CN107818224A - Sea clutter optimal soft survey instrument and method based on drosophila optimized algorithm Optimization of Wavelet neutral net - Google Patents
Sea clutter optimal soft survey instrument and method based on drosophila optimized algorithm Optimization of Wavelet neutral net Download PDFInfo
- Publication number
- CN107818224A CN107818224A CN201711117126.7A CN201711117126A CN107818224A CN 107818224 A CN107818224 A CN 107818224A CN 201711117126 A CN201711117126 A CN 201711117126A CN 107818224 A CN107818224 A CN 107818224A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- wavelet
- neural network
- drosophila
- 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of sea clutter optimal soft survey instrument and method based on drosophila algorithm optimization wavelet neural network, including radar, field intelligent instrument, control station, the spot database for depositing data, the optimal hard measurement host computer based on improved drosophila optimized algorithm Optimization of Wavelet neutral net and forecast hard measurement value display instrument.The described optimal hard measurement host computer based on drosophila algorithm optimization wavelet neural network, including data preprocessing module, wavelet neural network module, model modification module.The present invention realizes the online optimal hard measurement of sea clutter, and randomness caused by overcoming human factor influences, and improves the stability of model prediction, reduces the possibility that model prediction is absorbed in local optimum.
Description
Technical field
The present invention relates to optimal soft survey instrument and method field, is specifically that one kind is based on drosophila optimized algorithm Optimization of Wavelet
The sea clutter optimal soft survey instrument and method of neutral net.
Background technology
The echo-signal reflected from seawater surface is called sea clutter, sea clutter and sea condition, agitation, radar in field of radar
The many factors such as parameter are relevant.Worked in for seaward detector, shipborne radar etc. for the radar of marine environment, serious
Sea surface reflection echo will influence the detection to sea-surface target and tracking performance, grasp the property of sea clutter, and it is miscellaneous to establish accurately sea
Wave pattern is analysis and the premise for improving radar performance.The statistical property of sea clutter includes amplitude characteristic and correlation properties.Sea is miscellaneous
The correlation properties of ripple include temporal correlation and spatial coherence.Temporal correlation is also referred to as pulse-to-pulse correlation, and it is miscellaneous to reflect sea
Wave amplitude can be represented equivalently with the fluctuating of time with power spectrum.The spatial coherence of sea clutter is divided into attitude corrections
And distance correlation.The dynamic characteristic that sea clutter can study ocean for us provides help, still, if will be from sea clutter background
Lower detection target, such as floating ice, ship, it just turns into very big obstacle, it is necessary to suppresses as much as possible to weaken or eliminate these
Interference.Study the main purpose of sea clutter：On the one hand it is that the natural mechanism of sea clutter is explained, and then proposes rational mould
Type；On the other hand, it is interference of the sea clutter to be reduced to detection target, finds out and how will drown out the target in strong sea clutter background
The method that signal extraction comes out.The foundation of accurate sea clutter model is to realize the key of above-mentioned each purpose
The research work on the Modeling and Prediction of sea clutter is largely all concentrated on above artificial neural network in recent years, is taken
Obtained good effect.But artificial neural network the shortcomings that also having its own, such as the interstitial content of over-fitting, hidden layer and
The bad determination of parameter.Secondly, the data that observation site collects are not also because noise, manual operation error etc. be with necessarily true
Error is determined, so not strong using the general Generalization Ability of forecasting model of the strong artificial neural network of certainty.SVMs, by
Vapnik introduced in 1998, due to its good Generalization Ability, was widely used in pattern-recognition, fitting and classification problem
In.Because standard SVMs is sensitive to isolated point and noise, so having also been proposed wavelet neural network later.Wavelet neural
Network can preferably handle the sample data with noise compared to standard SVMs, be used for modeling here.Drosophila is excellent
Change algorithm, be i.e. Fruit Fly Optimization Algorithm, put forward by TaiWan, China Wen-Tsao professors Pan
A kind of a kind of biological intelligence optimizing algorithm deduced out based on drosophila foraging behavior from you, abbreviation FOA.The algorithm passes through colony
In it is interparticle influence each other, reduce the risk that searching algorithm is absorbed in locally optimal solution, there is good global search performance.
Drosophila optimized algorithm is used to search for the best parameter group of wavelet neural network, to reach the purpose of Optimized model.
The content of the invention
In order to overcome the shortcomings of the measurement accuracy of existing radar it is not high, it is low to noise sensitivity, promote poor performance, this hair
It is bright a kind of on-line measurement is provided, calculating speed is fast, model automatically updates, noise resisting ability is strong, it is good based on drosophila to promote performance
The sea clutter optimal soft survey instrument and method of optimized algorithm Optimization of Wavelet neutral net.
The purpose of the present invention is achieved through the following technical solutions：One kind is based on drosophila optimized algorithm Optimization of Wavelet god
Sea clutter optimal soft survey instrument through network, including radar, for measure easily survey variable field intelligent instrument, for measuring
The control station of performance variable, the spot database for depositing data and sea clutter forecast hard measurement value display instrument, the live intelligence
Energy instrument, control station and propylene polymerization production process connect, and the field intelligent instrument, control station and spot database connect,
The soft measuring instrument also includes the optimal hard measurement host computer based on drosophila optimized algorithm Optimization of Wavelet neutral net, described existing
Field data storehouse is connected with the input of the optimal hard measurement host computer based on drosophila optimized algorithm Optimization of Wavelet neutral net,
The output end of the optimal hard measurement host computer based on drosophila optimized algorithm Optimization of Wavelet neutral net and sea clutter hard measurement
It is worth display instrument connection, the optimal hard measurement host computer based on drosophila optimized algorithm Optimization of Wavelet neutral net includes：
Data preprocessing module, for the model training inputted from spot database sample to be pre-processed, to training
Center of a sample, that is, the average value of sample is subtracted, then it is standardized：
Calculate average：
Calculate variance：
Standardization：
Wherein, TX is training sample, and N is number of training,For the average of training sample, X is the training after standardization
Sample, σxTo calculate variance.
Wavelet neural network module, is modeled using wavelet neural network.Assuming that the node number of input layer is m,
The number of hidden layer wavelet neural member is n, and output layer node number is N, input sample Xn, export as Y, input layer with it is hidden
Connection weight containing node layer is wkj, and the connection weight of output layer and hidden layer node is wji, j-th hidden layer node
Flexible translation coefficient is respectively ajAnd bj.The wavelet neural member of hidden layer is using Morlet small echos as basic function ψ：
Wherein
Obtaining the first output h of j-th of wavelet neural of hidden layer by forward calculation is
Therefore the output y of network output layer is
Wherein w is connection weight, and h is the unit output of hidden layer.
Drosophila optimized algorithm optimization module, for the shift factor of wavelet neural network and being stretched using drosophila optimized algorithm
The contracting factor optimizes, and comprises the following steps that：
1. the Optimal Parameters for determining drosophila optimized algorithm are the shift factor and contraction-expansion factor, grain of wavelet neural network module
Subgroup individual amount popsize, largest loop optimizing number itermax, p-th particle initial Location Area X_axis, Y_
axis。
2. setting optimization object function, fitness is converted into, fitness function is calculated by corresponding error function,
And think that the big particle fitness of error is small, particle p fitness function is expressed as：
fp=1/ (Ep+1) (7)
In formula, EpIt is the error function of wavelet-neural network model, is expressed as：
In formula,Be wavelet-neural network model prediction output, OiExported for the target of wavelet-neural network model；N is
Number of training；
3. according to equation below, particle scans for,
In formula, RandomValue is detection range；
4. for particle p, the distance Dist with origin is pre-estimated, then calculates flavor concentration decision content S, the value is distance
It is reciprocal：
Disti=(Xi 2+Yi 2)1/2 (10)
Si=1/Disti (11)
5. by flavor concentration decision content Si(or it is fitness function fitness for people's flavor concentration decision function
Function), for obtaining the flavor concentration Smell of drosophila body positioni:
[bestSmell bestIndex]=min (Smell) (12)
6. recording optimum individual position and flavor concentration value, now all drosophila individuals will be flown using vision to this position
Go：
7. judging whether to meet performance requirement, if so, terminating optimizing, the ginseng of the wavelet neural network of one group of optimization is obtained
Number；Otherwise 3. return to step, continues iteration optimizing, until reaching maximum iteration itermax。
As a kind of preferable scheme, on the optimal hard measurement based on drosophila optimized algorithm Optimization of Wavelet neutral net
Position machine also includes：Model modification module, for the online updating of model, periodically offline analysis data is input in training set,
Update wavelet-neural network model.
A kind of optimal flexible measurement method of sea clutter based on drosophila optimized algorithm Optimization of Wavelet neutral net, the hard measurement
Method comprises the following steps：
1), to radar object, according to specificity analysis and climatic analysis, selection operation variable and easily survey variable are as model
Input, performance variable and easily survey variable are obtained by spot database；
2), the model training sample inputted from spot database is pre-processed, to training sample centralization, that is, subtracted
The average value of sample, is then standardized to it so that its average is 0, variance 1.The processing uses following formula process
To complete：
2.1) average is calculated：
2.2) variance is calculated：
2.3) standardize：
Wherein, TX is training sample, and N is number of training,For the average of training sample, X is the training sample after standardization
This.3), to the training sample for being transmitted through coming from data preprocessing module, it is modeled using wavelet neural network.Assuming that input layer
Node number be m, the number of hidden layer wavelet neural member is n, and output layer node number is N, input sample Xn, it is defeated
Go out for Y, the connection weight of input layer and hidden layer node is wkj, and the connection weight of output layer and hidden layer node is wji, the
The flexible translation coefficient of j hidden layer node is respectively ajAnd bj.The wavelet neural member of hidden layer uses Morlet small echo conducts
Basic function ψ：
Wherein
Obtaining the first output h of j-th of wavelet neural of hidden layer by forward calculation is
Therefore the output y of network output layer is
Wherein w is connection weight, and h is the unit output of hidden layer.
4), the penalty factor and error margin value of wavelet neural network are optimized using drosophila optimized algorithm, specifically
Step is as follows：
1. the Optimal Parameters for determining drosophila optimized algorithm are the shift factor and contraction-expansion factor, grain of wavelet neural network module
Subgroup individual amount popsize, largest loop optimizing number itermax, p-th particle initial Location Area X_axis, Y_
axis。
2. setting optimization object function, fitness is converted into, fitness function is calculated by corresponding error function,
And think that the big particle fitness of error is small, particle p fitness function is expressed as：
fp=1/ (Ep+1) (7)
In formula, EpIt is the error function of wavelet-neural network model, is expressed as：
In formula,Be wavelet-neural network model prediction output, OiExported for the target of wavelet-neural network model；N is
Number of training；
3. according to equation below, particle scans for,
In formula, RandomValue is detection range；
4. for particle p, the distance Dist with origin is pre-estimated, then calculates flavor concentration decision content S, the value is distance
It is reciprocal：
Disti=(Xi 2+Yi 2)1/2 (10)
Si=1/Disti (11)
5. by flavor concentration decision content Si(or it is fitness function fitness for people's flavor concentration decision function
Function), for obtaining the flavor concentration Smell of drosophila body positioni:
[bestSmell bestIndex]=min (Smell) (12)
6. recording optimum individual position and flavor concentration value, now all drosophila individuals will be flown using vision to this position
Go：
7. judging whether to meet performance requirement, if so, terminating optimizing, the ginseng of the wavelet neural network of one group of optimization is obtained
Number；Otherwise 3. return to step, continues iteration optimizing, until reaching maximum iteration itermax。
As a kind of preferable scheme：The flexible measurement method is further comprising the steps of：5), periodically by offline analysis data
It is input in training set, updates wavelet-neural network model.
The present invention technical concept be：Online optimal hard measurement is carried out to sea clutter, overcomes existing sea clutter measuring instrument
Table stability is poor, is easily absorbed in the deficiency of local optimum, and it is automatic to wavelet-neural network model progress excellent to introduce drosophila optimized algorithm
Change, it is not necessary to which artificial experience repeatedly to adjust the parameter of wavelet neural network, to obtain optimal hard measurement result.This model phase
Had the advantage that for existing sea clutter soft-sensing model：It is modeled, is had higher by wavelet-neural network model
Forecast precision；Existing model parameter typically determined by the experience of operative employee, have it is certain restricted and uncertain, such as
Once fruit value is improper, concussion and bigger prediction error that model prediction exports can be caused, and model is excellent by drosophila
Change algorithm and automatic optimal is carried out to the parameter of model, obtain optimal soft-sensing model.
Beneficial effects of the present invention are mainly manifested in：Realize the online optimal hard measurement of sea clutter, overcome it is artificial because
Randomness caused by element influences, and improves the stability of model prediction, reduces the possibility that model prediction is absorbed in local optimum.
Brief description of the drawings
Fig. 1 is the topology diagram of wavelet neural network；
Fig. 2 be sea clutter modeling process optimal soft survey instrument based on drosophila optimized algorithm Optimization of Wavelet neutral net and
The basic structure schematic diagram of method；
Fig. 3 is the optimal hard measurement host computer structural representation based on drosophila optimized algorithm Optimization of Wavelet neutral net.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.The embodiment of the present invention is used for illustrating the present invention, without
It is to limit the invention, in the protection domain of spirit and claims of the present invention, any is repaiied to what the present invention made
Change and change, both fall within protection scope of the present invention.
Embodiment 1
Reference picture 1, Fig. 2 and Fig. 3, a kind of optimal soft survey of sea clutter based on drosophila optimized algorithm Optimization of Wavelet neutral net
Measure instrument, including radar 1, for measuring easily survey the field intelligent instrument 2 of variable, the control station 3 for measuring performance variable, deposit
Put the spot database 4 and sea clutter hard measurement value display instrument 6 of data, the field intelligent instrument 2, control station 3 and radar 1
Connection, the field intelligent instrument 2, control station 3 are connected with spot database 4, and the soft measuring instrument also includes drosophila and optimized
The optimal hard measurement host computer 5 of algorithm optimization wavelet neural network, the spot database 4 are based on drosophila optimized algorithm with described
The input connection of the optimal hard measurement host computer 5 of Optimization of Wavelet neutral net, it is described to be based on drosophila optimized algorithm Optimization of Wavelet
The output end of the optimal hard measurement host computer 5 of neutral net is connected with sea clutter hard measurement value display instrument 6.Field intelligent instrument 2
The easy survey variable of instrumentation radar object, easy variable of surveying is transferred to spot database 4；The operation of the control radar object of control station 3
Variable, performance variable is transferred to spot database 4.The variable data recorded in spot database 4 is used as to be optimized based on drosophila
The input of the optimal hard measurement host computer 5 of algorithm optimization wavelet neural network, hard measurement value display instrument 6, which is used to show, is based on drosophila
The output of the optimal hard measurement host computer 5 of optimized algorithm Optimization of Wavelet neutral net, i.e. hard measurement value.It is described to be optimized based on drosophila
The optimal hard measurement host computer 5 of algorithm optimization wavelet neural network, including following 4 parts：
Data preprocessing module 7, for the model training inputted from spot database sample to be pre-processed, to training
Center of a sample, that is, the average value of sample is subtracted, then it is standardized：
Calculate average：
Calculate variance：
Standardization：
Wherein, TX is training sample, and N is number of training,For the average of training sample, X is the training after standardization
Sample, σxFor variance.
Wavelet neural network module 8, is modeled using wavelet neural network.Assuming that the node number of input layer is m,
The number of hidden layer wavelet neural member is n, and output layer node number is N, input sample Xn, export as Y, input layer with it is hidden
Connection weight containing node layer is wkj, and the connection weight of output layer and hidden layer node is wji, j-th hidden layer node
Flexible translation coefficient is respectively ajAnd bj.The wavelet neural member of hidden layer is using Morlet small echos as basic function ψ：
Wherein
Obtaining the first output h of j-th of wavelet neural of hidden layer by forward calculation is
Therefore the output y of network output layer is
Wherein w is connection weight, and h is the unit output of hidden layer.
Drosophila optimization algorithm module 9, for the penalty factor and error using drosophila optimized algorithm to wavelet neural network
Tolerance value optimizes, and comprises the following steps that：
1. the Optimal Parameters for determining drosophila optimized algorithm are the shift factor and contraction-expansion factor, grain of wavelet neural network module
Subgroup individual amount popsize, largest loop optimizing number itermax, p-th particle initial Location Area X_axis, Y_
axis。
2. setting optimization object function, fitness is converted into, fitness function is calculated by corresponding error function,
And think that the big particle fitness of error is small, particle p fitness function is expressed as：
fp=1/ (Ep+1) (7)
In formula, EpIt is the error function of wavelet-neural network model, is expressed as：
In formula,Be wavelet-neural network model prediction output, OiExported for the target of wavelet-neural network model；N is
Number of training；
3. according to equation below, particle scans for,
In formula, RandomValue is detection range；
4. for particle p, the distance Dist with origin is pre-estimated, then calculates flavor concentration decision content S, the value is distance
It is reciprocal：
Disti=(Xi 2+Yi 2)1/2 (10)
Si=1/Disti (11)
5. by flavor concentration decision content Si(or it is fitness function fitness for people's flavor concentration decision function
Function), for obtaining the flavor concentration Smell of drosophila body positioni:
[bestSmell bestIndex]=min (Smell) (12)
6. recording optimum individual position and flavor concentration value, now all drosophila individuals will be flown using vision to this position
Go：
7. judging whether to meet performance requirement, if so, terminating optimizing, the ginseng of the wavelet neural network of one group of optimization is obtained
Number；Otherwise 3. return to step, continues iteration optimizing, until reaching maximum iteration itermax。
As a kind of preferable scheme, on the optimal hard measurement based on drosophila optimized algorithm Optimization of Wavelet neutral net
Position machine also includes：Model modification module 10, for the online updating of model, offline analysis data is periodically input to training set
In, update wavelet-neural network model.
Embodiment 2
Reference picture 1, Fig. 2 and Fig. 3, a kind of optimal soft survey of sea clutter based on drosophila optimized algorithm Optimization of Wavelet neutral net
Amount method, the flexible measurement method comprise the following steps：
1), to radar object, according to industrial analysis and Operations Analyst, selection operation variable and easily survey variable are as model
Input, performance variable and easily survey variable are obtained by spot database；
2), the model training sample inputted from spot database is pre-processed, to training sample centralization, that is, subtracted
The average value of sample, is then standardized to it so that its average is 0, variance 1.The processing uses following formula process
To complete：
2.1) average is calculated：
2.2) variance is calculated：
2.3) standardize：
Wherein, TX is training sample, and N is number of training,For the average of training sample, X is the training after standardization
Sample, σxTo calculate variance.
3), to the training sample for being transmitted through coming from data preprocessing module, it is modeled using wavelet neural network.It is assuming that defeated
The node number for entering layer is m, and the number of hidden layer wavelet neural member is n, and output layer node number is N, and input sample is
Xn, export as Y, the connection weight of input layer and hidden layer node is wkj, and the connection weight of output layer and hidden layer node is
wji, the flexible translation coefficient of jth hidden layer node is respectively ajAnd bj.The wavelet neural member of hidden layer is small using Morlet
Ripple is as basic function ψ：
Wherein
Obtaining the first output h of j-th of wavelet neural of hidden layer by forward calculation is
Therefore the output y of network output layer is
Wherein w is connection weight, and h is the unit output of hidden layer.
4), the penalty factor and error margin value of wavelet neural network are optimized using drosophila optimized algorithm, specifically
Step is as follows：
1. the Optimal Parameters for determining drosophila optimized algorithm are the shift factor and contraction-expansion factor, grain of wavelet neural network module
Subgroup individual amount popsize, largest loop optimizing number itermax, p-th particle initial Location Area X_axis, Y_
axis。
2. setting optimization object function, fitness is converted into, fitness function is calculated by corresponding error function,
And think that the big particle fitness of error is small, particle p fitness function is expressed as：
fp=1/ (Ep+1) (7)
In formula, EpIt is the error function of wavelet-neural network model, is expressed as：
In formula,Be wavelet-neural network model prediction output, OiExported for the target of wavelet-neural network model；N is
Number of training；
3. according to equation below, particle scans for,
In formula, RandomValue is detection range；
4. for particle p, the distance Dist with origin is pre-estimated, then calculates flavor concentration decision content S, the value is distance
It is reciprocal：
Disti=(Xi 2+Yi 2)1/2 (10)
Si=1/Disti (11)
5. by flavor concentration decision content Si(or it is fitness function fitness for people's flavor concentration decision function
Function), for obtaining the flavor concentration Smell of drosophila body positioni:
[bestSmell bestIndex]=min (Smell) (12)
6. recording optimum individual position and flavor concentration value, now all drosophila individuals will be flown using vision to this position
Go：
7. judging whether to meet performance requirement, if so, terminating optimizing, the ginseng of the wavelet neural network of one group of optimization is obtained
Number；Otherwise 3. return to step, continues iteration optimizing, until reaching maximum iteration itermax。
As a kind of preferable scheme：The flexible measurement method is further comprising the steps of：4), periodically by offline analysis data
It is input in training set, updates wavelet-neural network model.
The method specific implementation step of the present embodiment is as follows：
Step 1：To radar object 1, according to specificity analysis and climatic analysis, selection operation variable and easily survey variable are as mould
The input of type.Performance variable and easily survey variable are obtained by spot database 4.
Step 2：Sample data is pre-processed, completed by data preprocessing module 7.
Step 3：Initial wavelet neural network model 8 is established based on model training sample data.Input data such as step 2 institute
Acquisition is stated, output data is obtained by offline chemical examination.
Step 4：Optimize the parameter of initial wavelet neural network model by drosophila optimization algorithm module 9.
Step 5：Offline analysis data is periodically input in training set by model modification module 10, updates wavelet neural network
Model, the optimal hard measurement host computer 5 based on drosophila optimized algorithm optimization wavelet neural network model, which is established, to be completed.
Step 6：Sea clutter hard measurement value display instrument 6 is shown based on drosophila optimized algorithm optimization wavelet neural network model
The output of optimal hard measurement host computer 5, complete the display to the optimal hard measurement of sea clutter.
Optimal hard measurement host computer based on drosophila algorithm optimization wavelet neural network, including it is data preprocessing module, small
Ripple neural network module, model modification module, and provide a kind of flexible measurement method realized with soft measuring instrument.The present invention
The online optimal hard measurement of sea clutter is realized, randomness caused by overcoming human factor influences, and improves model prediction
Stability, reduce the possibility that model prediction is absorbed in local optimum.
Claims (2)
1. a kind of sea clutter optimal soft survey instrument based on drosophila optimized algorithm Optimization of Wavelet neutral net, described is optimal soft
Measuring instrumentss, including radar, for measuring easily survey the field intelligent instrument of variable, the control station for measuring performance variable, deposit
Put the spot database and sea clutter hard measurement value display instrument of data；The field intelligent instrument, control station and radar connect,
The field intelligent instrument, control station and spot database connect, it is characterised in that：The soft measuring instrument also includes being based on fruit
The optimal hard measurement host computer of fly optimized algorithm Optimization of Wavelet neutral net, the spot database are optimized with described based on drosophila
The input connection of the optimal hard measurement host computer of algorithm optimization wavelet neural network, it is described small based on the optimization of drosophila optimized algorithm
The output end of the optimal hard measurement host computer of ripple neutral net is connected with sea clutter hard measurement value display instrument；It is described excellent based on drosophila
Changing the optimal hard measurement host computer of algorithm optimization wavelet neural network includes：
Data preprocessing module, for the model training inputted from spot database sample to be pre-processed, to training sample
Centralization, that is, the average value of sample is subtracted, then it is standardized：
Calculate average：
Calculate variance：
Standardization：
Wherein, TX is training sample, and N is number of training,For the average of training sample, X is the training sample after standardization,
σxFor for calculate variance.
Wavelet neural network module, is modeled using wavelet neural network, and wavelet neural network topological structure is as shown in Figure 1.
Assuming that the node number of input layer is m, the number of hidden layer wavelet neural member is n, and output layer node number is N, input
Sample is Xn, export as Y, the connection weight of input layer and hidden layer node is wkj, and the connection of output layer and hidden layer node
Weights are wji, the flexible translation coefficient of j-th of hidden layer node is respectively ajAnd bj.The wavelet neural member of hidden layer uses
Morlet small echos are as basic function ψ：
<mrow>
<msub>
<mi>&psi;</mi>
<mrow>
<mi>a</mi>
<mo>,</mo>
<mi>b</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<msubsup>
<mi>t</mi>
<mi>i</mi>
<mn>2</mn>
</msubsup>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mn>1.75</mn>
<msub>
<mi>t</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein
Obtaining the first output h of j-th of wavelet neural of hidden layer by forward calculation is
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mrow>
<mo>(</mo>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</munderover>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
</mrow>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mn>2</mn>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<mi>l</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
Therefore the output y of network output layer is
<mrow>
<mi>y</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msub>
<mi>w</mi>
<mi>j</mi>
</msub>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein w is connection weight, and h is the unit output of hidden layer.
Drosophila optimization algorithm module, for being entered using drosophila optimized algorithm to the shift factor and contraction-expansion factor of wavelet neural network
Row optimization, is comprised the following steps that：
1. the Optimal Parameters for determining drosophila optimized algorithm are the shift factor and contraction-expansion factor, population of wavelet neural network module
Individual amount popsize, largest loop optimizing number itermax, p-th particle initial Location Area X_axis, Y_axis.
2. setting optimization object function, fitness is converted into, fitness function is calculated by corresponding error function, and recognize
Small for the big particle fitness of error, particle p fitness function f is expressed as：
fp=1/ (Ep+1) (7)
In formula, EpIt is the error function of wavelet-neural network model, is expressed as：
<mrow>
<msub>
<mi>E</mi>
<mi>p</mi>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mover>
<mi>y</mi>
<mo>^</mo>
</mover>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>O</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>8</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula,Be wavelet-neural network model prediction output, OiExported for the target of wavelet-neural network model；N is training
Sample number；
3. according to equation below, particle scans for,
Xi=X_axis+Random value (9)
Yi=Y_axis+Random value
In formula, Random Value are detection range；
4. for particle p, the distance Dist with origin is pre-estimated, then calculates flavor concentration decision content S, the value is fallen for distance
Number：
Disti=(Xi 2+Yi 2)1/2 (10)
Si=1/Disti (11)
5. by flavor concentration decision content Si(or it is fitness function fitness for people's flavor concentration decision function
Function), for obtaining the flavor concentration Smell of drosophila body positioni:
[bestSmell bestIndex]=min (Smell) (12)
6. recording optimum individual position and flavor concentration value, now all drosophila individuals will be flown to using vision to this position：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>S</mi>
<mi>m</mi>
<mi>e</mi>
<mi>l</mi>
<mi>l</mi>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mo>=</mo>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mi>S</mi>
<mi>m</mi>
<mi>e</mi>
<mi>l</mi>
<mi>l</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>X</mi>
<mo>_</mo>
<mi>a</mi>
<mi>x</mi>
<mi>i</mi>
<mi>s</mi>
<mo>=</mo>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mi>I</mi>
<mi>n</mi>
<mi>d</mi>
<mi>e</mi>
<mi>x</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>Y</mi>
<mo>_</mo>
<mi>a</mi>
<mi>x</mi>
<mi>i</mi>
<mi>s</mi>
<mo>=</mo>
<mi>Y</mi>
<mrow>
<mo>(</mo>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mi>I</mi>
<mi>n</mi>
<mi>d</mi>
<mi>e</mi>
<mi>x</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>13</mn>
<mo>)</mo>
</mrow>
</mrow>
7. judging whether to meet performance requirement, if so, terminating optimizing, the parameter of the wavelet neural network of one group of optimization is obtained；It is no
Then 3. return to step, continues iteration optimizing, until reaching maximum iteration itermax。
Model modification module, for the online updating of model, periodically offline analysis data is input in training set, updates small echo
Neural network model.
A kind of 2. optimal hard measurement of sea clutter as claimed in claim 1 based on drosophila optimized algorithm Optimization of Wavelet neutral net
The flexible measurement method that instrument is realized, it is characterised in that：The flexible measurement method comprises the following steps：
1), to radar object, according to specificity analysis and climatic analysis, selection operation variable and easily survey variable are as the defeated of model
Enter, performance variable and easily survey variable are obtained by spot database；
2), the model training sample inputted from spot database is pre-processed, to training sample centralization, that is, subtracts sample
Average value, then it is standardized so that its average be 0, variance 1.The processing is using following formula process come complete
Into：
2.1) average is calculated：
2.2) variance is calculated：
2.3) standardize：
Wherein, TX is training sample, and N is number of training,For the average of training sample, X is the training sample after standardization,
σxTo calculate variance.
3) to the training sample for being transmitted through coming from data preprocessing module, it is modeled using wavelet neural network.Assuming that input layer
Node number be m, the number of hidden layer wavelet neural member is n, and output layer node number is N, input sample Xn, it is defeated
Go out for Y, the connection weight of input layer and hidden layer node is wkj, and the connection weight of output layer and hidden layer node is wji, the
The flexible translation coefficient of j hidden layer node is respectively ajAnd bj.The wavelet neural member of hidden layer is using Morlet small echos as base
Function ψ：
<mrow>
<msub>
<mi>&psi;</mi>
<mrow>
<mi>a</mi>
<mo>,</mo>
<mi>b</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<msubsup>
<mi>t</mi>
<mi>i</mi>
<mn>2</mn>
</msubsup>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mn>1.75</mn>
<msub>
<mi>t</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein
Obtaining the first output h of j-th of wavelet neural of hidden layer by forward calculation is
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mrow>
<mo>(</mo>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</munderover>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
</mrow>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mn>2</mn>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<mi>l</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
Therefore the output y of network output layer is
<mrow>
<mi>y</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msub>
<mi>w</mi>
<mi>j</mi>
</msub>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein w is connection weight, and h is the unit output of hidden layer.
4), the shift factor and contraction-expansion factor of wavelet neural network are optimized using drosophila optimized algorithm, specific steps are such as
Under：
1. the Optimal Parameters for determining drosophila optimized algorithm are the shift factor and contraction-expansion factor, population of wavelet neural network module
Individual amount popsize, largest loop optimizing number itermax, p-th particle initial Location Area X_axis, Y_axis.
2. setting optimization object function, fitness is converted into, fitness function is calculated by corresponding error function, and recognize
Small for the big particle fitness of error, particle p fitness function f is expressed as：
fp=1/ (Ep+1) (7)
In formula, EpIt is the error function of wavelet-neural network model, is expressed as：
<mrow>
<msub>
<mi>E</mi>
<mi>p</mi>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mover>
<mi>y</mi>
<mo>^</mo>
</mover>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>O</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>8</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula,Be wavelet-neural network model prediction output, OiExported for the target of wavelet-neural network model；N is training
Sample number；
3. according to equation below, particle scans for,
Xi=X_axis+Random value (9)
Yi=Y_axis+Random value
In formula, Random Value are detection range；
4. for particle p, the distance Dist with origin is pre-estimated, then calculates flavor concentration decision content S, the value is fallen for distance
Number：
Disti=(Xi 2+Yi 2)1/2 (10)
Si=1/Disti (11)
5. by flavor concentration decision content Si(or it is fitness function fitness for people's flavor concentration decision function
Function), for obtaining the flavor concentration Smell of drosophila body positioni:
[bestSmell bestIndex]=min (Smell) (12)
6. recording optimum individual position and flavor concentration value, now all drosophila individuals will be flown to using vision to this position：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>S</mi>
<mi>m</mi>
<mi>e</mi>
<mi>l</mi>
<mi>l</mi>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mo>=</mo>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mi>S</mi>
<mi>m</mi>
<mi>e</mi>
<mi>l</mi>
<mi>l</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>X</mi>
<mo>_</mo>
<mi>a</mi>
<mi>x</mi>
<mi>i</mi>
<mi>s</mi>
<mo>=</mo>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mi>I</mi>
<mi>n</mi>
<mi>d</mi>
<mi>e</mi>
<mi>x</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>Y</mi>
<mo>_</mo>
<mi>a</mi>
<mi>x</mi>
<mi>i</mi>
<mi>s</mi>
<mo>=</mo>
<mi>Y</mi>
<mrow>
<mo>(</mo>
<mi>b</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
<mi>I</mi>
<mi>n</mi>
<mi>d</mi>
<mi>e</mi>
<mi>x</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>13</mn>
<mo>)</mo>
</mrow>
</mrow>
7. judging whether to meet performance requirement, if so, terminating optimizing, the parameter of the wavelet neural network of one group of optimization is obtained；It is no
Then 3. return to step, continues iteration optimizing, until reaching maximum iteration itermax。
Periodically offline analysis data is input in training set, updates wavelet-neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711117126.7A CN107818224A (en) | 2017-11-13 | 2017-11-13 | Sea clutter optimal soft survey instrument and method based on drosophila optimized algorithm Optimization of Wavelet neutral net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711117126.7A CN107818224A (en) | 2017-11-13 | 2017-11-13 | Sea clutter optimal soft survey instrument and method based on drosophila optimized algorithm Optimization of Wavelet neutral net |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107818224A true CN107818224A (en) | 2018-03-20 |
Family
ID=61609571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711117126.7A Pending CN107818224A (en) | 2017-11-13 | 2017-11-13 | Sea clutter optimal soft survey instrument and method based on drosophila optimized algorithm Optimization of Wavelet neutral net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107818224A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536955A (en) * | 2018-04-08 | 2018-09-14 | 西安邮电大学 | A kind of hybrid forecasting method of underwater sound signal |
| CN111930844A (en) * | 2020-08-11 | 2020-11-13 | 罗忠明 | Financial prediction system based on block chain and artificial intelligence |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5504487A (en) * | 1995-05-17 | 1996-04-02 | Fastman, Inc. | System for extracting targets from radar signatures |
| CN102147463A (en) * | 2011-03-03 | 2011-08-10 | 浙江大学 | System and method for forecasting Qunzhi radar sea clutters |
-
2017
- 2017-11-13 CN CN201711117126.7A patent/CN107818224A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5504487A (en) * | 1995-05-17 | 1996-04-02 | Fastman, Inc. | System for extracting targets from radar signatures |
| CN102147463A (en) * | 2011-03-03 | 2011-08-10 | 浙江大学 | System and method for forecasting Qunzhi radar sea clutters |
Non-Patent Citations (2)
| Title |
|---|
| 徐婷: "基于遗传小波神经网络的海杂波预测", 《电子设计工程》 * |
| 王文川: "基于人工智能算法的聚丙烯熔融指数预报建模与优化研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536955A (en) * | 2018-04-08 | 2018-09-14 | 西安邮电大学 | A kind of hybrid forecasting method of underwater sound signal |
| CN111930844A (en) * | 2020-08-11 | 2020-11-13 | 罗忠明 | Financial prediction system based on block chain and artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107703491A (en) | Sea clutter optimal soft survey instrument and method based on improved drosophila optimized algorithm optimization RBF neural | |
| CN107703493A (en) | Sea clutter optimal soft survey instrument and method based on adaptive drosophila optimized algorithm Optimized Least Square Support Vector | |
| CN110689179A (en) | Water bloom prediction method based on space-time sequence mixed model | |
| CN108613645B (en) | A kind of Pb-Zn deposits absorbing well, absorption well surveying on sludge thickness method based on parameter Estimation | |
| CN107942312A (en) | A kind of Intelligent radar sea target detection system and method based on differential evolution invasive weed optimization algorithm | |
| CN110132373A (en) | A kind of large-scale inland lake and wetland water level inversion method based on Altimetry Data | |
| CN108896996B (en) | A kind of Pb-Zn deposits absorbing well, absorption well water sludge interface ultrasonic echo signal classification method based on random forest | |
| Zeng et al. | Wind speed inversion in high frequency radar based on neural network | |
| CN108983179A (en) | A kind of radar marine target detection system of colony intelligence agility | |
| CN107818224A (en) | Sea clutter optimal soft survey instrument and method based on drosophila optimized algorithm Optimization of Wavelet neutral net | |
| CN113900103A (en) | Weather self-adaptive rapid identification early warning improvement algorithm for sudden strong convection disaster | |
| CN111352113A (en) | Strong convection weather short-term forecasting method and system, storage medium and terminal | |
| Liang et al. | Soil moisture retrieval from UWB sensor data by leveraging fuzzy logic | |
| CN107656250A (en) | A kind of Intelligent radar sea target detection system and method based on artificial bee colony algorithm | |
| CN107907872A (en) | Sea clutter optimal soft survey instrument and method based on TSP question drosophila optimization algorithm optimization RBF neural | |
| CN117114374A (en) | Intelligent agricultural irrigation management system based on weather prediction | |
| 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 | |
| CN107843879A (en) | Sea clutter optimal soft survey instrument and method based on free searching algorithm Optimization of Wavelet neutral net | |
| CN107831482A (en) | Sea clutter optimal soft survey instrument and method based on improved free searching algorithm optimization RBF neural | |
| CN107832831A (en) | Sea clutter optimal soft survey instrument and method based on free searching algorithm optimization RBF neural | |
| CN107942304A (en) | Sea clutter optimal soft survey instrument and method based on drosophila optimization algorithm optimization least square method supporting vector machine | |
| CN107942313A (en) | Sea clutter optimal soft survey instrument and method based on TSP question drosophila optimization algorithm optimization wavelet neural network | |
| CN107942301A (en) | Sea clutter optimal soft survey instrument and method based on drosophila optimization algorithm optimization RBF fuzzy neural networks | |
| CN112782690B (en) | Offshore non-ocean waveform detection classification method and system for spaceborne radar altimeter |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180320 |