CN109799425A - Electric network failure diagnosis method and device - Google Patents
Electric network failure diagnosis method and device Download PDFInfo
- Publication number
- CN109799425A CN109799425A CN201910133422.9A CN201910133422A CN109799425A CN 109799425 A CN109799425 A CN 109799425A CN 201910133422 A CN201910133422 A CN 201910133422A CN 109799425 A CN109799425 A CN 109799425A
- Authority
- CN
- China
- Prior art keywords
- fault
- warning information
- diagnosis
- electric network
- fault diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of electric network failure diagnosis method and devices, this method comprises: the fault warning information of real-time monitoring power grid;Electric network fault is diagnosed according to fault warning information based on the hierarchical fault diagnosis model constructed in advance;Hierarchical fault diagnosis model includes: the first diagnostic horizon and second opinion layer;Wherein, the first diagnostic horizon is for diagnosing known electric network fault;The unknown electric network fault that second opinion layer is used to fail the first diagnostic horizon identification diagnoses, and the fault diagnosis result of second opinion layer is also used to update the first diagnostic horizon.The technical effect that the present invention is realized to known power grid Fault Quick Diagnosis, effectively identified to unknown electric network fault, and updates and safeguard to fault diagnosis model automatically.
Description
Technical field
The present invention relates to field of power system more particularly to a kind of electric network failure diagnosis method and devices.
Background technique
This part intends to provides background or context for the embodiment of the present invention stated in claims.Description herein
Recognize it is the prior art not because not being included in this section.
Electric network failure diagnosis is one of the basic project that smart power grid fault intelligent decision-makingization needs to solve, quickly, effectively
Ground diagnoses with isolated fault element electric network fault, avoids fault spread, and then takes corresponding measure fast recovery of power supply,
It is of great significance for shortening power off time and improving troubleshooting efficiency.
In recent years, effectively to diagnose to electric network fault, lot of domestic and foreign experts and scholars propose from different starting points
Many fault diagnosis technologies are (for example, expert system, artificial neural network, Bayesian network, Petri network, analytic modell analytical model, number
Value calculates analysis etc.), it can be obtained in the case that these fault diagnosis technologies are accurate in fault warning information and sample set is complete
Preferable diagnosis effect.The model maintenance of diagnosis for online electric network fault, these existing fault diagnosis technologies is complicated, and
In fault warning information errors, fault diagnosis accuracy rate is lower.
As a result, how on existing Research foundation, realizes the Accurate Model of electric network failure diagnosis and accurately solve, become
The urgent need of electric network failure diagnosis development at present.
Summary of the invention
The embodiment of the present invention provides a kind of electric network failure diagnosis method, to solve existing electric network failure diagnosis scheme,
It is low for online electric network failure diagnosis accuracy rate, and the technical problem of model maintenance complexity.This method comprises: real-time monitoring power grid
Fault warning information;Electric network fault is carried out according to fault warning information based on the hierarchical fault diagnosis model constructed in advance
Diagnosis;Hierarchical fault diagnosis model includes: the first diagnostic horizon and second opinion layer;Wherein, the first diagnostic horizon is used for known electric
Net failure is diagnosed;The unknown electric network fault that second opinion layer is used to fail the first diagnostic horizon identification diagnoses, and second
The fault diagnosis result of diagnostic horizon is also used to update the first diagnostic horizon.
The embodiment of the present invention also provides a kind of electric network failure diagnosis device, to solve existing electric network failure diagnosis side
Case, it is low for online electric network failure diagnosis accuracy rate, and the technical problem of model maintenance complexity.The device includes: power network monitoring
Module, the fault warning information for real-time monitoring power grid;Electric network failure diagnosis module, for based on the layering event constructed in advance
Barrier diagnostic model diagnoses electric network fault according to fault warning information;Hierarchical fault diagnosis model includes: the first diagnosis
Layer and second opinion layer;Wherein, the first diagnostic horizon is for diagnosing known electric network fault;Second opinion layer is used for first
The unknown electric network fault that diagnostic horizon fails identification is diagnosed, and the fault diagnosis result of second opinion layer is also used to update first and examines
Tomography.
The embodiment of the present invention also provides a kind of computer equipment, to solve existing electric network failure diagnosis scheme, for
Online electric network failure diagnosis accuracy rate is low, and the technical problem of model maintenance complexity.The computer equipment includes memory, processing
Device and storage on a memory and the computer program that can run on a processor, when processor executes computer program in realization
State electric network failure diagnosis method.
The embodiment of the present invention also provides a kind of computer readable storage medium, to solve existing electric network failure diagnosis side
Case, it is low for online electric network failure diagnosis accuracy rate, and the technical problem of model maintenance complexity.The computer readable storage medium
It is stored with the computer program for executing above-mentioned electric network failure diagnosis method.
In the embodiment of the present invention, a kind of hierarchical fault diagnosis model is provided, in the fault warning information for getting power grid
Afterwards, using the different levels of the hierarchical fault diagnosis model, the known fault and unknown failure of power grid are diagnosed, and in benefit
After being diagnosed with unknown failure diagnostic horizon to unknown failure, using the reciprocation between level, by unknown failure diagnostic horizon
Fault diagnosis result feed back to known fault diagnostic horizon, known fault diagnostic horizon is updated, so that known fault is examined
Tomography diagnoses more electric network faults.
Through the embodiment of the present invention, it realizes to known power grid Fault Quick Diagnosis, unknown electric network fault is effectively identified,
And the technical effect that fault diagnosis model is updated and is safeguarded automatically.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is a kind of electric network failure diagnosis method flow diagram provided in the embodiment of the present invention;
Fig. 2 is that the immune fault diagnosis model of a kind of layering for electric network failure diagnosis provided in the embodiment of the present invention shows
It is intended to;
Fig. 3 is the information exchange in the immune fault diagnosis model of layering provided in the embodiment of the present invention between each diagnostic horizon
Schematic diagram;
Fig. 4 is a kind of electric network failure diagnosis device schematic diagram provided in the embodiment of the present invention.
Specific embodiment
Understand in order to make the object, technical scheme and advantages of the embodiment of the invention clearer, with reference to the accompanying drawing to this hair
Bright embodiment is described in further details.Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but simultaneously
It is not as a limitation of the invention.
A kind of electric network failure diagnosis method is provided in the embodiment of the present invention, Fig. 1 is one provided in the embodiment of the present invention
Kind electric network failure diagnosis method flow diagram, as shown in Figure 1, this method comprises the following steps:
S101, the fault warning information of real-time monitoring power grid.
It should be noted that power grid can feed back fault warning information when electric network element breaks down, thus, above-mentioned electricity
The associated switching value of various elements (for example, bus, route, transformer etc.) in power grid is included at least in the fault warning information of net
Information.
S102 examines electric network fault according to fault warning information based on the hierarchical fault diagnosis model constructed in advance
It is disconnected;Hierarchical fault diagnosis model includes: the first diagnostic horizon and second opinion layer;Wherein, the first diagnostic horizon is used for known power grid
Failure is diagnosed;The unknown electric network fault that second opinion layer is used to fail the first diagnostic horizon identification diagnoses, and second examines
The fault diagnosis result of tomography is also used to update the first diagnostic horizon.
It should be noted that above-mentioned hierarchical fault diagnosis model refer to construct in advance by different levels come to known electric
The fault diagnosis model that net failure and unknown electric network fault are diagnosed, as a preferred embodiment, the present invention is implemented
Example passes through the interaction simulated between biological inherent immunity system and the layering defense mechanism and its level of adaptive immune system,
Construct a kind of immune fault diagnosis model of the layering based on immunity principle.
Fig. 2 is that the immune fault diagnosis model of a kind of layering for electric network failure diagnosis provided in the embodiment of the present invention shows
It is intended to, as shown in Fig. 2, the immune fault diagnosis model of layering provided in an embodiment of the present invention includes: inherent diagnosis layer (i.e. to known
The first diagnostic horizon that electric network fault is diagnosed) and adaptive diagnosis layer (i.e. to the first diagnostic horizon fail identification unknown power grid
The second opinion layer that failure is diagnosed).
From the foregoing, it will be observed that the embodiment of the present invention passes through constructs hierarchical fault diagnosis model in advance, in the failure for getting power grid
After warning information, using the different levels of the hierarchical fault diagnosis model, the known fault and unknown failure of power grid are examined
It is disconnected, and after being diagnosed using unknown failure diagnostic horizon to unknown failure, it, will unknown event using the reciprocation between level
The fault diagnosis result for hindering diagnostic horizon is fed back to known fault diagnostic horizon, is updated to known fault diagnostic horizon, so that
Know that fault diagnosis layer diagnoses more electric network faults.Through the embodiment of the present invention, it realizes fast to known electric network fault
The technical effect that speed diagnosis effectively identifies unknown electric network fault, and updates and safeguard to fault diagnosis model automatically.
It should be noted that in order to improve efficiency of fault diagnosis, electric network failure diagnosis scheme provided in an embodiment of the present invention,
So that the first diagnostic horizon in hierarchical fault diagnosis model diagnoses known electric network fault, and second opinion layer is only to first
The unknown electric network fault that diagnostic horizon fails identification is diagnosed.Based on the purpose, as an alternative embodiment, such as Fig. 1
Shown, above-mentioned S102 can specifically comprise the following steps:
S1021, by fault warning information input to the first diagnostic horizon;
S1022, judges whether the first diagnostic horizon exports the corresponding fault diagnosis result of fault warning information;
Fault warning information is transmitted to second in the case where the first diagnostic horizon does not export fault diagnosis result by S1023
Diagnostic horizon, the corresponding fault diagnosis result of output fault warning information.
It should be noted that the fault warning information in above-mentioned S1021 can be real-time monitoring power grid and the reality that gets
When fault warning information, the fault warning information obtained in real time is transmitted to the first diagnostic horizon of hierarchical fault diagnosis model, by
Known electric network fault is diagnosed in the first diagnostic horizon, if the fault warning information that the first diagnostic horizon receives is unknown electricity
The warning information of net failure, then the first diagnostic horizon can not be diagnosed to be as a result, being also impossible to export fault warning information correspondence
Fault diagnosis result.Thus, after the fault warning information got in real time is transmitted to the first diagnostic horizon by S1021,
Judge whether the first diagnostic horizon exports the corresponding fault diagnosis result of fault warning information by S1022, if the first diagnostic horizon
Fault diagnosis result is not exported, then the fault warning information is transmitted to the second of hierarchical fault diagnosis model by S1023
Diagnostic horizon effectively identifies unknown electric network fault by second opinion layer.
Wherein, judging whether the first diagnostic horizon exports the corresponding fault diagnosis result of fault warning information by S1022
When, can according to the feature vector of fault warning information, by the way of pattern match, search fault knowledge library in therefore
Hinder the matched electric network fault of warning information;It wherein, is failure with the electric network fault of fault warning information matches in fault knowledge library
The corresponding fault diagnosis result of warning information.
Optionally, above-mentioned that fault warning information is being transmitted to by second opinion layer by S1023, export fault warning information
When corresponding fault diagnosis result, it can specifically comprise the following steps: to construct fault diagnosis number according to fault warning information
Learn analytic modell analytical model;Based on fault diagnosis analytical mathematical models, parsing obtains the corresponding fault diagnosis result of fault warning information.
Wherein, fault diagnosis analytical mathematical models are being based on, parsing obtains the corresponding fault diagnosis knot of fault warning information
It after fruit, can further include: if parsing obtains the corresponding multiple fault diagnosis results of fault warning information, being based on
The electrical data of power grid recognizes multiple fault diagnosis results, determines that fault warning information is corresponding according to identification result
One fault diagnosis result.For example, it is assumed that the failure that a certain regional power grid occurs is unknown failure, pass through fault diagnosis mathematical solution
After model is analysed to unknown failure identification, determine that failure is likely to occur in route 1, route 2 or route 1, the transformer 1 of the power grid
When to get to two fault diagnosis results, then can be based further on route 1, route 2, the associated electrical quantity of transformer 1 letter
Breath, recognizes the voltage or current information of the element of each failure to be determined, which element failure determined.
In order to realize the purpose for automatically updating and safeguarding fault diagnosis model, in a kind of optional embodiment, above-mentioned
After S1023, electric network failure diagnosis method provided in an embodiment of the present invention can further include following steps: second is examined
The fault diagnosis result of tomography output feeds back to the first diagnostic horizon;Fault diagnosis result to the output of second opinion layer and corresponding
Fault warning information is trained study;According to training learning outcome, the first diagnostic horizon is updated.
By above embodiment, the second opinion layer in hierarchical fault diagnosis model that provides through the embodiment of the present invention
Unknown electric network fault is carried out after effectively identifying, the fault diagnosis result of second opinion layer is fed back into the first diagnostic horizon, is passed through
Training study updates the first diagnostic horizon, so that the first diagnostic horizon may be implemented to new failure to obtain new tracer
It is diagnosed.
Provided in an embodiment of the present invention to be layered in immune fault diagnosis model, inherent diagnosis layer mainly sending out by complete paired fault
The foundation and dimension of the quick diagnosis and immunological learning mechanism and fault knowledge library of known fault independent of each other on raw probability
Shield;Adaptive diagnosis layer solves the new failure that inherent diagnosis layer fails identification in an adaptive way.Wherein, inherent diagnosis layer
Fault diagnosis is using power network switch amount fault data as inputting, by constructing the event based on scheduling observation data and Model Matching degree
Hinder diagnostic model, is diagnosed using method for mode matching;Adaptive diagnosis layer receives the power grid that inherent diagnosis layer fails identification
Switching value fault data, and related electric amount data are called in, complete the diagnosis identification of new failure.
As shown in Fig. 2, inherent diagnosis layer is by humoral immunity study module, fault knowledge library and Pattern Matching Module group
At passing through humoral immunity and learn module and complete the building in fault knowledge library and realize the successive learning of new failure;For known event
The diagnosis of barrier, the tracer generated based on priori knowledge in application failure knowledge base, using the method for pattern match, with
The diagnostic knowledge known carries out quickly diagnosis identification to the real time fail warning information of goal systems.The simulation of adaptive diagnosis layer is suitable
The immunologic mechanism and defense reaction of answering property immune system solve the new event that inherent diagnosis layer fails identification in an adaptive way
Barrier, including unknown failure diagnosis identification and failure disaggregation recognize two links.
Wherein, in unknown failure diagnosis identification link, the fault diagnosis module based on analytical mathematical models is constructed, using suitable
The immunological learning and immunological memory characteristic of answering property immune system, solve electric network failure diagnosis by the way of multiple-objection optimization and ask
Topic.By seeking for the optimal solution to build object function, complete inherent diagnosis layer can not the diagnosis of matched new failure know
Not;Diagnostic result, which is fed back to inherent diagnosis layer, is used to generate new tracer simultaneously, to complete the company of unknown failure
Continuous study.
Fault warning information is received when unknown failure diagnoses identification link, and is examined using the failure based on analytical mathematical models
After disconnected module carries out diagnostic analysis, if failing to identify the failure (i.e. analytic modell analytical model generates more solutions), by the multiple solution of generation
Data offer to recognize link to failure disaggregation, call in the relevant electrical data of suspected fault element and are analyzed and determined.
In failure disaggregation identification link, the multiple solution problem that identification link generates is diagnosed for unknown failure, multiple
It introduces electrical data to suspected fault element within the scope of disaggregation to analyze, the suspected faults such as building bus, route, transformer
The electrical quantity criterion of element, using electrical quantity recognition result as the judgment basis of multiple solution, to complete asking for last diagnostic result
It takes.Diagnostic result is also fed back into inherent diagnosis layer simultaneously and carries out successive learning.
Fig. 3 is the information exchange in the immune fault diagnosis model of layering provided in the embodiment of the present invention between each diagnostic horizon
Schematic diagram, as shown in figure 3, offered between each level for the immune fault diagnosis model of layering that the present invention designs by antigen and
Activation signal carries out information and transmits and interact (for example, transmitting Diagnostic parameters, signal and diagnostic result), by between each level
It cooperates and carries out fault diagnosis, realize automatically updating for fault knowledge library, reach the diagnosis capability of fault diagnosis system
Optimal effect.As a preferred embodiment, provided in an embodiment of the present invention be layered examining for immune fault diagnosis model
Disconnected process mainly comprises the steps that
(1) real time fail warning information is described the behavioural characteristic of problem by fault diagnosis system as external signal.When
When electric network element breaks down, the fault warning information of feedback is obtained.
(2) call inherent diagnosis layer, by the feature vector of the fault warning information of real-time monitoring and fault knowledge library
Know that failure carries out diagnosis identification with method for mode matching.If diagnosing successfully, fault diagnosis result is exported, otherwise inherent diagnosis layer
Offer the fault warning information for failing identification to give adaptive diagnosis layer.
(3) adaptive diagnosis layer is called, identification link is diagnosed by unknown failure first and receives fault warning information, it is solid simultaneously
There is diagnostic horizon to issue dangerous activation signal to it, using these signal interactions, carries out adaptive diagnosis.
(4) it executes unknown failure diagnosis identification link and fault diagnosis mathematics to be optimized is determined according to fault warning information
Analytic modell analytical model, and optimize.If it is determined that unique failure solution, then export fault diagnosis result;If generating multiple solution (i.e. not
Can identify failure), then the multiple solution data of generation are offered to recognize link to failure disaggregation.
(5) it executes failure disaggregation and recognizes link, call in the relevant electrical data of suspected fault element and analyzed and determined,
The electrical quantity criterion for constructing the suspected faults elements such as bus, route, transformer is determined according to electrical quantity as a result, rejecting mistake solution
Collection obtains final correct fault diagnosis result.
(6) activation humoral immunity learns module, the fault diagnosis result obtained by learning feedback to step (4) or (5)
It is trained, generates the new tracer that can identify the fault warning information, and be fed back to the failure of inherent diagnosis layer
It is saved in knowledge base, when similar failure occurs again, can use fault knowledge library and carry out quick response.
Fault diagnosis model is immunized in layering provided in an embodiment of the present invention for electric network failure diagnosis, step by step, stage by stage
The electric network failure diagnosis that corresponding immune level is carried out using all kinds of failure relevant informations, realizes known fault by inherent diagnosis layer
Quick diagnosis, by applicability diagnostic horizon realize unknown failure effective identification, by study feedback mechanism to the new of generation
Failure carries out successive learning, gradually supplements and improve diagnostic knowledge, promotes trouble diagnosibility.
A kind of electric network failure diagnosis device is additionally provided in the embodiment of the present invention, as described in the following examples.Due to this
The principle that Installation practice solves the problems, such as is similar to electric network failure diagnosis method, therefore the implementation of the Installation practice may refer to
The implementation of method, overlaps will not be repeated.
Fig. 4 is a kind of electric network failure diagnosis device schematic diagram provided in the embodiment of the present invention, as shown in figure 4, the device
Include:
Power network monitoring module 41, the fault warning information for real-time monitoring power grid;
Electric network failure diagnosis module 42, for being believed according to fault warning based on the hierarchical fault diagnosis model constructed in advance
Breath, diagnoses electric network fault;Hierarchical fault diagnosis model includes: the first diagnostic horizon and second opinion layer;Wherein, it first examines
Tomography is for diagnosing known electric network fault;Second opinion layer is used to fail the first diagnostic horizon the unknown power grid event of identification
Barrier is diagnosed, and the fault diagnosis result of second opinion layer is also used to update the first diagnostic horizon.
From the foregoing, it will be observed that the embodiment of the present invention passes through constructs hierarchical fault diagnosis model in advance, in the failure for getting power grid
After warning information, using the different levels of the hierarchical fault diagnosis model, the known fault and unknown failure of power grid are examined
It is disconnected, and after being diagnosed using unknown failure diagnostic horizon to unknown failure, it, will unknown event using the reciprocation between level
The fault diagnosis result for hindering diagnostic horizon is fed back to known fault diagnostic horizon, is updated to known fault diagnostic horizon, so that
Know that fault diagnosis layer diagnoses more electric network faults.Through the embodiment of the present invention, it realizes fast to known electric network fault
The technical effect that speed diagnosis effectively identifies unknown electric network fault, and updates and safeguard to fault diagnosis model automatically.
In an alternative embodiment, above-mentioned electric network failure diagnosis module 42 can specifically include: fault warning information
Module 421 is obtained, is used for fault warning information input to the first diagnostic horizon;Known fault diagnostic module 422, for judging the
Whether one diagnostic horizon exports the corresponding fault diagnosis result of fault warning information;Unknown failure diagnostic module 423, for first
In the case that diagnostic horizon does not export fault diagnosis result, fault warning information is transmitted to second opinion layer, exports fault warning
The corresponding fault diagnosis result of information.
Optionally, above-mentioned known fault diagnostic module 422 is also used to the feature vector according to fault warning information, using mould
The matched mode of formula searches the electric network fault in fault knowledge library with fault warning information matches;Wherein, in fault knowledge library with
The electric network fault of fault warning information matches is the corresponding fault diagnosis result of fault warning information.
Optionally, above-mentioned unknown failure diagnostic module 423 is also used to construct fault diagnosis mathematics according to fault warning information
Analytic modell analytical model;Based on fault diagnosis analytical mathematical models, parsing obtains the corresponding fault diagnosis result of fault warning information.
Further, if above-mentioned unknown failure diagnostic module 423 is also used to parse, to obtain fault warning information corresponding
Multiple fault diagnosis results then recognize multiple fault diagnosis results based on the electrical data of power grid, are tied according to identification
Fruit determines the corresponding fault diagnosis result of fault warning information.
In an alternative embodiment, electric network failure diagnosis device provided in an embodiment of the present invention can also include: event
Barrier study feedback module 43, the fault diagnosis result for exporting second opinion layer feed back to the first diagnostic horizon;It examines second
The fault diagnosis result of tomography output and corresponding fault warning information are trained study;According to training learning outcome, update
First diagnostic horizon.
Based on any one of the above is optional or preferred Installation practice, as a preferred embodiment, this hair
Fault diagnosis mould is immunized using the layering based on immunity principle in hierarchical fault diagnosis model in bright each Installation practice
Type, the first diagnostic horizon are the inherent diagnosis layer for being layered immune fault diagnosis model, and second opinion layer is to be layered immune fault diagnosis
The adaptive diagnosis layer of model.
The embodiment of the present invention also provides a kind of computer equipment, to solve existing electric network failure diagnosis scheme, for
Online electric network failure diagnosis accuracy rate is low, and the technical problem of model maintenance complexity, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, processor realize above method embodiment when executing computer program
In any one optional or preferred electric network failure diagnosis method.
The embodiment of the present invention also provides a kind of computer readable storage medium, to solve existing electric network failure diagnosis side
Case, it is low for online electric network failure diagnosis accuracy rate, and the technical problem of model maintenance complexity, computer readable storage medium are deposited
Contain the computer program for executing any one optional or preferred electric network failure diagnosis method in above method embodiment.
In conclusion electric network failure diagnosis scheme provided in an embodiment of the present invention, the layering for using for reference Immune System is anti-
Imperial mechanism constructs electric network failure diagnosis model, proposes a kind of layering towards electric network failure diagnosis and fault diagnosis mould is immunized
Type carries out failure using the different levels of hierarchical fault diagnosis model respectively and examines for the known fault and unknown failure of power grid
It is disconnected, Diagnostic parameters, signal and diagnostic result are transmitted by the reciprocation between hierarchical fault diagnosis model level, had known
The function of the successive learning of the quick diagnosis of failure, effective identification of unknown failure and new failure;The model has taken into account electricity simultaneously
The fault diagnosis of net switching value and electrical quantity helps to improve the accurate of fault diagnosis so that information resources are rationally utilized
Rate and efficiency.
It should be understood by those skilled in the art that, the embodiment of the present invention 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 present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, 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 present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
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.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Range is protected, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of invention.
Claims (10)
1. a kind of electric network failure diagnosis method characterized by comprising
The fault warning information of real-time monitoring power grid;
Electric network fault is diagnosed according to the fault warning information based on the hierarchical fault diagnosis model constructed in advance;Institute
Stating hierarchical fault diagnosis model includes: the first diagnostic horizon and second opinion layer;Wherein, first diagnostic horizon is used for known electric
Net failure is diagnosed;The unknown electric network fault that the second opinion layer is used to fail first diagnostic horizon identification is examined
Disconnected, the fault diagnosis result of the second opinion layer is also used to update first diagnostic horizon.
2. the method as described in claim 1, which is characterized in that based on the hierarchical fault diagnosis model constructed in advance, according to institute
Fault warning information is stated, electric network fault is diagnosed, comprising:
By the fault warning information input to first diagnostic horizon;
Judge whether first diagnostic horizon exports the corresponding fault diagnosis result of the fault warning information;
In the case where first diagnostic horizon does not export fault diagnosis result, the fault warning information is transmitted to described
Two diagnostic horizons export the corresponding fault diagnosis result of the fault warning information.
3. method according to claim 2, which is characterized in that judge whether first diagnostic horizon exports the fault warning
The corresponding fault diagnosis result of information, comprising:
According to the feature vector of the fault warning information, by the way of pattern match, search fault knowledge library in it is described
The electric network fault of fault warning information matches;Wherein, the power grid in the fault knowledge library with the fault warning information matches
Failure is the corresponding fault diagnosis result of the fault warning information.
4. method according to claim 2, which is characterized in that the fault warning information is transmitted to the second opinion
Layer, exports the corresponding fault diagnosis result of the fault warning information, comprising:
According to the fault warning information, fault diagnosis analytical mathematical models are constructed;
Based on the fault diagnosis analytical mathematical models, parsing obtains the corresponding fault diagnosis result of the fault warning information.
5. method as claimed in claim 4, which is characterized in that be based on the fault diagnosis analytical mathematical models, parsing
To after the corresponding fault diagnosis result of the fault warning information, the method also includes:
If parsing obtains the corresponding multiple fault diagnosis results of the fault warning information, the electrical data based on power grid
The multiple fault diagnosis result is recognized, the corresponding failure of the fault warning information is determined according to identification result
Diagnostic result.
6. method according to claim 2, which is characterized in that the fault warning information is being transmitted to the second opinion
Layer, after exporting the corresponding fault diagnosis result of the fault warning information, the method also includes:
The fault diagnosis result that the second opinion layer exports is fed back into first diagnostic horizon;
Study is trained to the fault diagnosis result and corresponding fault warning information of second opinion layer output;
According to training learning outcome, first diagnostic horizon is updated.
7. the method as described in claim 1 to 6 is any, which is characterized in that the hierarchical fault diagnosis model is based on immune
Fault diagnosis model is immunized in the layering of principle, and first diagnostic horizon is the inherent diagnosis for being layered immune fault diagnosis model
Layer, the second opinion layer are the adaptive diagnosis layer for being layered immune fault diagnosis model.
8. a kind of electric network failure diagnosis device characterized by comprising
Power network monitoring module, the fault warning information for real-time monitoring power grid;
Electric network failure diagnosis module, for based on the hierarchical fault diagnosis model constructed in advance, according to the fault warning information,
Electric network fault is diagnosed;The hierarchical fault diagnosis model includes: the first diagnostic horizon and second opinion layer;Wherein, described
First diagnostic horizon is for diagnosing known electric network fault;The second opinion layer to first diagnostic horizon for failing to know
Other unknown electric network fault is diagnosed, and the fault diagnosis result of the second opinion layer is also used to update first diagnosis
Layer.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any electricity of claim 1 to 7 when executing the computer program
Net method for diagnosing faults.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has perform claim
It is required that the computer program of 1 to 7 any electric network failure diagnosis method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910133422.9A CN109799425B (en) | 2019-02-22 | 2019-02-22 | Power grid fault diagnosis method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910133422.9A CN109799425B (en) | 2019-02-22 | 2019-02-22 | Power grid fault diagnosis method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109799425A true CN109799425A (en) | 2019-05-24 |
CN109799425B CN109799425B (en) | 2022-02-18 |
Family
ID=66561174
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910133422.9A Active CN109799425B (en) | 2019-02-22 | 2019-02-22 | Power grid fault diagnosis method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109799425B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111579923A (en) * | 2020-05-19 | 2020-08-25 | 广东电网有限责任公司 | Power distribution network fault diagnosis system and method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160282416A1 (en) * | 2015-03-26 | 2016-09-29 | The University Of Akron | System and method for iterative condition monitoring and fault diagnosis of electric machines |
CN106980066A (en) * | 2016-12-29 | 2017-07-25 | 华北电力大学 | A kind of electric network failure diagnosis model building method based on humoral immune response mechanism |
CN107426741A (en) * | 2017-07-20 | 2017-12-01 | 重庆三峡学院 | A kind of wireless sensor network fault diagnosis method based on immune mechanism |
CN107681683A (en) * | 2017-11-10 | 2018-02-09 | 浙江大学 | A kind of alternating current-direct current receiving end line commutation failure trouble-saving method based on parametrization Thevenin's equivalence |
CN108594079A (en) * | 2018-05-02 | 2018-09-28 | 广东电网有限责任公司 | A kind of electrical power distribution network fault location method, device and computer-readable medium |
-
2019
- 2019-02-22 CN CN201910133422.9A patent/CN109799425B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160282416A1 (en) * | 2015-03-26 | 2016-09-29 | The University Of Akron | System and method for iterative condition monitoring and fault diagnosis of electric machines |
CN106980066A (en) * | 2016-12-29 | 2017-07-25 | 华北电力大学 | A kind of electric network failure diagnosis model building method based on humoral immune response mechanism |
CN107426741A (en) * | 2017-07-20 | 2017-12-01 | 重庆三峡学院 | A kind of wireless sensor network fault diagnosis method based on immune mechanism |
CN107681683A (en) * | 2017-11-10 | 2018-02-09 | 浙江大学 | A kind of alternating current-direct current receiving end line commutation failure trouble-saving method based on parametrization Thevenin's equivalence |
CN108594079A (en) * | 2018-05-02 | 2018-09-28 | 广东电网有限责任公司 | A kind of electrical power distribution network fault location method, device and computer-readable medium |
Non-Patent Citations (3)
Title |
---|
王守鹏等: "一种基于体液免疫原理的电网故障诊断模型设计方法", 《电力建设》 * |
田玉玲: "多层免疫模型及其在故障诊断中的应用研究", 《中国博士学位论文全文数据库(工程科技II辑)》 * |
田玉玲等: "多层免疫故障诊断模型的研究", 《计算机工程与应用》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111579923A (en) * | 2020-05-19 | 2020-08-25 | 广东电网有限责任公司 | Power distribution network fault diagnosis system and method |
CN111579923B (en) * | 2020-05-19 | 2022-04-15 | 广东电网有限责任公司 | Power distribution network fault diagnosis system and method |
Also Published As
Publication number | Publication date |
---|---|
CN109799425B (en) | 2022-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
CN109061341A (en) | Kalman filtering transformer fault prediction technique and system neural network based | |
EP3422518B1 (en) | A method for recognizing contingencies in a power supply network | |
CN109255440B (en) | Method for predictive maintenance of power production equipment based on Recurrent Neural Networks (RNN) | |
CN106662072A (en) | Wind turbine condition monitoring method and system | |
CN109501834A (en) | A kind of point machine failure prediction method and device | |
CN109948808A (en) | The banking process in substation equipment fault case library, fault diagnosis method and system | |
CN109800995A (en) | A kind of grid equipment fault recognition method and system | |
CN110163075A (en) | A kind of multi-information fusion method for diagnosing faults based on Weight Training | |
CN112464995A (en) | Power grid distribution transformer fault diagnosis method and system based on decision tree algorithm | |
CN108304567A (en) | High-tension transformer regime mode identifies and data classification method and system | |
CN110515781A (en) | A kind of complication system status monitoring and method for diagnosing faults | |
CN110082082A (en) | A kind of GIS state identification method based on vibration signal Principal Component Analysis | |
Hong et al. | Towards accurate and efficient classification of power system contingencies and cyber-attacks using recurrent neural networks | |
CN115221776A (en) | Training method and device for intelligent sensing diagnosis model of novel power distribution network | |
Nicolau et al. | Accident diagnosis system based on real-time decision tree expert system | |
CN114139589A (en) | Fault diagnosis method, device, equipment and computer readable storage medium | |
CN110378358A (en) | A kind of power distribution network isomeric data integration method and system | |
CN110361609A (en) | Extra-high voltage equipment monitors system and method | |
KR102366922B1 (en) | heavy electric equipment deterioration prediction system based on time-series isolation diagnostic information and method therefor | |
CN109799425A (en) | Electric network failure diagnosis method and device | |
CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
CN117011609A (en) | Automatic tracking system and method for textile processing progress | |
CN112286088A (en) | Method and application system for online application of power equipment fault prediction model | |
CN115859090A (en) | Turnout fault diagnosis method and system based on 1DCNN-LSTM |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |