CN103871003A - Power distribution network fault diagnosis method utilizing historical fault data - Google Patents

Power distribution network fault diagnosis method utilizing historical fault data Download PDF

Info

Publication number
CN103871003A
CN103871003A CN201410125125.7A CN201410125125A CN103871003A CN 103871003 A CN103871003 A CN 103871003A CN 201410125125 A CN201410125125 A CN 201410125125A CN 103871003 A CN103871003 A CN 103871003A
Authority
CN
China
Prior art keywords
fault
collection
item
data
distribution network
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
Application number
CN201410125125.7A
Other languages
Chinese (zh)
Inventor
李天友
陈青
王庆华
陈金祥
陈敏维
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Shandong University
Electric Power Research Institute of State Grid Fujian Electric Power Co Ltd
State Grid Fujian Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Shandong University
Electric Power Research Institute of State Grid Fujian Electric Power Co Ltd
State Grid Fujian Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Shandong University, Electric Power Research Institute of State Grid Fujian Electric Power Co Ltd, State Grid Fujian Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201410125125.7A priority Critical patent/CN103871003A/en
Publication of CN103871003A publication Critical patent/CN103871003A/en
Pending legal-status Critical Current

Links

Classifications

    • YGENERAL 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
    • Y04INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04SSYSTEMS 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
    • Y04S10/00Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention relates to a power distribution network fault diagnosis method utilizing historical fault data. The method comprises the following steps: firstly, a fault information database is established from power distribution network fault rescue records, fault attributes contained in the fault information database are determined; then, the data format of the fault attributes is made to conform to the standard, and fault attribute data in the fault information database are discretized; an association rule mining method is used for mining a strong association rule contained in the fault attribute data in the fault information database; finally, according to actual conditions of a fault and the mined strong association rule, a diagnosis result of the power distribution network fault is obtained. The power distribution network fault diagnosis method utilizing the historical fault data is beneficial for improving safe operation of a power distribution network, and is high in reliability; besides, the power distribution network fault diagnosis method has the advantages of being wide in application rage, flexible to apply, and capable of being operated off line, and being influenced by the distribution network automation degree to a low extent, and the like, thereby providing a good basis for power distribution network fault diagnosis and state evaluation.

Description

A kind of Fault Diagnosis Method for Distribution Networks of applicating history fault data
Technical field
The present invention relates to a kind of Fault Diagnosis Method for Distribution Networks of applicating history fault data, when relating in particular to power distribution network and breaking down, electrical power distribution automatization system cannot provide the method for diagnosing faults, particularly a kind of Fault Diagnosis Method for Distribution Networks of applicating history fault data of accurate monitoring result due to hardware, software or communication failure.
Background technology
Compared with power transmission network, distribution net work structure complexity, the fault diagnosis technology of power distribution network is mainly the operation of power networks status information providing according to automated systems such as electricity consumption acquisition system, monitoring system of distribution transformer, data acquisition and supervisor controls at present.These automated systems mainly comprise hardware components, software section and communications portion, in the time that arbitrary part breaks down in system, just cannot make accurate judgement to the running status of power distribution network.Especially in the time that power distribution network breaks down, hardware components and the communications portion of automated system also very likely break down, now automated system cannot provide failure condition accurately to maintainer, this just makes maintainer cannot recover in time the electric power supply of fault zone, reduce the reliability of mains supply, affected power consumer and produced normally, live.
The fault diagnosis technology of electric system comparative maturity has expert system, artificial neural network, petri net, rough set theory, fuzzy theory, Bayesian network etc. at present, and these methods are all the method for diagnosing faults at power transmission network field comparative maturity.Because network topology, the power equipment etc. of power distribution network have very big difference with power transmission network, these method for diagnosing faults all cannot be applied directly in power distribution network.And these method for diagnosing faults mostly depend on the operation of power networks status information that automated system provides, in the time that automated system breaks down, also cannot provide fault diagnosis result.
Existing Fault Diagnosis Method for Distribution Networks all depends on the monitoring of equipment information that power distribution automation equipment provides, and in the situation that lacking monitoring of equipment information, cannot provide fault diagnosis result.The accuracy of existing method diagnostic result also depends on the accuracy of obtained power distribution network Monitoring Data, in the time that mistake appears in power distribution network monitoring information, can produce wrong fault diagnosis result.Current diagnostic method cannot provide concrete failure cause, is mostly the diagnosis to fault type and abort situation.The present invention utilizes power distribution network historical failure data to carry out fault diagnosis, can under off-line case, provide diagnostic result, and also can provide correct diagnostic result in the situation that a small amount of mistake appears in fault data.And the present invention can pass through the analysis to historical data, and in conjunction with real time status, size to the failure cause that may occur and various failure cause possibilities is made diagnosis, this fixes a breakdown in time for maintainer, recover customer power supply, raising distribution network reliability all tool is of great significance.
Summary of the invention
The object of the present invention is to provide one to have applied widely, applying flexible, off-line operation, is subject to distribution network automated degree to affect the advantages such as little, and has the Fault Diagnosis Method for Distribution Networks of the applicating history fault data of higher reliability.
For achieving the above object, technical scheme of the present invention is: a kind of Fault Diagnosis Method for Distribution Networks of applicating history fault data, comprise the steps,
Step S01: set up failure information database by distribution network failure repairing record, and determine the fault attribute comprising in this failure information database;
Step S02: the data layout of standard fault attribute, by the fault attribute Data Discretization in failure information database;
Step S03: association rule digging method excavates the Strong association rule that the fault attribute data in failure information database comprise;
Step S04: according to the actual conditions of fault, according to the Strong association rule of above-mentioned excavation, distribution network failure situation is provided to diagnostic result.
In embodiments of the present invention, described step S02, specific implementation process is as follows,
Step S21: determine the also data layout of the each fault attribute of standard;
Step S22: the fault attribute data in failure information database are carried out to wide splitting, and this discretize process is specially,
The minimum value of setting fault duration is , maximal value is , according to formula: , obtain discontinuous point: ;
Wherein, δ is discrete width, and k is discrete counting.
In embodiments of the present invention, described step S03, is specially,
Utilize the Apriori algorithm in correlation rule to carry out association rule mining to the fault attribute data in failure information database; Carrying out before association rule mining, quantification type data need to be changed into Boolean type data, concrete conversion method is:
An if collection the set of item, value be quantized value, wherein, m is integer, and m=1,2,3 Quantitative Association Rule to be changed into Boolean Association Rules, form new item collection , need by each value after discretize and a collection in item corresponding;
Then the fault attribute data in failure information database are carried out to association rule mining, Apriori algorithm is topmost Boolean type frequent item set association rules mining algorithm; Apriori algorithm is to search for frequent item set by the mode of iterative search; First, search out the set of frequent 1-item collection , then by search , until the frequent item set of search is empty, till can not continuing search, wherein, for integer, =2,3 ..., n; The generation of this frequent item set mainly divides and connects and two steps of beta pruning:
Connect step: pass through be connected the set that produces candidate k-item collection with oneself, method of attachment , in item collection interconnect the set that generates candidate k-item collection ; In connection procedure, require the item collection connecting to share k-1;
Beta pruning step: in the set that connects step acquisition candidate after, determine frequently according to following formula the set an of-collection ,
Suppose a collection be a subset, at database in support Support refer to in comprise number of transactions with the percent value of middle affairs sum,
For item collection with transaction database , frequent item set refers to that support is not less than specified minimum support Min_support's nonvoid subset; Judge a collection for the condition of frequent item set is
But in this process, if very large, will need a large amount of calculating to obtain , can be by for reducing calculated amount in item collection ( )-subset does not exist in candidate -collection is deleted; Because according to Apriori character, all non-frequent ( a)-collection can not be frequent the subset of item collection, namely in all collection ( )-subset is all comprised in in;
Wherein, Apriori character: all nonvoid subsets of frequent item set must be all frequently; Frequent item set meets the item collection of minimum support; for frequent k-item collection.
In embodiments of the present invention, described correlation rule, is mainly divided into Boolean Association Rules and Quantitative Association Rule two classes, and when the property value that will excavate is 0 or 1, while being discrete value, correlation rule is boolean association rule; In the time that the property value that will excavate is quantized value, correlation rule is quantification type correlation rule.
Described Apriori algorithm belongs to boolean association rule mining algorithm.
Compared to prior art, the present invention has following beneficial effect:
1, the data source that the present invention utilizes is a large amount of fault handling data that produce in power distribution network operational process, these data are rough expression of distribution monitoring system data, comprise equally the information such as time of failure, the position of fault, equipment/circuit types, failure cause; Therefore, analyze these space-time datas, and excavate its internal association relation, the safe operation to power distribution network and management have important practical significance;
2, the present invention utilizes association rule mining method to carry out Association Rule Analysis to distribution network failure deal with data, excavate the correlation rule wherein comprising, for Fault Diagnosis of Distribution Network provides foundation, can also make reliability assessment to the operation conditions of Distribution Network Equipment, the impact of external environment condition on power distribution network etc.;
3, the present invention have applied widely, applying flexible, off-line operation, is subject to distribution network automated degree to affect the advantages such as little, for Fault Diagnosis of Distribution Network and state estimation are had laid a good foundation.
Accompanying drawing explanation
Fig. 1 is the Fault Diagnosis Method for Distribution Networks process flow diagram of applicating history data of the present invention.
Embodiment
Below in conjunction with accompanying drawing, technical scheme of the present invention is specifically described.
The Fault Diagnosis Method for Distribution Networks of a kind of applicating history fault data of the present invention, comprises the steps,
Step S01: set up failure information database by distribution network failure repairing record, and determine the fault attribute comprising in this failure information database;
Step S02: the data layout of standard fault attribute, by the fault attribute Data Discretization in failure information database;
Step S03: association rule digging method excavates the Strong association rule that the fault attribute data in failure information database comprise;
Step S04: according to the actual conditions of fault, according to the Strong association rule of above-mentioned excavation, distribution network failure situation is provided to diagnostic result.
Described step S02, specific implementation process is as follows,
Step S21: determine the also data layout of the each fault attribute of standard;
Step S22: the fault attribute data in failure information database are carried out to wide splitting, and this discretize process is specially,
The minimum value of setting fault duration is , maximal value is , according to formula: , obtain discontinuous point: ;
Wherein, δ is discrete width, and k is discrete counting.
Described step S03, is specially,
Utilize the Apriori algorithm in correlation rule to carry out association rule mining to the fault attribute data in failure information database; Carrying out before association rule mining, quantification type data need to be changed into Boolean type data, concrete conversion method is:
An if collection the set of item, value be quantized value, wherein, m is integer, and m=1,2,3 Quantitative Association Rule to be changed into Boolean Association Rules, form new item collection , need by each value after discretize and a collection in item corresponding;
Then the fault attribute data in failure information database are carried out to association rule mining, Apriori algorithm is topmost Boolean type frequent item set association rules mining algorithm; Apriori algorithm is to search for frequent item set by the mode of iterative search; First, search out the set of frequent 1-item collection , then by search , until the frequent item set of search is empty, till can not continuing search, wherein, for integer, =2,3 ..., n; The generation of this frequent item set mainly divides and connects and two steps of beta pruning:
Connect step: pass through be connected the set that produces candidate k-item collection with oneself, method of attachment , in item collection interconnect the set that generates candidate k-item collection ; In connection procedure, require the item collection connecting to share k-1;
Beta pruning step: in the set that connects step acquisition candidate after, determine frequently according to following formula the set an of-collection ,
Suppose a collection be a subset, at database in support Support refer to in comprise number of transactions with the percent value of middle affairs sum,
For item collection with transaction database , frequent item set refers to that support is not less than specified minimum support Min_support's nonvoid subset; Judge a collection for the condition of frequent item set is
But in this process, if very large, will need a large amount of calculating to obtain , can be by for reducing calculated amount in item collection ( )-subset does not exist in candidate -collection is deleted; Because according to Apriori character, all non-frequent ( a)-collection can not be frequent the subset of item collection, namely in all collection ( )-subset is all comprised in in;
Wherein, Apriori character: all nonvoid subsets of frequent item set must be all frequently; Frequent item set meets the item collection of minimum support; for frequent k-item collection.
Described correlation rule, is mainly divided into Boolean Association Rules and Quantitative Association Rule two classes, and when the property value that will excavate is 0 or 1, while being discrete value, correlation rule is boolean association rule; In the time that the property value that will excavate is quantized value, correlation rule is quantification type correlation rule; Described Apriori algorithm belongs to boolean association rule mining algorithm.
For allowing those skilled in the art more understand the inventive method, the following stated is specific embodiments of the invention.
As shown in Figure 1, a kind of Fault Diagnosis Method for Distribution Networks of applicating history fault data, concrete steps are:
Step 1: form failure information database, the fault attribute comprising in specified data storehouse by distribution network failure repairing record.
The a large amount of fault handling data that produce in power distribution network operational process are rough expression of distribution monitoring system data, wherein comprise the information such as time of failure, the position of fault, fault element, failure cause.
The approach that distribution network failure information recording obtains mainly contains the automated systems such as monitoring system of distribution transformer, electricity consumption acquisition system, data acquisition and supervisor control, GPMS system; Whether the distribution network failure attribute obtaining by these automated systems mainly contains time of failure, fault element, element corresponding device type, affiliated transformer station, affiliated area under one's jurisdiction, region 1, region 2, power failure reason, fault type, is transient fault, fault current, fault impedance, fault phase angle etc.
The failure information database that the distribution network failure repairing record of different regions forms can only be applicable to local Fault Diagnosis of Distribution Network; In the time setting up failure information database, first want time and the spatial dimension in specified data source, the accuracy of its less important specified data, screen and delete misdata and repeating data in data, to guarantee the accuracy of next step data correlation rule digging result.
Step 2: standard fault attribute data layout, select suitable method, by the Data Discretization in failure information database.
1. determine the data layout of each fault attribute.
Time of failure:
Time of failure is the time of breaking down, time interocclusal record content comprise year, month, day, time minute, second.
Fault element:
According to the content of the configuration feature of power distribution network and breakdown repair record, the element that power distribution network may break down mainly contains shaft tower, wire, insulator, isolating switch, on-load switch, fuse, disconnector, lightning arrester, cable body, cable termination, cable intermediate joint, transformer body, high-voltage lead of transformer, transformer low voltage distribution facility etc.
Element corresponding device type:
The element difference that different device types comprises, the different corresponding device types in identity element installation site are also different, and the main equipment types under power distribution network element has overhead transmission line, cable line, switchyard (switching station), ring main unit, outdoor distribution transformer, switchgear building, distribution substation, transformer station, subscriber equipment.The element that each device type comprises is listed in table 1.
Affiliated transformer station:
Fault element corresponding device type place transformer station.
Affiliated area under one's jurisdiction:
The administrative area under one's jurisdiction at fault element corresponding device type place.
Region 1:
According to the regionalism of power distribution network power supply area, power distribution network power supply area is divided into midtown, urban district, cities and towns, rural area four classes.The specific classification standard in four class regions is listed in table 2.
Region 2:
According to the load density of power distribution network power supply area, be A+, A, B, C, D, E six classes by power distribution network division of the power supply area.The concrete criteria for classifying in six class regions is listed in table 3.
Power failure reason:
Power failure reason is mainly responsibility and the cause having a power failure for describing power distribution network.Main point facility construction, Equipment, operation maintenance, external force factor, weather conditions, customer impact, distributed power source affect several classes, and every class failure cause is specifically divided into again several detailed reasons.Concrete power failure causality classification situation is listed in table 4.
Fault type:
When power distribution network breaks down, whether main fault type has fault type, fault rank, is transient fault, fault current, fault impedance, fault phase angle etc.
Whether be transient fault:
The operating experience of electric system shows; overhead transmission line fault is mostly " instantaneity "; the insulator surface flashover, the large wind-induced short that are for example caused by thunder and lightning, touch arc short-circuit causing etc. by the thing such as birds, branch on wire; after the protected rapid disconnection of circuit; electric arc is horizontal blanking; the dielectric strength of trouble spot is recovered again, and external object is also burnt by electric arc and disappeared.If the line-breaker disconnecting is closed and just can recover normal power supply, this class fault is just called transient fault.If after circuit is disconnected, they still exist, and are permanent fault.
Fault current:
Fault current refers to the fault current value of utilizing record ripple monitoring equipment to monitor when fault occurs.
Fault impedance:
Fault impedance refer to utilize when fault occurs between fault phase wire that record ripple monitoring equipment monitors and ground or with several fault phase wires between the improper impedance being connected that occurs.
Fault phase angle:
Fault phase angle refers in the time that fault occurs by the phase differential of recording between false voltage and the fault current that ripple monitoring equipment monitors.If for fault phase angle, for false voltage phase angle, for fault current phase angle, the computing method of fault phase angle as shown in Equation (1).
???????????????????????????????????????(1)
2. by the Data Discretization in failure information database.
Association rules mining algorithm processing be all the data of discrete type, distribution network failure space-time data is being carried out to before association rule mining, first will carry out discretize processing to data.In distribution network failure attribute, the property value of time of failure, fault current, fault impedance, fault phase angle is continuous data, need to before association rule mining, carry out discretize processing.
Wide division is more typical Method of Data Discretization, and concrete departure process is:
The minimum value of setting fault duration is , maximal value is , carry out the wide discrete two kinds of methods that mainly contain, a kind of method is first to set discrete width δ, asks the discrete k of counting; Another kind method is to ask discrete width δ by discrete counting.Calculation expression is shown in formula (2)
????????????????????????????????????(2)
Can obtain discontinuous point by the method
????????????????????????(3)
(note: discretize is herein to be the attribute of continuous type numerical value for property value, associated with the discretize of following step 3, for continuous type numerical attribute, need to first carry out discretize and by the conversion method described in following step 3, quantification type data be changed into discrete data again)
Step 3: apply suitable association rule mining method and carry out association rule mining, excavate the Strong association rule comprising in distribution network failure information.
Utilize the Apriori algorithm in association rule mining to carry out association rule mining to the data in failure information database; Correlation rule, is mainly divided into Boolean Association Rules and Quantitative Association Rule two classes; In the time that the property value that will excavate is 0 or 1 discrete value, correlation rule is boolean association rule; In the time that the property value that will excavate is quantized value, correlation rule is quantification type correlation rule.Apriori algorithm belongs to boolean association rule mining algorithm, carrying out before association rule mining, quantification type data need to be changed into Boolean type data; Concrete conversion method is:
An if collection the set of item, (m=1,2,3 ...) value be quantized value, Quantitative Association Rule be changed into Boolean Association Rules, form new item collection , need by each value after discretize and a collection in item corresponding; Concrete method for transformation is listed in table 5.
Table 6 is the situation in the time of n=2 in table 5,
Suppose a collection in value is 0,1,2,3, value be 0,1,2, by item collection in quantification type data change into collection the corresponding relation of middle Boolean type data is as shown in table 1, with value number and be 7, corresponding middle term is also 7.
When value be 0 o'clock, the item collection after conversion in value be 1, , , value be all 0; When value be 1 o'clock, collection in value be 1, , , value be 0; When value be 2 o'clock, collection in value be 1, , , value be 0; When value be 3 o'clock, collection in value be 1, , , value be 0;
When value be 0 o'clock, the item collection after conversion in value is 1, , value be all 0; When value be 1 o'clock, collection in value be 1, , value be 0; When value be 2 o'clock, collection in value be 1, , value be 0.
Apriori algorithm is topmost Boolean type frequent item set association rules mining algorithm; Apriori algorithm is to search for frequent item set by the mode of iterative search; First, search out the set of frequent 1-item collection , then by search ( =2,3 ..., n), until the frequent item set of search is empty, till can not continuing search; The generation of this frequent item set mainly divides and connects and two steps of beta pruning:
Connect step: pass through be connected the set that produces candidate k-item collection with oneself, method of attachment , in item collection interconnect the set that generates candidate k-item collection ; In connection procedure, require the item collection connecting to share k-1;
Beta pruning step: in the set that connects step acquisition candidate after, determine frequently according to formula (5) the set an of-collection ; But in this process, if very large, will need a large amount of calculating to obtain , can be by for reducing calculated amount in item collection ( )-subset does not exist in candidate -collection is deleted; Because according to Apriori character, all non-frequent ( a)-collection can not be frequent the subset of item collection, namely in all collection ( )-subset is all comprised in in.
Wherein, Apriori character: all nonvoid subsets of frequent item set must be all frequently, frequent item set meets the item collection of minimum support; for frequent k-item collection.
Suppose a collection be a subset, at database in support (Support) refer to in comprise number of transactions with the percent value of middle affairs sum,
;??????????????????????(4)
For item collection with transaction database , frequent item set refers to that support is not less than specified minimum support (Min_support) nonvoid subset; Judge a collection for the condition of frequent item set is
。(5)
Step 4: according to the actual conditions of fault, according to the content in association rule database, distribution network failure situation is provided to diagnostic result.
According to known fault attribute, as the time attribute of fault, space attribute, fault current etc., utilize the Strong association rule in association rule database, failure condition is made to diagnosis, as failure cause, fault element, fault type etc.
As the association rule database of the distribution network failure repairing record formation to a certain city 2009-2012 of China.Time, the fault zone that known fault occurs, the size of fault current, can be by obtaining in association rule database and this season, this region, failure cause, fault element, fault type that this fault current levels degree of association is the highest, thereby fault content is made to diagnosis, maintainer makes rapid reaction according to diagnostic result, fix a breakdown with prestissimo, recover fault zone electric power supply.
Be more than preferred embodiment of the present invention, all changes of doing according to technical solution of the present invention, when the function producing does not exceed the scope of technical solution of the present invention, all belong to protection scope of the present invention.

Claims (5)

1. a Fault Diagnosis Method for Distribution Networks for applicating history fault data, is characterized in that: comprises the steps,
Step S01: set up failure information database by distribution network failure repairing record, and determine the fault attribute comprising in this failure information database;
Step S02: the data layout of standard fault attribute, by the fault attribute Data Discretization in failure information database;
Step S03: association rule digging method excavates the Strong association rule that the fault attribute data in failure information database comprise;
Step S04: according to the actual conditions of fault, according to the Strong association rule of above-mentioned excavation, distribution network failure situation is provided to diagnostic result.
2. the Fault Diagnosis Method for Distribution Networks of a kind of applicating history fault data according to claim 1, is characterized in that: described step S02, and specific implementation process is as follows,
Step S21: determine the also data layout of the each fault attribute of standard;
Step S22: the fault attribute data in failure information database are carried out to wide splitting, and this discretize process is specially,
The minimum value of setting fault duration is , maximal value is , according to formula: , obtain discontinuous point: ;
Wherein, δ is discrete width, and k is discrete counting.
3. the Fault Diagnosis Method for Distribution Networks of a kind of applicating history fault data according to claim 2, is characterized in that: described step S03, be specially,
Utilize the Apriori algorithm in correlation rule to carry out association rule mining to the fault attribute data in failure information database; Carrying out before association rule mining, quantification type data need to be changed into Boolean type data, concrete conversion method is:
An if collection the set of item, value be quantized value, wherein, m is integer, and m=1,2,3 Quantitative Association Rule to be changed into Boolean Association Rules, form new item collection , need by each value after discretize and a collection in item corresponding;
Then the fault attribute data in failure information database are carried out to association rule mining, Apriori algorithm is topmost Boolean type frequent item set association rules mining algorithm; Apriori algorithm is to search for frequent item set by the mode of iterative search; First, search out the set of frequent 1-item collection , then by search , until the frequent item set of search is empty, till can not continuing search, wherein, for integer, =2,3 ..., n; The generation of this frequent item set mainly divides and connects and two steps of beta pruning:
Connect step: pass through be connected the set that produces candidate k-item collection with oneself, method of attachment , in item collection interconnect the set that generates candidate k-item collection ; In connection procedure, require the item collection connecting to share k-1;
Beta pruning step: in the set that connects step acquisition candidate after, determine frequently according to following formula the set an of-collection ,
Suppose a collection be a subset, at database in support Support refer to in comprise number of transactions with the percent value of middle affairs sum,
For item collection with transaction database , frequent item set refers to that support is not less than specified minimum support Min_support's nonvoid subset; Judge a collection for the condition of frequent item set is
But in this process, if very large, will need a large amount of calculating to obtain , can be by for reducing calculated amount in item collection ( )-subset does not exist in candidate -collection is deleted; Because according to Apriori character, all non-frequent ( a)-collection can not be frequent the subset of item collection, namely in all collection ( )-subset is all comprised in in;
Wherein, Apriori character: all nonvoid subsets of frequent item set must be all frequently; Frequent item set meets the item collection of minimum support; for frequent k-item collection.
4. the Fault Diagnosis Method for Distribution Networks of a kind of applicating history fault data according to claim 3, it is characterized in that: described correlation rule, mainly be divided into Boolean Association Rules and Quantitative Association Rule two classes, when the property value that will excavate is 0 or 1, while being discrete value, correlation rule is boolean association rule; In the time that the property value that will excavate is quantized value, correlation rule is quantification type correlation rule.
5. the Fault Diagnosis Method for Distribution Networks of a kind of applicating history fault data according to claim 3, is characterized in that: described Apriori algorithm belongs to boolean association rule mining algorithm.
CN201410125125.7A 2014-03-31 2014-03-31 Power distribution network fault diagnosis method utilizing historical fault data Pending CN103871003A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410125125.7A CN103871003A (en) 2014-03-31 2014-03-31 Power distribution network fault diagnosis method utilizing historical fault data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410125125.7A CN103871003A (en) 2014-03-31 2014-03-31 Power distribution network fault diagnosis method utilizing historical fault data

Publications (1)

Publication Number Publication Date
CN103871003A true CN103871003A (en) 2014-06-18

Family

ID=50909515

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410125125.7A Pending CN103871003A (en) 2014-03-31 2014-03-31 Power distribution network fault diagnosis method utilizing historical fault data

Country Status (1)

Country Link
CN (1) CN103871003A (en)

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104156881A (en) * 2014-06-20 2014-11-19 天津大学 Comprehensive power distribution network fault risk assessment method
CN104460651A (en) * 2014-10-24 2015-03-25 北京交控科技有限公司 ZC double-system downtime fault early-warning method and device based on autonomous learning
CN104808645A (en) * 2015-03-02 2015-07-29 中山大学 Discrete event system fault diagnosis method
CN105301450A (en) * 2015-11-26 2016-02-03 云南电网有限责任公司电力科学研究院 Distribution network fault automatic diagnosis method and system
CN105354336A (en) * 2015-12-07 2016-02-24 Tcl集团股份有限公司 Method and apparatus for processing transactional database data
CN105608519A (en) * 2015-11-09 2016-05-25 国家电网公司 Prediction method for operation state of electrical-network communication equipment
CN106019084A (en) * 2016-06-16 2016-10-12 上海交通大学 Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method
CN106022950A (en) * 2016-05-06 2016-10-12 中国电力科学研究院 Power distribution network secondary equipment type identification method and system
CN106294076A (en) * 2016-08-24 2017-01-04 浪潮(北京)电子信息产业有限公司 A kind of server relevant fault Forecasting Methodology and system thereof
CN106842106A (en) * 2017-02-23 2017-06-13 广东电网有限责任公司茂名供电局 Electrical energy meter fault Forecasting Methodology and device
CN107025293A (en) * 2017-04-13 2017-08-08 广东电网有限责任公司电力科学研究院 A kind of second power equipment defective data method for digging and system
CN107092993A (en) * 2017-06-05 2017-08-25 国网陕西省电力公司电力科学研究院 Reclosing success rate association analysis method based on Disasters Type and line information
CN107451708A (en) * 2017-04-26 2017-12-08 国家电网公司 A kind of grid equipment monitoring information confidence association analysis method based on Apriori algorithm
CN107483240A (en) * 2017-08-07 2017-12-15 国网安徽省电力公司淮北供电公司 Power communication network service health degree analysis method based on Internet resources incidence relation
CN107506467A (en) * 2017-08-30 2017-12-22 山东鲁能智能技术有限公司 A kind of method and system of charging pile maintenance
CN107562603A (en) * 2017-09-25 2018-01-09 郑州云海信息技术有限公司 A kind of intelligent fault alignment system and method based on linux
CN107633093A (en) * 2017-10-10 2018-01-26 南通大学 A kind of structure and its querying method of DECISION KNOWLEDGE collection of illustrative plates of powering
CN107918670A (en) * 2017-11-29 2018-04-17 国网电力信息通信有限公司 A kind of alert processing method applied to power communication system
CN107967199A (en) * 2017-12-05 2018-04-27 广东电网有限责任公司东莞供电局 A kind of power equipment temperature pre-warning analysis method based on association rule mining
CN108320040A (en) * 2017-01-17 2018-07-24 国网重庆市电力公司 Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm
CN108873859A (en) * 2018-05-31 2018-11-23 浙江工业大学 Based on the bridge-type grab ship unloader fault prediction model method for improving correlation rule
CN109034604A (en) * 2018-07-23 2018-12-18 长沙理工大学 A kind of Distribution Network Failure Association Rule Analysis method considering equipment state and temperature
CN109032872A (en) * 2018-08-13 2018-12-18 广州供电局有限公司 Equipment fault diagnosis method and system based on bayesian network
CN109254219A (en) * 2018-11-22 2019-01-22 国网湖北省电力有限公司电力科学研究院 A kind of distribution transforming transfer learning method for diagnosing faults considering multiple factors Situation Evolution
CN109814526A (en) * 2018-12-29 2019-05-28 卡斯柯信号有限公司 Maintenance diagnostic method towards trackside safety signal system
CN110244184A (en) * 2019-07-04 2019-09-17 国网江苏省电力有限公司 A kind of distribution line fault observer method for digging, system and the medium of frequent item set
CN110632439A (en) * 2019-09-29 2019-12-31 国网河南省电力公司电力科学研究院 Power distribution network single-phase earth fault diagnosis technology based on synchronous waveform and association rule
CN112016602A (en) * 2020-08-18 2020-12-01 广东电网有限责任公司韶关供电局 Method, equipment and storage medium for analyzing correlation between power grid fault cause and state quantity

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
李栋: "面向故障诊断的并行关联规则算法研究与实现", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 *
李育凤 等: "基于云模型的配电网故障停电风险综合评价", 《电力与电工》 *
梁志瑞 等: "关联规则挖掘在电厂设备故障监测中的应用", 《电力自动化设备》 *
王海龙 等: "基于关联规则挖掘技术的配电网故障数据分析", 《中国高等学校电力系统及其自动化专业第29届学术年会会议》 *

Cited By (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104156881A (en) * 2014-06-20 2014-11-19 天津大学 Comprehensive power distribution network fault risk assessment method
CN104460651A (en) * 2014-10-24 2015-03-25 北京交控科技有限公司 ZC double-system downtime fault early-warning method and device based on autonomous learning
CN104808645A (en) * 2015-03-02 2015-07-29 中山大学 Discrete event system fault diagnosis method
CN105608519A (en) * 2015-11-09 2016-05-25 国家电网公司 Prediction method for operation state of electrical-network communication equipment
CN105301450A (en) * 2015-11-26 2016-02-03 云南电网有限责任公司电力科学研究院 Distribution network fault automatic diagnosis method and system
CN105354336A (en) * 2015-12-07 2016-02-24 Tcl集团股份有限公司 Method and apparatus for processing transactional database data
CN106022950A (en) * 2016-05-06 2016-10-12 中国电力科学研究院 Power distribution network secondary equipment type identification method and system
CN106019084A (en) * 2016-06-16 2016-10-12 上海交通大学 Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method
CN106019084B (en) * 2016-06-16 2020-11-17 上海交通大学 Medium-voltage power distribution network disconnection fault diagnosis method based on power distribution and utilization data correlation
CN106294076B (en) * 2016-08-24 2019-03-15 浪潮(北京)电子信息产业有限公司 A kind of server relevant fault prediction technique and its system
CN106294076A (en) * 2016-08-24 2017-01-04 浪潮(北京)电子信息产业有限公司 A kind of server relevant fault Forecasting Methodology and system thereof
CN108320040B (en) * 2017-01-17 2021-01-26 国网重庆市电力公司 Acquisition terminal fault prediction method and system based on Bayesian network optimization algorithm
CN108320040A (en) * 2017-01-17 2018-07-24 国网重庆市电力公司 Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm
CN106842106A (en) * 2017-02-23 2017-06-13 广东电网有限责任公司茂名供电局 Electrical energy meter fault Forecasting Methodology and device
CN107025293A (en) * 2017-04-13 2017-08-08 广东电网有限责任公司电力科学研究院 A kind of second power equipment defective data method for digging and system
CN107451708A (en) * 2017-04-26 2017-12-08 国家电网公司 A kind of grid equipment monitoring information confidence association analysis method based on Apriori algorithm
CN107092993A (en) * 2017-06-05 2017-08-25 国网陕西省电力公司电力科学研究院 Reclosing success rate association analysis method based on Disasters Type and line information
CN107483240A (en) * 2017-08-07 2017-12-15 国网安徽省电力公司淮北供电公司 Power communication network service health degree analysis method based on Internet resources incidence relation
CN107506467A (en) * 2017-08-30 2017-12-22 山东鲁能智能技术有限公司 A kind of method and system of charging pile maintenance
CN107562603A (en) * 2017-09-25 2018-01-09 郑州云海信息技术有限公司 A kind of intelligent fault alignment system and method based on linux
CN107633093A (en) * 2017-10-10 2018-01-26 南通大学 A kind of structure and its querying method of DECISION KNOWLEDGE collection of illustrative plates of powering
CN107918670A (en) * 2017-11-29 2018-04-17 国网电力信息通信有限公司 A kind of alert processing method applied to power communication system
CN107967199B (en) * 2017-12-05 2019-11-08 广东电网有限责任公司东莞供电局 A kind of power equipment temperature pre-warning analysis method based on association rule mining
CN107967199A (en) * 2017-12-05 2018-04-27 广东电网有限责任公司东莞供电局 A kind of power equipment temperature pre-warning analysis method based on association rule mining
CN108873859A (en) * 2018-05-31 2018-11-23 浙江工业大学 Based on the bridge-type grab ship unloader fault prediction model method for improving correlation rule
CN108873859B (en) * 2018-05-31 2020-07-31 浙江工业大学 Bridge type grab ship unloader fault prediction model method based on improved association rule
CN109034604A (en) * 2018-07-23 2018-12-18 长沙理工大学 A kind of Distribution Network Failure Association Rule Analysis method considering equipment state and temperature
CN109032872A (en) * 2018-08-13 2018-12-18 广州供电局有限公司 Equipment fault diagnosis method and system based on bayesian network
CN109032872B (en) * 2018-08-13 2021-08-10 广东电网有限责任公司广州供电局 Bayesian network-based equipment fault diagnosis method and system
CN109254219A (en) * 2018-11-22 2019-01-22 国网湖北省电力有限公司电力科学研究院 A kind of distribution transforming transfer learning method for diagnosing faults considering multiple factors Situation Evolution
CN109814526A (en) * 2018-12-29 2019-05-28 卡斯柯信号有限公司 Maintenance diagnostic method towards trackside safety signal system
CN109814526B (en) * 2018-12-29 2021-06-08 卡斯柯信号有限公司 Maintenance diagnosis method for trackside safety signal system
CN110244184A (en) * 2019-07-04 2019-09-17 国网江苏省电力有限公司 A kind of distribution line fault observer method for digging, system and the medium of frequent item set
CN110632439A (en) * 2019-09-29 2019-12-31 国网河南省电力公司电力科学研究院 Power distribution network single-phase earth fault diagnosis technology based on synchronous waveform and association rule
CN112016602A (en) * 2020-08-18 2020-12-01 广东电网有限责任公司韶关供电局 Method, equipment and storage medium for analyzing correlation between power grid fault cause and state quantity
CN112016602B (en) * 2020-08-18 2021-08-10 广东电网有限责任公司韶关供电局 Method, equipment and storage medium for analyzing correlation between power grid fault cause and state quantity

Similar Documents

Publication Publication Date Title
CN103871003A (en) Power distribution network fault diagnosis method utilizing historical fault data
Jarventausta et al. Using fuzzy sets to model the uncertainty in the fault location process of distribution networks
CN101968525B (en) Fault positioning method for power distribution network by combining simulation calculation and real-time monitoring
CN103093276B (en) Urban power grid risk assessment method
CN105467276B (en) A kind of line fault monitoring method and system
CN105281435A (en) Intelligent distribution network oriented distribution type fault detection and isolation system and working method
CN105576660A (en) Region power distribution network on-line simulation analysis device and system
CN105119251A (en) Method suitable for determining grounding resistance scheme of flexible direct-current power distribution system
Ciapessoni et al. An integrated platform for power system security assessment implementing probabilistic and deterministic methodologies
Siirto et al. Fault location, isolation and restoration in a city distribution network
Liang et al. Typical fault cause recognition of single-phase-to-ground fault for overhead lines in nonsolidly earthed distribution networks
CN111478324A (en) Power station alarm analysis system
Taylor et al. Integrated SCADA/DMS/OMS: Increasing distribution operations efficiency
Emjedi et al. Reliability evaluation of distribution networks using fuzzy logic
Dimov et al. Influence of the type of electrical distribution network on the indices of continuity of the power supply
Bragatto et al. Assessment and possible solution to increase the resilience of Terni distribution Grid: The ice sleeves formation threat
Behal Substation Innovations: The Heart and Brain of the Grid [Guest Editorial]
Suslov et al. Flexible Power Distribution Networks: New Opportunities and Applications.
Hussein et al. Fault location and isolation using multi agent systems in 16 buses distribution system
Bragatto et al. Assessment and possible solution to increase resilience: heat waves in Terni distribution grid
Kargbo et al. Electric grid disaster response management—A systems of systems engineering approach
Nanadikar et al. Improved outage prediction using asset management data and intelligent multiple interruption event handling with fuzzy control during extreme climatic conditions
Grujić et al. Fuzzy logic‐based concept for high‐voltage substation risk management against lightning
CN105391030A (en) Planned island division method through load gradual loading and aggregation based on network topology structure
CN107748315B (en) A kind of Distribution Network Failure active forewarning method

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20140618

RJ01 Rejection of invention patent application after publication