CN107045596A - The method and device that analysis atmospheric conditions parameter influences on the air gap discharge voltage - Google Patents
The method and device that analysis atmospheric conditions parameter influences on the air gap discharge voltage Download PDFInfo
- Publication number
- CN107045596A CN107045596A CN201710322375.3A CN201710322375A CN107045596A CN 107045596 A CN107045596 A CN 107045596A CN 201710322375 A CN201710322375 A CN 201710322375A CN 107045596 A CN107045596 A CN 107045596A
- Authority
- CN
- China
- Prior art keywords
- discharge voltage
- air gap
- chebyshev
- atmospheric conditions
- gap discharge
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The method and device that atmospheric conditions parameter influences on the air gap discharge voltage is analyzed the embodiment of the invention discloses a kind of, the embodiment of the present invention is based on different inputs, set up corresponding Chebyshev neutral nets, pass through comparing check resultant error, draw effect of each atmospheric conditions parameter to the air gap discharge voltage, simple and fast of the present invention, can reflect effect of each atmospheric conditions parameter to the air gap discharge voltage.
Description
Technical field
The present invention relates to electrical equipment online monitoring technical field, more particularly to a kind of analysis atmospheric conditions parameter is to air
The method and device of gap discharge voltage influence.
Background technology
The flash-over characteristic of the air gap is the important evidence of high voltage power transmission and transforming external insulation design.It is theoretical from electric discharge, it is empty
Gas gap discharge voltage is influenceed by atmospheric conditions (air pressure, temperature, humidity etc.).
Influence for atmospheric conditions parameter to discharge voltage, has carried out substantial amounts of experimental study, but research master both at home and abroad
The relation curve concentrated between single atmospheric parameter and discharge voltage is big to each Atmopheric Parameters on Discharge Voltages influence degree
Shortage is also compared in small research.
Therefore it provides a kind of method of influence of analysis atmospheric conditions parameter to the air gap discharge voltage, and then determine
Atmospheric conditions parameter is provided for the external insulation design of electrical equipment and is referenced as ability to the influence degree of the air gap discharge voltage
Field technique personnel's technical issues that need to address.
The content of the invention
The embodiments of the invention provide it is a kind of analyze the method that is influenceed on the air gap discharge voltage of atmospheric conditions parameter and
Device, it is determined that atmospheric conditions parameter, to the influence degree of the air gap discharge voltage, is that the external insulation design of electrical equipment is carried
For reference.
The method that atmospheric conditions parameter influences on the air gap discharge voltage, bag are analyzed the embodiments of the invention provide a kind of
Include：
Get atmospheric conditions parameter training sample, the air gap corresponding with atmospheric conditions parameter training sample electric discharge electricity
Press training sample, atmospheric conditions parametric test sample, the air gap discharge voltage corresponding with atmospheric conditions parametric test sample
Test samples, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
Using air pressure, temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, ginseng is built
According to Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to reference
Chebyshev neutral nets are trained, the reference neutral net after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples obtain missing with reference to assay to testing with reference to neutral net after training
Difference；
Using temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, first is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to first
Chebyshev neutral nets are trained, the first nerves network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the first nerves network after training, obtain the first assay mistake
Difference；
Using air pressure, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, second is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to second
Chebyshev neutral nets are trained, the nervus opticus network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the nervus opticus network after training, obtain the second assay mistake
Difference；
Using air pressure, temperature, relative humidity and illumination as input, using the air gap discharge voltage as output, the 3rd is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 3rd
Chebyshev neutral nets are trained, the third nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the third nerve network after training, obtain the 3rd assay mistake
Difference；
Using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage as output, the 4th is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 4th
Chebyshev neutral nets are trained, the fourth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fourth nerve network after training, obtain the 4th assay mistake
Difference；
Using air pressure, temperature, wind speed and relative humidity as input, using the air gap discharge voltage as output, the 5th is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 5th
Chebyshev neutral nets are trained, the fifth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fifth nerve network after training, obtain the 5th assay mistake
Difference；
By the first assay error, the second assay error, the 3rd assay error, the 4th assay error
With the 5th assay error respectively with carrying out asking poor calculating with reference to assay error, the first difference, the second difference, the are obtained
Three differences, the 4th difference and the 5th difference.
Preferably, the first assay error, the second assay error, the 3rd assay error, the 4th are examined
Resultant error and the 5th assay error with carrying out asking poor calculating with reference to assay error, obtain the first difference, the respectively
Also include after two differences, the 3rd difference, the 4th difference and the 5th difference：
The first difference, the second difference, the 3rd difference, the 4th difference and the 5th difference are carried out according to order from big to small
Sequence, obtains difference ranking results.
Preferably, according to order from big to small to the first difference, the second difference, the 3rd difference, the 4th difference and the 5th
Difference is ranked up, and obtains also including after difference ranking results：
Difference ranking results are converted into air pressure, temperature, wind speed, relative humidity and illumination to the air gap discharge voltage
Influence degree ranking results.
Preferably, with reference to Chebyshev neutral nets, the first Chebyshev neutral nets, the 2nd Chebyshev nerves
Network, the 3rd Chebyshev neutral nets, the 4th Chebyshev neutral nets, the 5th Chebyshev neutral nets are three
Layer Chebyshev neutral nets.
Preferably, three layers of Chebyshev neutral nets include：Input layer, hidden layer and output layer.
Preferably, the embodiment of the present invention additionally provides a kind of analysis atmospheric conditions parameter and the air gap discharge voltage is influenceed
Device, including：
Acquiring unit, for getting atmospheric conditions parameter training sample, corresponding with atmospheric conditions parameter training sample
The air gap discharge voltage training sample, atmospheric conditions parametric test sample, sky corresponding with atmospheric conditions parametric test sample
Gas gap discharge voltage test samples, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
With reference to NE, for using air pressure, temperature, wind speed, relative humidity and illumination as input, being discharged with the air gap
Voltage is output, is built with reference to Chebyshev neutral nets, and is discharged by atmospheric conditions parameter training sample, the air gap
Voltage training sample with reference to Chebyshev neutral nets to being trained, the reference neutral net after being trained, then by big
Gas bar part parametric test sample, the air gap discharge voltage test samples are obtained to being tested after training with reference to neutral net
To with reference to assay error；
First network unit, for using temperature, wind speed, relative humidity and illumination as input, with the air gap discharge voltage
For output, the first Chebyshev neutral nets are built, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage
Training sample is trained to the first Chebyshev neutral nets, the first nerves network after being trained, then passes through big gas bar
Part parametric test sample, the air gap discharge voltage test samples are tested to the first nerves network after training, obtain
One assay error；
Second NE, for using air pressure, wind speed, relative humidity and illumination as input, with the air gap discharge voltage
For output, the 2nd Chebyshev neutral nets are built, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage
Training sample is trained to the 2nd Chebyshev neutral nets, the nervus opticus network after being trained, then passes through big gas bar
Part parametric test sample, the air gap discharge voltage test samples are tested to the nervus opticus network after training, obtain
Two assay errors；
3rd NE, for using air pressure, temperature, relative humidity and illumination as input, with the air gap discharge voltage
For output, the 3rd Chebyshev neutral nets are built, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage
Training sample is trained to the 3rd Chebyshev neutral nets, the third nerve network after being trained, then passes through big gas bar
Part parametric test sample, the air gap discharge voltage test samples are tested to the third nerve network after training, obtain
Three assay errors；
4th NE, for using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage to be defeated
Go out, build the 4th Chebyshev neutral nets, and train by atmospheric conditions parameter training sample, the air gap discharge voltage
Sample is trained to the 4th Chebyshev neutral nets, the fourth nerve network after being trained, then is joined by atmospheric conditions
Number test samples, the air gap discharge voltage test samples are tested to the fourth nerve network after training, obtain the 4th inspection
Test resultant error；
5th NE, for using air pressure, temperature, wind speed and relative humidity as input, with the air gap discharge voltage
For output, the 5th Chebyshev neutral nets are built, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage
Training sample is trained to the 5th Chebyshev neutral nets, the fifth nerve network after being trained, then passes through big gas bar
Part parametric test sample, the air gap discharge voltage test samples are tested to the fifth nerve network after training, obtain
Five assay errors；
Computing unit, for by the first assay error, the second assay error, the 3rd assay error,
Four assay errors and the 5th assay error with carrying out asking poor calculating with reference to assay error, obtain first poor respectively
Value, the second difference, the 3rd difference, the 4th difference and the 5th difference.
Preferably, a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention influences on the air gap discharge voltage
Device also includes：
Sequencing unit, for the order of basis from big to small to the first difference, the second difference, the 3rd difference, the 4th difference
It is ranked up with the 5th difference, obtains difference ranking results.
Preferably, a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention influences on the air gap discharge voltage
Device also includes：
Converting unit, for difference ranking results to be converted into air pressure, temperature, wind speed, relative humidity and illumination to air
The influence degree ranking results of gap discharge voltage.
Preferably, with reference to Chebyshev neutral nets, the first Chebyshev neutral nets, the 2nd Chebyshev nerves
Network, the 3rd Chebyshev neutral nets, the 4th Chebyshev neutral nets, the 5th Chebyshev neutral nets are three
Layer Chebyshev neutral nets.
Preferably, three layers of Chebyshev neutral nets include：Input layer, hidden layer and output layer.
As can be seen from the above technical solutions, the embodiment of the present invention has advantages below：
The embodiments of the invention provide it is a kind of analyze the method that is influenceed on the air gap discharge voltage of atmospheric conditions parameter and
Device, the embodiment of the present invention is set up corresponding Chebyshev neutral nets, is passed through comparing check result based on different inputs
Error, draws effect of each atmospheric conditions parameter to the air gap discharge voltage, and simple and fast of the present invention can reflect
Effect of each atmospheric conditions parameter to the air gap discharge voltage.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
The side that Fig. 1 influences for a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention on the air gap discharge voltage
The schematic flow sheet of method；
The side that Fig. 2 influences for a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention on the air gap discharge voltage
Another schematic flow sheet of method；
The dress that Fig. 3 influences for a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention on the air gap discharge voltage
The structural representation put；
Fig. 4 is three layers of Chebyshev neural network topology structure figures.
Embodiment
The embodiments of the invention provide it is a kind of analyze the method that is influenceed on the air gap discharge voltage of atmospheric conditions parameter and
Device, it is determined that atmospheric conditions parameter, to the influence degree of the air gap discharge voltage, is that the external insulation design of electrical equipment is carried
For reference.
To enable goal of the invention, feature, the advantage of the present invention more obvious and understandable, below in conjunction with the present invention
Accompanying drawing in embodiment, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of embodiment of the invention, and not all embodiment.Based on the embodiment in the present invention, this area
All other embodiment that those of ordinary skill is obtained under the premise of creative work is not made, belongs to protection of the present invention
Scope.
Referring to Fig. 1, a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention is to the air gap discharge voltage shadow
One embodiment of loud method, including：
101st, atmospheric conditions parameter training sample, the air gap corresponding with atmospheric conditions parameter training sample is got to put
Piezoelectric voltage training sample, atmospheric conditions parametric test sample, the air gap corresponding with atmospheric conditions parametric test sample electric discharge
Voltage test samples, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
102nd, using air pressure, temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, structure
Build with reference to Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage training sample pair
It is trained with reference to Chebyshev neutral nets, the reference neutral net after being trained, then passes through atmospheric conditions parametric test
Sample, the air gap discharge voltage test samples are obtained with reference to assay to being tested after training with reference to neutral net
Error；
103rd, using temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage for output, structure the
One Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to first
Chebyshev neutral nets are trained, the first nerves network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the first nerves network after training, obtain the first assay mistake
Difference；
104th, using air pressure, wind speed, relative humidity and illumination as input, using the air gap discharge voltage for output, structure the
Two Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to second
Chebyshev neutral nets are trained, the nervus opticus network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the nervus opticus network after training, obtain the second assay mistake
Difference；
105th, using air pressure, temperature, relative humidity and illumination as input, using the air gap discharge voltage for output, structure the
Three Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 3rd
Chebyshev neutral nets are trained, the third nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the third nerve network after training, obtain the 3rd assay mistake
Difference；
106th, using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage as output, the 4th is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 4th
Chebyshev neutral nets are trained, the fourth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fourth nerve network after training, obtain the 4th assay mistake
Difference；
107th, using air pressure, temperature, wind speed and relative humidity as input, using the air gap discharge voltage for output, structure the
Five Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 5th
Chebyshev neutral nets are trained, the fifth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fifth nerve network after training, obtain the 5th assay mistake
Difference；
108th, by the first assay error, the second assay error, the 3rd assay error, the 4th assay
Error and the 5th assay error with carrying out asking poor calculating with reference to assay error, obtain the first difference, second poor respectively
Value, the 3rd difference, the 4th difference and the 5th difference.
The embodiment of the present invention is set up corresponding Chebyshev neutral nets, is passed through comparing check knot based on different inputs
Fruit error, draws effect of each atmospheric conditions parameter to the air gap discharge voltage, simple and fast of the present invention can be anti-
Reflect effect of each atmospheric conditions parameter to the air gap discharge voltage.
Referring to Fig. 2, a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention is to the air gap discharge voltage shadow
Another embodiment of loud method, including：
201st, atmospheric conditions parameter training sample, the air gap corresponding with atmospheric conditions parameter training sample is got to put
Piezoelectric voltage training sample, atmospheric conditions parametric test sample, the air gap corresponding with atmospheric conditions parametric test sample electric discharge
Voltage test samples, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
202nd, using air pressure, temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, structure
Build with reference to Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage training sample pair
It is trained with reference to Chebyshev neutral nets, the reference neutral net after being trained, then passes through atmospheric conditions parametric test
Sample, the air gap discharge voltage test samples are obtained with reference to assay to being tested after training with reference to neutral net
Error；
203rd, using temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage for output, structure the
One Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to first
Chebyshev neutral nets are trained, the first nerves network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the first nerves network after training, obtain the first assay mistake
Difference；
204th, using air pressure, wind speed, relative humidity and illumination as input, using the air gap discharge voltage for output, structure the
Two Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to second
Chebyshev neutral nets are trained, the nervus opticus network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the nervus opticus network after training, obtain the second assay mistake
Difference；
205th, using air pressure, temperature, relative humidity and illumination as input, using the air gap discharge voltage for output, structure the
Three Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 3rd
Chebyshev neutral nets are trained, the third nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the third nerve network after training, obtain the 3rd assay mistake
Difference；
206th, using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage as output, the 4th is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 4th
Chebyshev neutral nets are trained, the fourth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fourth nerve network after training, obtain the 4th assay mistake
Difference；
207th, using air pressure, temperature, wind speed and relative humidity as input, using the air gap discharge voltage for output, structure the
Five Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 5th
Chebyshev neutral nets are trained, the fifth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fifth nerve network after training, obtain the 5th assay mistake
Difference；
208th, by the first assay error, the second assay error, the 3rd assay error, the 4th assay
Error and the 5th assay error with carrying out asking poor calculating with reference to assay error, obtain the first difference, second poor respectively
Value, the 3rd difference, the 4th difference and the 5th difference；
209th, according to order from big to small to the first difference, the second difference, the 3rd difference, the 4th difference and the 5th difference
It is ranked up, obtains difference ranking results；
210th, difference ranking results are converted into air pressure, temperature, wind speed, relative humidity and illumination to the air gap electric discharge electricity
The influence degree ranking results of pressure.
In the present embodiment, it is necessary to explanation, the first assay error be with temperature, wind speed, relative humidity and
Illumination is trained and examined obtained error amount for the neutral net of input, therefore the first assay error with reference to inspection with tying
The first difference that fruit error (using air pressure, temperature, wind speed, relative humidity and illumination as input) carries out asking difference to obtain then represents gas
The influence degree to the air gap discharge voltage is pressed, similarly, the second difference represents shadow of the temperature to the air gap discharge voltage
The degree of sound, the 3rd difference represents influence degree of the wind speed to the air gap discharge voltage, and the 4th difference represents relative humidity
To the influence degree of the air gap discharge voltage, the 5th difference represents influence degree of the illumination to the air gap discharge voltage.
Further, with reference to Chebyshev neutral nets, the first Chebyshev neutral nets, the 2nd Chebyshev god
It is through network, the 3rd Chebyshev neutral nets, the 4th Chebyshev neutral nets, the 5th Chebyshev neutral nets
Three layers of Chebyshev neutral nets.
Further, three layers of Chebyshev neutral nets include：Input layer, hidden layer and output layer.
The above is that a kind of method that analysis atmospheric conditions parameter influences on the air gap discharge voltage is carried out specifically
It is bright, for ease of understanding, atmospheric conditions parameter will be analyzed one kind with a concrete application scene below to the air gap discharge voltage
The application of the method for influence is illustrated, and application examples includes：
(1) sample data is chosen, every group of sample data includes atmospheric conditions parameter and corresponding the air gap discharge voltage,
Wherein atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination.Sample data is divided into training sample and inspection
Test sample.
(2) using air pressure, temperature, wind speed, relative humidity and illumination as input, corresponding the air gap discharge voltage is defeated
Go out, build three layers of Chebyshev neutral nets (i.e. foregoing with reference to Chebyshev neutral nets), instructed using training sample
Practice network, and the network trained is detected using test samples, obtain assay error.Fig. 4 is refreshing for three layers of Chebyshev
Through network topology structure figure.
Three layers of Chebyshev neutral nets described in the application example include input layer, hidden layer and output layer, network
It is output as：
Wherein, piFor input vector P i-th of element, tkFor output vector t k-th of element, wjiFor input layer and hidden
Connection weight containing layer, ckjFor hidden layer and output layer connection weight, I is the dimension of input vector, Tj(x) it is Chebyshev
Orthogonal polynomial, J is the exponent number of Chebyshev orthogonal polynomials.
Chebyshev orthogonal polynomials described in the application example are set as relevant with exponent number, and its expression formula is：
T1(x)=1
T2(x)=x
Tj(x)=2j-1xTj-1(x)-2j-2Tj-2(x) j=3,4, m
In network training process, the connection weight w of input layer and hidden layerjiWith hidden layer and output layer connection weight ckj
Innovation representation be：
ckj←ckj-ηΔckj
wji←wji-ηΔwji
Wherein, η is Learning Step, Δ ckjWith Δ wjiBy asking local derviation to obtain：
Wherein,For k-th of element of n-th sample desired output vector,For n-th
K-th of element of individual network of samples output vector, K is the dimension of output vector, and N is training sample number, and E is network error,
Its expression formula is：
The network trained is detected using test samples, assay error is obtained.Wherein assay error calculation is public
Formula is：
By calculating, assay error is 1.62%.
(3) changing the input of network, (i.e. input is respectively 1. temperature, wind speed, relative humidity, illumination；2. air pressure, wind speed,
Relative humidity, illumination；3. air pressure, temperature, relative humidity, illumination；4. air pressure, temperature, wind speed, illumination；5. air pressure, temperature, wind
Speed, relative humidity), output keeps constant, and corresponding three layers of Chebyshev neutral nets (i.e. foregoing first is built respectively
Chebyshev neutral nets, the 2nd Chebyshev neutral nets, the 3rd Chebyshev neutral nets, the 4th Chebyshev god
Through network, the 5th Chebyshev neutral nets), detect what is trained using training sample training network, and using test samples
Network, obtains the corresponding assay error of different inputs.
By calculating, when input is temperature, wind speed, relative humidity, illumination, assay error is 20.16%；When defeated
When entering for air pressure, wind speed, relative humidity, illumination, assay error is 12.34%；When input be air pressure, it is temperature, relatively wet
When degree, illumination, assay error is 1.89%；When input is air pressure, temperature, wind speed, illumination, assay error is
1.72%；When input is air pressure, temperature, wind speed, relative humidity, assay error is 1.63%.
The assay error that each assay error that step (3) is obtained is obtained with step (2) respectively asks poor, difference
Sort by size, you can obtain effect of each atmospheric parameter to the air gap discharge voltage.
The assay error that each assay error that step (3) is obtained is obtained with step (2) respectively asks poor, respectively
For 18.54%, 10.72%, 0.27%, 0.10% and 0.01%.
Then each atmospheric parameter is air pressure from big to small to the effect of the air gap discharge voltage>Temperature>Wind speed>Phase
To humidity>Illumination.
Referring to Fig. 3, a kind of analysis atmospheric conditions parameter provided in an embodiment of the present invention is to the air gap discharge voltage shadow
One embodiment of loud device, including：
Acquiring unit 301, for getting atmospheric conditions parameter training sample, corresponding with atmospheric conditions parameter training sample
The air gap discharge voltage training sample, atmospheric conditions parametric test sample, corresponding with atmospheric conditions parametric test sample
The air gap discharge voltage test samples, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
With reference to NE 302, for using air pressure, temperature, wind speed, relative humidity and illumination as input, with the air gap
Discharge voltage is output, is built with reference to Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap
Discharge voltage training sample with reference to Chebyshev neutral nets to being trained, the reference neutral net after being trained, then leads to
Atmospheric conditions parametric test sample, the air gap discharge voltage test samples are crossed to being examined after training with reference to neutral net
Test, obtain with reference to assay error；
First network unit 303, for using temperature, wind speed, relative humidity and illumination as input, being discharged with the air gap electric
Press to export, build the first Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap electric discharge electricity
Pressure training sample is trained to the first Chebyshev neutral nets, the first nerves network after being trained, then passes through air
Conditional parameter test samples, the air gap discharge voltage test samples are tested to the first nerves network after training, are obtained
First assay error；
Second NE 304, for using air pressure, wind speed, relative humidity and illumination as input, being discharged with the air gap electric
Press to export, build the 2nd Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap electric discharge electricity
Pressure training sample is trained to the 2nd Chebyshev neutral nets, the nervus opticus network after being trained, then passes through air
Conditional parameter test samples, the air gap discharge voltage test samples are tested to the nervus opticus network after training, are obtained
Second assay error；
3rd NE 305, for using air pressure, temperature, relative humidity and illumination as input, being discharged with the air gap electric
Press to export, build the 3rd Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap electric discharge electricity
Pressure training sample is trained to the 3rd Chebyshev neutral nets, the third nerve network after being trained, then passes through air
Conditional parameter test samples, the air gap discharge voltage test samples are tested to the third nerve network after training, are obtained
3rd assay error；
4th NE 306, for using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage as
Output, builds the 4th Chebyshev neutral nets, and instruct by atmospheric conditions parameter training sample, the air gap discharge voltage
Practice sample to be trained the 4th Chebyshev neutral nets, the fourth nerve network after being trained, then pass through atmospheric conditions
Parametric test sample, the air gap discharge voltage test samples are tested to the fourth nerve network after training, obtain the 4th
Assay error；
5th NE 307, for using air pressure, temperature, wind speed and relative humidity as input, being discharged with the air gap electric
Press to export, build the 5th Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap electric discharge electricity
Pressure training sample is trained to the 5th Chebyshev neutral nets, the fifth nerve network after being trained, then passes through air
Conditional parameter test samples, the air gap discharge voltage test samples are tested to the fifth nerve network after training, are obtained
5th assay error；
Computing unit 308, for by the first assay error, the second assay error, the 3rd assay error,
4th assay error and the 5th assay error with carrying out asking poor calculating with reference to assay error, obtain first respectively
Difference, the second difference, the 3rd difference, the 4th difference and the 5th difference；
Sequencing unit 309, for according to order from big to small to the first difference, the second difference, the 3rd difference, the 4th poor
Value and the 5th difference are ranked up, and obtain difference ranking results；
Converting unit 310, for difference ranking results to be converted into air pressure, temperature, wind speed, relative humidity and illumination to sky
The influence degree ranking results of gas gap discharge voltage.
Further, with reference to Chebyshev neutral nets, the first Chebyshev neutral nets, the 2nd Chebyshev god
It is through network, the 3rd Chebyshev neutral nets, the 4th Chebyshev neutral nets, the 5th Chebyshev neutral nets
Three layers of Chebyshev neutral nets.
Further, three layers of Chebyshev neutral nets include：Input layer, hidden layer and output layer.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, such as multiple units or component
Another system can be combined or be desirably integrated into, or some features can be ignored, or do not perform.It is another, it is shown or
The coupling each other discussed or direct-coupling or communication connection can be the indirect couplings of device or unit by some interfaces
Close or communicate to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially
The part contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are to cause a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the invention
Portion or part steps.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
Described above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those within the art that：It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent substitution is carried out to which part technical characteristic；And these
Modification is replaced, and the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a kind of analyze the method that atmospheric conditions parameter influences on the air gap discharge voltage, it is characterised in that including：
Get atmospheric conditions parameter training sample, the air gap discharge voltage corresponding with atmospheric conditions parameter training sample instruction
Practice sample, atmospheric conditions parametric test sample, the air gap discharge voltage corresponding with atmospheric conditions parametric test sample to examine
Sample, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
Using air pressure, temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, reference is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to reference
Chebyshev neutral nets are trained, the reference neutral net after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples obtain missing with reference to assay to testing with reference to neutral net after training
Difference；
Using temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, first is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to first
Chebyshev neutral nets are trained, the first nerves network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the first nerves network after training, obtain the first assay mistake
Difference；
Using air pressure, wind speed, relative humidity and illumination as input, using the air gap discharge voltage as output, second is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to second
Chebyshev neutral nets are trained, the nervus opticus network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the nervus opticus network after training, obtain the second assay mistake
Difference；
Using air pressure, temperature, relative humidity and illumination as input, using the air gap discharge voltage as output, the 3rd is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 3rd
Chebyshev neutral nets are trained, the third nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the third nerve network after training, obtain the 3rd assay mistake
Difference；
Using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage as output, the 4th Chebyshev god is built
Through network, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 4th Chebyshev nerves
Network is trained, the fourth nerve network after being trained, then is discharged by atmospheric conditions parametric test sample, the air gap
Voltage test samples are tested to the fourth nerve network after training, obtain the 4th assay error；
Using air pressure, temperature, wind speed and relative humidity as input, using the air gap discharge voltage as output, the 5th is built
Chebyshev neutral nets, and by atmospheric conditions parameter training sample, the air gap discharge voltage training sample to the 5th
Chebyshev neutral nets are trained, the fifth nerve network after being trained, then pass through atmospheric conditions parametric test sample
Originally, the air gap discharge voltage test samples are tested to the fifth nerve network after training, obtain the 5th assay mistake
Difference；
By the first assay error, the second assay error, the 3rd assay error, the 4th assay error and
Five assay errors with carrying out asking poor calculating with reference to assay error, obtain the first difference, the second difference, the 3rd poor respectively
Value, the 4th difference and the 5th difference.
2. the method that analysis atmospheric conditions parameter according to claim 1 influences on the air gap discharge voltage, its feature
Be, by the first assay error, the second assay error, the 3rd assay error, the 4th assay error and
5th assay error with carrying out asking poor calculating with reference to assay error, obtains the first difference, the second difference, the 3rd respectively
Also include after difference, the 4th difference and the 5th difference：
The first difference, the second difference, the 3rd difference, the 4th difference and the 5th difference are arranged according to order from big to small
Sequence, obtains difference ranking results.
3. the method that analysis atmospheric conditions parameter according to claim 2 influences on the air gap discharge voltage, its feature
It is, the first difference, the second difference, the 3rd difference, the 4th difference and the 5th difference is arranged according to order from big to small
Sequence, obtains also including after difference ranking results：
Difference ranking results are converted into the influence of air pressure, temperature, wind speed, relative humidity and illumination to the air gap discharge voltage
Degree ranking results.
4. the method that analysis atmospheric conditions parameter according to claim 1 influences on the air gap discharge voltage, its feature
It is, with reference to Chebyshev neutral nets, the first Chebyshev neutral nets, the 2nd Chebyshev neutral nets, the 3rd
Chebyshev neutral nets, the 4th Chebyshev neutral nets, the 5th Chebyshev neutral nets are three layers
Chebyshev neutral nets.
5. the method that analysis atmospheric conditions parameter according to claim 4 influences on the air gap discharge voltage, its feature
It is, three layers of Chebyshev neutral nets include：Input layer, hidden layer and output layer.
6. a kind of analyze the device that atmospheric conditions parameter influences on the air gap discharge voltage, it is characterised in that including：
Acquiring unit, for getting atmospheric conditions parameter training sample, air corresponding with atmospheric conditions parameter training sample
Between gap discharge voltage training sample, atmospheric conditions parametric test sample, air corresponding with atmospheric conditions parametric test sample
Gap discharge voltage test samples, wherein, atmospheric conditions parameter includes air pressure, temperature, wind speed, relative humidity and illumination；
With reference to NE, for using air pressure, temperature, wind speed, relative humidity and illumination as input, with the air gap discharge voltage
For output, build with reference to Chebyshev neutral nets, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage
Training sample with reference to Chebyshev neutral nets to being trained, the reference neutral net after being trained, then passes through big gas bar
Part parametric test sample, the air gap discharge voltage test samples are joined to being tested after training with reference to neutral net
According to assay error；
First network unit, for using temperature, wind speed, relative humidity and illumination as input, using the air gap discharge voltage to be defeated
Go out, build the first Chebyshev neutral nets, and train by atmospheric conditions parameter training sample, the air gap discharge voltage
Sample is trained to the first Chebyshev neutral nets, the first nerves network after being trained, then is joined by atmospheric conditions
Number test samples, the air gap discharge voltage test samples are tested to the first nerves network after training, obtain the first inspection
Test resultant error；
Second NE, for using air pressure, wind speed, relative humidity and illumination as input, using the air gap discharge voltage to be defeated
Go out, build the 2nd Chebyshev neutral nets, and train by atmospheric conditions parameter training sample, the air gap discharge voltage
Sample is trained to the 2nd Chebyshev neutral nets, the nervus opticus network after being trained, then is joined by atmospheric conditions
Number test samples, the air gap discharge voltage test samples are tested to the nervus opticus network after training, obtain the second inspection
Test resultant error；
3rd NE, for using air pressure, temperature, relative humidity and illumination as input, using the air gap discharge voltage to be defeated
Go out, build the 3rd Chebyshev neutral nets, and train by atmospheric conditions parameter training sample, the air gap discharge voltage
Sample is trained to the 3rd Chebyshev neutral nets, the third nerve network after being trained, then is joined by atmospheric conditions
Number test samples, the air gap discharge voltage test samples are tested to the third nerve network after training, obtain the 3rd inspection
Test resultant error；
4th NE, for using air pressure, temperature, wind speed and illumination as input, using the air gap discharge voltage as output, structure
The 4th Chebyshev neutral nets are built, and pass through atmospheric conditions parameter training sample, the air gap discharge voltage training sample pair
4th Chebyshev neutral nets are trained, the fourth nerve network after being trained, then pass through atmospheric conditions parametric test
Sample, the air gap discharge voltage test samples are tested to the fourth nerve network after training, obtain the 4th assay
Error；
5th NE, for using air pressure, temperature, wind speed and relative humidity as input, using the air gap discharge voltage to be defeated
Go out, build the 5th Chebyshev neutral nets, and train by atmospheric conditions parameter training sample, the air gap discharge voltage
Sample is trained to the 5th Chebyshev neutral nets, the fifth nerve network after being trained, then is joined by atmospheric conditions
Number test samples, the air gap discharge voltage test samples are tested to the fifth nerve network after training, obtain the 5th inspection
Test resultant error；
Computing unit, for the first assay error, the second assay error, the 3rd assay error, the 4th to be examined
Test resultant error and the 5th assay error respectively with reference to assay error carry out ask poor calculating, obtain the first difference,
Second difference, the 3rd difference, the 4th difference and the 5th difference.
7. the device that analysis atmospheric conditions parameter according to claim 6 influences on the air gap discharge voltage, its feature
It is, in addition to：
Sequencing unit, for according to order from big to small to the first difference, the second difference, the 3rd difference, the 4th difference and the
Five differences are ranked up, and obtain difference ranking results.
8. the device that analysis atmospheric conditions parameter according to claim 7 influences on the air gap discharge voltage, its feature
It is, in addition to：
Converting unit, for difference ranking results to be converted into air pressure, temperature, wind speed, relative humidity and illumination to the air gap
The influence degree ranking results of discharge voltage.
9. the device that analysis atmospheric conditions parameter according to claim 6 influences on the air gap discharge voltage, its feature
It is, with reference to Chebyshev neutral nets, the first Chebyshev neutral nets, the 2nd Chebyshev neutral nets, the 3rd
Chebyshev neutral nets, the 4th Chebyshev neutral nets, the 5th Chebyshev neutral nets are three layers
Chebyshev neutral nets.
10. the device that analysis atmospheric conditions parameter according to claim 9 influences on the air gap discharge voltage, its feature
It is, three layers of Chebyshev neutral nets include：Input layer, hidden layer and output layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322375.3A CN107045596A (en) | 2017-05-09 | 2017-05-09 | The method and device that analysis atmospheric conditions parameter influences on the air gap discharge voltage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322375.3A CN107045596A (en) | 2017-05-09 | 2017-05-09 | The method and device that analysis atmospheric conditions parameter influences on the air gap discharge voltage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107045596A true CN107045596A (en) | 2017-08-15 |
Family
ID=59546570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710322375.3A Pending CN107045596A (en) | 2017-05-09 | 2017-05-09 | The method and device that analysis atmospheric conditions parameter influences on the air gap discharge voltage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107045596A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598333A (en) * | 2018-11-29 | 2019-04-09 | 广东电网有限责任公司 | Prediction technique is greatly reduced in a kind of the air gap discharge voltage |
| CN109614676A (en) * | 2018-11-29 | 2019-04-12 | 广东电网有限责任公司 | A kind of evaluation the air gap discharge voltage influence factor method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768029A (en) * | 2012-07-24 | 2012-11-07 | 广东电网公司清远供电局 | Method and device for industrial control by aid of sag monitoring |
| CN102982339A (en) * | 2012-10-31 | 2013-03-20 | 浙江大学 | Hyperspectral characteristic variable selection method |
| CN103679211A (en) * | 2013-12-05 | 2014-03-26 | 河海大学 | Method and device for selecting characteristics based on neural network sensitivity |
| CN103678773A (en) * | 2013-11-15 | 2014-03-26 | 华南理工大学 | Sphere gap discharge voltage detection method |
| CN106548025A (en) * | 2016-10-28 | 2017-03-29 | 广东电网有限责任公司珠海供电局 | A kind of the air gap discharge voltage Forecasting Methodology and device |
-
2017
- 2017-05-09 CN CN201710322375.3A patent/CN107045596A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768029A (en) * | 2012-07-24 | 2012-11-07 | 广东电网公司清远供电局 | Method and device for industrial control by aid of sag monitoring |
| CN102982339A (en) * | 2012-10-31 | 2013-03-20 | 浙江大学 | Hyperspectral characteristic variable selection method |
| CN103678773A (en) * | 2013-11-15 | 2014-03-26 | 华南理工大学 | Sphere gap discharge voltage detection method |
| CN103679211A (en) * | 2013-12-05 | 2014-03-26 | 河海大学 | Method and device for selecting characteristics based on neural network sensitivity |
| CN106548025A (en) * | 2016-10-28 | 2017-03-29 | 广东电网有限责任公司珠海供电局 | A kind of the air gap discharge voltage Forecasting Methodology and device |
Non-Patent Citations (2)
| Title |
|---|
| 张耿斌 等: "大气条件对气隙放电电压的影响及神经网络在放电电压预测中的应用", 《高压电技术》 * |
| 杨宝华 等: "属性重要性评分方法的改进", 《计算机工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598333A (en) * | 2018-11-29 | 2019-04-09 | 广东电网有限责任公司 | Prediction technique is greatly reduced in a kind of the air gap discharge voltage |
| CN109614676A (en) * | 2018-11-29 | 2019-04-12 | 广东电网有限责任公司 | A kind of evaluation the air gap discharge voltage influence factor method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Avci et al. | Wireless and real-time structural damage detection: A novel decentralized method for wireless sensor networks | |
| CN104166731B (en) | A kind of overlapping community discovery system and method for social networks | |
| CN107391852B (en) | Transient stability real-time evaluation method and device based on deep belief network | |
| Peng et al. | Random forest based optimal feature selection for partial discharge pattern recognition in HV cables | |
| Yu et al. | A wavelet packet transform-based deep feature transfer learning method for bearing fault diagnosis under different working conditions | |
| Zhang et al. | A cable fault recognition method based on a deep belief network | |
| CN103440497B (en) | A kind of GIS insulation defect shelf depreciation collection of illustrative plates mode identification method | |
| CN106443380B (en) | A kind of distribution cable local discharge signal recognition methods and device | |
| CN105225223A (en) | Based on the damage Detection of Smart Composite Structure method of wavelet analysis and BP neural network | |
| CN107168281A (en) | Multi-agent system method for diagnosing faults based on finite time observer | |
| CN108154223A (en) | Power distribution network operating mode recording sorting technique based on network topology and long timing information | |
| CN110991472B (en) | Method for diagnosing minor faults of high-speed train traction system | |
| CN107782442A (en) | Transformer multiple features parameter selection method based on big data and random forest | |
| CN115577436B (en) | Combined deep learning method for solving wind-induced vibration response of uncertain structure | |
| CN106548025A (en) | A kind of the air gap discharge voltage Forecasting Methodology and device | |
| CN107045596A (en) | The method and device that analysis atmospheric conditions parameter influences on the air gap discharge voltage | |
| CN107295537A (en) | A kind of method and system for wireless sensor network reliability of testing and assessing | |
| CN106707118B (en) | Partial Discharge Pattern Recognition Method and device | |
| CN106644035A (en) | Vibration source identification method and system based on time-frequency transformation characteristics | |
| Tariq et al. | An Optimized Solution for Fault Detection and Location in Underground Cables Based on Traveling Waves | |
| CN110163263A (en) | A kind of fault recognition method and device | |
| CN105823634A (en) | Bearing damage identification method based on time frequency relevance vector convolution Boltzmann machine | |
| CN105515859A (en) | Method and system for carrying out community detection to symbol network based on path similarity | |
| CN106778692A (en) | A kind of cable local discharge signal recognition method and device based on S-transformation | |
| CN106656464A (en) | Complex network side attack method under power exponent adjustable attack cost |
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: 20170815 |
|
| RJ01 | Rejection of invention patent application after publication |