CN106249101A - A kind of intelligent distribution network fault identification method - Google Patents
A kind of intelligent distribution network fault identification method Download PDFInfo
- Publication number
- CN106249101A CN106249101A CN201610503338.8A CN201610503338A CN106249101A CN 106249101 A CN106249101 A CN 106249101A CN 201610503338 A CN201610503338 A CN 201610503338A CN 106249101 A CN106249101 A CN 106249101A
- Authority
- CN
- China
- Prior art keywords
- fault
- matrix
- distribution network
- node
- intelligent distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Locating Faults (AREA)
Abstract
The present invention proposes a kind of intelligent distribution network fault identification method.This invention basic thought is to upload information first with WAMS, multi-dimensional state monitoring matrix is formed by data prediction and data fusion, this matrix carried out Multidimensional Scaling and calculates its LOF value, realizing the fault detection and location of intelligent distribution network according to the size of each node LOF value；Again three-phase voltage at fault is carried out wavelet transformation, fault signature Sample Storehouse is set up with the wavelet singular entropy of three-phase voltage, fault is presorted by the residual voltage low frequency energy utilizing reflection earth fault information, and sets up SVM fault type differentiation forecast model based on this.This invention can carry out effective fault detection and location to intelligent distribution network, and fault zone different faults type can be carried out Rational Classification.
Description
Technical field
The present invention relates to intelligent distribution network protection control method research, be particularly well-suited to intelligent distribution network fault location and
Fault type differentiates.
Background technology
Along with being continuously increased and the access of distributed power source of intelligent distribution network capacity, the network structure of power distribution network and fortune
Line mode is the most complicated so that traditional relay protecting method is difficult to meet requirement.After power distribution network breaks down, the most quickly
Effectively being diagnosed to be abort situation, identification of defective type, this is to reducing failure recovery time, improves the safety and stability fortune of power distribution network
The reliability of row and power supply is significant.
For distribution network failure positions, generally utilize the size of three-phase current Sudden Changing Rate before and after trouble point and waveform
Inconsistent, identify fault zone；By comparing active power distribution network fault and the amplitude of short circuit of non-faulting section both sides
Relation, it is achieved fault location.Above guard method can preferably realize fault location, but taken fault characteristic value is more single
One, when there is sensor failure or communication abnormality, easily causing tripping or the malfunction of protection device, and there is the whole of complexity
Fixed value calculation.
When power distribution network generation permanent fault, fault zone, and the fault type to fault zone should be judged rapidly
Manually overhaul, normal power supply could be recovered after finding out failure cause, when this adds failture evacuation to a certain extent
Between and the allotment of personnel, and the continued power for some crux loads has a certain impact.Therefore, the most promptly define
Fault zone also judges that fault type has certain practice significance.
During in view of small current neutral grounding system generation singlephase earth fault, its fault-signal is difficult to detect, and false voltage,
Current signal is affected by system operation mode and abort situation etc., therefore, how to utilize voltage, electric current that protection device collects
Signal extraction fault spy measures, and this is most important to distribution network failure type identification.Owing to wavelet transformation, empirical mode decomposition are to place
Manage non-linear, non-stationary signal and there is the biggest superiority, it is therefore proposed that decompose based on to transient voltage electric current, from each point
Amount is extracted the fault characteristic value of faults signal, utilizes comentropy or approximate entropy index, fault characteristic value is quantified
Statistics.The present invention is by carrying out wavelet transformation to voltage signal, in conjunction with singular value decomposition and information entropy theory, extracts three-phase voltage
Wavelet singular entropy measures fault signature.Along with the development of artificial intelligence, neural network algorithm is in intelligent grid transient state
The aspects such as protection, failure line selection have a wide range of applications, but this algorithm is easily trapped into local minimum, and required sample is very big,
Convergence rate is the slowest.Therefore, neural network algorithm is Shortcomings in terms of smart power grid fault process, and SVM algorithm can be very well
Solution problem above.Not only required sample is few and has more preferable convergence rate and generalization ability relative to neutral net for SVM.Electricity
The probability that Force system fault occurs is the least, it is desirable to fault is made process rapidly, belongs to small sample event, therefore divide with SVM
Appliances has great advantage.
In consideration of it, the present invention proposes fault location and the fault type discrimination method that a kind of LOF and SVM combines.The party
Method basic thought is to utilize WAMS to upload information, forms multi-dimensional state by data prediction and data fusion and monitors
Matrix, carries out Multidimensional Scaling and calculates its LOF value this matrix, according to the LOF value size of each node to power distribution network network
Carry out fault location, then fault zone transient state three-phase voltage is carried out wavelet transformation, in conjunction with singular value decomposition and information entropy theory,
Using the wavelet singular entropy of three-phase voltage as the input quantity of SVM, by the various failure classes in analogue simulation different faults region
Type, is trained its sample, can failure judgement phase exactly, and to reflect the residual voltage low frequency energy of earth-fault signal
Discriminate whether as earth fault.Being emulated by MATLAB, demonstrate the feasibility of this algorithm, this algorithm can accurately realize by ratio
Intelligent distribution network fault location and fault type differentiate, and are not affected by transition resistance, abort situation etc..
Summary of the invention
The technical problem to be solved is to provide a kind of local outlier factor detection (local outlier
Factor, LOF) and the intelligent distribution network fault identification that combines of support vector machine (Support Vector Machine, SVM)
Method.Detecting with LOF by status monitoring matrix being carried out multi-dimentional scale dimensionality reduction, can judge whether power distribution network has event rapidly
Barrier, and judge malfunctioning node；Extracting three-phase voltage wavelet singular entropy at fault zone again is test sample collection, pre-with SVM
Survey the model realization differentiation to fault type.
The present invention solves the technical scheme of above-mentioned technical problem and comprises the following steps:
Step 1: WAMS is uploaded with target electric current time unified and power information number according to measuring protection device
According to, by data prediction and data fusion, it is processed into the multi-dimensional state monitoring matrix comprising multiple electric characteristic amount.
Step 2: multi-dimensional state monitoring matrix is carried out multi-dimentional scale dimensionality reduction and the detection of LOF local outlier factor, it is achieved intelligence
Can distribution network failure detection and location.
Step 3: after wavelet transformation, extracts the residual voltage ground floor low frequency energy at fault zone, to fault type
Presort, fault is divided into earth fault type and phase fault type；
Step 4: after fault location, carries out wavelet transformation, and the coefficient to wavelet transformation to three-phase voltage at fault zone
Matrix carries out singular value decomposition, combining information entropy theory, and the diagonal matrix after singular value decomposition is processed into probability distribution,
And calculate three-phase voltage wavelet singular entropy.
Step 5: by analog simulation, set up Sample Storehouse with three-phase voltage wavelet singular entropy, and set up based on this
SVM fault type discrimination model.
Further, when carrying out described step 1, data prediction includes that fault characteristic value is chosen, built network associate square
Battle array and area difference process.The present invention chooses electric current and power two kinds of electric characteristic amount carries out fault location；Data
Merge and build the multi-dimensional state monitoring matrix comprising multiple electric characteristic amount exactly.
Further, when carrying out described step 2, utilize Multidimensional Scaling that dimensional state monitoring matrix W is carried out dimensionality reduction.
First calculate the Euclidean distance between the dimensional state monitoring each object of matrix, form the similarity matrix of each node；And according to phase
Product matrix in different degree matrix calculus centralization；Solve the first two characteristic root of center internalization product matrix and the orthogonalization feature of correspondence
Vector x (1), x (2), finally make M=(x (1), x (2)), M be the expression at two-dimensional space of the dimensional state monitoring matrix W.
Further, when carrying out described step 2, low-dimensional status monitoring matrix M is carried out outlier detection analysis.First calculate
The K distance of each node in M, K distance definition is the distance of each node and the node nearest away from it.Calculate the K neighborhood of each node again
And the local reach distance of each node.Calculate the local outlier factor of each node the most respectively.
Further, when carrying out described step 4, after three-phase voltage is carried out wavelet transformation, matrix of wavelet coefficients A is entered again
Row singular value decomposition, i.e. A=USVT, in formula, U and V is respectively m rank and n rank orthogonal matrix, and S divides broad sense diagonal matrix, its diagonal angle
Element arranges in descending order；Combining information entropy theory, is processed into a probability distribution the diagonal matrix after singular value decomposition,
And calculate three-phase voltage wavelet singular entropy, computing formula is:In formula, k and L is
Diagonal element number, λiAnd λjDiagonal element for broad sense diagonal matrix S.Owing to being difficult to faults letter close to the element of zero
Number feature, in order to reduce amount of calculation, the present invention chooses front 9 effective diagonal elements.The diagonal element of broad sense diagonal matrix S big
Little can the time-frequency distributions feature of faults signal well.
Further, when carrying out described step 5, the fault type choosing certain 10kV power distribution network difference circuit different sets up sample
This storehouse, and choose some samples as training set, different faults type is respectively taken 10 groups of samples.
The present invention is directed to intelligent power distribution network protection method and there is the easy misoperation of complexity, inaccurate coordination and protection device of adjusting
Etc. problem, it is proposed that the intelligent distribution network fault identification method that the detection of a kind of local outlier factor and support vector machine combine.
The present invention can carry out fault location according to the LOF value of each node, be not required to compare electric characteristic amount and judge, it is to avoid complexity
Adaptive setting；Wavelet singular entropy can distinguish the signal of different complexity compactly, therefore can identify the event under different faults
Barrier phase；Wavelet singular entropy according to three-phase voltage can accurate discriminating fault types.
Accompanying drawing explanation
Fig. 1 is that LOF Yu SVM fault location differentiates flow process with fault type；
Fig. 2 is certain 10kV power distribution network topological diagram containing distributed power source；
Fig. 3 is linear processes svm classifier schematic diagram；
Fig. 4 is region Z4 failure state monitoring matrix multi-dimentional scale visualization result figure；
Fig. 5 is region Z4 failure state monitoring matrix L OF analysis visualization result figure；
SVM failure modes result figure when Fig. 6 is region Z4 fault；
SVM failure modes knot relative error figure when Fig. 7 is region Z4 fault；
Fig. 8 is region Z5 failure state monitoring matrix multi-dimentional scale visualization result figure；
Fig. 9 is region Z5 failure state monitoring matrix L OF analysis visualization result figure；
SVM failure modes result figure when Figure 10 is region Z5 fault；
SVM failure modes knot relative error figure when Figure 11 is region Z5 fault；
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
And accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described.It should be noted that described reality
Executing example is only a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, this area is general
The every other embodiment that logical technical staff is obtained under not making creative work premise, broadly falls into present invention protection
Scope.
The detailed description of the invention of the present invention is described below in conjunction with the accompanying drawings.
Embodiment
In order to verify that the intelligence that a kind of local outlier factor detection proposed by the invention and support vector machine combine is joined
Data grid fault identification method, with certain the intelligent distribution network demonstration area domestic shown in Fig. 2, the 10kV power distribution network containing double DG is right for research
As, under MATLAB emulates, build this model, concrete handling process is as it is shown in figure 1, simulated domain 4 fault is single-phase earthing event
Barrier, region 5 fault is AB two-phase short-circuit fault.
Singlephase earth fault is analyzed
When feeder line section Z4 occurs A phase earth fault, and as shown in Figure 4,5, node 4,5 and generalized node 17 are away from other
Node, LOF value is about 90, and occurs outlier in multi-dimentional scale dimensionality reduction result figure, therefore can determine that region 4 is for faulty section
Territory.
SVM fault type differentiates result as shown in Figure 6,1,2,3 corresponding singlephase earth faults, respectively AG, BG, CG event
Barrier；4,5,6 corresponding alternate ground short circuit fault, respectively ABG, BCG, ACG fault；Different faults respectively takes ten groups of samples carry out
Training, abscissa 1 to 60 is corresponding training sample point, and 61 is sample to be tested, judges that 61 are classified as the first kind through SVM training, belongs to
In AG fault.As seen from Figure 7, failure modes relative error is within 0.1%.
Two-phase short-circuit fault is analyzed
When region bus nodes Z5 occurs AB two-phase short-circuit fault, Fig. 8, LOF value shown in 9 can be seen that, node 5,6,
9 and generalized node 17 away from other node, and LOF value is about 270, and occur in multi-dimentional scale dimensionality reduction result figure from
Group's point, therefore can determine that region 5 is fault zone.
SVM fault type differentiates as shown in Figure 10,1,2,3 corresponding two-phase short-circuit faults, respectively AB, BC, AC short circuit event
Barrier；4 corresponding three phase short circuit fault, for ABC short circuit；Different faults respectively taking ten groups of samples be trained, abscissa 1 to 40 is right
Answering training sample point, 41 is sample to be tested, judges that 41 are classified as the first kind through SVM training, belongs to AB short trouble.Such as Figure 11 institute
Showing, failure modes relative error is within 0.1%.
The present invention proposes the intelligent distribution network fault identification that the detection of a kind of local outlier factor combines with support vector machine
Method.First power distribution network mass data is carried out data prediction and data fusion, selects electric current and two electric characteristics of power
Amount, utilizes LOF local outlier factor detection method to position fault；Again the three-phase voltage at fault is carried out small echo change
Change, the matrix of wavelet coefficients after conversion is carried out SVD decomposition, utilizes information entropy theory, the diagonal matrix after decomposing is processed
Become a probability distribution, carry out the fault phase of identification three-phase voltage signal with the wavelet singular entropy of this sequence, and use residual voltage
Ground floor low frequency energy carries out preliminary classification to fault type；Finally the wavelet singular entropy with three-phase voltage is built for sample space
Vertical SVM failure modes model, in order to judge fault type.The effectiveness of the inventive method is demonstrated by simulation analysis.
The present invention can carry out fault location according to the LOF value of each node, is not required to compare electric characteristic amount and judges, keeps away
Exempt from the adaptive setting of complexity；Wavelet singular entropy can distinguish the signal of different complexity compactly, therefore can identify different event
Fault phase under Zhang；Wavelet singular entropy according to three-phase voltage can accurate discriminating fault types.
Claims (6)
1. an intelligent distribution network fault identification method, it is characterised in that including:
Step 1: WAMS is uploaded with target electric current time unified and power information data according to measuring protection device, logical
Cross data prediction and data fusion, electric current and power information data are processed into the multi-dimensional state comprising multiple electric characteristic amounts
Monitoring matrix；
Step 2: described multi-dimensional state monitoring matrix is carried out multi-dimentional scale dimensionality reduction and the detection of LOF local outlier factor, it is achieved intelligence
Can distribution network failure detection and location；
Step 3: three-phase voltage at fault zone carries out wavelet transformation, extracts the residual voltage ground floor low frequency at fault zone
Energy, presorts to fault type, and fault is divided into earth fault type and phase fault type；
Step 4: the coefficient matrix of wavelet transformation is carried out singular value decomposition, processes the diagonal matrix after singular value decomposition
Become probability distribution, and calculate three-phase voltage wavelet singular entropy；
Step 5: by analog simulation, set up Sample Storehouse with described three-phase voltage wavelet singular entropy, and with this Sample Storehouse as base
Plinth sets up SVM fault type discrimination model.
Intelligent distribution network fault identification method the most according to claim 1, it is characterised in that in step 1, data prediction
Choose including fault characteristic value, build network associate matrix and area difference process；Data fusion is to build to comprise multiple electricity
The multi-dimensional state monitoring matrix of gas characteristic quantity.
Intelligent distribution network fault identification method the most according to claim 1, it is characterised in that in step 2, utilizes multidimensional chi
Degree is analyzed and dimensional state monitoring matrix W is carried out dimensionality reduction: first calculate euclidean between the dimensional state monitoring each object of matrix away from
From, form the similarity matrix of each node；And according to product matrix in similarity matrix calculating centralization；Solve center internalization product moment
The first two characteristic root of battle array and the orthogonalized eigenvectors x (1) of correspondence, x (2), finally make low-dimensional status monitoring matrix M=(x
(1), x (2)), low-dimensional status monitoring matrix M is the expression at two-dimensional space of the dimensional state monitoring matrix W.
Intelligent distribution network fault identification method the most according to claim 3, it is characterised in that in step 2, LOF local is different
Constant factor detection method i.e. carries out outlier detection analysis to low-dimensional status monitoring matrix M: first calculate the K distance of each node in M,
K distance definition is the distance of each node and the node nearest away from it, then the local of the K neighborhood and each node calculating each node can
Reach distance, calculate the local outlier factor of each node the most respectively.
Intelligent distribution network fault identification method the most according to claim 1, it is characterised in that in step 4, to three-phase voltage
After carrying out wavelet transformation, matrix of wavelet coefficients A is carried out again singular value decomposition, i.e. A=USVT, in formula, U and V be respectively m rank and
N rank orthogonal matrix, S is broad sense diagonal matrix, and the diagonal element of S arranges in descending order；Combining information entropy theory, dividing through singular value
Diagonal matrix after solution is processed into a probability distribution, and calculates three-phase voltage wavelet singular entropy Mk, computing formula is:In formula, k and L is the diagonal element number of broad sense diagonal matrix S, λiAnd λjFor extensively
The diagonal element of justice diagonal matrix S.
Intelligent distribution network fault identification method the most according to claim 1, it is characterised in that in step 5, chooses 10kV and joins
The different fault type of electrical network difference circuit sets up Sample Storehouse, and chooses S sample as training set, each to different faults type
Take 10 groups of samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610503338.8A CN106249101A (en) | 2016-06-30 | 2016-06-30 | A kind of intelligent distribution network fault identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610503338.8A CN106249101A (en) | 2016-06-30 | 2016-06-30 | A kind of intelligent distribution network fault identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106249101A true CN106249101A (en) | 2016-12-21 |
Family
ID=57614047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610503338.8A Pending CN106249101A (en) | 2016-06-30 | 2016-06-30 | A kind of intelligent distribution network fault identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106249101A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107222169A (en) * | 2017-08-01 | 2017-09-29 | 河海大学常州校区 | A kind of photovoltaic array based on outlier detection is monitored and fault detection method in real time |
| CN107870893A (en) * | 2017-10-24 | 2018-04-03 | 顺特电气设备有限公司 | A kind of daily load similitude quantitative analysis method of intelligent transformer |
| CN108344904A (en) * | 2017-03-23 | 2018-07-31 | 长沙理工大学 | A kind of direct current cables malfunction monitoring and new method for identifying |
| CN109103991A (en) * | 2018-10-23 | 2018-12-28 | 国网陕西省电力公司铜川供电公司 | A kind of big data analysis method of intelligent distribution network |
| CN109241944A (en) * | 2018-09-07 | 2019-01-18 | 福州大学 | A kind of distribution network failure recognition methods based on improvement multi-category support vector machines |
| CN109342887A (en) * | 2018-11-22 | 2019-02-15 | 广州供电局有限公司 | Distribution network failure based on phasor measuring set unifies localization method and system |
| CN109406949A (en) * | 2018-12-14 | 2019-03-01 | 国网山东省电力公司电力科学研究院 | Power distribution network incipient fault detection method and device based on support vector machines |
| CN109711012A (en) * | 2018-12-14 | 2019-05-03 | 华北电力大学 | A kind of PMU single channel based on singular spectrum analysis loses the restoration methods of data |
| CN110648741A (en) * | 2018-06-27 | 2020-01-03 | 清华大学 | Method and device for identifying doctor with abnormal prescription based on local outlier factor |
| CN110991240A (en) * | 2019-10-31 | 2020-04-10 | 湖南世优电力科技股份有限公司 | Single-phase fault identification and classification method for low-voltage neutral point ungrounded system |
| CN111239549A (en) * | 2020-02-18 | 2020-06-05 | 国网信通亿力科技有限责任公司 | Power distribution fault rapid positioning method based on discrete wavelet transform |
| CN111505434A (en) * | 2020-04-10 | 2020-08-07 | 国网浙江余姚市供电有限公司 | Method for identifying fault hidden danger of low-voltage distribution meter box line and meter box |
| CN111579936A (en) * | 2020-06-30 | 2020-08-25 | 上海交通大学 | Positioning method and system suitable for arc light grounding fault |
| CN111965486A (en) * | 2020-08-07 | 2020-11-20 | 国网江苏省电力有限公司电力科学研究院 | Power distribution network fault identification method and system based on intelligent data fusion analysis |
| CN112083292A (en) * | 2020-10-26 | 2020-12-15 | 积成电子股份有限公司 | Power distribution network active fault studying and judging method based on multi-source non-sound information fusion |
| CN112114232A (en) * | 2020-09-22 | 2020-12-22 | 福州大学 | Monopole earth fault distance measuring method based on wavelet decomposition and DBN |
| CN112363012A (en) * | 2020-10-29 | 2021-02-12 | 国家电网有限公司 | Power grid fault early warning device and method |
| CN112462193A (en) * | 2020-11-05 | 2021-03-09 | 重庆邮电大学 | Power distribution network automatic reclosing judgment method based on real-time fault filtering data |
| CN112557819A (en) * | 2020-11-27 | 2021-03-26 | 广东电网有限责任公司肇庆供电局 | Active power distribution network fault identification method and system and computer readable storage medium |
| CN112578315A (en) * | 2020-11-26 | 2021-03-30 | 贵州电网有限责任公司 | Control loop disconnection fault judgment method based on matrix diagram |
| CN113030764A (en) * | 2021-03-04 | 2021-06-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN113125902A (en) * | 2021-04-19 | 2021-07-16 | 福州大学 | Direct current power distribution system fault detection method based on IEWT and IMDMF |
| CN113490857A (en) * | 2019-02-06 | 2021-10-08 | 利萨·德雷克塞迈尔有限责任公司 | Method and test device |
| CN113702760A (en) * | 2021-08-26 | 2021-11-26 | 济南大学 | Method and system for identifying transverse fault and ferromagnetic resonance state of distribution line |
| CN114142611A (en) * | 2021-11-30 | 2022-03-04 | 贵州电网有限责任公司 | Power distribution network intelligent measurement and control universal terminal based on open architecture and measurement and control method |
| CN115034337A (en) * | 2022-08-10 | 2022-09-09 | 江西科骏实业有限公司 | Method and device for identifying state of traction motor in rail transit vehicle and medium |
| CN115241901A (en) * | 2022-07-27 | 2022-10-25 | 天津大学 | Intelligent energy storage soft switch data driving voltage control method considering data quality |
| CN115510927A (en) * | 2021-06-03 | 2022-12-23 | 中国移动通信集团四川有限公司 | Fault detection method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907681A (en) * | 2010-07-15 | 2010-12-08 | 南京航空航天大学 | Analog circuit dynamic online failure diagnosing method based on GSD-SVDD |
| CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
| CN104614638A (en) * | 2014-12-24 | 2015-05-13 | 国家电网公司 | Grounding line selection method for small current system |
-
2016
- 2016-06-30 CN CN201610503338.8A patent/CN106249101A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907681A (en) * | 2010-07-15 | 2010-12-08 | 南京航空航天大学 | Analog circuit dynamic online failure diagnosing method based on GSD-SVDD |
| CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
| CN104614638A (en) * | 2014-12-24 | 2015-05-13 | 国家电网公司 | Grounding line selection method for small current system |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108344904A (en) * | 2017-03-23 | 2018-07-31 | 长沙理工大学 | A kind of direct current cables malfunction monitoring and new method for identifying |
| CN107222169A (en) * | 2017-08-01 | 2017-09-29 | 河海大学常州校区 | A kind of photovoltaic array based on outlier detection is monitored and fault detection method in real time |
| CN107870893A (en) * | 2017-10-24 | 2018-04-03 | 顺特电气设备有限公司 | A kind of daily load similitude quantitative analysis method of intelligent transformer |
| CN110648741A (en) * | 2018-06-27 | 2020-01-03 | 清华大学 | Method and device for identifying doctor with abnormal prescription based on local outlier factor |
| CN109241944A (en) * | 2018-09-07 | 2019-01-18 | 福州大学 | A kind of distribution network failure recognition methods based on improvement multi-category support vector machines |
| CN109103991B (en) * | 2018-10-23 | 2021-10-22 | 国网陕西省电力公司铜川供电公司 | Big data analysis method for intelligent power distribution network |
| CN109103991A (en) * | 2018-10-23 | 2018-12-28 | 国网陕西省电力公司铜川供电公司 | A kind of big data analysis method of intelligent distribution network |
| CN109342887A (en) * | 2018-11-22 | 2019-02-15 | 广州供电局有限公司 | Distribution network failure based on phasor measuring set unifies localization method and system |
| CN109406949A (en) * | 2018-12-14 | 2019-03-01 | 国网山东省电力公司电力科学研究院 | Power distribution network incipient fault detection method and device based on support vector machines |
| CN109711012A (en) * | 2018-12-14 | 2019-05-03 | 华北电力大学 | A kind of PMU single channel based on singular spectrum analysis loses the restoration methods of data |
| CN113490857B (en) * | 2019-02-06 | 2024-04-02 | 利萨·德雷克塞迈尔有限责任公司 | Method and test device |
| CN113490857A (en) * | 2019-02-06 | 2021-10-08 | 利萨·德雷克塞迈尔有限责任公司 | Method and test device |
| CN110991240A (en) * | 2019-10-31 | 2020-04-10 | 湖南世优电力科技股份有限公司 | Single-phase fault identification and classification method for low-voltage neutral point ungrounded system |
| CN110991240B (en) * | 2019-10-31 | 2023-06-09 | 湖南世优电力科技股份有限公司 | Single-phase fault identification and classification method for low-voltage neutral point ungrounded system |
| CN111239549A (en) * | 2020-02-18 | 2020-06-05 | 国网信通亿力科技有限责任公司 | Power distribution fault rapid positioning method based on discrete wavelet transform |
| CN111505434A (en) * | 2020-04-10 | 2020-08-07 | 国网浙江余姚市供电有限公司 | Method for identifying fault hidden danger of low-voltage distribution meter box line and meter box |
| CN111505434B (en) * | 2020-04-10 | 2022-03-22 | 国网浙江余姚市供电有限公司 | Method for identifying fault hidden danger of low-voltage distribution meter box line and meter box |
| CN111579936A (en) * | 2020-06-30 | 2020-08-25 | 上海交通大学 | Positioning method and system suitable for arc light grounding fault |
| CN111579936B (en) * | 2020-06-30 | 2021-12-03 | 上海交通大学 | Positioning method and system suitable for arc light grounding fault |
| CN111965486B (en) * | 2020-08-07 | 2023-12-15 | 国网江苏省电力有限公司电力科学研究院 | Power distribution network fault identification method and system based on intelligent data fusion analysis |
| CN111965486A (en) * | 2020-08-07 | 2020-11-20 | 国网江苏省电力有限公司电力科学研究院 | Power distribution network fault identification method and system based on intelligent data fusion analysis |
| CN112114232A (en) * | 2020-09-22 | 2020-12-22 | 福州大学 | Monopole earth fault distance measuring method based on wavelet decomposition and DBN |
| CN112083292B (en) * | 2020-10-26 | 2023-09-05 | 积成电子股份有限公司 | Active fault studying and judging method for power distribution network based on multisource non-robust information fusion |
| CN112083292A (en) * | 2020-10-26 | 2020-12-15 | 积成电子股份有限公司 | Power distribution network active fault studying and judging method based on multi-source non-sound information fusion |
| CN112363012A (en) * | 2020-10-29 | 2021-02-12 | 国家电网有限公司 | Power grid fault early warning device and method |
| CN112462193B (en) * | 2020-11-05 | 2023-10-24 | 重庆邮电大学 | Automatic reclosing judgment method for power distribution network based on real-time fault filtering data |
| CN112462193A (en) * | 2020-11-05 | 2021-03-09 | 重庆邮电大学 | Power distribution network automatic reclosing judgment method based on real-time fault filtering data |
| CN112578315B (en) * | 2020-11-26 | 2022-08-26 | 贵州电网有限责任公司 | Control loop disconnection fault judgment method based on matrix diagram |
| CN112578315A (en) * | 2020-11-26 | 2021-03-30 | 贵州电网有限责任公司 | Control loop disconnection fault judgment method based on matrix diagram |
| CN112557819A (en) * | 2020-11-27 | 2021-03-26 | 广东电网有限责任公司肇庆供电局 | Active power distribution network fault identification method and system and computer readable storage medium |
| CN113030764B (en) * | 2021-03-04 | 2022-01-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN113030764A (en) * | 2021-03-04 | 2021-06-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN113125902A (en) * | 2021-04-19 | 2021-07-16 | 福州大学 | Direct current power distribution system fault detection method based on IEWT and IMDMF |
| CN113125902B (en) * | 2021-04-19 | 2022-07-22 | 福州大学 | IEWT and IMDMF based fault detection method for direct current power distribution system |
| CN115510927B (en) * | 2021-06-03 | 2024-04-12 | 中国移动通信集团四川有限公司 | Fault detection method, device and equipment |
| CN115510927A (en) * | 2021-06-03 | 2022-12-23 | 中国移动通信集团四川有限公司 | Fault detection method, device and equipment |
| CN113702760A (en) * | 2021-08-26 | 2021-11-26 | 济南大学 | Method and system for identifying transverse fault and ferromagnetic resonance state of distribution line |
| CN113702760B (en) * | 2021-08-26 | 2023-08-25 | 济南大学 | Method and system for identifying transverse faults and ferromagnetic resonance states of distribution line |
| CN114142611A (en) * | 2021-11-30 | 2022-03-04 | 贵州电网有限责任公司 | Power distribution network intelligent measurement and control universal terminal based on open architecture and measurement and control method |
| CN115241901B (en) * | 2022-07-27 | 2023-06-20 | 天津大学 | Intelligent energy storage soft switch data driving voltage control method considering data quality |
| CN115241901A (en) * | 2022-07-27 | 2022-10-25 | 天津大学 | Intelligent energy storage soft switch data driving voltage control method considering data quality |
| CN115034337A (en) * | 2022-08-10 | 2022-09-09 | 江西科骏实业有限公司 | Method and device for identifying state of traction motor in rail transit vehicle and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106249101A (en) | A kind of intelligent distribution network fault identification method | |
| CN104753461B (en) | Method for diagnosing and classifying faults of photovoltaic power generation arrays on basis of particle swarm optimization support vector machines | |
| CN108120903B (en) | A kind of low-current single-phase earth fault line selection method based on pulse nerve membranous system | |
| CN108196165A (en) | Power grid abnormal state detection method based on sample covariance matrix maximum eigenvalue | |
| Ravikumar et al. | Application of support vector machines for fault diagnosis in power transmission system | |
| CN105322519B (en) | A kind of intelligent distribution network big data convergence analysis and method for monitoring operation states | |
| CN105425118A (en) | Multi-information fusion fault arc detection method and device | |
| CN106856322B (en) | A kind of flexible direct current power distribution network intelligent protection system based on neural network | |
| CN106777984A (en) | A kind of method that photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm | |
| CN104297628B (en) | The section fault detection of the power distribution network containing DG and localization method | |
| CN106707094A (en) | Classification recognition method of arc fault of low voltage power supply and distribution line | |
| CN106990325B (en) | Distribution small current grounding fault determination method based on mutation logic array | |
| CN109975661A (en) | A kind of electric transmission line fault detection method based on Spearman's correlation coefficient | |
| CN106127047A (en) | A kind of power system malicious data detection method based on Jensen Shannon distance | |
| CN110470937A (en) | Based on FEEMD Sample Entropy+neural network HVDC transmission system line fault and commutation failure method for diagnosing faults | |
| CN102930408B (en) | A kind of 750kV electric grid secondary equipment state appraisal procedure based on information fusion | |
| CN103311960A (en) | Method for dividing coherent stability regions of strong-connection power grids | |
| CN112083270A (en) | Wind power plant current collection line single-phase earth fault line selection method based on correlation coefficient | |
| CN106980051B (en) | A kind of intermittence tandem type fault electric arc recognition methods | |
| CN111062569A (en) | Low-current fault discrimination method based on BP neural network | |
| CN107462810A (en) | A kind of fault section location method suitable for active power distribution network | |
| Wu et al. | Transmission line fault cause identification method based on transient waveform image and MCNN-LSTM | |
| Yang et al. | Fast assessment of short-term voltage stability of AC/DC power grid based on CNN | |
| CN116054224A (en) | Quick evaluation method for commutation failure of multi-feed direct-current transmission system | |
| Zhengyi et al. | A lstm line selection method of single-phase ground fault based on big-data platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161221 |