CN109655712A - A kind of distribution network line fault analysis of causes method and system - Google Patents
A kind of distribution network line fault analysis of causes method and system Download PDFInfo
- Publication number
- CN109655712A CN109655712A CN201910029740.0A CN201910029740A CN109655712A CN 109655712 A CN109655712 A CN 109655712A CN 201910029740 A CN201910029740 A CN 201910029740A CN 109655712 A CN109655712 A CN 109655712A
- Authority
- CN
- China
- Prior art keywords
- failure
- major class
- data
- failure cause
- 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
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 126
- 238000009826 distribution Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000005540 biological transmission Effects 0.000 claims description 47
- 238000012549 training Methods 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 28
- 238000010276 construction Methods 0.000 claims description 25
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000012423 maintenance Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 8
- 241000607479 Yersinia pestis Species 0.000 claims description 7
- 238000002474 experimental method Methods 0.000 claims description 6
- 230000032683 aging Effects 0.000 claims description 4
- 208000015181 infectious disease Diseases 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims 1
- 238000013024 troubleshooting Methods 0.000 abstract description 4
- 238000010801 machine learning Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000005611 electricity Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention relates to a kind of distribution network line fault analysis of causes method and systems, include: data when obtaining current line failure, based on acquisition current line failure when data and in advance the failure cause major class analysis model that constructs determines affiliated failure cause major class；The failure cause group analysis model constructed based on the failure cause major class and in advance determines line fault reason.The present invention is a kind of distribution network line fault analysis of causes method and system, based on acquisition current line failure when data and in advance the failure cause major class analysis model that constructs determine belonging to failure cause major class, the failure cause group analysis model constructed based on the failure cause major class and in advance determines line fault reason, solving artificial judgement influences the timeliness of troubleshooting, simultaneously, since staff is often incomplete in received failure relevant information in short-term, judged accordingly, the problem of the accuracy of impact analysis conclusion.
Description
Technical field
The invention belongs to electric power system and its automation fields, and in particular to a kind of distribution network line fault analysis of causes side
Method and system.
Background technique
Distribution line (English: distribution circuit), which refers to from step-down substation electric power, is sent to distribution transformer
Device or the route that the electric power of distribution substation is sent to electricity unit.
Distribution circuit electric voltage is 3.6kV~40.5kV, claims high-tension distributing line；Distribution voltage is no more than 1kV, frequency does not surpass
Cross 1000Hz, direct current is no more than 1500V, title low-voltage distributing line.The construction requirements of distribution line are safe and reliable, keep for being electrically connected
Continuous property, reduces line loss, improves power transmission efficiency, guarantees that power quality is good.
Distribution network line fault is the most important factor for influencing power supply reliability.After line fault occurs for power distribution network, a side
Face needs timely and accurately to determine the position of fault, quickly carries out Fault Isolation, and restores fault zone power supply, on the other hand, needs
Failure cause is searched, eliminates the security risk of operation of power networks from the root, fault rate is effectively reduced, improving power supply can
By property, guarantee customer power supply quality.
Currently, the common line fault analysis of causes, relies on artificial micro-judgment more.Work of the which to personnel are judged
Skill requirement is higher, and is completely dependent on subjective judgement, lacks scientific quantitative analysis foundation.In addition, artificial judgement influences troubleshooting
Timeliness judged accordingly simultaneously as staff is often incomplete in received failure relevant information in short-term,
The accuracy of impact analysis conclusion.
Summary of the invention
The timeliness of troubleshooting is influenced to solve above-mentioned artificial judgement, simultaneously as staff is received in short-term
The problem of failure relevant information is often incomplete, is judged accordingly, the accuracy of impact analysis conclusion, the present invention relates to
A kind of distribution network line fault analysis of causes method, which comprises
Obtain data when current line failure；
Based on acquisition current line failure when data and in advance the failure cause major class analysis model that constructs determines institute
Belong to failure cause major class；
The failure cause group analysis model constructed based on the failure cause major class and in advance determines line fault reason.
Preferably, the type of the current line failure includes overhead transmission line failure and cable line fault.
Preferably, the building of the failure cause major class analysis model:
Historical failure data is obtained, and the historical failure data is set as training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and instruct
Practice, obtains the relationship in the historical failure data between fault state and failure major class；
The relationship between fault state and failure major class is modified using test data.
Preferably, the historical situation when overhead transmission line failure includes: weather conditions, fault state and relevant device shape
Condition, the failure major class include: external force reason, customer impact, natural cause, Equipment and operation and maintenance reason；
The historical situation when cable line fault includes: fault state, relevant device situation and region construction
Situation, the failure major class include customer impact, external force reason and Equipment.
Preferably, the building of the failure cause group analysis model includes:
Historical failure data is obtained, and the historical failure data is set as training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and instruct
Practice, obtains the relationship in the historical failure data between failure major class and failure cause；
The relationship between failure major class and failure cause is modified using test data.
Preferably, under overhead transmission line failure in situation, when failure major class is external force reason, failure cause is foreign matter, tree
Line, vehicular traffic, bird pest or theft；
When failure major class is natural cause, failure cause is thunder and lightning, heavy rain, strong wind or earthquake；
When failure major class is Equipment, failure cause is that mounting process is bad, product quality technique is bad or equipment is old
Change；
When failure major class is operation and maintenance reason, failure cause is checking experiment, safeguards that improper or liability cause is unclear.
Preferably, in the case where cable line fault, when failure major class is customer impact, failure cause is construction infection
Or other external force；
When failure major class is Equipment, failure cause is cable intermediate joint failure, tag failure or electricity
Cable ontology failure.
Preferably, the weather conditions include: temperature, wind-force, rainfall, snowfall；
The fault state includes: fault type and abort situation；
The relevant device situation includes: device model, service life and frequency of maintenance.
A kind of distribution network line fault analysis of causes system, comprising:
Obtain module: for obtaining data when current line failure；
Failure cause major class determining module: data when for current line failure based on acquisition and construct in advance therefore
Hinder reason major class analysis model and determines affiliated failure cause major class；
Failure cause determining module: the small alanysis of failure cause for constructing based on affiliated failure cause major class and in advance
Model determines line fault reason.
Preferably, the failure cause major class determining module includes: failure cause major class analysis model construction unit；
The failure cause major class analysis model construction unit is used for: obtaining historical failure data, and the history is former
Hindering data setting is training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and instruct
Practice, obtains the relationship in the historical failure data between fault state and failure major class；
The relationship between fault state and failure major class is modified using test data.
Preferably, the failure cause group determining module includes: failure cause group analysis model construction unit；
The failure cause group analysis model construction unit is for obtaining historical failure data, and by the historical failure
Data setting is training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and instruct
Practice, obtains the relationship in the historical failure data between failure major class and failure cause；
The relationship between failure major class and failure cause is modified using test data.
Compared with immediate documents, the application is also had the following beneficial effects:
1, the present invention be a kind of distribution network line fault analysis of causes method and system, obtain current line failure when
Data, based on acquisition current line failure when data and in advance belonging to the failure cause major class analysis model that constructs determines therefore
Hinder reason major class, the failure cause group analysis model constructed based on the failure cause major class and in advance determines that line fault is former
Cause, solving artificial judgement influences the timeliness of troubleshooting, simultaneously as staff is in received failure correlation letter in short-term
The problem of breath is often incomplete, is judged accordingly, the accuracy of impact analysis conclusion；
2, the present invention is a kind of distribution network line fault analysis of causes method and system, and the present invention makes full use of power distribution network
Multiple information sources condition establishes distribution network line fault analysis of causes decision tree, carries out the distribution network failure analysis of causes accordingly, should be certainly
Plan tree is with " distribution network line fault alarm " for entrance, and circuit types, is based on historical data, utilizes engineering according to different faults
Learning method constructs failure cause major class analysis model respectively, and obtains corresponding failure reason major class accordingly；
3, the present invention is a kind of distribution network line fault analysis of causes method and system, big for each failure cause
Class further constructs failure cause group analysis model, realizes failure cause by the method for machine learning or rule judgement
Explication de texte；
4, the present invention is a kind of distribution network line fault analysis of causes method and system, by multi-level Analysis of Policy Making,
Accurate, quick, the reliable judgement for realizing distribution network line fault reason, eliminates operation of power networks convenient for related personnel from the root
Security risk, be effectively reduced fault rate, improve power supply reliability, guarantee customer power supply quality.
Detailed description of the invention
Fig. 1 is method flow schematic diagram of the invention；
Fig. 2 is the n-th season of overhead transmission line failure cause major class analysis model input/output relation of the invention；
Fig. 3 is BP neural network structure of the invention；
Fig. 4 is the small alanysis mould of failure cause caused by overhead transmission line n-th (n=1,2,3,4) season external force of the invention
Type input/output relation；
Fig. 5 is cable line fault reason major class analysis model input/output relation of the invention；
Fig. 6 is distribution network line fault analysis of causes decision tree of the invention；
Fig. 7 is of the invention a kind of implemented based on the distribution network line fault analysis of causes method of decision tree and machine learning
Example.
Specific embodiment
Currently, with the continuous improvement of power distribution network digitlization and automatization level, information abundant is able to real-time or quasi- reality
When be transmitted to control centre, this make comprehensive utilization acquire all kinds of real time information carry out distribution network line fault analysis of causes
It is possibly realized.In addition, China various regions power grid just sets about starting the construction of integrated data platform, after building up integrated data platform, it is
The WAMS information of system, SCADA information, Fault Recorder Information, relay protection information, 95598 information, Weather information, construction
Information etc. can directly be extracted from data platform, provide abundant, comprehensive and timeliness for the distribution network failure analysis of causes
High precious information.
Meanwhile the machine learning based on data, it is conversion artificial experience to mathematical model, provides a kind of effective technology
Means specifically include neural network method, support vector machine method etc..These methods are as the weight in modern artificial intelligence technology
Aspect is wanted, research is from observation data (sample) set off in search rule, using these rules to Future Data or the number that can not be observed
According to being predicted.By these methods, a kind of base can be converted into effectively by the failure cause analysis method of traditional dependence experience
In the failure cause analysis method of machine learning, this method has scientific basis and Consideration is more comprehensive, hereby it is possible to
To more quick, accurate, reliable failure reason analysis conclusion.
In addition, the line fault reason in power distribution network is varied, and there are particle size differences, and failure reason analysis must be got over
Careful, corresponding treatment measures are also more clear, and the processing time is also rapider.For example, as cause line fault it is main because
One of element, external force reason can be subdivided into foreign matter, tree line, vehicular traffic, bird pest again or steal caused failure.More event in order to obtain
Hinder reason, decision tree means can be used, based on fault diagnosis conclusion and internal and external environment factor, carries out multi-level failure cause point
Analysis.
In summary problem and the state of the art comb the pests occurrence rule and influence factor of all kinds of line faults in power distribution network,
Existing multiple information sources condition is made full use of, decision tree and machine learning techniques are based on, it is former to form the multi-level line fault of power distribution network
Because of analysis method, accurate, quick, detailed failure reason analysis is realized.
Below with reference to specific embodiment, the present invention will be further explained and explanation:
Embodiment 1
A kind of distribution network line fault analysis of causes method as shown in Figure 1, steps are as follows:
Step 1: obtaining data when current line failure
Step 2: data when current line failure based on acquisition and the failure cause major class analysis model constructed in advance
Failure cause major class belonging to determining；
Step 3: the failure cause group analysis model constructed based on the failure cause major class and in advance determine route therefore
Hinder reason.
Explanation is explained in detail to above-mentioned steps below:
Explanation to step 2
Differentiation is overhead transmission line failure or cable fault, if overhead transmission line failure, then enters overhead transmission line failure cause
Major class analysis model；If cable fault, then into cable line fault reason major class analysis model.
Which overhead transmission line failure is distinguished to occur to be based on the big alanysis mould of corresponding failure cause of corresponding season in season in
Type occurs corresponding actual state according to failure, determines overhead transmission line failure cause major class.This example failure occurred in the first season
Degree, therefore it is based on overhead transmission line first quarter failure cause major class analysis model, corresponding actual state is occurred according to failure, is determined
The failure cause major class of overhead transmission line is external force reason.
Explanation to step 3
Overhead transmission line failure cause major class is distinguished, then is based on corresponding failure reason group analysis model, determines overhead transmission line
Failure cause group is based further on external force reason group analysis model, judges overhead transmission line failure cause group, and determination is tree
Overhead transmission line failure caused by line terminates.
4. being based on cable line fault reason major class analysis model, corresponding actual state is occurred according to failure, determines electricity
Cable road failure cause major class.
5. distinguishing cable line fault reason major class, then it is based on corresponding failure reason group analysis model, determines cable
Road failure cause group.Such as, by cable line fault reason major class analysis model, determine that cable line fault reason major class is
External force reason is then based further on external force reason group analysis model, judges cable line fault reason group, and determination is construction
Cable line fault caused by influence or other external force, then terminate.
Embodiment 2
For embodiment illustrated in fig. 7, it is specifically described the method for the invention.
The present invention initially sets up the multi-level failure reason analysis model library of power distribution network:
It the influence factor that is broken down under Various Seasonal due to different distribution line types (overhead line or cable) and accounts for
Than being different, and failure cause, in addition to the major class such as external force, user, nature, there are also foreign matter, tree line, vehicular traffic, bird pest, thunders
It hits, the groups such as heavy rain, strong wind.In order to realize more acurrate, more detailed failure reason analysis, need for different distribution line classes
Type, towards Various Seasonal, different failure reason analysis models is established in refinement, and synthesis forms the multi-level line fault of power distribution network
Analysis of causes model library.The multilayered structure of the model library is as shown in the table:
Distribution network line fault analysis of causes model library multilayered structure
Below for each model in above-mentioned model library, corresponding modeling method is provided:
1. overhead transmission line first quarter failure cause major class analysis model
Because input and output correspond to relationship complexity, therefore machine learning method is used, be based on historical data, establishes overhead transmission line event
Hinder reason major class analysis model.Below by taking BP neural network (a kind of machine learning method) as an example, the overhead transmission line first season is provided
Spend failure cause major class analysis model modeling method.
(1) determine that mode input exports
Fault occurrences and major influence factors based on the overhead transmission line first quarter, the input for combing out the model are defeated
Out, input includes that corresponding weather conditions (temperature, wind-force, rainfall, snowfall), fault state (failure occur for a certain failure
Type and abort situation), relevant device situation (device model, service life, frequency of maintenance), it is corresponding to export the failure accordingly
Occurrence cause major class, i.e. external force reason, customer impact, natural cause, Equipment or operation and maintenance reason.
(2) historical data is arranged
The historical data for taking the overhead transmission line first quarter to break down is arranged, and is obtained under each historical failure situation,
Corresponding weather conditions (temperature, wind-force, rainfall, snowfall), fault state (fault type and abort situation), relevant device
The physical fault reason of situation (device model, service life, frequency of maintenance) and the failure, the instruction as BP neural network
Practice data.
(3) model training with build
Model structure determines: the BP neural network input layer number n (n is 9 in the model) established, output layer section
Points be 1, the number of hidden nodes be set as I (Wherein a is constant between 1~10, and specific value passes through multiple
It is trained to be obtained with test experiments.Such as by repeatedly trained and test experiments it is found that the model has preferable training when a takes 3
Speed and recognition effect, then the number of hidden nodes is set as)。
Model training with build: the historical data that will be put in order is divided into two parts, wherein 90% be used as training data,
10% is used as test data.Each of training data training sample, including the generation of each historical failure are corresponding such as Fig. 2 institute
Show weather conditions (temperature, wind-force, rainfall, snowfall), fault state (fault type and abort situation), relevant device situation
(device model, service life, frequency of maintenance) and the corresponding physical fault reason of the historical failure.Wherein, historical failure is sent out
Raw corresponding weather conditions (temperature, wind-force, rainfall, snowfall), related set fault state (fault type to abort situation)
Standby situation (device model, service life, frequency of maintenance) as input data required for network training, the historical failure is corresponding
Physical fault reason as target data required for network training.As shown in Figure 3 is theoretical based on BP neural network, passes through
Constantly model training and test, are finally completed BP neural network model buildings, establish the pass of internal and external environment and failure cause
Gang mould type, i.e. overhead transmission line first quarter failure cause major class analysis model.
2. failure cause group analysis model caused by overhead transmission line first quarter external force
Equally by taking BP neural network (a kind of machine learning method) as an example, the model modelling approach is provided.
Firstly, determining mode input output.A situation arises based on failure caused by overhead transmission line first quarter external force and
Major influence factors comb out the input and output of the model, and input includes that corresponding wind occurs for a certain external force failure as shown in Figure 4
Power, fault type, abort situation, provincial characteristics, fault moment and failure are monthly, export the corresponding generation of external force failure accordingly
Reason group, i.e. foreign matter, tree line, vehicular traffic, bird pest or theft.
Later, historical data is arranged, model training is carried out and builds, the process and overhead transmission line first quarter failure cause
The modeling process of major class analysis model is identical, repeats no more.
3. failure cause group analysis model caused by overhead transmission line first quarter natural weather
The mode input export corresponding relationship it is simple, climatic condition when being occurred according to failure, that is, can determine that be thunder and lightning,
Failure caused by heavy rain, strong wind or earthquake.
4. failure cause group analysis model caused by overhead transmission line first quarter equipment
It is simple that the mode input exports corresponding relationship, according to the installation of failure corresponding equipment, maintenance and respective batch state,
It can determine that it is failure caused by mounting process is bad, product quality is bad or ageing equipment.
5. failure cause group analysis model caused by overhead transmission line first quarter operation and maintenance
It is related to Responsibility of Staff due to operation and maintenance, so needing according to fault state, in conjunction with Responsibility of Staff and fortune
Situation is tieed up, artificial comprehensive judgement is checking experiment, safeguards the unknown caused failure of improper or liability cause.
Other of overhead transmission line in seasons failure reason analysis model modeling process, the same to first quarter, the history number only used
According to the fault data for corresponding season.
6. cable line fault reason major class analysis model
Equally by taking BP neural network (a kind of machine learning method) as an example, the model modelling approach is provided.
Firstly, determining mode input output.Fault occurrences and major influence factors based on cable run, comb out
The input and output of the model, input includes the fault state (fault type and abort situation), relevant device situation as shown in Figure 5
(device model, service life, frequency of maintenance) and region construction situation, exports the corresponding generation of the cable fault accordingly
Reason major class, i.e. customer impact, external force reason or Equipment.
7. cable line fault external force reason group analysis model
Cable line fault external force reason group analysis model, causality is relatively simple, in combination with construction and
Other external force situations obtain the conclusion of corresponding reason group.
8. cable line fault Equipment group analysis model
The small alanysis of cable line fault Equipment, can according to cable fault position, distinguish cable intermediate joint failure,
Cable terminal failure or cable body failure.
For power distribution network shown in Fig. 7, it is assumed that in the first quarter, short circuit event occurs for overhead transmission line folded by switch A and switch B
Barrier, the method carries out failure reason analysis through the invention.After breaking down, by method for diagnosing faults, failure is determined
Position and fault type, later, according to physical fault situation, using above-mentioned model, based on decision tree shown in Fig. 6, analysis is determined
Distribution network line fault reason:
1. differentiation is that overhead transmission line failure or cable fault if overhead transmission line failure then enter step 2；If cable
Failure then enters step 4.This example is overhead transmission line failure, therefore enters step 2.
2. distinguishing overhead transmission line failure to occur to be based on the big alanysis mould of corresponding failure cause of corresponding season in which season in
Type occurs corresponding actual state according to failure, determines overhead transmission line failure cause major class.This example failure occurred in the first season
Degree, therefore it is based on overhead transmission line first quarter failure cause major class analysis model, corresponding actual state is occurred according to failure, is determined
The failure cause major class of overhead transmission line is external force reason.
3. distinguishing overhead transmission line failure cause major class, then it is based on corresponding failure reason group analysis model, determines overhead line
Road failure cause group.It is based further on external force reason group analysis model in this example, judges overhead transmission line failure cause group,
Determination is overhead transmission line failure caused by tree line.Enter step 6.
4. being based on cable line fault reason major class analysis model, corresponding actual state is occurred according to failure, determines electricity
Cable road failure cause major class.
5. distinguishing cable line fault reason major class, then it is based on corresponding failure reason group analysis model, determines cable
Road failure cause group.Such as, it by step 4, determines that cable line fault reason major class is external force reason, is then based further on outer
Power reason group analysis model, judges cable line fault reason group, and determination is electricity caused by construction infection or other external force
Cable line fault.Enter step 6.
6. terminating.
Embodiment 3
The invention further relates to a kind of distribution network line fault analysis of causes systems, comprising:
Obtain module: for obtaining data when current line failure；
Failure cause major class determining module: data when for current line failure based on acquisition and construct in advance therefore
Hinder reason major class analysis model and determines affiliated failure cause major class；
Failure cause determining module: the small alanysis of failure cause for constructing based on affiliated failure cause major class and in advance
Model determines line fault reason；
The failure cause major class determining module includes failure cause major class analysis model construction unit；
The failure cause major class analysis model construction unit is used to determine failure original based on the historical data to break down
Because of the input and output of major class analysis model, wherein the historical data includes training data and test data；
The training data is brought into neural network model to be trained；
The test data is brought into trained neural network model and is tested, when test result and actual value not
The neural network model is corrected when consistent, obtains the neural network model by test as the big alanysis mould of failure cause
Type；
The failure cause determining module includes failure cause group analysis model construction unit；
The failure cause group analysis model construction unit is used for: determining failure original based on the historical data to break down
Because of the input and output of group analysis model, wherein the historical data includes training data and test data；
The training data is brought into neural network model to be trained；
The test data is brought into trained neural network model and is tested, when test result and actual value not
The neural network model is corrected when consistent, obtains the neural network model by test as the small alanysis mould of failure cause
Type.
The failure cause group analysis model construction unit includes that failure cause determines subelement；
The failure cause subelement is used for the input by failure cause group analysis model by the failure cause major class
The output of analysis model determines；
Failure cause is determined by the output of failure cause group analysis model；
It include: to work as fault type for overhead transmission line failure, and the input of the failure cause group analysis model is external force
When reason, export as foreign matter, tree line, vehicular traffic, bird pest or theft；
When fault type be overhead transmission line failure, and the input of the failure cause group analysis model be natural cause
When, it exports as thunder and lightning, heavy rain, strong wind or earthquake；
When fault type be overhead transmission line failure, and the input of the failure cause group analysis model be Equipment
When, it exports as technique is bad, product quality aging or ageing equipment；
When fault type be cable line fault, and the input of failure cause group analysis model be operation and maintenance reason
When, it exports as checking experiment, safeguard that improper or liability cause is unclear；
When fault type be cable line fault, and the input of failure cause group analysis model be customer impact, output
Including construction infection or other external force；
When fault type be cable line fault, and the input of failure cause group analysis model be external force reason, output
Including cable intermediate joint failure, cable terminal failure or cable body failure.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above is only the embodiment of the present invention, are not intended to restrict the invention, all in the spirit and principles in the present invention
Within, any modification, equivalent substitution, improvement and etc. done are all contained in and apply within pending scope of the presently claimed invention.
Claims (11)
1. a kind of distribution network line fault analysis of causes method, which is characterized in that the described method includes:
Obtain data when current line failure；
Based on acquisition current line failure when data and in advance belonging to the failure cause major class analysis model that constructs determines therefore
Hinder reason major class；
The failure cause group analysis model constructed based on the failure cause major class and in advance determines line fault reason.
2. a kind of distribution network line fault analysis of causes method as described in claim 1, which is characterized in that the current line
The type of failure includes overhead transmission line failure and cable line fault.
3. a kind of distribution network line fault analysis of causes method as claimed in claim 2, which is characterized in that the failure cause
The building of major class analysis model:
Historical failure data is obtained, and the historical failure data is set as training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and be trained, obtain
Obtain the relationship in the historical failure data between fault state and failure major class；
The relationship between fault state and failure major class is modified using test data.
4. a kind of distribution network line fault analysis of causes method as claimed in claim 2, which is characterized in that
Historical situation when the overhead transmission line failure includes: weather conditions, fault state and relevant device situation, the failure
Major class includes: external force reason, customer impact, natural cause, Equipment and operation and maintenance reason；
The historical situation when cable line fault includes: fault state, relevant device situation and region construction situation,
The failure major class includes customer impact, external force reason and Equipment.
5. a kind of distribution network line fault analysis of causes method as claimed in claim 2, which is characterized in that the failure cause
The building of group analysis model includes:
Historical failure data is obtained, and the historical failure data is set as training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and be trained, obtain
Obtain the relationship in the historical failure data between failure major class and failure cause；
The relationship between failure major class and failure cause is modified using test data.
6. a kind of distribution network line fault analysis of causes method as claimed in claim 4, which is characterized in that in overhead transmission line event
Hinder in lower situation, when failure major class is external force reason, failure cause is foreign matter, tree line, vehicular traffic, bird pest or theft；
When failure major class is natural cause, failure cause is thunder and lightning, heavy rain, strong wind or earthquake；
When failure major class is Equipment, failure cause is that mounting process is bad, product quality technique is bad or ageing equipment；
When failure major class is operation and maintenance reason, failure cause is checking experiment, safeguards that improper or liability cause is unclear.
7. a kind of distribution network line fault analysis of causes method as claimed in claim 4, which is characterized in that in cable run event
In the case where barrier, when failure major class is customer impact, failure cause is construction infection or other external force；
When failure major class is Equipment, failure cause is cable intermediate joint failure, tag failure or cable sheet
Body failure.
8. a kind of distribution network line fault analysis of causes method as claimed in claim 4, which is characterized in that the weather conditions
It include: temperature, wind-force, rainfall, snowfall；
The fault state includes: fault type and abort situation；
The relevant device situation includes: device model, service life and frequency of maintenance.
9. a kind of distribution network line fault analysis of causes system characterized by comprising
Obtain module: for obtaining data when current line failure；
Failure cause major class determining module: data when for current line failure based on acquisition and the failure constructed in advance are former
Because of failure cause major class belonging to the determination of major class analysis model；
Failure cause determining module: the failure cause group analysis model for constructing based on affiliated failure cause major class and in advance
Determine line fault reason.
10. a kind of distribution network line fault analysis of causes system as claimed in claim 8, which is characterized in that the failure cause is big
Class determining module includes: failure cause major class analysis model construction unit；
The failure cause major class analysis model construction unit is used for: obtaining historical failure data, and by the historical failure number
According to being set as training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and be trained, obtain
Obtain the relationship in the historical failure data between fault state and failure major class；
The relationship between fault state and failure major class is modified using test data.
11. a kind of distribution network line fault analysis of causes system as claimed in claim 8, which is characterized in that the failure cause is small
Class determining module includes: failure cause group analysis model construction unit；
The failure cause group analysis model construction unit is for obtaining historical failure data, and by the historical failure data
It is set as training data and test data；
According to the type of the distribution network line to break down, brings the training data into neural network model and be trained, obtain
Obtain the relationship in the historical failure data between failure major class and failure cause；
The relationship between failure major class and failure cause is modified using test data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910029740.0A CN109655712A (en) | 2019-01-14 | 2019-01-14 | A kind of distribution network line fault analysis of causes method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910029740.0A CN109655712A (en) | 2019-01-14 | 2019-01-14 | A kind of distribution network line fault analysis of causes method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109655712A true CN109655712A (en) | 2019-04-19 |
Family
ID=66119477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910029740.0A Pending CN109655712A (en) | 2019-01-14 | 2019-01-14 | A kind of distribution network line fault analysis of causes method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109655712A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222247A (en) * | 2019-06-10 | 2019-09-10 | 交通运输部公路科学研究所 | A kind of highway engineering construction safety hazard analysis system |
| CN110703135A (en) * | 2019-10-18 | 2020-01-17 | 国网福建省电力有限公司 | Full study and judgment method for fault handling of power distribution network |
| CN110866739A (en) * | 2019-11-29 | 2020-03-06 | 国网四川省电力公司电力科学研究院 | Power distribution network comprehensive power failure time representation method considering troubleshooting path |
| CN111812457A (en) * | 2020-07-17 | 2020-10-23 | 重庆东电通信技术有限公司 | Dynamic and static characteristic full-coverage fault assessment model for power transmission line and tower equipment |
| CN112036449A (en) * | 2020-08-11 | 2020-12-04 | 广州番禺电缆集团有限公司 | Fault analysis decision platform and fault analysis method based on intelligent cable |
| CN112510699A (en) * | 2020-11-25 | 2021-03-16 | 国网湖北省电力有限公司咸宁供电公司 | Transformer substation secondary equipment state analysis method and device based on big data |
| CN113093985A (en) * | 2021-06-09 | 2021-07-09 | 中国南方电网有限责任公司超高压输电公司广州局 | Sensor data link abnormity detection method and device and computer equipment |
| CN113625109A (en) * | 2021-08-04 | 2021-11-09 | 广西电网有限责任公司电力科学研究院 | Intelligent diagnosis method and device for power line faults |
| CN113960409A (en) * | 2021-09-14 | 2022-01-21 | 广州番禺电缆集团有限公司 | Cable fault cause determination method, device, equipment and storage medium |
| CN114200243A (en) * | 2021-12-24 | 2022-03-18 | 广西电网有限责任公司 | Low-voltage transformer area fault intelligent diagnosis method and system |
| CN114372596A (en) * | 2022-03-21 | 2022-04-19 | 广东电网有限责任公司佛山供电局 | Power data analysis method and system based on data fusion |
| CN114696467A (en) * | 2022-05-31 | 2022-07-01 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing fault tripping event of high-voltage transmission long line |
| CN116170283A (en) * | 2023-04-23 | 2023-05-26 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101782625A (en) * | 2009-01-16 | 2010-07-21 | 复旦大学 | Power electronic system fault diagnostic method based on Gradation-boosting algorithm |
| CN103871004A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network failure cause analyzing method based on expert system and D-S evidence theory |
| CN104573740A (en) * | 2014-12-22 | 2015-04-29 | 山东鲁能软件技术有限公司 | SVM classification model-based equipment fault diagnosing method |
| CN105140898A (en) * | 2015-08-14 | 2015-12-09 | 国家电网公司 | Comprehensive prevention and control method for rural power grid distribution line fault |
| CN105301388A (en) * | 2015-10-14 | 2016-02-03 | 杭州南车城市轨道交通车辆有限公司 | Rail transit transformer fault diagnosis method |
| CN107358366A (en) * | 2017-07-20 | 2017-11-17 | 国网辽宁省电力有限公司 | A kind of distribution transformer failure risk monitoring method and system |
| CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
| CN108009037A (en) * | 2017-11-24 | 2018-05-08 | 中国银行股份有限公司 | Batch processing job fault handling method, device, storage medium and equipment |
| CN108375715A (en) * | 2018-03-08 | 2018-08-07 | 中国电力科学研究院有限公司 | A kind of distribution network line fault risk day prediction technique and system |
-
2019
- 2019-01-14 CN CN201910029740.0A patent/CN109655712A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101782625A (en) * | 2009-01-16 | 2010-07-21 | 复旦大学 | Power electronic system fault diagnostic method based on Gradation-boosting algorithm |
| CN103871004A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network failure cause analyzing method based on expert system and D-S evidence theory |
| CN104573740A (en) * | 2014-12-22 | 2015-04-29 | 山东鲁能软件技术有限公司 | SVM classification model-based equipment fault diagnosing method |
| CN105140898A (en) * | 2015-08-14 | 2015-12-09 | 国家电网公司 | Comprehensive prevention and control method for rural power grid distribution line fault |
| CN105301388A (en) * | 2015-10-14 | 2016-02-03 | 杭州南车城市轨道交通车辆有限公司 | Rail transit transformer fault diagnosis method |
| CN107358366A (en) * | 2017-07-20 | 2017-11-17 | 国网辽宁省电力有限公司 | A kind of distribution transformer failure risk monitoring method and system |
| CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
| CN108009037A (en) * | 2017-11-24 | 2018-05-08 | 中国银行股份有限公司 | Batch processing job fault handling method, device, storage medium and equipment |
| CN108375715A (en) * | 2018-03-08 | 2018-08-07 | 中国电力科学研究院有限公司 | A kind of distribution network line fault risk day prediction technique and system |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222247A (en) * | 2019-06-10 | 2019-09-10 | 交通运输部公路科学研究所 | A kind of highway engineering construction safety hazard analysis system |
| CN110703135B (en) * | 2019-10-18 | 2021-10-29 | 国网福建省电力有限公司 | Full study and judgment method for fault handling of power distribution network |
| CN110703135A (en) * | 2019-10-18 | 2020-01-17 | 国网福建省电力有限公司 | Full study and judgment method for fault handling of power distribution network |
| CN110866739A (en) * | 2019-11-29 | 2020-03-06 | 国网四川省电力公司电力科学研究院 | Power distribution network comprehensive power failure time representation method considering troubleshooting path |
| CN110866739B (en) * | 2019-11-29 | 2022-08-12 | 国网四川省电力公司电力科学研究院 | Power distribution network comprehensive power failure time representation method considering troubleshooting path |
| CN111812457A (en) * | 2020-07-17 | 2020-10-23 | 重庆东电通信技术有限公司 | Dynamic and static characteristic full-coverage fault assessment model for power transmission line and tower equipment |
| CN112036449A (en) * | 2020-08-11 | 2020-12-04 | 广州番禺电缆集团有限公司 | Fault analysis decision platform and fault analysis method based on intelligent cable |
| CN112510699A (en) * | 2020-11-25 | 2021-03-16 | 国网湖北省电力有限公司咸宁供电公司 | Transformer substation secondary equipment state analysis method and device based on big data |
| CN113093985B (en) * | 2021-06-09 | 2021-09-10 | 中国南方电网有限责任公司超高压输电公司广州局 | Sensor data link abnormity detection method and device and computer equipment |
| CN113093985A (en) * | 2021-06-09 | 2021-07-09 | 中国南方电网有限责任公司超高压输电公司广州局 | Sensor data link abnormity detection method and device and computer equipment |
| CN113625109A (en) * | 2021-08-04 | 2021-11-09 | 广西电网有限责任公司电力科学研究院 | Intelligent diagnosis method and device for power line faults |
| CN113960409A (en) * | 2021-09-14 | 2022-01-21 | 广州番禺电缆集团有限公司 | Cable fault cause determination method, device, equipment and storage medium |
| CN113960409B (en) * | 2021-09-14 | 2023-10-24 | 广州番禺电缆集团有限公司 | Cable fault cause determining method, device, equipment and storage medium |
| CN114200243A (en) * | 2021-12-24 | 2022-03-18 | 广西电网有限责任公司 | Low-voltage transformer area fault intelligent diagnosis method and system |
| CN114200243B (en) * | 2021-12-24 | 2023-10-24 | 广西电网有限责任公司 | Intelligent diagnosis method and system for faults of low-voltage transformer area |
| CN114372596A (en) * | 2022-03-21 | 2022-04-19 | 广东电网有限责任公司佛山供电局 | Power data analysis method and system based on data fusion |
| CN114696467A (en) * | 2022-05-31 | 2022-07-01 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing fault tripping event of high-voltage transmission long line |
| CN116170283A (en) * | 2023-04-23 | 2023-05-26 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
| CN116170283B (en) * | 2023-04-23 | 2023-07-14 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109655712A (en) | A kind of distribution network line fault analysis of causes method and system | |
| CN106021596B (en) | A kind of analysis method of electric network fault rush of current topological diagram | |
| CN110929853A (en) | Power distribution network line fault prediction method based on deep learning | |
| CN108074021A (en) | A kind of power distribution network Risk Identification system and method | |
| Hardiman et al. | An advanced tool for analyzing multiple cascading failures | |
| CN108846591A (en) | A kind of more operating status intelligent monitor systems of switch cabinet of converting station and appraisal procedure | |
| CN109241169A (en) | The multi-source heterogeneous data fusion geo-database integration method of power distribution network operation information | |
| CN116169778A (en) | Processing method and system based on power distribution network anomaly analysis | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN106651128A (en) | Power transmission and transformation system risk early warning method | |
| CN113435492A (en) | Power system dominant instability mode discrimination method based on active learning | |
| CN114936450A (en) | Digital twin evaluation method and system for dynamic capacity increase of wind power transmission line | |
| CN108459269A (en) | A kind of 10kV pvs (pole-mounted vacuum switch)s state on-line evaluation method and apparatus | |
| CN111209535B (en) | Power equipment successive fault risk identification method and system | |
| Li et al. | A line-fault cause analysis method for distribution network based on decision-making tree and machine learning | |
| CN106952178B (en) | Telemetry bad data identification and reason distinguishing method based on measurement balance | |
| CN106093636A (en) | The analog quantity check method of the secondary device of intelligent grid and device | |
| CN116595459A (en) | Pollution flashover early warning method and system based on electric field signals | |
| Sun et al. | Transmission Line Fault Diagnosis Method Based on Improved Multiple SVM Model | |
| CN106159940B (en) | The optimal points distributing methods of PMU based on network load specificity analysis | |
| CN109035066A (en) | The high breaking route genetic analysis of 10 kilovolts of distributions and administering method based on SVM | |
| CN116170283B (en) | Processing method based on network communication fault system | |
| Ren et al. | Research on causes of transmission line fault based on decision tree classification | |
| CN114156865B (en) | Low-voltage distribution network topology generation and fault prediction method considering state perception | |
| CN108667073A (en) | A kind of anti-isolated island method of photovoltaic based on dispatch automated system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200519 Address after: 100192 Beijing city Haidian District Qinghe small Camp Road No. 15 Applicant after: CHINA ELECTRIC POWER RESEARCH INSTITUTE Co.,Ltd. Applicant after: STATE GRID CORPORATION OF CHINA Applicant after: STATE GRID SHANDONG ELECTRIC POWER Co. Applicant after: DEZHOU POWER SUPPLY COMPANY OF STATE GRID SHANDONG ELECTRIC POWER Co. Address before: 100192 Beijing city Haidian District Qinghe small Camp Road No. 15 Applicant before: CHINA ELECTRIC POWER RESEARCH INSTITUTE Co.,Ltd. Applicant before: STATE GRID CORPORATION OF CHINA Applicant before: STATE GRID SHANDONG ELECTRIC POWER Co. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |