CN109861182A - It is a kind of that soft straight electric network fault guard method is maked somebody a mere figurehead based on intelligent control algorithm - Google Patents
It is a kind of that soft straight electric network fault guard method is maked somebody a mere figurehead based on intelligent control algorithm Download PDFInfo
- Publication number
- CN109861182A CN109861182A CN201811467763.1A CN201811467763A CN109861182A CN 109861182 A CN109861182 A CN 109861182A CN 201811467763 A CN201811467763 A CN 201811467763A CN 109861182 A CN109861182 A CN 109861182A
- Authority
- CN
- China
- Prior art keywords
- fault
- intelligent
- detection model
- output
- target detection
- 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
Landscapes
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention discloses a kind of to make somebody a mere figurehead soft straight electric network fault guard method based on intelligent control algorithm, method includes the following steps: analyzing the fault characteristic for making somebody a mere figurehead soft straight power grid first, chooses the input feature vector amount of reflection internal fault external fault otherness；Then, the off-line training that a large amount of training sample carries out intelligent control is acquired, fault identification ability is made it have；Further, classifier is designed according to fault distinguishing type, target value is exported based on intelligent control, realize the Fault Isolation of rapidity, selectivity, guarantee the normal operation of non-faulting part, to improve safety in operation and power supply reliability, solves the problems, such as that action value adjusting is difficult, it is complicated to calculate.
Description
Technical field
The invention belongs to flexible direct-current transmission field, more particularly, to it is a kind of based on intelligent control algorithm make somebody a mere figurehead it is soft
Straight electric network fault guard method.
Background technique
In recent years, (the modular multilevel of the high voltage dc transmission technology based on modularization multi-level converter
Converter based high voltage direct current, MMC-HVDC) contain by its modular construction, harmonic wave
The features such as low, idle low with active independent control and switching loss is measured, in asynchronous interconnection, marine wind electric field power generation, urban distribution network
Increase-volume has wide application scenarios to island power supply, the weak AC network of connection and large capacity transmission etc..With renewable
Growing, development trend one of of the multiterminal flexible direct current power grid as the following smart grid of the grid-connected demand of the energy.
DC network is low inertia system, and when short trouble occurs for DC line, fault current can be risen rapidly, and cause
The equipment such as inverter are burned out, and endanger the safe operation of system.Therefore, it is necessary to, selectivity quick using high voltage DC breaker
Failure is removed on ground, guarantees the normal operation of non-faulting part.This proposes high requirement to fault protecting method.
For the error protection research of HVDC transmission system, traveling-wave protection obtains in conventional high-pressure DC transmission system
To extensive use.However, traveling-wave protection comes with some shortcomings, and such as: wave head detection difficult, the size of wave impedance need known, close
Distance fault can not detect, high resistance earthing fault tripping etc..For the detection speed for improving wavefront, wavelet transformation starts extensively
In the protection of flexible HVDC transmission system.Based on the protection scheme of the mathematical tools such as Wavelet transformation, to high resistive fault
Sensitivity is higher.Traveling wave, inspection of the mathematical tools such as wavelet transformation to singular point, catastrophe point are detected relative to derivative method or integration method
It surveys sharper.However, the protection scheme based on mathematical tools such as wavelet transformations has principle complicated, anti-interference ability is poor etc. is asked
Topic.In view of the above problems, many scholars propose the protection scheme based on boundary condition, program noise resisting ability is strong, and has
Have and preferably react transition resistance ability, but there is a problem of adjusting difficulty and calculating complexity.
With the development of artificial intelligence, intelligent algorithm starts the protection field for being gradually applied to electric system.With it is non intelligent
Protection algorism is compared, and intelligent protection method avoids complicated tuning process and calculating process, shows good protective value.
However, intelligent control algorithm is more applied to AC network protection field, for the DC grid failure of intelligent control algorithm
Protection, is currently in the elementary step of research.
Therefore, research makes somebody a mere figurehead soft straight electric network protection scheme based on intelligent control algorithm, and DC grid operation can be improved
Safety and power supply reliability, improve the protective value of existing protection scheme.
Summary of the invention
Aiming at the above defects or improvement requirements of the prior art, the present invention provides a kind of framves based on intelligent control algorithm
Empty soft straight electric network fault guard method solves the problems, such as that the adjusting of GPF (General Protection False scheme is difficult and it is complicated to calculate, realizes that large capacity is remote
Distance makes somebody a mere figurehead soft straight electric network fault detection, guarantees the safe operation of system, improves the power supply reliability of system.
To achieve the above object, the present invention provides a kind of makes somebody a mere figurehead soft straight electric network fault protection based on intelligent control algorithm
Method, comprising:
(1) by carrying out Faults Characteristic Analysis to the internal fault external fault situation maked somebody a mere figurehead in soft straight power grid, acquisition is able to reflect
The fault characteristic value of internal fault external fault otherness extracts training sample and test sample from the sample as sample respectively；
(2) using each fault characteristic value in the training sample as the input of intelligent measurement model to the intelligent measurement
Model is trained to obtain Intelligent target detection model, and the output of the Intelligent target detection model is limited by classifier；
(3) the Intelligent target detection model is tested by each fault characteristic value in the test sample, if
The output accuracy of the Intelligent target detection model meets default accuracy requirement, then passes through the Intelligent target detection model
Fault detection is carried out to DC line to be detected.
Preferably, step (1) includes:
It is electric to different type in soft straight power grid, different location and difference is maked somebody a mere figurehead in such a way that time domain and/or frequency domain combine
The internal fault external fault situation of resistance carries out Faults Characteristic Analysis, extracts the corresponding fault characteristic value of each fault condition as sample,
In, the electrical quantity for carrying out Faults Characteristic Analysis includes voltage and or current.
Wherein, by measuring the above electrical quantity, it is analyzed using corresponding mathematical tool, extraction is able to reflect inside and outside area
The characteristic quantity of fault signature otherness, the input quantity as intelligent measurement model.In order to meet the requirement of quick-action, failure is chosen
The time window of characteristic quantity should be no more than 1.5ms.
Preferably, the output that the Intelligent target detection model is limited by classifier, comprising:
It is 1 or 0 by the output that classifier limits the Intelligent target detection model, wherein export indicates to occur for 1
Troubles inside the sample space, exporting indicates that external short-circuit failure or fault-free, which occurs, to be occurred for 0.
It is preferably, described that fault detection is carried out to DC line to be detected by the Intelligent target detection model, comprising:
The fault characteristic value to be detected for extracting DC line to be detected, using the fault characteristic value to be detected as the mesh
The input of intelligent measurement model is marked, and limits the output of the Intelligent target detection model by classifier；
If the output of the classifier is 1, show that troubles inside the sample space occurs, and to the DC line two sides to be detected
Dc circuit breaker, which issues, cut-offs instruction；If the output of the classifier is 0, show that external area error or fault-free, which occurs, to be occurred,
Then breaker is failure to actuate.
Preferably, it if the output accuracy of the Intelligent target detection model is unsatisfactory for default accuracy requirement, returns
It executes step (2), intelligent measurement model is continued to train.
Wherein, presetting accuracy requirement can be determine according to actual needs, it is contemplated that protection algorism should have absolute choosing
Selecting property, the default accuracy observation can be set to 100%.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, can obtain down and show
Beneficial effect:
(1) the method proposed by the present invention that make somebody a mere figurehead soft straight electric network fault protection based on intelligent control algorithm, according to intelligence
The online output of detection model come rapidly, selectively carry out Fault Isolation, guarantee the normal operation of non-faulting part, from
And improve safety in operation and power supply reliability；
(2) compared with non intelligent protection algorism, intelligent protection method avoids complicated tuning process and calculating process, is in
Reveal good protective value.
Detailed description of the invention
Fig. 1 is that one kind provided in an embodiment of the present invention makes somebody a mere figurehead soft straight topological structure of electric；
Fig. 2 is a kind of semi-bridge type MMC topological structure provided in an embodiment of the present invention；
Fig. 3 is a kind of hybrid high-voltage direct-current breaker topology provided in an embodiment of the present invention；
Fig. 4 is a kind of double circle controling mode provided in an embodiment of the present invention；
Fig. 5 be it is provided in an embodiment of the present invention it is a kind of using Fast Fourier Transform (FFT) (Fast Fourier Transform,
FFT a kind of fault characteristic) analyzed；
Fig. 6 is the schematic diagram of a kind of test sample and training sample provided in an embodiment of the present invention；
Fig. 7 is provided in an embodiment of the present invention a kind of using novel heuristic dynamic programming model (goal
Representation heuristic dynamic programming, GrHDP) algorithm principle figure；
Fig. 8 is provided in an embodiment of the present invention a kind of to make somebody a mere figurehead soft straight electric network fault detection method based on intelligent control algorithm
Flow diagram.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
The invention discloses a kind of to make somebody a mere figurehead soft straight electric network fault guard method based on intelligent control algorithm, passes through failure spy
Property analysis, design error failure feature input quantity and target output valve, and acquire a large amount of training sample and be trained；Further
Ground, design classifier by the output of intelligent measurement model algorithm to be " 1 " and " 0 "；Finally, using test sample to training
As a result it is tested.If accuracy is met the requirements, intelligent measurement model can be put into the on-line checking of DC grid line fault；
If the output of intelligent measurement model is " 1 ", show that troubles inside the sample space occurs, and issue and cut-off to the dc circuit breaker of route two sides
Instruction；If the output of intelligent measurement model is " 0 ", show that external area error or fault-free, which occurs, to be occurred.Existed by this method
Line detection, can rapidly, selectively carry out the isolation of fault zone, guarantee the normal operation of non-faulting part, thus
Improve safety in operation and power supply reliability.
Fig. 1 is that one kind used in the embodiment of the present invention makes somebody a mere figurehead soft straight electric network fault protection scheme.Its submodule uses half-bridge
Type structure.Since semi-bridge type MMC does not have failure self-cleaning ability, it is therefore desirable to install high voltage DC breaker in route two sides
To carry out Fault Isolation.For the size of fault current limiting, current-limiting reactor is installed in route two sides.The system is symmetrical monopolar
System, overhead transmission line use frequency dependent model.For protecting CB12, consider selectivity, F12 is troubles inside the sample space, F1, F2 and
F14 is external area error.When short trouble occurring at F12, breaker CB12 should be acted；Break down F1, F2 and F14 when, break
Road device should remain stationary.
Fig. 2 is semi-bridge type MMC topological structure.Wherein, UsmIndicate submodule output voltage, UcIndicate submodule capacitor electricity
Pressure, ismExpression flows into the electric current of submodule.By cut-offfing for control IGBT, submodule work can be made in different modes.
The following table 1 lists the different working modes and working condition of submodule.
Table 1
| State | Mode | T1 | T2 | D1 | D2 | Current direction | Usm | Explanation |
| Locking | 1 | Shutdown | Shutdown | Conducting | Shutdown | It is positive | Uc | Capacitor charging |
| 2 | Shutdown | Shutdown | Shutdown | Conducting | It is negative | 0 | Bypass | |
| Investment | 1 | Conducting | Shutdown | Shutdown | Shutdown | It is negative | Uc | Capacitor electric discharge |
| 2 | Shutdown | Shutdown | Conducting | Shutdown | It is positive | Uc | Capacitor charging | |
| Excision | 1 | Shutdown | Conducting | Shutdown | Shutdown | It is positive | 0 | Bypass |
| 2 | Shutdown | Shutdown | Shutdown | Conducting | It is negative | 0 | Bypass |
Fig. 3 is a kind of hybrid high-voltage direct-current breaker topology used in the embodiment of the present invention.For hybrid high straightening
Breaker is flowed, when normal operation, DC current flows through through-flow branch, to reduce the on-state loss of main circuit breaker.DC Line Fault hair
After life, direct fault current gradually the change of current to main circuit breaker branch.When through-flow branch current is reduced to zero, quick isolation switch exists
It is disconnected in the case of zero current, time-consuming 2ms or so.IGBT shutdown in subsequent main circuit breaker, fault current are transferred to energy consumption branch,
Fault energy is consumed by arrester.When combined floodgate, since main circuit breaker branch on state resistance is big, main circuit breaker branch is connected first to subtract
Small combined floodgate immediate current.Then, it is closed quick isolation switch and auxiliary circuit breaker, DC current is transferred to through-flow branch.
Fig. 4 is a kind of double circle controling mode used in the embodiment of the present invention.Direct current outer ring is using constant dc power control or determines
DC voltage control exports IdrefAnd IqrefReference value is controlled by PI to direct current inner ring and generates HVDC Modulation ratio Md、Mq, into one
Step ground is pressed algorithm that algorithm and Staircase wave is pressed to export bridge arm investment submodule number N, to export DC voltage.
A kind of fault characteristic that Fig. 5 uses FFT to analyze by the embodiment of the present invention.Troubles inside the sample space F occurs12, to direct current
Pressure carries out FFT, and frequency spectrum is as shown in Figure 5.It can be obtained by result of spectrum analysis, DC voltage contains biggish high fdrequency component, therefore should
Characteristic can be used as a fault signature input quantity of Fault Model.
Fig. 6 is the schematic diagram of test sample provided in an embodiment of the present invention and training sample.The quantity of training sample will foot
Enough is big.Training sample should comprising different faults position, different faults type, different faults resistance area inside and outside short trouble,
And ratio is suitable, prevents algorithm from falling into hypersaturated state.Similarly, test sample should also include different faults position, different events
Hinder type, different faults resistance area inside and outside short trouble.Preferably, the quantity of test sample and the quantity of training sample meet
The ratio of 7:3.
Fig. 7 is a kind of schematic diagram of intelligent algorithm GrHDP algorithm used by the embodiment of the present invention.GrHDP is by more than three
Layer feedforward neural network composition, i.e. execution network, evaluation network and target network.With well adapting to property, and can optimize defeated
Enter signal and exports the mapping relations between control amount, the fault identification effect reached.Each layer neural network is anti-using error
Network weight is modified to propagation algorithm, to realize fault detection capability.
Fig. 8 is provided in an embodiment of the present invention a kind of to make somebody a mere figurehead soft straight electric network fault guard method based on intelligent control algorithm
Flow diagram, comprising the following steps:
(1) fault characteristic is analyzed first, finds one group of fault characteristic value [x for being able to reflect internal fault external fault otherness1,
x2,...,xn], wherein xi(i=1,2 ..., n) indicate i-th of fault characteristic value.Using features described above amount as intelligent measurement mould
The input quantity of type, and require setting target to export according to expected；
Fault characteristic value in embodiments of the present invention, it includes but be not limited to different type, different location, different resistance
Fault message.Selection is able to reflect the feature input quantity of internal fault external fault otherness, is that intelligent control algorithm training is successful
It is crucial.The faulty resistance of factor of fault identification, the method for operation, fault type etc. are influenced, therefore, frequently with time domain and/or frequency
Domain in conjunction with analysis method extract fault characteristic value.Wherein, temporal signatures amount is simple and reliable and is easily achieved comprising but not
It is limited to voltage and current change rate, variable quantity；Frequency domain character amount reflects that transition resistance ability is strong, high reliablity comprising but not
It is limited to voltage and current high frequency characteristics, resonance frequency.
(2) then, it acquires a large amount of training sample and off-line training is carried out to intelligent measurement model, make it have fault identification
Ability；Further, the output of intelligent measurement model is made to be " 1 " or " 0 " by classifier；
Intelligent algorithm have parallel processing, good fault-tolerance, adaptively with self study, nonlinearity, knowledge distributing
Storage and the features such as self organization ability, therefore it is widely used in Nonlinear Mapping, pattern-recognition, classification and cluster, associative memory, excellent
The problems such as changing calculating, the acquisition of knowledge and deposit.
Intelligent measurement model employed in the embodiment of the present invention can be model, base based on artificial neural network algorithm
It model in particle swarm algorithm, the model based on FUZZY ALGORITHMS FOR CONTROL, the model based on machine learning algorithm and is opened based on novel
Which kind of intelligent measurement model the model etc. of the adaptive dynamic programming algorithm of hairdo, specifically use, and the embodiment of the present invention is not done uniquely
Property limit.
(3) finally, acquiring a large amount of test sample, the intelligent measurement model terminated to training is tested, and is observed just
True rate.If accuracy is met the requirements, show to train successfully；It, will be again to intelligent measurement mould if accuracy is unsatisfactory for requiring
Type is trained, until accuracy is met the requirements.
(4) intelligent measurement model successful for training, can be used for DC grid line fault on-line checking；If intelligence inspection
The output for surveying model is " 1 ", then shows that troubles inside the sample space occurs, and issue to the dc circuit breaker of route two sides and cut-off instruction；If
The output of intelligent measurement model is " 0 ", then shows that external area error or fault-free, which occurs, to be occurred, breaker is failure to actuate.
On-line checking by the method for the invention can rapidly, selectively carry out the isolation of fault zone, guarantee
The normal operation of non-faulting part, to improve safety in operation and power supply reliability；It is whole that the invention simultaneously solves action value
Fixed problem that is difficult, calculating complexity, shows preferable protective value.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (5)
1. a kind of make somebody a mere figurehead soft straight electric network fault guard method based on intelligent control algorithm characterized by comprising
(1) by carrying out Faults Characteristic Analysis to the internal fault external fault situation maked somebody a mere figurehead in soft straight power grid, acquisition is able to reflect in area
The fault characteristic value of outer failure otherness extracts training sample and test sample from the sample as sample respectively；
(2) using each fault characteristic value in the training sample as the input of intelligent measurement model to the intelligent measurement model
It is trained to obtain Intelligent target detection model, and limits the output of the Intelligent target detection model by classifier；
(3) the Intelligent target detection model is tested by each fault characteristic value in the test sample, if described
The output accuracy of Intelligent target detection model meets default accuracy requirement, then is treated by the Intelligent target detection model
It detects DC line and carries out fault detection.
2. the method according to claim 1, wherein step (1) includes:
To making somebody a mere figurehead different type in soft straight power grid, different location and different resistance in such a way that time domain and/or frequency domain combine
Internal fault external fault situation carries out Faults Characteristic Analysis, extracts the corresponding fault characteristic value of each fault condition as sample, wherein into
The electrical quantity of row Faults Characteristic Analysis includes voltage and or current.
3. method according to claim 1 or 2, which is characterized in that described to limit the Intelligent target inspection by classifier
Survey the output of model, comprising:
It is 1 or 0 by the output that classifier limits the Intelligent target detection model, wherein exporting indicates in generating region for 1
Failure, exporting indicates that external short-circuit failure or fault-free, which occurs, to be occurred for 0.
4. according to the method described in claim 3, it is characterized in that, it is described by the Intelligent target detection model to be detected
DC line carries out fault detection, comprising:
The fault characteristic value to be detected for extracting DC line to be detected, using the fault characteristic value to be detected as the target intelligence
Can detection model input, and limit by classifier the output of the Intelligent target detection model；
If the output of the classifier is 1, show that troubles inside the sample space occurs, and to the direct current of the DC line two sides to be detected
Breaker, which issues, cut-offs instruction；If the output of the classifier is 0, show that external area error or fault-free, which occurs, to be occurred, then is broken
Road device is failure to actuate.
5. the method according to claim 1, wherein if the output accuracy of the Intelligent target detection model not
Meet default accuracy requirement, then returns to step (2), intelligent measurement model is continued to train.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811467763.1A CN109861182A (en) | 2018-12-03 | 2018-12-03 | It is a kind of that soft straight electric network fault guard method is maked somebody a mere figurehead based on intelligent control algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811467763.1A CN109861182A (en) | 2018-12-03 | 2018-12-03 | It is a kind of that soft straight electric network fault guard method is maked somebody a mere figurehead based on intelligent control algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109861182A true CN109861182A (en) | 2019-06-07 |
Family
ID=66890532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811467763.1A Pending CN109861182A (en) | 2018-12-03 | 2018-12-03 | It is a kind of that soft straight electric network fault guard method is maked somebody a mere figurehead based on intelligent control algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109861182A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112924810A (en) * | 2021-01-27 | 2021-06-08 | 国网山东省电力公司淄博供电公司 | Power cable fault diagnosis method and system based on high-frequency signal identification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005755A (en) * | 2010-10-29 | 2011-04-06 | 昆明理工大学 | Extra-high voltage direct current transmission line boundary element forming method based on support vector machine |
| US20130193766A1 (en) * | 2012-01-31 | 2013-08-01 | Atlantic Grid Operations A., Llc | Control and protection of a dc power grid |
| CN104865499A (en) * | 2015-05-11 | 2015-08-26 | 昆明理工大学 | Super-high voltage direct-current power transmission line region internal and external fault identification method |
| CN106291233A (en) * | 2016-07-29 | 2017-01-04 | 武汉大学 | A kind of fault phase-selecting method based on convolutional neural networks |
| CN106291234A (en) * | 2016-07-29 | 2017-01-04 | 武汉大学 | A kind of transmission line of electricity internal fault external fault based on convolutional neural networks judges and fault phase-selecting method |
| CN108667027A (en) * | 2018-05-15 | 2018-10-16 | 四川大学 | Ac and dc systems power flow transfer search containing flexible direct current and quantitative analysis method |
-
2018
- 2018-12-03 CN CN201811467763.1A patent/CN109861182A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005755A (en) * | 2010-10-29 | 2011-04-06 | 昆明理工大学 | Extra-high voltage direct current transmission line boundary element forming method based on support vector machine |
| US20130193766A1 (en) * | 2012-01-31 | 2013-08-01 | Atlantic Grid Operations A., Llc | Control and protection of a dc power grid |
| CN104865499A (en) * | 2015-05-11 | 2015-08-26 | 昆明理工大学 | Super-high voltage direct-current power transmission line region internal and external fault identification method |
| CN106291233A (en) * | 2016-07-29 | 2017-01-04 | 武汉大学 | A kind of fault phase-selecting method based on convolutional neural networks |
| CN106291234A (en) * | 2016-07-29 | 2017-01-04 | 武汉大学 | A kind of transmission line of electricity internal fault external fault based on convolutional neural networks judges and fault phase-selecting method |
| CN108667027A (en) * | 2018-05-15 | 2018-10-16 | 四川大学 | Ac and dc systems power flow transfer search containing flexible direct current and quantitative analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 张峻榤 等: "含直流断路器的架空柔性直流电网直流故障保护方案研究", 《中国电机工程学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112924810A (en) * | 2021-01-27 | 2021-06-08 | 国网山东省电力公司淄博供电公司 | Power cable fault diagnosis method and system based on high-frequency signal identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kong et al. | Fault detection and location method for mesh-type DC microgrid using pearson correlation coefficient | |
| Biswas et al. | State‐of‐the‐art on the protection of FACTS compensated high‐voltage transmission lines: a review | |
| Wu et al. | Single pole-to-ground fault location system for MMC-HVDC transmission lines based on active pulse and CEEMDAN | |
| CN109613400A (en) | Soft straight electric network fault detection method is maked somebody a mere figurehead based on the current-limiting reactor voltage difference opposite sex | |
| CN109613395A (en) | It is a kind of that soft straight electric network fault detection method is maked somebody a mere figurehead based on ANN | |
| Hlalele et al. | Faults classification and identification on smart grid: Part-a status review | |
| Yuan et al. | Faulty feeder detection for single line-to-ground fault in distribution networks with DGs based on correlation analysis and harmonics energy | |
| Wang et al. | An intelligent fault diagnosis method for open-circuit faults in power-electronics energy conversion system | |
| CN113702767B (en) | Island direct-current microgrid fault diagnosis method based on wavelet sliding window energy | |
| Sharif et al. | Fault detection and location in dc microgrids by recurrent neural networks and decision tree classifier | |
| Yuan et al. | Faulty-Feeder Detection for Single Phase-to-Ground Faults in Distribution Networks Based on Waveform Encoding and Waveform Segmentation | |
| Venkata et al. | Data mining model based differential microgrid fault classification using svm considering voltage and current distortions | |
| CN109861182A (en) | It is a kind of that soft straight electric network fault guard method is maked somebody a mere figurehead based on intelligent control algorithm | |
| Chang et al. | Fault location identification in power transmission networks: Using novel nonintrusive fault-monitoring systems | |
| Shahriyari et al. | Fast prediction of angle stability using support vector machine and fault duration data | |
| Li et al. | A decentralized fault section location method using autoencoder and feature fusion in resonant grounding distribution systems | |
| Hosny et al. | ANN-based protection system for controllable series-compensated transmission lines | |
| Biswas et al. | Superimposed component-based protection scheme for upfc compensated transmission lines | |
| Ekka et al. | Fault identification using fuzzy in renewable energy interfaced IEEE 13 bus system | |
| Moravej et al. | Artificial Intelligence Application for HVDC Protection | |
| Ding et al. | Research on power grid fault diagnosis method based on PMU data and convolutional neural network | |
| Wen et al. | Simulation Research on Short-Circuit Fault Protection of Grid-Connected AC Microgrid Considering Topology Change | |
| Zhao et al. | Waveform characteristic analysis and recognition of short-circuit fault in grid-connected AC microgrid | |
| Merlin et al. | A frequency spectrum-based method for detecting and classifying faults in HVDC systems | |
| Liu et al. | A Dice similarity coefficient-based pilot protection method for 500kV transmission lines of large-scale integrated photovoltaic power supply |
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: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |