
(3) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output square Y:
Wherein, D indicates reconstruct dimension, and D is natural number, and the value range of D < N, D are 50-70.
Fuzzy Wavelet Network modeling module: it to establish forecasting model, is completed using following process:
(1) Fuzzy Wavelet Network is one five layers of network structure, comprising input layer, blurring layer, rules layer, small
Wave resultant layer, output layer.The fuzzy rule of the network obeys following form:
Wherein, x1,x2,…,xnIndicate input variable, ψ1,ψ2,…,ψMIndicate output variable, AkjIt is comprising Gauss member's letter
K-th several of fuzzy sets, ωikIt is connection weight.
To being described as follows for each layer of node:
First layer (input layer): in this layer, one input variable of each node on behalf, each input variableThe output of node is all mapped directly at node, wherein n indicates the number of wherein input variable.
The second layer (blurring layer): input of the output of first layer as member function, corresponding membership function values can be with
It is calculated according to following Gaussian function:
Wherein, mjAnd σjCenter and the width of Gauss member function are respectively indicated, M indicates the number of rule.
Third layer (rules layer): in this layer, number of nodes is equal to regular number, each node represents one to defeated
Enter the T- norm operation of variable, input variable here is the output valve of second layer blurring layer, and the output of node is input
Relevance grade of the variable to this rule.The then output of k-th of node is
Wherein, the connection weight being blurred between layer and rules layerIt is set as 1.
4th layer (small echo resultant layer): wavelet layer receives variable x1,x2,…,xnAs input signal, it includes M small echo
Neural network, and the resultant layer of the corresponding fuzzy rule of each wavelet neural network.ψkIt is the output of wavelet neural network,
It is expressed as follows:
The node of resultant layer receives the input from wavelet layer and rules layer, and the two is multiplied, the output as this layer:
Wherein, the connection weight between resultant layer and rules layerIt is set as 1.
Layer 5 (output layer): each output of this layer represents an output variable, and output variable is by the layer
The 4th layer of node set of input variable value and anti fuzzy method is carried out to it, here using weighted sum as anti fuzzy method letter
Number.Calculate the final output of network:
(2) Learning Algorithms
The modified parameter sets are needed to be in Fuzzy Wavelet NetworkIncluding
The center m of Gauss member function in two layersjAnd width csj, the shift factor b of wavelet functionikWith zoom factor aik, the 4th layer small
The weighting parameter ω of wave layerik, the connection weight of layer 5
In gradient descent algorithm, the structural parameters of network are adjusted according to the opposite direction of target function gradientObjective function is as follows:
Wherein, y and f respectively indicate predicted value and true value.
The update rule of Fuzzy Wavelet Network parameter is shown below:
Θ (t+1)=Θ (t)+Δ Θ (12)
Wherein, η=(ηm,ησ,ηb,ηa,ηω1,ηω2) indicating the corresponding learning rate of each parameter, the differential term in above formula can
To be calculated according to Back Propagation Algorithm described below.
Layer 5: this layer needs the error term propagated to be
Correspondingly, connection weightIncremental computations it is as follows:
4th layer: this layer needs the error term propagated to be
Wavelet layer weighting parameter ωikIncremental computations it is as follows:
Zoom factor aikIncremental computations it is as follows:
Shift factor bikIncremental computations it is as follows:
Third layer: this layer needs the error term propagated to be
The second layer: the error term of this layer calculates as follows:
Correspondingly, member function Center Parameter mjIncremental computations it is as follows:
Member function width parameter σjIncremental computations it is as follows:
Therefore, as long as learning rate η=(η has been determinedm,ησ,ηb,ηa,ηω1,ηω2), so that it may adjust the structure ginseng of network
Number, so that neural network forecast output be made constantly to approach desired output.
Sea clutter forecast module: it to carry out sea clutter prediction, is completed using following process:
(1) D sea clutter echo-signal amplitude is acquired in sampling instant t obtain TX=[xt-D+1,…,xt], xt-D+1It indicates
The sea clutter echo-signal amplitude of t-D+1 sampling instant, xtIndicate the sea clutter echo-signal amplitude of t sampling instant;
(2) it is normalized:
(3) the sea clutter predicted value that sampling instant (t+1) is calculated in Fuzzy Wavelet Network modeling module is substituted into.
Host computer in the adaptive radar sea clutter forecast system further include: discrimination model update module, to
By the sampling time interval of setting, data are acquired, by obtained measured data compared with model prediction value, if relative error is big
In 10%, then training sample data are added in new data, update forecasting model.And result display module, to by sea clutter
The predicted value that forecast module is calculated is shown in host computer.
Beneficial effects of the present invention are mainly manifested in: the present invention forecasts radar sea clutter, overcomes conventional radar extra large
The weak deficiency of the influence of the artificial selection parameter of clutter forecasting procedure, system noise resistance interference performance, it is special using the chaos of sea clutter
Property, in conjunction with neural network and fuzzy system, Fuzzy Wavelet Network is proposed, Fuzzy Wavelet Network model passes through online
Study, the structure and parameter of dynamic adjustment model improves the stability of model, so that the anti-noise jamming ability of system is strong.
Detailed description of the invention
Fig. 1 is the hardware structure diagram of system proposed by the invention;
Fig. 2 is the functional block diagram of host computer proposed by the invention.
Specific embodiment
The present invention is illustrated below according to attached drawing.
Referring to Fig.1, Fig. 2, a kind of adaptive radar sea clutter forecast system, including radar 1, database 2 and host computer
3, radar 1, database 2 and host computer 3 are sequentially connected, and 1 pair of detected sea area of the radar is irradiated, and by radar sea clutter
To the database 2, the host computer 3 includes: data storage
Data preprocessing module 4: pre-processing the radar sea clutter data of database input, complete using following process
At:
(1) N number of radar sea clutter echo-signal amplitude x is acquired from databaseiAs training sample, i=1,2 ..., N;
(2) training sample is normalized, obtains normalization amplitude
Wherein, min x indicates the minimum value in training sample, and max x indicates the maximum value in training sample;
(3) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output square Y:
Wherein, D indicates reconstruct dimension, and D is natural number, and the value range of D < N, D are 50-70.
Fuzzy Wavelet Network modeling module 5: it to establish forecasting model, is completed using following process:
(1) Fuzzy Wavelet Network is one five layers of network structure, comprising input layer, blurring layer, rules layer, small
Wave resultant layer, output layer.The fuzzy rule of the network obeys following form:
Wherein, x1,x2,…,xnIndicate input variable, ψ1,ψ2,…,ψMIndicate output variable, AkjIt is comprising Gauss member's letter
K-th several of fuzzy sets, ωikIt is connection weight.
To being described as follows for each layer of node:
First layer (input layer): in this layer, one input variable of each node on behalf, each input variableThe output of node is all mapped directly at node, wherein n indicates the number of wherein input variable.
The second layer (blurring layer): input of the output of first layer as member function, corresponding membership function values can be with
It is calculated according to following Gaussian function:
Wherein, mjAnd σjCenter and the width of Gauss member function are respectively indicated, M indicates the number of rule.
Third layer (rules layer): in this layer, number of nodes is equal to regular number, each node represents one to defeated
Enter the T- norm operation of variable, input variable here is the output valve of second layer blurring layer, and the output of node is input
Relevance grade of the variable to this rule.The then output of k-th of node is
Wherein, the connection weight being blurred between layer and rules layerIt is set as 1.
4th layer (small echo resultant layer): wavelet layer receives variable x1,x2,…,xnAs input signal, it includes M small echo
Neural network, and the resultant layer of the corresponding fuzzy rule of each wavelet neural network.ψkIt is the output of wavelet neural network,
It is expressed as follows:
The node of resultant layer receives the input from wavelet layer and rules layer, and the two is multiplied, the output as this layer:
Wherein, the connection weight between resultant layer and rules layerIt is set as 1.
Layer 5 (output layer): each output of this layer represents an output variable, and output variable is by the layer
The 4th layer of node set of input variable value and anti fuzzy method is carried out to it, here using weighted sum as anti fuzzy method letter
Number.Calculate the final output of network:
(2) Learning Algorithms
The modified parameter sets are needed to be in Fuzzy Wavelet NetworkIncluding
The center m of Gauss member function in two layersjAnd width csj, the shift factor b of wavelet functionikWith zoom factor aik, the 4th layer small
The weighting parameter ω of wave layerik, the connection weight of layer 5
In gradient descent algorithm, the structural parameters of network are adjusted according to the opposite direction of target function gradientObjective function is as follows:
Wherein, y and f respectively indicate predicted value and true value.
The update rule of Fuzzy Wavelet Network parameter is shown below:
Θ (t+1)=Θ (t)+Δ Θ (12)
Wherein, η=(ηm,ησ,ηb,ηa,ηω1,ηω2) indicating the corresponding learning rate of each parameter, the differential term in above formula can
To be calculated according to Back Propagation Algorithm described below.
Layer 5: this layer needs the error term propagated to be
Correspondingly, connection weightIncremental computations it is as follows:
4th layer: this layer needs the error term propagated to be
Wavelet layer weighting parameter ωikIncremental computations it is as follows:
Zoom factor aikIncremental computations it is as follows:
Shift factor bikIncremental computations it is as follows:
Third layer: this layer needs the error term propagated to be
The second layer: the error term of this layer calculates as follows:
Correspondingly, member function Center Parameter mjIncremental computations it is as follows:
Member function width parameter σjIncremental computations it is as follows:
Therefore, as long as learning rate η=(η has been determinedm,ησ,ηb,ηa,ηω1,ηω2), so that it may adjust the structure ginseng of network
Number, so that neural network forecast output be made constantly to approach desired output.
Sea clutter forecast module 6: it to carry out sea clutter prediction, is completed using following process:
(1) D sea clutter echo-signal amplitude is acquired in sampling instant t obtain TX=[xt-D+1,…,xt], xt-D+1It indicates
The sea clutter echo-signal amplitude of t-D+1 sampling instant, xtIndicate the sea clutter echo-signal amplitude of t sampling instant;
(2) it is normalized:
(3) the sea clutter predicted value that sampling instant (t+1) is calculated in Fuzzy Wavelet Network modeling module is substituted into.
The host computer 3 further include: discrimination model update module 7 acquires data by the sampling time interval of setting, will
Compared with model prediction value, if relative error is greater than 10%, number of training is added in new data by obtained measured data
According to update forecasting model.
The host computer 3 further include: result display module 8, the predicted value for sea clutter forecast module to be calculated
It is shown in host computer.
The hardware components of the host computer 3 include: I/O element, for the acquisition of data and the transmitting of information;Data storage
Device, data sample and operating parameter etc. needed for storage operation;The software program of functional module is realized in program storage, storage;
Arithmetic unit executes program, realizes specified function;Display module shows the parameter and operation result of setting.
The embodiment of the present invention is used to illustrate the present invention, rather than limits the invention, in spirit of the invention
In scope of protection of the claims, to any modifications and changes that the present invention makes, protection scope of the present invention is both fallen within.
Claims (4)
1. a kind of adaptive radar sea clutter forecast system, including radar, database and host computer;Radar, database and
Host computer is sequentially connected, and radar is irradiated detected sea area, and by radar sea clutter data storage into database, upper
Machine carries out Modeling and Prediction to the sea clutter data in database;The host computer includes data preprocessing module, fuzzy wavelet
Neural net model establishing module, sea clutter forecast module, discrimination model update module and result display module.
2. adaptive radar sea clutter forecast system according to claim 1, which is characterized in that the data prediction mould
Block pre-processes the radar sea clutter data that database inputs, and is completed using following process:
(1) N number of radar sea clutter echo-signal amplitude x is acquired from databaseiAs training sample, i=1,2 ..., N;
(2) training sample is normalized, obtains normalization amplitude
Wherein, min x indicates the minimum value in training sample, and max x indicates the maximum value in training sample;
(3) training sample after normalization is reconstructed, respectively obtains input matrix X and corresponding output square Y:
Wherein, D indicates reconstruct dimension, and D is natural number, and the value range of D < N, D are 50-70.
3. adaptive radar sea clutter forecast system according to claim 1, which is characterized in that the fuzzy wavelet nerve
Network modelling module is completed to establish forecasting model using following process:
(1) Fuzzy Wavelet Network is one five layers of network structure, includes input layer, blurring layer, rules layer, small echo knot
Fruit layer, output layer.The fuzzy rule of the network obeys following form:
Wherein, x1,x2,…,xnIndicate input variable, ψ1,ψ2,…,ψMIndicate output variable, AkjIt is comprising Gauss member function
K-th of fuzzy set, ωikIt is connection weight.
To being described as follows for each layer of node:
First layer (input layer): in this layer, one input variable of each node on behalf, each input variableThe output of node is all mapped directly at node, wherein n indicates the number of wherein input variable.
The second layer (blurring layer): input of the output of first layer as member function, corresponding membership function values can basis
Following Gaussian function is calculated:
Wherein, mjAnd σjCenter and the width of Gauss member function are respectively indicated, M indicates the number of rule.
Third layer (rules layer): in this layer, number of nodes is equal to regular number, each node represents one and becomes to input
The T- norm of amount operates, and input variable here is the output valve of second layer blurring layer, and the output of node is input variable
To the relevance grade of this rule.The then output of k-th of node is
Wherein, the connection weight being blurred between layer and rules layerIt is set as 1.
4th layer (small echo resultant layer): wavelet layer receives variable x1,x2,…,xnAs input signal, it includes M wavelet neural
Network, and the resultant layer of the corresponding fuzzy rule of each wavelet neural network.ψkIt is the output of wavelet neural network, indicates
It is as follows:
The node of resultant layer receives the input from wavelet layer and rules layer, and the two is multiplied, the output as this layer:
Wherein, the connection weight between resultant layer and rules layerIt is set as 1.
Layer 5 (output layer): each output of this layer represents an output variable, and output variable is the section by this layer
The input variable value that the 4th layer of point set simultaneously carries out anti fuzzy method to it, here using weighted sum as anti fuzzy method function.
Calculate the final output of network:
(2) Learning Algorithms
The modified parameter sets are needed to be in Fuzzy Wavelet NetworkIncluding the second layer
The center m of middle Gauss member functionjAnd width csj, the shift factor b of wavelet functionikWith zoom factor aik, the 4th layer of wavelet layer
Weighting parameter ωik, the connection weight of layer 5
In gradient descent algorithm, the structural parameters of network are adjusted according to the opposite direction of target function gradientObjective function is as follows:
Wherein, y and f respectively indicate predicted value and true value.
The update rule of Fuzzy Wavelet Network parameter is shown below:
Θ (t+1)=Θ (t)+Δ Θ (12)
Wherein, η=(ηm,ησ,ηb,ηa,ηω1,ηω2) indicating the corresponding learning rate of each parameter, the differential term in above formula can root
It is calculated according to Back Propagation Algorithm described below.
Layer 5: this layer needs the error term propagated to be
Correspondingly, connection weightIncremental computations it is as follows:
4th layer: this layer needs the error term propagated to be
Wavelet layer weighting parameter ωikIncremental computations it is as follows:
Zoom factor aikIncremental computations it is as follows:
Shift factor bikIncremental computations it is as follows:
Third layer: this layer needs the error term propagated to be
The second layer: the error term of this layer calculates as follows:
Correspondingly, member function Center Parameter mjIncremental computations it is as follows:
Member function width parameter σjIncremental computations it is as follows:
Therefore, as long as learning rate η=(η has been determinedm,ησ,ηb,ηa,ηω1,ηω2), so that it may the structural parameters for adjusting network, from
And neural network forecast output is made constantly to approach desired output.
4. adaptive radar sea clutter forecast system according to claim 1, which is characterized in that the sea clutter forecasts mould
Block is completed to carry out sea clutter prediction using following process:
(1) D sea clutter echo-signal amplitude is acquired in sampling instant t obtain TX=[xt-D+1,…,xt], xt-D+1Indicate t-D
The sea clutter echo-signal amplitude of+1 sampling instant, xtIndicate the sea clutter echo-signal amplitude of t sampling instant;
(2) it is normalized:
(3) the sea clutter predicted value that sampling instant (t+1) is calculated in Fuzzy Wavelet Network modeling module is substituted into.
The adaptive radar sea clutter forecast system, the host computer further include: discrimination model update module, to by setting
Fixed sampling time interval acquires data, by obtained measured data compared with model prediction value, if relative error is greater than
10%, then training sample data are added in new data, update forecasting model.And result display module, to sea clutter is pre-
The predicted value that report module is calculated is shown in host computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810691874.4A CN108983183A (en) | 2018-06-28 | 2018-06-28 | A kind of adaptive radar sea clutter forecast system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810691874.4A CN108983183A (en) | 2018-06-28 | 2018-06-28 | A kind of adaptive radar sea clutter forecast system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108983183A true CN108983183A (en) | 2018-12-11 |
Family
ID=64538795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810691874.4A Pending CN108983183A (en) | 2018-06-28 | 2018-06-28 | A kind of adaptive radar sea clutter forecast system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108983183A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826526A (en) * | 2019-11-19 | 2020-02-21 | 上海无线电设备研究所 | Method for cloud detection radar to identify clouds |
CN112668507A (en) * | 2020-12-31 | 2021-04-16 | 南京信息工程大学 | Sea clutter prediction method and system based on hybrid neural network and attention mechanism |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7372393B2 (en) * | 2006-07-07 | 2008-05-13 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for determining unwrapped phases from noisy two-dimensional wrapped-phase images |
CN101718870A (en) * | 2009-11-13 | 2010-06-02 | 西安电子科技大学 | High-speed weak target flight path detection method of image field |
CN102147465A (en) * | 2011-03-03 | 2011-08-10 | 浙江大学 | System and method for detecting sea target by chaos optimizing radar |
CN102147463A (en) * | 2011-03-03 | 2011-08-10 | 浙江大学 | System and method for forecasting Qunzhi radar sea clutters |
CN102183749A (en) * | 2011-03-03 | 2011-09-14 | 浙江大学 | Sea target detecting system of adaptive radar and method thereof |
-
2018
- 2018-06-28 CN CN201810691874.4A patent/CN108983183A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7372393B2 (en) * | 2006-07-07 | 2008-05-13 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for determining unwrapped phases from noisy two-dimensional wrapped-phase images |
CN101718870A (en) * | 2009-11-13 | 2010-06-02 | 西安电子科技大学 | High-speed weak target flight path detection method of image field |
CN102147465A (en) * | 2011-03-03 | 2011-08-10 | 浙江大学 | System and method for detecting sea target by chaos optimizing radar |
CN102147463A (en) * | 2011-03-03 | 2011-08-10 | 浙江大学 | System and method for forecasting Qunzhi radar sea clutters |
CN102183749A (en) * | 2011-03-03 | 2011-09-14 | 浙江大学 | Sea target detecting system of adaptive radar and method thereof |
Non-Patent Citations (1)
Title |
---|
张宇: "大型风力机叶片的振动分析与优化设计", 《中国优秀博士学位论文全文数据库 工程科技II辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826526A (en) * | 2019-11-19 | 2020-02-21 | 上海无线电设备研究所 | Method for cloud detection radar to identify clouds |
CN112668507A (en) * | 2020-12-31 | 2021-04-16 | 南京信息工程大学 | Sea clutter prediction method and system based on hybrid neural network and attention mechanism |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pan et al. | Water level prediction model based on GRU and CNN | |
Li et al. | Ship motion prediction using dynamic seasonal RvSVR with phase space reconstruction and the chaos adaptive efficient FOA | |
Nayak et al. | A survey on rainfall prediction using artificial neural network | |
CN112684701A (en) | Ship motion forecasting method based on long-time and short-time memory network and Gaussian process regression | |
Mahjoobi et al. | Hindcasting of wave parameters using different soft computing methods | |
CN102147465B (en) | System and method for detecting sea target by chaos optimizing radar | |
CN109001736B (en) | Radar echo extrapolation method based on deep space-time prediction neural network | |
CN109389058A (en) | Sea clutter and noise signal classification method and system | |
CN106355151A (en) | Recognition method, based on deep belief network, of three-dimensional SAR images | |
CN108734171A (en) | A kind of SAR remote sensing image ocean floating raft recognition methods of depth collaboration sparse coding network | |
CN108509910A (en) | Deep learning gesture identification method based on fmcw radar signal | |
CN108983177A (en) | A kind of radar sea clutter forecast system that parameter is optimal and method | |
CN108983180A (en) | A kind of high-precision radar sea clutter forecast system of colony intelligence | |
CN108983183A (en) | A kind of adaptive radar sea clutter forecast system | |
CN110852440A (en) | Ocean front detection method based on dynamic fuzzy neural network | |
CN108983181A (en) | A kind of radar marine target detection system of gunz optimizing | |
CN108983178A (en) | A kind of Intelligent radar sea target detection system that agility is adaptive | |
Bai et al. | Learning networks for extrapolation and radar target identification | |
CN106204314A (en) | A kind of southeast Pacific jumbo flying squid cental fishing ground Forecasting Methodology | |
CN108983184A (en) | A kind of adaptive high-precision Intelligent radar sea target detection system | |
CN115081590A (en) | Short-term wind speed prediction method based on complex value acceleration algorithm | |
CN107942303A (en) | A kind of Intelligent radar sea clutter forecast system and method based on improvement artificial bee colony algorithm | |
CN108983185A (en) | A kind of radar marine target detection system and method for intelligent adaptive | |
Hsiao et al. | Study on the current velocity prediction by Artificial Neural Network at the entrance of Hualien Port of Taiwan | |
Kelly et al. | An ensemble modelling approach for spatiotemporally explicit estimation of fish distributions using data assimilation |
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: 20181211 |
|
RJ01 | Rejection of invention patent application after publication |