CN108663600A - A kind of method for diagnosing faults, device and storage medium based on power transmission network - Google Patents
A kind of method for diagnosing faults, device and storage medium based on power transmission network Download PDFInfo
- Publication number
- CN108663600A CN108663600A CN201810437585.1A CN201810437585A CN108663600A CN 108663600 A CN108663600 A CN 108663600A CN 201810437585 A CN201810437585 A CN 201810437585A CN 108663600 A CN108663600 A CN 108663600A
- Authority
- CN
- China
- Prior art keywords
- power transmission
- data
- transmission network
- network model
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of method for diagnosing faults based on power transmission network, including:The target data of the failure generation area of the recorder data of acquisition power transmission network, failure cause data corresponding with recorder data and power transmission network, then utilizes recorder data, failure cause data and target data to build target nerve network model;The real time data of power transmission network is analyzed using target nerve network model to determine the fault type of power transmission network.In this programme, pass through the recorder data of power transmission network, its precision higher of the data structure target nerve network model of the target data three types of the failure generation area of failure cause data corresponding with recorder data and power transmission network, to when being analyzed the real time data of power transmission network using the target nerve network, it is more accurate to the identification of the type of the failure of power transmission network, improve the reliability to the fault diagnosis of power transmission network.The invention also discloses a kind of trouble-shooter and storage medium based on power transmission network, effect are as above.
Description
Technical field
The present invention relates to electric power network technique field, more particularly to a kind of method for diagnosing faults based on power transmission network, device and deposit
Storage media.
Background technology
With the development of science and technology, electric energy plays abnormal important role in people's lives.Therefore, user is to electricity
The requirement of the quality and stability of power supply is higher and higher.It, can be with prestissimo to transmission of electricity meanwhile when power transmission network breaks down
The failure of net is diagnosed and is repaired also particularly important.
The method that traditional failure to power transmission network is diagnosed is to carry out failure by analyzing the recorder data of power transmission network
Diagnosis mainly carries out event when being diagnosed to the failure of power transmission network using recorder data by artificial mode and neural network
Barrier diagnosis;Wherein, when carrying out fault diagnosis using artificial mode, since the working experience of the staff of power transmission network is variant,
It is difficult to ensure the reliability of power transmission network fault diagnosis.When carrying out fault diagnosis using neural network, due to the unicity of data,
It can not ensure the reliability of the fault diagnosis of power transmission network.
Therefore, it is those skilled in the art's problem to be solved to the reliability of the fault diagnosis of power transmission network as improved.
Invention content
It is an object of the invention to disclose a kind of method for diagnosing faults, device and storage medium based on power transmission network, improve
To the reliability of the fault diagnosis of power transmission network.
To achieve the above object, an embodiment of the present invention provides following technical solutions:
An embodiment of the present invention provides a kind of method for diagnosing faults based on power transmission network, including:
The recorder data of acquisition power transmission network, failure cause data corresponding with the recorder data and the power transmission network
The target data of failure generation area;
Target nerve network mould is built using the recorder data, the failure cause data and the target data
Type;
The real time data of the power transmission network is analyzed with the determination transmission of electricity using the target nerve network model
The fault type of net.
Preferably, described to build nerve using the recorder data, the failure cause data and the target data
Network model includes:
Multi-scale wavelet transformation is carried out to obtain recording characteristic value data to the recorder data;
Fault signature value matrix is built according to the recording characteristic value data and the target data;
The target nerve network model is built according to the fault signature value matrix and the failure cause data.
Preferably, described that the target nerve net is built according to the fault signature value matrix and the failure cause data
Network model includes:
Determine the number of the characteristic value in the fault signature value matrix;
The number of the neuron of the input layer in neural network model is set as the number of the characteristic value;
Failure during the number of the neuron of the output layer in the neural network model is set as the failure cause data
The number of the type of reason;
The initial weight value of each neuron node of hidden layer in the neural network model is set as between 0 to 1
Random number;
The neural network model is built using the input layer, the output layer and the initial weight value and to institute
Neural network model is stated to be trained to obtain the target nerve network model.
Preferably, described to build the nerve net using the input layer, the output layer and the initial weight value
Network model is simultaneously trained after obtaining the target nerve network model neural network model, further includes:
Judge whether the training error of the target nerve network meets condition;
If it is not, then in the target nerve network LayerSize, NodeSize, Iterations and
Tetra- parameters of LearningRate are adjusted.
Preferably, described LayerSize, NodeSize, Iterations in the target nerve network and
Tetra- parameters of LearningRate be adjusted including:
Determine the number of plies of the hidden layer in the target nerve network model and the neuron node number of the hidden layer;
By changing the neuron section of the number of plies of the hidden layer, the hidden layer in the target nerve network
Tetra- parameters of LayerSize, NodeSize, Iterations and LearningRate are adjusted.
Preferably, described that the real time data of the power transmission network is analyzed with true using the target nerve network model
After the fault type of the fixed power transmission network, further include:
The target nerve network model is trained again to update the target nerve using the real time data
The weighted value of each neuron in network model.
Preferably, the target data includes:Temperature information, humidity information, longitude and latitude in the failure generation area
Information, altitude information and wind scale information.
Then, the embodiment of the invention discloses a kind of trouble-shooters based on power transmission network, including:
Acquisition module, the recorder data for obtaining power transmission network, failure cause data corresponding with the recorder data with
And the target data of the failure generation area of the power transmission network;
Module is built, for building mesh using the recorder data, the failure cause data and the target data
Mark neural network model;
Determining module, for using the target nerve network model to the real time data of the power transmission network analyzed with
Determine the fault type of the power transmission network.
Secondly, the embodiment of the invention discloses trouble-shooter of the another kind based on power transmission network, including:
Memory, for storing computer program;
Processor, for executing the computer program stored in the memory to realize that any one of them as above is based on
The step of method for diagnosing faults of power transmission network.
Finally, it the embodiment of the invention discloses a kind of computer readable storage medium, is deposited on computer readable storage medium
Computer program is contained, realizes that failure of any one of them as above based on power transmission network is examined when computer program is executed by processor
The step of disconnected method.
As it can be seen that a kind of method for diagnosing faults based on power transmission network disclosed by the invention, including:Obtain the recording number of power transmission network
According to then the target data of the failure generation area of failure cause data corresponding with recorder data and power transmission network utilizes record
Wave number evidence, failure cause data and target data build target nerve network model;Using target nerve network model to defeated
The real time data of power grid is analyzed to determine the fault type of power transmission network.In the present solution, by the recorder data of power transmission network, with
The data structure of the target data three types of the failure generation area of the corresponding failure cause data of recorder data and power transmission network
Target nerve network model its precision higher is built, to divide the real time data of power transmission network using the target nerve network
It is more accurate to the identification of the type of the failure of power transmission network when analysis, improve the reliability to the fault diagnosis of power transmission network.This hair
Bright to also disclose a kind of trouble-shooter and storage medium based on power transmission network, effect is as above.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of method for diagnosing faults flow diagram based on power transmission network disclosed by the embodiments of the present invention;
Fig. 2 is a kind of trouble-shooter structural schematic diagram based on power transmission network disclosed by the embodiments of the present invention;
Fig. 3 is another trouble-shooter structural schematic diagram based on power transmission network disclosed by the embodiments of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a kind of method for diagnosing faults, device and storage medium based on power transmission network, improves
To the reliability of the fault diagnosis of power transmission network.
Fig. 1 is referred to, Fig. 1 is a kind of method for diagnosing faults flow signal based on power transmission network disclosed by the embodiments of the present invention
Figure, this method include:
The event of S101, the recorder data for obtaining power transmission network, failure cause data corresponding with recorder data and power transmission network
Hinder the target data of generation area.
Specifically, in the present embodiment, the recorder data of power transmission network can be the history recorder data of power transmission network, can wrap
Include the data such as failure scene, time of failure, three-phase voltage amount.Certainly, the recorder data in the present embodiment with it is existing
Recorder data in technology is consistent, and the embodiment of the present invention is no longer described in detail.Failure cause data include that surface layer failure is former
Cause and deep layer failure cause, wherein surface layer failure cause has singlephase earth fault (including A phases earth fault, B phase earth faults
And C phases earth fault), double earthfault (including AB phases earth fault, AC phases earth fault, BC phases earth fault), three
Phase earth fault (i.e. ABC phase faults), two-phase short-circuit fault (including AB phases short trouble, AC phases short trouble and BC phases are short
Road failure), three phase short circuit fault (i.e. ABC phases short trouble);Deep layer failure cause includes:Icing failure, wind leaning fault, lightning stroke
Failure, pollution flashover failure, bird pest failure, metallic foreign body wiring faults, non-metal foreign body wiring faults, floating material failure, mountain fire
Failure and screen of trees etc..The target data of the failure generation area of power transmission network is properly termed as various dimensions integrated data, target data
Including:Temperature, humidity, precipitation, longitude and latitude, vegetation, height above sea level, landform, soil, the wind-force etc. of power transmission network failure generation area
The information such as grade, cloud amount, wherein as preferred embodiment, target data includes:It is temperature information in failure generation area, wet
Spend information, latitude and longitude information, altitude information and wind scale information.
Further, recorder data can be collected by SCADA system, and failure cause data are by power transmission network
Failure generation area is collected after confirming, by crawler technology in the environment for having uploaded faulty generation area when target data
Collection obtains on the network of information.
S102, target nerve network model is built using recorder data, failure cause data and target data.
Specifically, in the present embodiment, when building target nerve network according to the data of above-mentioned several types, first
Assignment conversion is carried out to recorder data and deletes and (multi-scale wavelet transformation is carried out to recorder data), to obtain transient characteristic
Value Data (recording characteristic value data), as preferred embodiment, step S102 includes:Multi-scale wavelet is carried out to recorder data
Transformation is to obtain recording characteristic value data;Fault signature value matrix is built according to recording characteristic value data and target data;According to
Fault signature value matrix and failure cause data build target nerve network model.In the present embodiment, recording characteristic value data packet
Include time of failure, failure scene, three-phase voltage data amount, three-phase current data volume, zero-sequence current data amount and event
Hinder reclosing action frequency etc..After obtaining recording characteristic, as preferred embodiment, according to fault signature value matrix and
Failure cause data build target nerve network model:Determine the number of the characteristic value in fault signature value matrix;Setting
The number of the neuron of input layer in neural network model is characterized the number of value;Set the output layer in neural network model
Neuron number be failure cause data in failure cause type number;By the hidden layer in neural network model
The initial weight value of each neuron node is set as the random number between 0 to 1;Utilize input layer, output layer and initial weight
Value builds neural network model and is trained to obtain target nerve network model to neural network model.Specifically, this implementation
In example, the characteristic value in fault signature value matrix is the data type in recording characteristic, for example, in recording characteristic value data
Data include time of failure, failure scene, three-phase voltage data amount, three-phase current data volume, zero-sequence current number
According to amount and failure reclosing action frequency.Then the quantity of the characteristic value in fault signature value matrix is 10, corresponding, neural network
The number of the neuron of input layer in model is 10;With the failure cause data instance mentioned in above-described embodiment, if therefore
Barrier reason data is singlephase earth fault, double earthfault, three-phase ground failure, two-phase short-circuit fault, three phase short circuit fault.
Then the number of the type of the failure cause in failure cause data is then 11, corresponding, the output layer in neural network model
The number of neuron is then 11.Or fault signature value matrix includes data type and the failure generating region in recording characteristic
Data type in the target data in domain, for example, the data in recording characteristic value data include time of failure, failure generation
Place, three-phase voltage data amount, three-phase current data volume, zero-sequence current data amount and failure reclosing action frequency.Number of targets
Data in include temperature information, humidity information, latitude and longitude information, altitude information and wind scale information.Then failure is special
The quantity of characteristic value in value indicative matrix is 15, corresponding, and the number of the neuron of the input layer in neural network model is 15
It is a;With the failure cause data instance mentioned in above-described embodiment, if failure cause data are icing failure, wind leaning fault, thunder
Hit failure, pollution flashover failure, bird pest failure, metallic foreign body wiring faults, non-metal foreign body wiring faults, floating material failure, mountain
Fiery failure, screen of trees.Then the number of the type of the failure cause in failure cause data is then 10, corresponding, neural network model
In output layer neuron number then be 10.Determine the input layer of neural network model and the neuron number of output layer
Afterwards, the initial weight value of each neuron node of the hidden layer in neural network model is then set as random between 0 to 1
Then number in the initial neural network model for determining input layer, output layer and initial weight value rear part, recycles recording
Data, failure cause data and target data are trained to obtain target nerve network to the initial neural network model of structure
Model.Wherein, when being trained to initial neural network model, when a triggering condition is met, the excitation function F of neural network
(Zi) come into force, to which the initial weight value of neuron node is updated and be adjusted, detailed process is:Judge neural network mould
Whether the iterations of type reach threshold value;If so, triggering excitation function F (Zi), to utilize excitation function to each neuron section
The initial weight value of point is updated to obtain target nerve network model;Wherein, F (Zi)=max (CZi, Zi), C is non-negative
Number, ZiFor i-th of element of each neuron.Size the present embodiment of iterations herein and is not construed as limiting.Wherein, as preferred
Embodiment, the value of C can be selected as 0.01.Certainly, the value of C may be other values, and the embodiment of the present invention does not limit herein
It is fixed.Pass through call function F (Zi)=max (CZi, Zi) incidence that disappears of gradient when can reduce neural metwork training, it can
Constantly update weights in entire training process, avoid the training time it is long when, lead to the unrenewable problem of weights.
Further, it is contemplated that the training error for building the target nerve network of completion is larger, so that utilizing the target
The not accurate problem of the fault type for the power transmission network that neural network obtains.As preferred embodiment, input layer, output are being utilized
Layer and initial weight value structure neural network model simultaneously are trained neural network model to obtain target nerve network model
Later, further include:Judge whether the training error of target nerve network meets condition;If it is not, then in target nerve network
Tetra- parameters of LayerSize, NodeSize, Iterations and LearningRate are adjusted.Wherein, for modification
The step of tetra- parameters of LayerSize, NodeSize, Iterations and LearningRate are adjusted, as preferred
Embodiment, to tetra- parameters of LayerSize, NodeSize, Iterations and LearningRate in target nerve network
Be adjusted including:Determine the number of plies of the hidden layer in target nerve network model and the neuron node number of hidden layer;Pass through
Change the number of plies of hidden layer, hidden layer neuron section in target nerve network LayerSize, NodeSize,
Tetra- parameters of Iterations and LearningRate are adjusted.It wherein, can also be by changing simultaneously the hidden layer number of plies, changing
Become the neuron node number of the intrerneuron of hidden layer, changes four aspects of iterations and Schistosomiasis control rate to target
Four parameters in neural network are modified.Specifically, the embodiment of the present invention and being not construed as limiting.
S103, the real time data of power transmission network is analyzed using target nerve network model to determine the failure of power transmission network
Type.
Specifically, in the present embodiment, the real time data of power transmission network is input in target nerve network model, is then utilized
Target nerve network judges the fault type of power transmission network at this time.
It should be noted that the data when real time data in the present embodiment can break down for power transmission network, it can also
It is the data (may be the fault data of power transmission network, or the non-faulting data of power transmission network) of power transmission network any time.
As it can be seen that a kind of method for diagnosing faults based on power transmission network disclosed by the embodiments of the present invention, including:Obtain power transmission network
The target data of the failure generation area of recorder data, failure cause data corresponding with recorder data and power transmission network, then
Target nerve network model is built using recorder data, failure cause data and target data;Utilize target nerve network mould
Type is analyzed the real time data of power transmission network to determine the fault type of power transmission network.In the present solution, the recording for passing through power transmission network
The target data three types of the failure generation area of data, failure cause data corresponding with recorder data and power transmission network
Its precision higher of data structure target nerve network model, in the real time data using the target nerve network to power transmission network
It is more accurate to the identification of the type of the failure of power transmission network when being analyzed, it improves to the reliable of the fault diagnosis of power transmission network
Property.
In the following, a kind of trouble-shooter based on power transmission network disclosed by the embodiments of the present invention is introduced, refer to
Fig. 2, Fig. 2 are a kind of trouble-shooter structural schematic diagram based on power transmission network disclosed by the embodiments of the present invention, which includes:
Acquisition module 201, the recorder data for obtaining power transmission network, failure cause data corresponding with recorder data and
The target data of the failure generation area of power transmission network;
Module 202 is built, for building target nerve network using recorder data, failure cause data and target data
Model;
Determining module 203, for being analyzed the real time data of power transmission network with determination using target nerve network model
The fault type of power transmission network.
As it can be seen that a kind of trouble-shooter based on power transmission network disclosed by the invention, acquisition module obtains the record of power transmission network
The target data of the failure generation area of wave number evidence, failure cause data corresponding with recorder data and power transmission network, then structure
It models block and builds target nerve network model using recorder data, failure cause data and target data;Determining module utilizes
Target nerve network model is analyzed the real time data of power transmission network to determine the fault type of power transmission network.In the present solution, logical
The target of the failure generation area of the recorder data for crossing power transmission network, failure cause data corresponding with recorder data and power transmission network
Data structure target nerve network model its precision higher of data three types, to using the target nerve network to defeated
It is more accurate to the identification of the type of the failure of power transmission network when the real time data of power grid is analyzed, it improves to power transmission network
The reliability of fault diagnosis.
Fig. 3 is referred to, Fig. 3 is that another trouble-shooter structure based on power transmission network provided in an embodiment of the present invention is shown
It is intended to, including:
Memory 301, for storing computer program;
Processor 302, for executing the computer program stored in the memory to realize what any of the above item was mentioned
The step of method for diagnosing faults based on power transmission network.
It should be noted that trouble-shooter of the another kind disclosed in the present embodiment based on power transmission network and a upper embodiment
A kind of disclosed trouble-shooter based on power transmission network technique effect having the same, the embodiment of the present invention are no longer superfluous herein
It states.
This programme in order to better understand, a kind of computer readable storage medium provided in an embodiment of the present invention, computer
It is stored with computer program on readable storage medium storing program for executing, realizes that any embodiment as above is mentioned when computer program is executed by processor
The method for diagnosing faults based on power transmission network the step of.
It should be noted that a kind of computer readable storage medium disclosed in the present embodiment is disclosed with any of the above-described embodiment
A kind of method for diagnosing faults/device technique effect having the same based on power transmission network, the embodiment of the present invention is no longer superfluous herein
It states.
A kind of method for diagnosing faults, device and storage medium based on power transmission network provided herein are carried out above
It is discussed in detail.Specific examples are used herein to illustrate the principle and implementation manner of the present application, above example
Illustrate to be merely used to help understand the present processes and its core concept.It should be pointed out that for the common skill of the art
For art personnel, under the premise of not departing from the application principle, can also to the application, some improvement and modification can also be carried out, these change
It is also fallen into the application scope of the claims into modification.
Each embodiment is described by the way of progressive in specification, the highlights of each of the examples are with other realities
Apply the difference of example, just to refer each other for identical similar portion between each embodiment.For device disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related place is referring to method part illustration
.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only that
A little elements, but also include other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Claims (10)
1. a kind of method for diagnosing faults based on power transmission network, which is characterized in that including:
Obtain the failure of the recorder data of power transmission network, failure cause data corresponding with the recorder data and the power transmission network
The target data of generation area;
Target nerve network model is built using the recorder data, the failure cause data and the target data;
The real time data of the power transmission network is analyzed with the determination power transmission network using the target nerve network model
Fault type.
2. according to the method for diagnosing faults described in claim 1 based on power transmission network, which is characterized in that described in the utilization
Recorder data, the failure cause data and target data structure neural network model include:
Multi-scale wavelet transformation is carried out to obtain recording characteristic value data to the recorder data;
Fault signature value matrix is built according to the recording characteristic value data and the target data;
The target nerve network model is built according to the fault signature value matrix and the failure cause data.
3. the method for diagnosing faults based on power transmission network according to the claim 2, which is characterized in that described in the basis
Fault signature value matrix and the failure cause data build the target nerve network model:
Determine the number of the characteristic value in the fault signature value matrix;
The number of the neuron of the input layer in neural network model is set as the number of the characteristic value;
Failure cause during the number of the neuron of the output layer in the neural network model is set as the failure cause data
Type number;
By the initial weight value of each neuron node of the hidden layer in the neural network model be set as between 0 to 1 with
Machine number;
The neural network model is built using the input layer, the output layer and the initial weight value and to the god
It is trained to obtain the target nerve network model through network model.
4. the method for diagnosing faults based on power transmission network according to the claim 3, which is characterized in that described in the utilization
Input layer, the output layer and the initial weight value build the neural network model and to the neural network model into
After row training obtains the target nerve network model, further include:
Judge whether the training error of the target nerve network meets condition;
If it is not, then to LayerSize, NodeSize, Iterations and LearningRate in the target nerve network
Four parameters are adjusted.
5. the method for diagnosing faults based on power transmission network according to the claim 4, which is characterized in that described to the mesh
Tetra- parameters of LayerSize, NodeSize, Iterations and LearningRate in mark neural network are adjusted packet
It includes:
Determine the number of plies of the hidden layer in the target nerve network model and the neuron node number of the hidden layer;
By changing the neuron section of the number of plies of the hidden layer, the hidden layer in the target nerve network
Tetra- parameters of LayerSize, NodeSize, Iterations and LearningRate are adjusted.
6. according to the method for diagnosing faults described in claim 1 based on power transmission network, which is characterized in that described in the utilization
Target nerve network model analyzes with after the fault type of the determination power transmission network real time data of the power transmission network,
Further include:
The target nerve network model is trained again using the real time data to update the target nerve network
The weighted value of each neuron in model.
7. according to the method for diagnosing faults based on power transmission network described in claim 1 to 6 any one, which is characterized in that
The target data includes:Temperature information, humidity information, latitude and longitude information, altitude information in the failure generation area with
And wind scale information.
8. a kind of trouble-shooter based on power transmission network, which is characterized in that including:
Acquisition module, the recorder data for obtaining power transmission network, failure cause data corresponding with the recorder data and institute
State the target data of the failure generation area of power transmission network;
Module is built, for utilizing the recorder data, the failure cause data and target data structure target god
Through network model;
Determining module, for being analyzed the real time data of the power transmission network with determination using the target nerve network model
The fault type of the power transmission network.
9. a kind of trouble-shooter based on power transmission network, which is characterized in that including:
Memory, for storing computer program;
Processor, for executing the computer program stored in the memory to realize as described in any one of claim 1 to 7
The method for diagnosing faults based on power transmission network the step of.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the computer program realize the event as described in any one of claim 1 to 7 based on power transmission network when being executed by processor
The step of hindering diagnostic method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810437585.1A CN108663600B (en) | 2018-05-09 | 2018-05-09 | Fault diagnosis method and device based on power transmission network and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810437585.1A CN108663600B (en) | 2018-05-09 | 2018-05-09 | Fault diagnosis method and device based on power transmission network and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108663600A true CN108663600A (en) | 2018-10-16 |
CN108663600B CN108663600B (en) | 2020-11-10 |
Family
ID=63778829
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810437585.1A Active CN108663600B (en) | 2018-05-09 | 2018-05-09 | Fault diagnosis method and device based on power transmission network and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108663600B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109270407A (en) * | 2018-11-16 | 2019-01-25 | 国网山东省电力公司电力科学研究院 | Extra high voltage direct current transmission line failure cause discrimination method based on Multi-source Information Fusion |
CN111078456A (en) * | 2019-12-26 | 2020-04-28 | 新奥数能科技有限公司 | Equipment fault diagnosis method and device, computer readable storage medium and electronic equipment |
CN111880046A (en) * | 2020-07-22 | 2020-11-03 | 国网河北省电力有限公司 | Device and method for quickly identifying line fault reason |
CN112363012A (en) * | 2020-10-29 | 2021-02-12 | 国家电网有限公司 | Power grid fault early warning device and method |
CN113189448A (en) * | 2021-04-29 | 2021-07-30 | 广东电网有限责任公司清远供电局 | Method and device for detecting fault type of power transmission line |
CN116170283A (en) * | 2023-04-23 | 2023-05-26 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0618600A (en) * | 1992-07-01 | 1994-01-25 | Hitachi Cable Ltd | System for locating faulty section of power transmission line |
CN102142716A (en) * | 2011-02-17 | 2011-08-03 | 国电南瑞科技股份有限公司 | Power grid online fault diagnosis method based on three-state data multidimensional cooperative processing |
CN103161668A (en) * | 2013-02-21 | 2013-06-19 | 上海交通大学 | Intelligent wind turbine generator working condition identification system and method |
CN103163430A (en) * | 2013-03-29 | 2013-06-19 | 昆明理工大学 | Resonant grounding system fault line selection method by combining complex wavelets with ANN (artificial neural network) |
CN103728507A (en) * | 2013-11-18 | 2014-04-16 | 芜湖大学科技园发展有限公司 | Grid fault diagnosis method based on data mining |
CN104238546A (en) * | 2014-08-28 | 2014-12-24 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Direct current master device fault diagnosis method based on hybrid neural network |
CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
CN105676067A (en) * | 2016-01-26 | 2016-06-15 | 云南电网有限责任公司电力科学研究院 | Fault diagnosis method and system of power transmission lines |
CN106093713A (en) * | 2016-08-24 | 2016-11-09 | 广东工业大学 | A kind of power distribution network section Fault Locating Method containing distributed power source and system |
CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
CN107909118A (en) * | 2017-12-11 | 2018-04-13 | 北京映翰通网络技术股份有限公司 | A kind of power distribution network operating mode recording sorting technique based on deep neural network |
-
2018
- 2018-05-09 CN CN201810437585.1A patent/CN108663600B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0618600A (en) * | 1992-07-01 | 1994-01-25 | Hitachi Cable Ltd | System for locating faulty section of power transmission line |
CN102142716A (en) * | 2011-02-17 | 2011-08-03 | 国电南瑞科技股份有限公司 | Power grid online fault diagnosis method based on three-state data multidimensional cooperative processing |
CN103161668A (en) * | 2013-02-21 | 2013-06-19 | 上海交通大学 | Intelligent wind turbine generator working condition identification system and method |
CN103163430A (en) * | 2013-03-29 | 2013-06-19 | 昆明理工大学 | Resonant grounding system fault line selection method by combining complex wavelets with ANN (artificial neural network) |
CN103728507A (en) * | 2013-11-18 | 2014-04-16 | 芜湖大学科技园发展有限公司 | Grid fault diagnosis method based on data mining |
CN104238546A (en) * | 2014-08-28 | 2014-12-24 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Direct current master device fault diagnosis method based on hybrid neural network |
CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
CN105676067A (en) * | 2016-01-26 | 2016-06-15 | 云南电网有限责任公司电力科学研究院 | Fault diagnosis method and system of power transmission lines |
CN106093713A (en) * | 2016-08-24 | 2016-11-09 | 广东工业大学 | A kind of power distribution network section Fault Locating Method containing distributed power source and system |
CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
CN107909118A (en) * | 2017-12-11 | 2018-04-13 | 北京映翰通网络技术股份有限公司 | A kind of power distribution network operating mode recording sorting technique based on deep neural network |
Non-Patent Citations (3)
Title |
---|
孙玎 等: "改进聚类分析在电网故障定位中的应用", 《广东电力》 * |
朱文羽: "基于云遗传算法优化的BP神经网络的配电网故障定位", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
林圣 等: "输电网络故障诊断方法综述与发展趋势", 《电力系统保护与控制》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109270407A (en) * | 2018-11-16 | 2019-01-25 | 国网山东省电力公司电力科学研究院 | Extra high voltage direct current transmission line failure cause discrimination method based on Multi-source Information Fusion |
CN109270407B (en) * | 2018-11-16 | 2022-02-25 | 国网山东省电力公司电力科学研究院 | Extra-high voltage direct current transmission line fault reason identification method based on multi-source information fusion |
CN111078456A (en) * | 2019-12-26 | 2020-04-28 | 新奥数能科技有限公司 | Equipment fault diagnosis method and device, computer readable storage medium and electronic equipment |
CN111078456B (en) * | 2019-12-26 | 2023-05-16 | 新奥数能科技有限公司 | Device fault diagnosis method, device, computer readable storage medium and electronic device |
CN111880046A (en) * | 2020-07-22 | 2020-11-03 | 国网河北省电力有限公司 | Device and method for quickly identifying line fault reason |
CN112363012A (en) * | 2020-10-29 | 2021-02-12 | 国家电网有限公司 | Power grid fault early warning device and method |
CN113189448A (en) * | 2021-04-29 | 2021-07-30 | 广东电网有限责任公司清远供电局 | Method and device for detecting fault type of power transmission line |
CN116170283A (en) * | 2023-04-23 | 2023-05-26 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
CN116170283B (en) * | 2023-04-23 | 2023-07-14 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
Also Published As
Publication number | Publication date |
---|---|
CN108663600B (en) | 2020-11-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108663600A (en) | A kind of method for diagnosing faults, device and storage medium based on power transmission network | |
Hung et al. | An artificial neural network model for rainfall forecasting in Bangkok, Thailand | |
CN104182830B (en) | A kind of distribution Power System Reliability weak link method for digging based on multidimensional analysis | |
CN106777984A (en) | A kind of method that photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm | |
CN109272146A (en) | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network | |
KR101761707B1 (en) | Typhoon surge automatic forecasting method using active data collection type script and numerical model | |
Castellani et al. | Wind power forecasting techniques in complex terrain: ANN vs. ANN-CFD hybrid approach | |
CN108027908A (en) | Analogy method and system | |
CN104732058B (en) | A kind of appraisal procedure of various dimensions transmission facility state | |
CN107704992A (en) | The method and device of transmission line lightning stroke risk assessment | |
CN108632832B (en) | Network coverage analysis method and system | |
CN104407273B (en) | Electric energy quality disturbance source positioning method considering monitoring reliability | |
CN106651007A (en) | Method and device for GRU-based medium and long-term prediction of irradiance of photovoltaic power station | |
CN105974232A (en) | Power grid fault diagnosis method suitable for high tension transmission network | |
CN106126944A (en) | A kind of power transformer top-oil temperature interval prediction method and system | |
CN105930900A (en) | Method and system for predicting hybrid wind power generation | |
CN106199443A (en) | A kind of lithium battery degeneration discrimination method and degeneration warning system | |
WO2021063461A1 (en) | Method for planning a layout of a renewable energy site | |
CN106570582A (en) | Method and system for building transmission line dancing tripping risk prediction network model | |
CN108269197A (en) | Wind turbines power characteristic appraisal procedure and device | |
Freedman et al. | The Wind Forecast Improvement Project (WFIP): A public/private partnership for improving short term wind energy forecasts and quantifying the benefits of utility operations. The Southern Study Area, Final Report | |
Johnston et al. | Investigating avoidance and attraction responses in lesser black-backed gulls Larus fuscus to offshore wind farms | |
CN113689053B (en) | Strong convection weather overhead line power failure prediction method based on random forest | |
CN106679761A (en) | Method and system for forecasting comprehensive water levels of sea areas in real time | |
CN103675356A (en) | Anemometer fault detection method and system on the basis of particle swarm optimization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |