CN106324429A - RS-IA data mining-based power distribution network fault locating method - Google Patents
RS-IA data mining-based power distribution network fault locating method Download PDFInfo
- Publication number
- CN106324429A CN106324429A CN201610631526.9A CN201610631526A CN106324429A CN 106324429 A CN106324429 A CN 106324429A CN 201610631526 A CN201610631526 A CN 201610631526A CN 106324429 A CN106324429 A CN 106324429A
- Authority
- CN
- China
- Prior art keywords
- fault
- decision
- distribution network
- attribute
- antibody
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an RS-IA data mining-based power distribution network fault locating method comprising the following steps: a power distribution network fault mining database is built; fault features are extracted, condition attributes and decision attributes of a corresponding object are determined, an input vector set is a condition attribute set, an output vector set is a decision attribute set, a fault mode set is converted into an RS decision table via set condition attributes and decision attributes, a problem of calculating reduction in the RS decision table is changed into a problem of calculating reduction with a minimum combination number in a discernible matrix, dependency of the decision attributes on the condition attributes can be calculated, an initial antibody group of an immunization algorithm is generated, a binary system is adopted for coding operation, optimal reduction obtained via the immunization algorithm is used, a fault locating rule is extracted from an optimal attribute reduction set, and power distribution network faults are located via the generated fault positioning rule. Fault tolerance performance of the RS-IA data mining-based power distribution network fault locating method can be improved.
Description
Technical field
The present invention relates to Fault Diagnosis for Electrical Equipment field, particularly belong to distribution network line fault localization method.
Background technology
Distribution network failure location is one of critical function of power distribution automation.When distribution is actual break down after, by therefore
Barrier positioning function can rapidly find out fault occur region, for isolated fault and recover as early as possible the power supply to user provide effectively finger
Lead, significant to improving power supply reliability.At present, join based on ca bin (FTU) reporting fault information
The analysis method of electric network fault location mainly has two classes: a class is that distribution network failure section judges and the unified matrix of isolation is calculated
Method, this diagnostic mode carries out fault location based on the information of perfecting, more tradition, and reliability is high, but higher to request memory and
Diagnose limited;Another kind of is the manual intelligent method for diagnosing faults risen in recent years, and correlation theory has specialist system, manually god
Warp, fuzzy theory, genetic algorithm and immune algorithm etc..Manual intelligent method for diagnosing faults can be based on non-sound fault letter
Breath carries out diagnosis location, has higher practicality and the most wide application prospect, its also much need technically into
The place of one step research.
China is scarcely out of swaddling-clothes about the research of power distribution network manual intelligent fault diagnosis at present, existing methodical appearance
Mistake, accuracy, rapidity still need to improve further and improve.The data mining technology that development in recent years is swift and violent can be asked for discovery
Topic rule is found solution and is preferably provided reference information." the power distribution network based on data mining model that Liao Zhiwei etc. deliver
Fault section diagnosis " apply based on the theoretical data mining (Data combined with genetic algorithm of rough set (Rough Sets, RS)
Mining, DM) model carry out acquisition information occur lose or distortion in the case of distribution network failure positioning analysis.Relatively send out
Existing, the accuracy of program level diagnosis far above conventional manual's neutral net (Artificial Neural Network,
ANN) model.But genetic algorithm is the most more absorbed in the situation of local optimum, converges on local optimum prematurely, has " precocious "
Shortcoming.
Summary of the invention
It is an object of the invention to, overcome the drawbacks described above of prior art, it is provided that one is the most simple and quick effectively, have more preferably
The electrical power distribution network fault location method of fault freedom.Technical scheme is as follows:
A kind of electrical power distribution network fault location method based on RS-IA data mining, comprises the following steps:
1) structure distribution network failure mining data storehouse: by occurring in acquisition information that a distortion information constructs fault mode
Collection, builds single distortion information trunk net fault location model that circuit element number does not waits, in advance as decision rules data
Storehouse;Failure mode information consists of: input vector is the out-of-limit information sequence of electric current of each switch, is opened from service entrance switch by each switch
Beginning is arranged in order, and the faulty electric current of switch before fault element circuit flows through, and " 1 " indicates that electric current gets over limited signal;Afterwards
Switch no current get over limited signal and represent with " 0 ";Output vector is the status switch of circuit element, and at circuit, malfunction is used
" 1 " represents;Normal condition represents with " 0 ";
2) extracting fault signature, determine conditional attribute and the decision attribute of corresponding object, wherein input vector collection is combined into bar
Part community set, and output vector set forms decision attribute set;
3) according to the most fixed conditional attribute and decision attribute, fault mode collection is converted into RS decision table;
4) problem asking for yojan from RS decision table is converted in differentiation matrix, asks for the yojan that number of combinations is minimum;
5) decision attribute degree of dependence to conditional attribute is calculated;
6) produce the initial antibodies group of immune algorithm and use binary system to encode;
7) calculate the affinity between antigen and antibody, take the inverse fitness function as antibody of affinity;Calculate
Antibody concentration in population;
8) according to affinity and concentration, antagonist promotes accordingly and suppresses;
9) affinity high in each antibody population, the antibody of low concentration are stored in data base and retain and constantly update;
10) carry out selecting, intersecting and mutation operation, form parent antibody population of future generation;
11) repetitive operation 7) to 10), to meeting end condition, obtain the yojan that number of combinations is minimum, i.e. utilize immune algorithm
The optimal yojan obtained;
12) extraction fault location rule is concentrated from best attributes yojan;
13) Distribution Network Failure section location is carried out according to the fault location rule generated.
The present invention, on existing Research foundation, overcomes the most methodical deficiency, proposes a kind of based on RS-IA data mining
Electrical power distribution network fault location method, the method achieve FTU running environment compared with severe, components and parts are impaired or information dropout etc. is led
Cause the distribution network failure location in the case of fault message variation, solve well and cause because distribution obtains the distortion of information
Fault location erroneous judgement problem.Compared with genetic algorithm, immune algorithm is more excellent to the yojan performance of rough set, based on RS-IA data
Excavate electrical power distribution network fault location method than method based on RS-GA compare the most simple and quick effectively, there is more preferable fault-tolerance
Energy.
Accompanying drawing explanation
Fig. 1 is three power supply looped network open loop operation power distribution network in the embodiment of the present invention.
Fig. 2 is single trunk net in the embodiment of the present invention.
Fig. 3 is the immune algorithm convergence curve in the embodiment of the present invention.
Fig. 4 is the simple flow figure of the present invention.
Detailed description of the invention
In order to be illustrated more clearly that the present invention, below in conjunction with embodiment and accompanying drawing, the present invention is further illustrated.
The present invention emulates with the single failure supposed, with typical 3 power supply looped network open loop operation power distribution networks
As a example by, as shown in Figure 1.Figure has 3 choppers, 2 interconnection switches, 16 block switches, 19 corresponding 19 location of feeder line
Section.With chopper for mark, 3 stand-alone power distribution regions can be divided into interconnection switch for boundary.
Distribution fault localization method based on RS-IA data mining carries out comprehensive simulation to distribution.According to DM fault mode
Structure principle, the basic fault sample mode of this circuit should be 11 (10 line fault and without circuit fault mode), therefore
Barrier sample input vector is made up of 10 elements.Consider to be likely to occur the principle of an element distortion, each basic fault pattern
10 variation mode can be derived, have 110 patterns.
Utilization IA concentrates at broad sense fault mode and carries out global optimization search, asks for the best attributes yojan of RS, its tool
Body algorithm flow is as follows.Wherein, N is antibody population scale, and m is immunological memory storehouse size, and n is antibody length, and Tac1 is immunity choosing
Selecting setting threshold value, MAX is the end condition that maximum iteration time, i.e. algorithm terminate.
1) decision attribute D degree of dependence K to conditional attribute C is calculatedC.OrderRemove certain single attribute successively
A ∈ C, if Kc-a≠Kc, then Core (C)=Core (C) ∪ a, i.e. core is Core (C).If KCore=KC, then Core is best attributes
Yojan, otherwise steps performed 2).
2) initial antibodies group and coding thereof are produced.The present invention uses binary coding mode, and the i.e. condition of the length of antibody belongs to
Property C number, each gene of antibody represents the choice state of respective conditions attribute, 1 represent yojan time select this condition to belong to
Property, this conditional attribute is cast out in 0 expression.During initialization, the conditional attribute correspondence position in core takes 1, and remaining position takes 0 or 1 at random.Antibody
The form of expression be [011 ... 01], the scale that thus produces is the initial antibodies group of N.
3) affinity is calculated.Affinity between antigen and antibody represents the feasible solution satisfaction degree to problem, affinity
The highest, Xie Yuehao is described.The inverse that affinity function is fitness function that the present invention chooses, fitness function such as following formula:
In formula, n is the number of conditional attribute;lvIt is the number of " 1 " in antibody, the namely conditional attribute after yojan
Number;α is regulatory factor;K is the decision attribute degree of dependence to conditional attribute.
4) calculating antibody concentration.First calculating the affinity between two antibody, formula is as follows:
Wherein, differvwIt is the bond strength between two antibody, the number that i.e. same position gene code value is different.
Then antibody V concentration in population is:
5) promotion of antibody and suppression.For ensureing the multiformity of antibody, the antibody concentration that affinity is big improves, but crosses higher position
Can be suppressed, otherwise improve generation and the select probability of low concentration antibody accordingly.
6) data base is updated.S antibody of affinity high in each antibody population, low concentration is stored in data base and retains also
Constantly update.
7) carry out selecting, intersecting and mutation operation, form parent antibody population of future generation.
8) meet end condition then to terminate, export result;Otherwise turn 3).
The present embodiment data base capacity takes 30, and population scale is 60, crossover probability pc=0.5, mutation probability pm=0.05,
Concentration threshold takes 0.7.The maximum of algorithm iteration number of times is set to 150.Fault location best attributes yojan obtained by excavation is such as
Table 1.
Table 1 fault location correlation analysis best attributes yojan
In order to enable the essence clearly illustrating to study a question, extract from all emulation one have 10 circuits, 9 points
The trunk net of Duan Kaiguan, wherein has an instantiation during line failure to describe.As in figure 2 it is shown, wherein a, b ...
J is circuit, S1, S2 ... S9 is block switch.
As a example by circuit b breaks down, IA method is utilized to ask for the convergence curve of the optimal yojan of RS as shown in Figure 3.
The distribution network failure pattern obtained based on RS-IA data mining Fault Locating Method and the diagnostic result such as table of formation
Shown in 2.Wherein, input element marks * for distortion information position, output element marks the element for misjudgement of #.
Table 2 line fault pattern
As shown in Table 2, it is very sensitive to the distortion of information, without fault-tolerant ability, pole that conventional electric current gets over limited signal diagnostic method
It is easily caused the erroneous judgement of fault, misjudgement.The distribution fault localization method based on RS-IA data mining that the present invention proposes has higher
Fault-tolerant ability, can accurately realize the fault location of power distribution network in most cases.
In order to verify the superiority of the carried model of the present invention, the DA model that RS-IA model is combined with based on RS with GA
Method contrasts, and has worked out distribution fault finder based on two kinds of models with MATLAB, has carried out trunk net shown in Fig. 2
Its fault location of the Realization of Simulation.Two kinds of algorithm basic setups are identical, and the maximum iteration time of algorithm all takes 150 times, test result
As shown in table 3.
Table 3 attribute reduction experimental result
As shown in Table 3, in the case of identical setting, RS-IA model can preferably try to achieve best attributes yojan, Er Qieshou
Hold back speed.And IA algorithm is after introducing concentration mechanism, it is possible to the generation of the solution of higher concentration in Restrainable algorithms, prevent algorithm
Converge on local optimum prematurely, the shortcoming effectively overcoming genetic algorithm " precocious ", both improve efficiency, made again accuracy rate
Promote.This embodiment proves to be capable of the distribution under fault message mistake or distortion state by the method for the invention
Net fault location.
Fig. 4 is the simple flow figure of the present invention.Below technical scheme is done and sums up:
1) according to previous experiences and fault relevant information, distribution network failure mining data storehouse is constructed.In view of from FTU's
Fault message is easily lost or makes a variation, and the present invention is by occurring in acquisition information that a distortion information constructs fault mode collection, in advance
First build single distortion information trunk net fault location model that circuit element number does not waits, as decision rules data base.Therefore
Barrier pattern information consists of: inputs the electric current for each switch (including chopper, block switch, interconnection switch etc.) and gets over limit information sequence
Row.Start to be arranged in order from service entrance switch (power supply) by each switch, the switch faulty electric current stream before fault element circuit
Crossing, " 1 " indicates that electric current gets over limited signal;Switch no current afterwards is got over limited signal and is represented with " 0 ".It is output as the shape of circuit element
State sequence, at circuit, malfunction represents with " 1 ";Normal condition represents with " 0 ".
2) extract fault signature, determine conditional attribute and the decision attribute of corresponding object.Wherein input vector collection is combined into bar
Part community set, and output vector set forms decision attribute set.
3) according to the most fixed conditional attribute and decision attribute, fault mode set is converted into RS decision table.
4) problem asking for yojan from decision table is converted in differentiation matrix, asks for the yojan that number of combinations is minimum.
5) the decision attribute D degree of dependence to conditional attribute C is calculated.
6) produce the initial antibodies group of immune algorithm and use binary system to encode.
7) calculate the affinity between antigen and antibody, take the inverse fitness function as antibody of affinity;Calculate
Antibody concentration in population.
8) according to affinity and concentration, antagonist promotes accordingly and suppresses.
9) affinity high in each antibody population, the antibody of low concentration are stored in data base and retain and constantly update.
10) carry out selecting, intersecting and mutation operation, form parent antibody population of future generation.
11) repetitive operation 7) to 10), to meeting end condition, obtain the yojan that number of combinations is minimum, i.e. utilize immune algorithm
The optimal yojan obtained.
12) extraction diagnosis rule is concentrated from best attributes yojan.
13) Distribution Network Failure section location is carried out according to the fault location rule generated.
After distribution is broken down, it is installed on the FTU at each switch and fault current detected, with predetermined fault current definite value
Form discrete fault message more afterwards.After the fault alarm information collected as FTU is uploaded to control main website, can basis
The decision rules that RS-IA data mining model obtains, analyzes block switch electric current and gets over the pass between limit information and faulty line position
System, finds out this block switch electric current and gets over the line fault conditions corresponding to limit information, thus carrying out distribution network failure circuit just
Determine position.
The above, only presently preferred embodiments of the present invention, it is not intended to limit protection scope of the present invention.
Claims (1)
1. an electrical power distribution network fault location method based on RS-IA data mining, comprises the following steps:
1) structure distribution network failure mining data storehouse: by occurring in acquisition information that a distortion information constructs fault mode collection,
Build single distortion information trunk net fault location model that circuit element number does not waits in advance, as decision rules data base;
Failure mode information consists of: input vector is the out-of-limit information sequence of electric current of each switch, by each switch from the beginning of service entrance switch
Being arranged in order, the faulty electric current of switch before fault element circuit flows through, and " 1 " indicates that electric current gets over limited signal;Afterwards
Switch no current is got over limited signal and is represented with " 0 ";Output vector is the status switch of circuit element, and at circuit, malfunction uses " 1 "
Represent;Normal condition represents with " 0 ";
2) extracting fault signature, determine conditional attribute and the decision attribute of corresponding object, wherein input vector collection is combined into condition genus
Property set, and output vector set formed decision attribute set;
3) according to the most fixed conditional attribute and decision attribute, fault mode collection is converted into RS decision table;
4) problem asking for yojan from RS decision table is converted in differentiation matrix, asks for the yojan that number of combinations is minimum;
5) decision attribute degree of dependence to conditional attribute is calculated;
6) produce the initial antibodies group of immune algorithm and use binary system to encode;
7) calculate the affinity between antigen and antibody, take the inverse fitness function as antibody of affinity;Calculating antibody
Concentration in population;
8) according to affinity and concentration, antagonist promotes accordingly and suppresses;
9) affinity high in each antibody population, the antibody of low concentration are stored in data base and retain and constantly update;
10) carry out selecting, intersecting and mutation operation, form parent antibody population of future generation;
11) repetitive operation 7) to 10), to meeting end condition, obtain the yojan that number of combinations is minimum, i.e. utilize immune algorithm to obtain
Optimal yojan;
12) extraction fault location rule is concentrated from best attributes yojan;
13) Distribution Network Failure section location is carried out according to the fault location rule generated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610631526.9A CN106324429B (en) | 2016-08-02 | 2016-08-02 | Power distribution network fault positioning method based on RS-IA data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610631526.9A CN106324429B (en) | 2016-08-02 | 2016-08-02 | Power distribution network fault positioning method based on RS-IA data mining |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106324429A true CN106324429A (en) | 2017-01-11 |
CN106324429B CN106324429B (en) | 2023-06-02 |
Family
ID=57740710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610631526.9A Active CN106324429B (en) | 2016-08-02 | 2016-08-02 | Power distribution network fault positioning method based on RS-IA data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106324429B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106841927A (en) * | 2017-03-17 | 2017-06-13 | 国网江苏省电力公司宿迁供电公司 | Fault Locating Method containing distributed power distribution network |
CN107579844A (en) * | 2017-08-18 | 2018-01-12 | 北京航空航天大学 | It is a kind of that failure method for digging is dynamically associated based on service path and frequency matrix |
CN107861026A (en) * | 2017-11-02 | 2018-03-30 | 湖北工业大学 | A kind of electrical power distribution network fault location method based on hybrid artificial immune system |
CN108649575A (en) * | 2018-06-19 | 2018-10-12 | 清华大学 | Alternating current-direct current mixing micro-capacitance sensor and its protection control centre and protection control method |
CN108693771A (en) * | 2017-04-10 | 2018-10-23 | 南京理工大学 | A kind of distribution network failure section location algorithm based on Multiple-population Genetic Algorithm |
CN109490704A (en) * | 2018-10-16 | 2019-03-19 | 河海大学 | A kind of Fault Section Location of Distribution Network based on random forests algorithm |
US11616390B2 (en) | 2018-06-19 | 2023-03-28 | Tsinghua University | Micro-grid reconstruction method and device, micro-grid protection control center, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488802A (en) * | 2013-10-16 | 2014-01-01 | 国家电网公司 | EHV (Extra-High Voltage) power grid fault rule mining method based on rough set association rule |
CN104598968A (en) * | 2014-10-13 | 2015-05-06 | 芜湖扬宇机电技术开发有限公司 | Fault diagnosis method of transformer |
CN104731966A (en) * | 2015-04-07 | 2015-06-24 | 河海大学 | Subway fault diagnosis method based on data mining |
CN104931857A (en) * | 2015-06-25 | 2015-09-23 | 山东大学 | Power distribution network fault locating method based on D-S evidence theory |
-
2016
- 2016-08-02 CN CN201610631526.9A patent/CN106324429B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488802A (en) * | 2013-10-16 | 2014-01-01 | 国家电网公司 | EHV (Extra-High Voltage) power grid fault rule mining method based on rough set association rule |
CN104598968A (en) * | 2014-10-13 | 2015-05-06 | 芜湖扬宇机电技术开发有限公司 | Fault diagnosis method of transformer |
CN104731966A (en) * | 2015-04-07 | 2015-06-24 | 河海大学 | Subway fault diagnosis method based on data mining |
CN104931857A (en) * | 2015-06-25 | 2015-09-23 | 山东大学 | Power distribution network fault locating method based on D-S evidence theory |
Non-Patent Citations (2)
Title |
---|
郭壮志;徐其兴;洪俊杰;孟安波;毛晓明;陈华;: "配电网故障区段定位的互补约束新模型与算法", 中国电机工程学报 * |
郭壮志;徐其兴;洪俊杰;毛晓明;: "配电网快速高容错性故障定位的线性整数规划方法", 中国电机工程学报 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106841927A (en) * | 2017-03-17 | 2017-06-13 | 国网江苏省电力公司宿迁供电公司 | Fault Locating Method containing distributed power distribution network |
CN106841927B (en) * | 2017-03-17 | 2019-05-31 | 国网江苏省电力公司宿迁供电公司 | Fault Locating Method containing distributed power distribution network |
CN108693771A (en) * | 2017-04-10 | 2018-10-23 | 南京理工大学 | A kind of distribution network failure section location algorithm based on Multiple-population Genetic Algorithm |
CN107579844A (en) * | 2017-08-18 | 2018-01-12 | 北京航空航天大学 | It is a kind of that failure method for digging is dynamically associated based on service path and frequency matrix |
CN107861026A (en) * | 2017-11-02 | 2018-03-30 | 湖北工业大学 | A kind of electrical power distribution network fault location method based on hybrid artificial immune system |
CN107861026B (en) * | 2017-11-02 | 2019-11-08 | 湖北工业大学 | A kind of electrical power distribution network fault location method based on hybrid artificial immune system |
CN108649575A (en) * | 2018-06-19 | 2018-10-12 | 清华大学 | Alternating current-direct current mixing micro-capacitance sensor and its protection control centre and protection control method |
US11616390B2 (en) | 2018-06-19 | 2023-03-28 | Tsinghua University | Micro-grid reconstruction method and device, micro-grid protection control center, and storage medium |
CN109490704A (en) * | 2018-10-16 | 2019-03-19 | 河海大学 | A kind of Fault Section Location of Distribution Network based on random forests algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN106324429B (en) | 2023-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106324429A (en) | RS-IA data mining-based power distribution network fault locating method | |
Lin et al. | A fault diagnosis method of power systems based on improved objective function and genetic algorithm-tabu search | |
CN106443297B (en) | The decision tree SVM method for diagnosing faults of photovoltaic diode Clamp three-level inverter | |
CN108037414B (en) | A kind of electrical power distribution network fault location method based on hierarchical mode and intelligent checking algorithm | |
CN103336243B (en) | Based on the circuit breaker failure diagnostic method of divide-shut brake coil current signal | |
CN105785231B (en) | A kind of linear integer programming method of the online fault tolerance positioning of power distribution network | |
CN101478534B (en) | Network exception detecting method based on artificial immunity principle | |
CN109270442A (en) | High-voltage circuitbreaker fault detection method based on DBN-GA neural network | |
CN110398348A (en) | Memory, Mechanical Failure of HV Circuit Breaker diagnostic method and device | |
CN107271852B (en) | Complicated Distribution Network Fault Locating Method based on voltage dip information | |
CN108693771A (en) | A kind of distribution network failure section location algorithm based on Multiple-population Genetic Algorithm | |
CN111413565B (en) | Intelligent power grid fault diagnosis method capable of identifying and measuring tampering attack | |
CN105067956A (en) | Anti-colony-algorithm-based distribution network fault positioning method | |
CN103840967A (en) | Method for locating faults in power communication network | |
CN109633370A (en) | A kind of electric network failure diagnosis method based on fault message coding and fusion method | |
Qu et al. | False data injection attack detection in power systems based on cyber-physical attack genes | |
CN110535878A (en) | A kind of threat detection method based on sequence of events | |
CN109557414A (en) | Integrated power system fault diagnosis alarming processing system and method | |
CN107450016A (en) | Fault Diagnosis for HV Circuit Breakers method based on RST CNN | |
CN109474067A (en) | A kind of dispatching of power netwoks troubleshooting aid decision-making method | |
CN109768877A (en) | A kind of electric network failure diagnosis method based on space optimum code collection and DHNN error correction | |
CN109782124A (en) | A kind of main adapted integration Fault Locating Method and system based on gradient descent algorithm | |
CN102802182A (en) | Fault diagnosis device and method for wireless sensor network | |
CN109001596A (en) | A kind of electric network failure diagnosis and transmission line parameter identification system | |
CN106483425A (en) | The method for diagnosing faults of pulse nerve membranous system based on Triangular Fuzzy Number and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |