CN106199276A - The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system - Google Patents
The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system Download PDFInfo
- Publication number
- CN106199276A CN106199276A CN201610589498.9A CN201610589498A CN106199276A CN 106199276 A CN106199276 A CN 106199276A CN 201610589498 A CN201610589498 A CN 201610589498A CN 106199276 A CN106199276 A CN 106199276A
- Authority
- CN
- China
- Prior art keywords
- model
- abnormal
- abnormity diagnosis
- exception
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/66—Testing of connections, e.g. of plugs or non-disconnectable joints
- G01R31/67—Testing the correctness of wire connections in electric apparatus or circuits
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses intelligent diagnosis system and the method for abnormal information in a kind of power information acquisition system, the system of the present invention is made up of anomaly analysis experts database, self-learning module and GIS fault location module three part, each several part collaborative work, enhances the monitoring capacity running power information acquisition system.The data that the present invention is gathered with power information acquisition system are for relying on, by anomaly analysis experts database and self-learning module, all kinds of electricity consumption data obtained are added up, analyze and diagnosed, judge Exception Type and the order of severity, and lock the particular location of fault spot rapidly and accurately by GIS fault location module, improve the accuracy of malfunction monitoring and the efficiency of troubleshooting largely.
Description
Technical field
The present invention relates to a kind of abnormal information diagnostic techniques field, be specifically related in a kind of power information acquisition system abnormal
The intelligent diagnosing method of information.
Background technology
The construction of power information acquisition system, contributes to national energy-saving and reduces discharging implementing of policy, complied with State Grid's body
The developing direction of system reform.National Development and Reform Committee's " if about this suggestion deepening power system reform further " points out " actively
Carry out demand Side Management and energy efficiency management, by using modern information technologies, cultivate electric energy service, implement demand response
Deng, promote the equilibrium of supply and demand and energy-saving and emission-reduction." " the distribution network construction modernization system plan (2015-that prints and distributes in National Energy Board
The year two thousand twenty) " in, clearly propose and " advance power distribution automation and intelligent electricity consumption information acquisition system Construction, it is achieved power distribution network is objective
Controlled.Meet the diversification load growth requirements such as new forms of energy, distributed energy and electric automobile, promote intelligent grid construction with mutual
Networking depth integration " developing goal.
Recruitment is answered by State Grid Corporation of China and the construction of Southern Power Grid Company great attention power information acquisition system and function
Making, State Grid Corporation of China started to start company's power information acquisition system comprehensively and builds in 2009, it is contemplated that within 2015, will realize
Automatically gather more than 300,000,000 family power informations.
But power information acquisition system O&M technology is the most extensive at present, there are some problem demanding prompt solutions.One is
System O&M efficiency has much room for improvement, and field adjustable, system monitoring and fault defect elimination need to expend substantial amounts of manpower and materials；Two is to be
System data dispersion, integrated level and accuracy rate are relatively low, and abnormal directivity is poor, and abundant collection data also do not play one's part to the full；Three
That system intelligent degree is relatively low, comprehensive not to the support of electric power enterprise service application, to the monitoring of various collecting devices and
Abnormal alarm ability also has to be strengthened.The problems referred to above constrain development further and the application of power information acquisition system, are badly in need of
Solve.
Summary of the invention
For the problems referred to above, the present invention proposes the intelligent diagnosing method of abnormal information in a kind of power information acquisition system,
Improve power information acquisition system operation monitoring ability, performance system big data perception, analyze, technology in terms of monitoring excellent
Gesture, supports for power marketing service provision technology, achieves good result in actual applications.
Realizing above-mentioned technical purpose, reach above-mentioned technique effect, the present invention is achieved through the following technical solutions:
The intelligent diagnosis system of abnormal information in a kind of power information acquisition system, including anomaly analysis experts database, self-study
Practise module and GIS fault location module, logical between described anomaly analysis experts database, self-learning module and GIS fault location module
Cross wireless network to connect, it is achieved sharing of fault message；
If described anomaly analysis experts database includes that Ganlei's abnormity diagnosis analyzes model；
Described self-learning module is for by using NB Algorithm to carry out the data in anomaly analysis experts database
Training, forms the criterion analyzing judgement abnormal information type corresponding to model with each abnormity diagnosis, and is used for accepting, analyzing use
The abnormal information that power utilization information collection system provides, utilizes and judges that the criterion of abnormal information type judges the type of abnormal information, and
Compare with anomaly analysis experts database, when the abnormity diagnosis of the type existing in anomaly analysis experts database analyzes model, then will
This abnormal information is referred in anomaly analysis experts database the abnormity diagnosis of correspondence and analyzes in model, and is passed to by this Exception Type
GIS fault location module；If the abnormity diagnosis not having the type in anomaly analysis experts database analyzes model, then the type is abnormal
Pass to staff, staff, after being analyzed, the new abnormity diagnosis arranging correspondence analyzes model, and this is abnormal
Information categorization analyzes model to new abnormity diagnosis, and the mode manually inputted is by this abnormal information, new Exception Type, new
Abnormity diagnosis analyze model modification in anomaly analysis experts database, and this Exception Type is passed to GIS fault location module,
Simultaneously in the abnormal menace level judge module of GIS fault location module, manually set this new Exception Type with serious etc.
The association of level, and self-learning module re-starts training to the data of new anomaly analysis experts database, formed judge new different
The often criterion of information type, and this new abnormal information is passed to self-learning module again carry out classification judgement, verify new exception
The judgment criterion of information is successfully formed the most；
Described GIS fault location module includes that the GPS positioner being arranged on each equipment, abnormal menace level judge mould
Block and GIS numerical map, GPS positioner obtains the positional information of faulty equipment for being automatically positioned faulty equipment,
Abnormal menace level judge module is for judging the menace level of this exception；GIS numerical map is for by the position of faulty equipment
Information, Exception Type, abnormal menace level show on GIS numerical map, it is achieved the quick search of abort situation.
Described abnormity diagnosis is analyzed model and is divided into single diagnostic analysis model and relevant diagnosis to analyze model, described single examines
Disconnected model of analyzing includes that electricity abnormity diagnosis model, voltage x current abnormity diagnosis model, abnormal electricity consumption diagnostic cast, load are abnormal
Diagnostic cast, clock abnormity diagnosis model, wiring abnormity diagnosis model, take control abnormity diagnosis model；Described relevant diagnosis analysis
Model includes that doubtful stealing model, equipment fault model, error connection model, distribution transforming need Extension Model, on-site maintenance model, battery
Failure model, loop Exception Model, multiplexing electric abnormality model.
Described abnormal menace level judge module is used for judging the menace level of this exception, particularly as follows: according to presetting
Exception Type and menace level between dependency relation, the Exception Type received is carried out menace level judgement；Described GIS
Numerical map specifically for demonstrating the position of faulty equipment according to the positional information of faulty equipment, and root on a corresponding position
According to Exception Type and abnormal menace level, all kinds of faulty equipments are alerted with different colors and mark respectively, and carrying out
After abnormal flow processing, the result of real-time exhibition troubleshooting.
Described abnormal menace level includes:
1 grade: emergency, there is doubtful electricity filching behavior event including user, to specially becoming customer charge on off state
Monitoring event class need the event of very first time active reporting；Corresponding abnormity diagnosis is analyzed model and is included: electricity
Abnormity diagnosis model, abnormal electricity consumption diagnostic cast, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis
Model, doubtful stealing model；
2 grades: critical event, including power down, parameter modification class influential event properly functioning on equipment；Correspond
Abnormity diagnosis analyze model include: equipment fault model, battery failure model；
3 grades: more important event, including decompression, the influential event of time overproof class electricity consumption reliable on user；In contrast
The abnormity diagnosis answered is analyzed model and is included: voltage x current abnormity diagnosis model, loop Exception Model, distribution transforming need Extension Model, use
Electrical anomaly model；
4 grades: the common event, including remotely-or locally equipment being carried out command operation, can need to carry out core according to management
The event looked into and process；Corresponding abnormity diagnosis is analyzed model and is included: on-site maintenance model, error connection model, expense control
Abnormity diagnosis model.
The intelligent diagnosing method of abnormal information in a kind of power information acquisition system, comprises the following steps:
Step one, data prediction: the repetition data in the abnormal information collect power information acquisition system are carried out
Pick weight；
Step 2, this abnormal information collection point owning user information is compared with marketing flow process, whether check archives
Mistake；
Step 3, when roll checking is errorless, self-learning module by use NB Algorithm special to anomaly analysis
Data in family storehouse are trained, and form the criterion analyzing judgement abnormal information type corresponding to model with each abnormity diagnosis,
And accept, analyze the abnormal information that power information acquisition system provides, utilize the criterion judging abnormal information type to judge abnormal
The type of information, and compare with anomaly analysis experts database, thus perform following operation:
A: if the abnormity diagnosis of existing the type analyzes model in anomaly analysis experts database, then this abnormal information is referred to
Abnormity diagnosis corresponding in anomaly analysis experts database is analyzed in model, and Exception Type passes to GIS fault location module；
B: if not having the abnormity diagnosis of the type to analyze model in anomaly analysis experts database, then pass to abnormal for the type
Staff, staff, after being analyzed, the new abnormity diagnosis arranging correspondence analyzes model, and this abnormal information is returned
Class analyzes model to new abnormity diagnosis, and the mode manually inputted is by this abnormal information, new Exception Type, new exception
Diagnostic analysis model modification is in anomaly analysis experts database, and this Exception Type passes to GIS fault location module, exists simultaneously
In the abnormal menace level judge module of GIS fault location module, manually set the pass of this new Exception Type and menace level
Join, and self-learning module re-starts training to the data of new anomaly analysis experts database, is formed and judges new abnormal information
The criterion of type, and this new abnormal information is passed to self-learning module again carry out classification judgement, verify new abnormal information
Judgment criterion is successfully formed the most；
Step 4, utilize GPS positioner that faulty equipment location obtains the positional information of faulty equipment, abnormal the most serious etc.
Level judge module judges the menace level of this exception according to the abnormal information received；Finally utilize GIS numerical map by fault
The menace level of the positional information of equipment, Exception Type and exception shows on GIS numerical map, it is achieved abort situation quick
Inquiry；
Step 5, staff arrange processing sequence according to the menace level of the warning message on GIS data map, go forward side by side
Row processes；
After step 6, abnormality processing terminate, the result of GIS fault location module real-time exhibition troubleshooting.
In described step 3, described abnormity diagnosis is analyzed model and is divided into single diagnostic analysis model and relevant diagnosis to analyze mould
Type, described single diagnostic analysis model includes electricity abnormity diagnosis model, voltage x current abnormity diagnosis model, exception electrodiagnosis
Model, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis model, take control abnormity diagnosis model；Described
Relevant diagnosis is analyzed model and is included that doubtful stealing model, equipment fault model, error connection model, distribution transforming need Extension Model, scene
Safeguard model, battery failure model, loop Exception Model, multiplexing electric abnormality model.
In described step 4, described abnormal menace level judge module is used for judging the menace level of this exception, particularly as follows:
According to the dependency relation between Exception Type set in advance and menace level, the Exception Type received is carried out menace level
Judge；Described GIS numerical map specifically for demonstrating the position of faulty equipment according to the positional information of faulty equipment, and in phase
According to Exception Type and abnormal menace level, all kinds of faulty equipments are carried out with different colors and mark respectively on the position answered
Alarm.
In described step 4, menace level is specifically divided into:
1 grade: emergency, there is doubtful electricity filching behavior event including user, to specially becoming customer charge on off state
Monitoring event class need the event of very first time active reporting；Corresponding abnormity diagnosis is analyzed model and is included: electricity is different
Often diagnostic cast, abnormal electricity consumption diagnostic cast, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis mould
Type, doubtful stealing model；
2 grades: critical event, corresponding including power down, parameter modification class influential event properly functioning on equipment
Abnormity diagnosis is analyzed model and is included: equipment fault model, battery failure model；
3 grades: more important event, the most corresponding including decompression, the influential event of time overproof class electricity consumption reliable on user
Abnormity diagnosis analyze model include: voltage x current abnormity diagnosis model, loop Exception Model, distribution transforming need Extension Model, electricity consumption
Exception Model；
4 grades: the common event, including remotely-or locally equipment being carried out command operation, can need to carry out core according to management
The corresponding abnormity diagnosis of event looked into and process is analyzed model and is included: on-site maintenance model, error connection model, expense control are extremely
Diagnostic cast.
Beneficial effects of the present invention:
The data that the present invention is gathered with power information acquisition system are for relying on, by anomaly analysis experts database and self study
All kinds of electricity consumption data obtained are added up, analyze and are diagnosed by module, it is determined that Exception Type and the order of severity, and pass through GIS
Fault location module locks the particular location of fault spot rapidly and accurately, improves the accurate of malfunction monitoring largely
Degree and the efficiency of troubleshooting.
Accompanying drawing explanation
Fig. 1 is the topology diagram of the intelligent diagnosis system of abnormal information in a kind of power information acquisition system.
Fig. 2 is the workflow diagram of the intelligent diagnosing method of abnormal information in a kind of power information acquisition system.
Fig. 3 is the functional frame composition of the Intelligent Diagnosis Technology of abnormal information in a kind of power information acquisition system.
In figure: 1-anomaly analysis experts database, 2-self-learning module, 3-GIS fault location module, 4-abnormity diagnosis analyzes mould
Type, 5-power information acquisition system, 6-GPS positioner, 7-GIS numerical map.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with embodiment, to the present invention
It is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not used to
Limit the present invention.
Below in conjunction with the accompanying drawings the application principle of the present invention is explained in detail.
As it is shown in figure 1, the intelligent diagnosis system of abnormal information in a kind of power information acquisition system, special including anomaly analysis
Family storehouse 1, self-learning module 2 and GIS fault location module 3, described anomaly analysis experts database 1, self-learning module 2 and GIS fault
Connected by wireless network between locating module 3, it is achieved sharing of fault message；
If described anomaly analysis experts database 1 includes that Ganlei's abnormity diagnosis analyzes model 4；In invention, each single exception
In diagnostic analysis model, comprise the various abnormal datas of same type, such as: voltage out-of-limit model includes the various use collected
The electric energy meter overvoltage at family and under-voltage exceptional value, we are often referred to as training data.
Described self-learning module 2 is for by using NB Algorithm to carry out the data in anomaly analysis experts database
Training, forms the criterion analyzing judgement abnormal information type corresponding to model with each abnormity diagnosis, and is used for accepting, analyzing use
The abnormal information that power utilization information collection system provides, utilizes and judges that the criterion of abnormal information type judges the type of abnormal information, and
Compare with anomaly analysis experts database, when the abnormity diagnosis of the type existing in anomaly analysis experts database analyzes model, then will
This abnormal information is referred in anomaly analysis experts database the abnormity diagnosis of correspondence and analyzes in model, and is passed to by this Exception Type
GIS fault location module；If the abnormity diagnosis not having the type in anomaly analysis experts database analyzes model, then the type is abnormal
Pass to staff, staff, after being analyzed, the new abnormity diagnosis arranging correspondence analyzes model, and this is abnormal
Information categorization analyzes model to new abnormity diagnosis, and the mode manually inputted is by this abnormal information, new Exception Type, new
Abnormity diagnosis analyze model modification in anomaly analysis experts database, and this Exception Type is passed to GIS fault location module,
Simultaneously in the abnormal menace level judge module of GIS fault location module, manually set this new Exception Type with serious etc.
Association (the input of in the present invention, described new Exception Type, it is simply that artificial judgment also creates new abnormal diagnostic analysis of level
After model, requirement or perhaps the condition of the title of this exception with some parameters are deposited in experts database), and self study mould
Block re-starts training to the data of new anomaly analysis experts database, forms the criterion judging new abnormal information type, and will
This new abnormal information is again passed to self-learning module and is carried out classification judgement, verifies that the judgment criterion of new abnormal information becomes the most
Merit is formed；
Described self-learning module 2 forms the criterion analyzing judgement abnormal information type corresponding to model with each abnormity diagnosis
I.e. ask for each abnormity diagnosis and analyze the prior probability of model.Concrete steps are exemplified below:
A given training set { (x1,y1),(x2,y2),…,(xn,yn) comprise n bar training data (such as: x1Represent electricity
Press out-of-limit, y1Represent electric voltage exception), wherein x1=(x1 (1),x1 (2),…,x1 (M))TIt is that (voltage out-of-limit has multiple exception to M dimensional vector
Feature, such as: less than rated voltage 5%～10%, 10%～20% etc., higher than rated voltage 5%～10%, 10%～20%
Deng), y1∈{c1,c2,...ckBelong to the class in Exception Type.
First by y1Substitute into formula (1), calculate p (y=ck)=p (y=y1)；
If there is L value, then certain value a of certain dimensional feature in the jth dimension of M dimensional featurejl, at given certain classification ckUnder
Conditional probability is:
Such as: x1Represent voltage out-of-limit, take a kind of off-note less than rated voltage 5%～10%This is different
The abnormal voltage value a of Chang TezhengjlSubstituting into formula (2), other off-notes by that analogy, i.e. can get the base of electric voltage exception type
This probability, the most just completes the forming process of the criterion judging abnormal information type.
By the probability acquired, given unfiled new abnormal instance X, it is possible to by judging the criterion of abnormal information type
(prior probability) carries out judging (calculating), obtains this exception example and belongs to the posterior probability p (y=c of each Exception Typek| X), its
The Exception Type of middle maximum of probability is type belonging to this exception example.
Described GIS fault location module includes that the GPS positioner 6 being arranged on each equipment, abnormal menace level judge
Module and GIS numerical map 7, GPS positioner for being automatically positioned the position letter obtaining faulty equipment to faulty equipment
Breath, abnormal menace level judge module is for judging the menace level of this exception；GIS numerical map is for by the position of faulty equipment
Confidence breath, Exception Type, abnormal menace level show on GIS numerical map, it is achieved the quick search of abort situation.At this
In invention, warping apparatus and abnormal information are associated, and by identifying the device number in abnormal information source, then utilize GPS
Positioner 6 positions out-of-the way position.
Described abnormity diagnosis is analyzed model and is derived from the analysis result of data gathered to electric energy meter and acquisition terminal, it is possible to
The running status of electric power meter is judged.
Described abnormity diagnosis is analyzed model and is divided into single diagnostic analysis model and relevant diagnosis to analyze model, described single examines
Disconnected model of analyzing includes that electricity abnormity diagnosis model, voltage x current abnormity diagnosis model, abnormal electricity consumption diagnostic cast, load are abnormal
Diagnostic cast, clock abnormity diagnosis model, wiring abnormity diagnosis model, take control abnormity diagnosis model；Described relevant diagnosis analysis
Model includes that doubtful stealing model, equipment fault model, error connection model, distribution transforming need Extension Model, on-site maintenance model, battery
Failure model, loop Exception Model, multiplexing electric abnormality model.
Described abnormal menace level judge module is used for judging the menace level of this exception, particularly as follows: according to presetting
Exception Type and menace level between dependency relation, the Exception Type received is carried out menace level judgement；Described GIS
Numerical map specifically for demonstrating the position of faulty equipment according to the positional information of faulty equipment, and root on a corresponding position
According to Exception Type and abnormal menace level, all kinds of faulty equipments are alerted with different colors and mark respectively, and carrying out
After abnormal flow processing, the result of real-time exhibition troubleshooting.
Described abnormal menace level includes:
1 grade: emergency, there is doubtful electricity filching behavior event including user, to specially becoming customer charge on off state
Monitoring event class need the event of very first time active reporting；Corresponding abnormity diagnosis is analyzed model and is included: electricity
Abnormity diagnosis model, abnormal electricity consumption diagnostic cast, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis
Model, doubtful stealing model；
2 grades: critical event, including power down, parameter modification class influential event properly functioning on equipment；Correspond
Abnormity diagnosis analyze model include: equipment fault model, battery failure model；
3 grades: more important event, including decompression, the influential event of time overproof class electricity consumption reliable on user；In contrast
The abnormity diagnosis answered is analyzed model and is included: voltage x current abnormity diagnosis model, loop Exception Model, distribution transforming need Extension Model, use
Electrical anomaly model；
4 grades: the common event, including remotely-or locally equipment being carried out command operation, can need to carry out core according to management
The event looked into and process；Corresponding abnormity diagnosis is analyzed model and is included: on-site maintenance model, error connection model, expense control
Abnormity diagnosis model.
As in figure 2 it is shown, the intelligent diagnosing method of abnormal information in a kind of power information acquisition system, comprise the following steps:
Step one, data prediction: the repetition data in the abnormal information collect power information acquisition system are carried out
Pick weight；Data are picked and are heavily represented the abnormal information that rejecting is identical, such as: the electric voltage exception monitoring cycle of system is 15 minutes, little
In the time of 15 minutes, repeatedly occur that voltage surmounts standard limits and the electric voltage exception information that records belongs to repetition abnormal information,
Data should be carried out and pick weight.
Step 2, this abnormal information collection point owning user information is compared with marketing flow process, whether check archives
Mistake；In invention, the archive information of user represents the belonging relation of user and equipment, realizes checking and approving by marketing flow process
User Profile information be updated to power information acquisition system and GIS fault location module from sales service system synchronization, its
Process is likely to occur fault.Therefore, the correctness of user and equipment belonging relation need to be checked, it is to avoid abnormal wrong report phenomenon occurs.
Step 3, when roll checking is errorless, self-learning module by use NB Algorithm special to anomaly analysis
Data in family storehouse are trained, and form the criterion analyzing judgement abnormal information type corresponding to model with each abnormity diagnosis,
And accept, analyze the abnormal information that power information acquisition system provides, utilize the criterion judging abnormal information type to judge abnormal
The type of information, and compare with anomaly analysis experts database, thus perform following operation:
A: if the abnormity diagnosis of existing the type analyzes model in anomaly analysis experts database, then this abnormal information is referred to
Abnormity diagnosis corresponding in anomaly analysis experts database is analyzed in model, and Exception Type passes to GIS fault location module；
B: if not having the abnormity diagnosis of the type to analyze model in anomaly analysis experts database, then pass to abnormal for the type
Staff, staff, after being analyzed, the new abnormity diagnosis arranging correspondence analyzes model, and this abnormal information is returned
Class analyzes model to new abnormity diagnosis, and the mode manually inputted is by this abnormal information, new Exception Type, new exception
Diagnostic analysis model modification is in anomaly analysis experts database, and this Exception Type passes to GIS fault location module, exists simultaneously
In the abnormal menace level judge module of GIS fault location module, manually set the pass of this new Exception Type and menace level
Join, and self-learning module re-starts training to the data of new anomaly analysis experts database, is formed and judges new abnormal information
The criterion of type, and this new abnormal information is passed to self-learning module again carry out classification judgement, verify new abnormal information
Judgment criterion is successfully formed the most；
Step 4, utilize GPS positioner that faulty equipment location obtains the positional information of faulty equipment, abnormal the most serious etc.
Level judge module judges the menace level of this exception according to the abnormal information received；Finally utilize GIS numerical map by fault
The menace level of the positional information of equipment, Exception Type and exception shows on GIS numerical map, it is achieved abort situation quick
Inquiry；
Step 5, staff arrange processing sequence according to the menace level of the warning message on GIS data map, go forward side by side
Row processes；
GIS numerical map real-time exhibition troubleshooting after step 6, abnormality processing terminate, in GIS fault location module
Result；Particularly as follows: solve when abnormal, then the mark of corresponding on GIS numerical map abnormal information just should be deleted.
In described step 3, described abnormity diagnosis is analyzed model and is divided into single diagnostic analysis model and relevant diagnosis to analyze mould
Type, described single diagnostic analysis model includes electricity abnormity diagnosis model, voltage x current abnormity diagnosis model, exception electrodiagnosis
Model, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis model, take control abnormity diagnosis model；Described
Relevant diagnosis is analyzed model and is included that doubtful stealing model, equipment fault model, error connection model, distribution transforming need Extension Model, scene
Safeguard model, battery failure model, loop Exception Model, multiplexing electric abnormality model.
In described step 4, described abnormal menace level judge module is used for judging the menace level of this exception, particularly as follows:
According to the dependency relation between Exception Type set in advance and menace level, the Exception Type received is carried out menace level
Judge；Described GIS numerical map specifically for demonstrating the position of faulty equipment according to the positional information of faulty equipment, and in phase
According to Exception Type and abnormal menace level, all kinds of faulty equipments are carried out with different colors and mark respectively on the position answered
Alarm.In an embodiment of the present invention, described alerts with different colors and mark respectively, particularly as follows: respectively
With red, orange, yellow, blue and corresponding mark, emergency, critical event, more important event, the common event are alerted.
In described step 4, menace level is specifically divided into:
1 grade: emergency, there is doubtful electricity filching behavior event including user, to specially becoming customer charge on off state
Monitoring event class need the corresponding abnormity diagnosis of event of very first time active reporting to analyze model to include: electricity is abnormal
Diagnostic cast, abnormal electricity consumption diagnostic cast, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis model,
Doubtful stealing model；
2 grades: critical event, corresponding including power down, parameter modification class influential event properly functioning on equipment
Abnormity diagnosis is analyzed model and is included: equipment fault model, battery failure model；
3 grades: more important event, the most corresponding including decompression, the influential event of time overproof class electricity consumption reliable on user
Abnormity diagnosis analyze model include: voltage x current abnormity diagnosis model, loop Exception Model, distribution transforming need Extension Model, electricity consumption
Exception Model；
4 grades: the common event, including remotely-or locally equipment being carried out command operation, can need to carry out core according to management
The corresponding abnormity diagnosis of event looked into and process is analyzed model and is included: on-site maintenance model, error connection model, expense control are extremely
Diagnostic cast.
As it is shown on figure 3, be a kind of real of the intelligent diagnosis system of abnormal information in the power information acquisition system of the present invention
Execute example, including acquisition platform layer, support platform layer and service application layer；Described acquisition platform layer includes power information collection system
System, specifically includes: specially transformer terminals, concentrator, net list and harvester, in the gatherer process that concrete power information gathers,
Gone to gather power information by special transformer terminals, concentrator, net list and harvester；Described support platform layer includes: anomaly analysis is special
Family storehouse, self-learning module and GIS fault location module；Described service application layer includes: warping apparatus locating module, exception are online
Alarm module, abnormal graph display module, metering anomaly analysis module, unit exception analyze module and multiplexing electric abnormality analyzes mould
Block；Described metering anomaly analysis module, unit exception analyze module and multiplexing electric abnormality analyze module by self-learning module point
Class algorithm realizes the support to its function, and described warping apparatus locating module uses GPS positioner to go to realize；Described exception exists
Line alarm module is for carrying out with different colors and mark all kinds of faulty equipments according to Exception Type and abnormal menace level
Alarm；Described abnormal graph display module is used for after carrying out abnormal flow processing, the result of real-time exhibition troubleshooting.
The ultimate principle of the present invention and principal character and advantages of the present invention have more than been shown and described.The technology of the industry
Personnel, it should be appreciated that the present invention is not restricted to the described embodiments, simply illustrating this described in above-described embodiment and description
The principle of invention, without departing from the spirit and scope of the present invention, the present invention also has various changes and modifications, and these become
Change and improvement both falls within scope of the claimed invention.Claimed scope by appending claims and
Equivalent defines.
Claims (8)
1. the intelligent diagnosis system of abnormal information in a power information acquisition system, it is characterised in that: include that anomaly analysis is special
Family storehouse, self-learning module and GIS fault location module, described anomaly analysis experts database, self-learning module and GIS fault location mould
Connected by wireless network between block, it is achieved sharing of fault message；
If described anomaly analysis experts database includes that Ganlei's abnormity diagnosis analyzes model；
Described self-learning module is used for by using NB Algorithm to be trained the data in anomaly analysis experts database,
Form the criterion analyzing judgement abnormal information type corresponding to model with each abnormity diagnosis, and be used for accepting, analyzing use
The abnormal information that power utilization information collection system provides, utilizes and judges that the criterion of abnormal information type judges the type of abnormal information, and
Compare with anomaly analysis experts database, when the abnormity diagnosis of the type existing in anomaly analysis experts database analyzes model, then will
This abnormal information is referred in anomaly analysis experts database the abnormity diagnosis of correspondence and analyzes in model, and is passed to by this Exception Type
GIS fault location module；If the abnormity diagnosis not having the type in anomaly analysis experts database analyzes model, then the type is abnormal
Pass to staff, staff, after being analyzed, the new abnormity diagnosis arranging correspondence analyzes model, and this is abnormal
Information categorization analyzes model to new abnormity diagnosis, and the mode manually inputted is by this abnormal information, new Exception Type, new
Abnormity diagnosis analyze model modification in anomaly analysis experts database, and this Exception Type is passed to GIS fault location module,
Simultaneously in the abnormal menace level judge module of GIS fault location module, manually set this new Exception Type with serious etc.
The association of level, and self-learning module re-starts training to the data of new anomaly analysis experts database, formed judge new different
The often criterion of information type, and this new abnormal information is passed to self-learning module again carry out classification judgement, verify new exception
The judgment criterion of information is successfully formed the most；
The GPS positioner that described GIS fault location module includes being arranged on each equipment, abnormal menace level judge module and
GIS numerical map, GPS positioner obtains the positional information of faulty equipment for being automatically positioned faulty equipment, abnormal
Menace level judge module is for judging the menace level of this exception；GIS numerical map for by the positional information of faulty equipment,
Exception Type, abnormal menace level show on GIS numerical map, it is achieved the quick search of abort situation.
The intelligent diagnosis system of abnormal information, its feature in a kind of power information acquisition system the most according to claim 1
It is: described abnormity diagnosis is analyzed model and is divided into single diagnostic analysis model and relevant diagnosis to analyze model, described single diagnosis
Analyze model and include that electricity abnormity diagnosis model, voltage x current abnormity diagnosis model, abnormal electricity consumption diagnostic cast, load are examined extremely
Disconnected model, clock abnormity diagnosis model, wiring abnormity diagnosis model, take and control abnormity diagnosis model；Described relevant diagnosis analyzes mould
Type includes that doubtful stealing model, equipment fault model, error connection model, distribution transforming need Extension Model, on-site maintenance model, battery to lose
Effect model, loop Exception Model, multiplexing electric abnormality model.
The intelligent diagnosis system of abnormal information in a kind of power information acquisition system the most according to claim 1 and 2, it is special
Levy and be: described abnormal menace level judge module is used for judging the menace level of this exception, particularly as follows: according to set in advance
Dependency relation between Exception Type and menace level, carries out menace level judgement to the Exception Type received；Described GIS number
Word map specifically for demonstrating the position of faulty equipment according to the positional information of faulty equipment, and basis on a corresponding position
All kinds of faulty equipments are alerted by Exception Type and abnormal menace level respectively with different colors and mark, and carry out different
Often after flow processing, the result of real-time exhibition troubleshooting.
The intelligent diagnosis system of abnormal information, its feature in a kind of power information acquisition system the most according to claim 3
Being, described abnormal menace level includes:
1 grade: emergency, there is doubtful electricity filching behavior event including user, to the prison specially becoming customer charge on off state
Survey event class needs the event of very first time active reporting；Corresponding abnormity diagnosis is analyzed model and is included: electricity is abnormal
Diagnostic cast, abnormal electricity consumption diagnostic cast, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis model,
Doubtful stealing model；
2 grades: critical event, including power down, parameter modification class influential event properly functioning on equipment；Corresponding different
Often diagnostic analysis model includes: equipment fault model, battery failure model；
3 grades: more important event, including decompression, the influential event of time overproof class electricity consumption reliable on user；Corresponding
Abnormity diagnosis is analyzed model and is included: voltage x current abnormity diagnosis model, loop Exception Model, distribution transforming need Extension Model, electricity consumption different
Norm type；
4 grades: the common event, including remotely-or locally equipment being carried out command operation, can according to management needs carry out verify and
The event processed；Corresponding abnormity diagnosis is analyzed model and is included: on-site maintenance model, error connection model, expense control are extremely
Diagnostic cast.
5. the intelligent diagnosing method of abnormal information in a power information acquisition system, it is characterised in that comprise the following steps:
Step one, data prediction: the repetition data in the abnormal information collect power information acquisition system pick weight；
Step 2, this abnormal information collection point owning user information is compared with marketing flow process, check archives whether mistake；
Step 3, when roll checking is errorless, self-learning module by use NB Algorithm to anomaly analysis experts database
In data be trained, formed and the criterion of each abnormity diagnosis analysis judgement abnormal information type corresponding to model, and connect
It is subject to, analyzes the abnormal information that power information acquisition system provides, utilize and judge that the criterion of abnormal information type judges abnormal information
Type, and compare with anomaly analysis experts database, thus perform following operation:
A: if the abnormity diagnosis of existing the type analyzes model in anomaly analysis experts database, then this abnormal information is referred to exception
Abnormity diagnosis corresponding in assayer storehouse is analyzed in model, and Exception Type passes to GIS fault location module；
B: if not having the abnormity diagnosis of the type to analyze model in anomaly analysis experts database, then pass to work by abnormal for the type
Personnel, staff, after being analyzed, the new abnormity diagnosis arranging correspondence analyzes model, and this abnormal information is referred to
New abnormity diagnosis analyzes model, and the mode manually inputted is by this abnormal information, new Exception Type, new abnormity diagnosis
Analyze model modification in anomaly analysis experts database, and this Exception Type is passed to GIS fault location module, simultaneously at GIS
In the abnormal menace level judge module of fault location module, manually set associating of this new Exception Type and menace level,
And self-learning module re-starts training to the data of new anomaly analysis experts database, formed and judge new abnormal information type
Criterion, and this new abnormal information passed to self-learning module again carry out classification judgement, verify the judgement of new abnormal information
Criterion is successfully formed the most；
Step 4, utilizing GPS positioner that faulty equipment location is obtained the positional information of faulty equipment, abnormal menace level is sentenced
Disconnected module judges the menace level of this exception according to the abnormal information received；Finally utilize GIS numerical map by faulty equipment
The menace level of positional information, Exception Type and exception show on GIS numerical map, it is achieved the fast quick checking of abort situation
Ask；
Step 5, staff arrange processing sequence according to the menace level of the warning message on GIS data map, and locate
Reason；
After step 6, abnormality processing terminate, the knot of the GIS numerical map real-time exhibition troubleshooting in GIS fault location module
Really.
The intelligent diagnosing method of abnormal information, its feature in a kind of power information acquisition system the most according to claim 5
Being, in described step 3, described abnormity diagnosis is analyzed model and is divided into single diagnostic analysis model and relevant diagnosis to analyze model,
Described single diagnostic analysis model includes electricity abnormity diagnosis model, voltage x current abnormity diagnosis model, exception electrodiagnosis mould
Type, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis model, take control abnormity diagnosis model；Described pass
Connection diagnostic analysis model includes that doubtful stealing model, equipment fault model, error connection model, distribution transforming need Extension Model, on-the-spot dimension
Protect model, battery failure model, loop Exception Model, multiplexing electric abnormality model.
The intelligent diagnosing method of abnormal information, its feature in a kind of power information acquisition system the most according to claim 5
Being, in described step 4, described abnormal menace level judge module is for judging the menace level of this exception, particularly as follows: root
According to the dependency relation between Exception Type set in advance and menace level, the Exception Type received is carried out menace level and sentences
Disconnected；Described GIS numerical map specifically for demonstrating the position of faulty equipment according to the positional information of faulty equipment, and accordingly
Position on according to Exception Type and abnormal menace level, all kinds of faulty equipments are accused with different colors and mark respectively
Alert.
The intelligent diagnosing method of abnormal information, its feature in a kind of power information acquisition system the most according to claim 7
Being, in described step 4, menace level is specifically divided into:
1 grade: emergency, there is doubtful electricity filching behavior event including user, to the prison specially becoming customer charge on off state
Survey event class needs the event of very first time active reporting, and corresponding abnormity diagnosis is analyzed model and included: electricity is abnormal
Diagnostic cast, abnormal electricity consumption diagnostic cast, load abnormity diagnosis model, clock abnormity diagnosis model, wiring abnormity diagnosis model,
Doubtful stealing model；
2 grades: critical event, including power down, parameter modification class influential event properly functioning on equipment, corresponding different
Often diagnostic analysis model includes: equipment fault model, battery failure model；
3 grades: more important event, including decompression, the influential event of time overproof class electricity consumption reliable on user, corresponding
Abnormity diagnosis is analyzed model and is included: voltage x current abnormity diagnosis model, loop Exception Model, distribution transforming need Extension Model, electricity consumption different
Norm type；
4 grades: the common event, including remotely-or locally equipment being carried out command operation, can according to management needs carry out verify and
The event processed, corresponding abnormity diagnosis analysis model includes: on-site maintenance model, error connection model, expense control are extremely
Diagnostic cast.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610589498.9A CN106199276B (en) | 2016-07-25 | 2016-07-25 | The intelligent diagnosis system and method for exception information in a kind of power information acquisition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610589498.9A CN106199276B (en) | 2016-07-25 | 2016-07-25 | The intelligent diagnosis system and method for exception information in a kind of power information acquisition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106199276A true CN106199276A (en) | 2016-12-07 |
| CN106199276B CN106199276B (en) | 2018-11-30 |
Family
ID=57494813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610589498.9A Active CN106199276B (en) | 2016-07-25 | 2016-07-25 | The intelligent diagnosis system and method for exception information in a kind of power information acquisition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106199276B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292025A (en) * | 2017-06-21 | 2017-10-24 | 北京航空航天大学 | The sealing life Forecasting Methodology of soft bag lithium ionic cell |
| CN107392457A (en) * | 2017-07-17 | 2017-11-24 | 贵州电网有限责任公司电力科学研究院 | Metering automation intelligence operational system based on line loss anomaly analysis |
| CN107748954A (en) * | 2017-10-17 | 2018-03-02 | 国网江苏省电力公司盐城供电公司 | A kind of transformer station's balancing monitor and control system |
| CN107944716A (en) * | 2017-11-29 | 2018-04-20 | 国网江苏省电力有限公司 | Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome |
| CN108045230A (en) * | 2017-11-15 | 2018-05-18 | 苏州工业园区职业技术学院 | A kind of cell managing device with automatic learning device |
| CN109213787A (en) * | 2018-11-07 | 2019-01-15 | 闫福录 | A kind of anti-electricity-theft algorithm chip and electricity anti-theft method in integration characteristic library |
| CN109308587A (en) * | 2018-10-30 | 2019-02-05 | 国网江苏省电力有限公司苏州供电分公司 | The reliability analysis system and its intelligent diagnosing method of electric automobile charging pile |
| CN109444498A (en) * | 2018-12-21 | 2019-03-08 | 云南电网有限责任公司电力科学研究院 | A kind of electricity anti-theft method, apparatus and system |
| CN109859431A (en) * | 2019-03-25 | 2019-06-07 | 软通智慧科技有限公司 | Method, system, equipment and medium for detecting fire safety hidden danger |
| CN110491098A (en) * | 2019-08-12 | 2019-11-22 | 青岛聚好联科技有限公司 | A kind of control of bluetooth access equipment fault early-warning method and device based on deep learning |
| CN111008778A (en) * | 2019-12-03 | 2020-04-14 | 国网天津市电力公司电力科学研究院 | Method and system for diagnosing abnormity of metering points of transformer area |
| CN111027026A (en) * | 2019-12-31 | 2020-04-17 | 广东电网有限责任公司 | Meter reading data abnormity intelligent diagnosis system |
| CN111274056A (en) * | 2018-11-20 | 2020-06-12 | 河南许继仪表有限公司 | Self-learning method and device for intelligent electric energy meter fault library |
| CN107196804B (en) * | 2017-06-01 | 2020-07-10 | 国网山东省电力公司信息通信公司 | Alarm centralized monitoring system and method for terminal communication access network of power system |
| CN111537818A (en) * | 2020-05-11 | 2020-08-14 | 国网上海市电力公司 | Intelligent diagnosis device for abnormal loss of public transformer |
| CN113029592A (en) * | 2021-03-11 | 2021-06-25 | 奇瑞新能源汽车股份有限公司 | Electric automobile testing method and device |
| CN113297441A (en) * | 2021-05-13 | 2021-08-24 | 江苏南工科技集团有限公司 | Multi-protocol fusion analysis method based on Internet of things technology |
| CN113486078A (en) * | 2021-06-15 | 2021-10-08 | 国网山东省电力公司金乡县供电公司 | Distributed power distribution network operation monitoring method and system |
| CN113655341A (en) * | 2021-09-10 | 2021-11-16 | 国网山东省电力公司鱼台县供电公司 | Power distribution network fault positioning method and system |
| CN113988723A (en) * | 2021-12-28 | 2022-01-28 | 广东电网有限责任公司佛山供电局 | User behavior locking method and system based on power consumption data anomaly analysis |
| CN116091457A (en) * | 2023-01-16 | 2023-05-09 | 北京航科星云科技有限公司 | Satellite solar cell array anomaly prediction method and device and computer equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62237850A (en) * | 1986-04-09 | 1987-10-17 | Nec Corp | Fault diagnostic system |
| GB2224373A (en) * | 1988-09-28 | 1990-05-02 | Fuji Heavy Ind Ltd | Diagnostic system for a motor vehicle |
| CN102122431A (en) * | 2010-12-15 | 2011-07-13 | 广东电网公司电力科学研究院 | Method and system for intelligently diagnosing faults of electricity information collection terminal |
| CN103488800A (en) * | 2013-10-16 | 2014-01-01 | 云南电力试验研究院（集团）有限公司电力研究院 | SVM (Support Vector Machine)-based power consumption abnormality detection method |
| CN104219315A (en) * | 2014-09-10 | 2014-12-17 | 国家电网公司 | Operation monitoring system for electricity consumption information acquisition system and monitoring method thereof |
| CN104360208A (en) * | 2014-12-05 | 2015-02-18 | 国家电网公司 | Acquisition failure analyzing and processing method of electricity utilization information acquisition operating and maintaining system |
| CN105203924A (en) * | 2015-10-10 | 2015-12-30 | 上海博英信息科技有限公司 | Electricity usage trend abnormity suspicion analysis method and anti-electric-larceny monitoring system |
-
2016
- 2016-07-25 CN CN201610589498.9A patent/CN106199276B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62237850A (en) * | 1986-04-09 | 1987-10-17 | Nec Corp | Fault diagnostic system |
| GB2224373A (en) * | 1988-09-28 | 1990-05-02 | Fuji Heavy Ind Ltd | Diagnostic system for a motor vehicle |
| CN102122431A (en) * | 2010-12-15 | 2011-07-13 | 广东电网公司电力科学研究院 | Method and system for intelligently diagnosing faults of electricity information collection terminal |
| CN103488800A (en) * | 2013-10-16 | 2014-01-01 | 云南电力试验研究院（集团）有限公司电力研究院 | SVM (Support Vector Machine)-based power consumption abnormality detection method |
| CN104219315A (en) * | 2014-09-10 | 2014-12-17 | 国家电网公司 | Operation monitoring system for electricity consumption information acquisition system and monitoring method thereof |
| CN104360208A (en) * | 2014-12-05 | 2015-02-18 | 国家电网公司 | Acquisition failure analyzing and processing method of electricity utilization information acquisition operating and maintaining system |
| CN105203924A (en) * | 2015-10-10 | 2015-12-30 | 上海博英信息科技有限公司 | Electricity usage trend abnormity suspicion analysis method and anti-electric-larceny monitoring system |
Non-Patent Citations (2)
| Title |
|---|
| 杜艳 等: "基于BP神经网络的用电信息采集网络智能分析***的设计", 《2014年中国电机工程学会年会论文集》 * |
| 肖坚红 等: "基于数据挖掘的计量装置在线监测与智能诊断***的设计与实现", 《电测与仪表》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107196804B (en) * | 2017-06-01 | 2020-07-10 | 国网山东省电力公司信息通信公司 | Alarm centralized monitoring system and method for terminal communication access network of power system |
| CN107292025B (en) * | 2017-06-21 | 2019-08-06 | 北京航空航天大学 | The sealing life prediction technique of soft bag lithium ionic cell |
| CN107292025A (en) * | 2017-06-21 | 2017-10-24 | 北京航空航天大学 | The sealing life Forecasting Methodology of soft bag lithium ionic cell |
| CN107392457A (en) * | 2017-07-17 | 2017-11-24 | 贵州电网有限责任公司电力科学研究院 | Metering automation intelligence operational system based on line loss anomaly analysis |
| CN107748954A (en) * | 2017-10-17 | 2018-03-02 | 国网江苏省电力公司盐城供电公司 | A kind of transformer station's balancing monitor and control system |
| CN108045230A (en) * | 2017-11-15 | 2018-05-18 | 苏州工业园区职业技术学院 | A kind of cell managing device with automatic learning device |
| CN107944716A (en) * | 2017-11-29 | 2018-04-20 | 国网江苏省电力有限公司 | Based on the modified substation's electrical energy measurement cycle balance abnormality diagnostic method of learning outcome |
| CN109308587A (en) * | 2018-10-30 | 2019-02-05 | 国网江苏省电力有限公司苏州供电分公司 | The reliability analysis system and its intelligent diagnosing method of electric automobile charging pile |
| CN109213787A (en) * | 2018-11-07 | 2019-01-15 | 闫福录 | A kind of anti-electricity-theft algorithm chip and electricity anti-theft method in integration characteristic library |
| CN111274056A (en) * | 2018-11-20 | 2020-06-12 | 河南许继仪表有限公司 | Self-learning method and device for intelligent electric energy meter fault library |
| CN111274056B (en) * | 2018-11-20 | 2023-10-03 | 河南许继仪表有限公司 | Self-learning method and device for fault library of intelligent electric energy meter |
| CN109444498A (en) * | 2018-12-21 | 2019-03-08 | 云南电网有限责任公司电力科学研究院 | A kind of electricity anti-theft method, apparatus and system |
| CN109859431A (en) * | 2019-03-25 | 2019-06-07 | 软通智慧科技有限公司 | Method, system, equipment and medium for detecting fire safety hidden danger |
| CN109859431B (en) * | 2019-03-25 | 2022-02-18 | 软通智慧科技有限公司 | Method, system, equipment and medium for detecting fire safety hidden danger |
| CN110491098A (en) * | 2019-08-12 | 2019-11-22 | 青岛聚好联科技有限公司 | A kind of control of bluetooth access equipment fault early-warning method and device based on deep learning |
| CN111008778A (en) * | 2019-12-03 | 2020-04-14 | 国网天津市电力公司电力科学研究院 | Method and system for diagnosing abnormity of metering points of transformer area |
| CN111027026A (en) * | 2019-12-31 | 2020-04-17 | 广东电网有限责任公司 | Meter reading data abnormity intelligent diagnosis system |
| CN111537818A (en) * | 2020-05-11 | 2020-08-14 | 国网上海市电力公司 | Intelligent diagnosis device for abnormal loss of public transformer |
| CN113029592A (en) * | 2021-03-11 | 2021-06-25 | 奇瑞新能源汽车股份有限公司 | Electric automobile testing method and device |
| CN113297441A (en) * | 2021-05-13 | 2021-08-24 | 江苏南工科技集团有限公司 | Multi-protocol fusion analysis method based on Internet of things technology |
| CN113486078A (en) * | 2021-06-15 | 2021-10-08 | 国网山东省电力公司金乡县供电公司 | Distributed power distribution network operation monitoring method and system |
| CN113486078B (en) * | 2021-06-15 | 2023-11-21 | 国网山东省电力公司金乡县供电公司 | Distributed power distribution network operation monitoring method and system |
| CN113655341A (en) * | 2021-09-10 | 2021-11-16 | 国网山东省电力公司鱼台县供电公司 | Power distribution network fault positioning method and system |
| CN113655341B (en) * | 2021-09-10 | 2024-01-23 | 国网山东省电力公司鱼台县供电公司 | Fault positioning method and system for power distribution network |
| CN113988723A (en) * | 2021-12-28 | 2022-01-28 | 广东电网有限责任公司佛山供电局 | User behavior locking method and system based on power consumption data anomaly analysis |
| CN116091457A (en) * | 2023-01-16 | 2023-05-09 | 北京航科星云科技有限公司 | Satellite solar cell array anomaly prediction method and device and computer equipment |
| CN116091457B (en) * | 2023-01-16 | 2023-10-27 | 北京航科星云科技有限公司 | Satellite solar cell array anomaly prediction method and device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106199276B (en) | 2018-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106199276A (en) | The intelligent diagnosis system of abnormal information and method in a kind of power information acquisition system | |
| CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
| CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
| CN108336725B (en) | Power grid dispatching equipment monitoring management and intelligent analysis system | |
| CN104931857B (en) | A kind of electrical power distribution network fault location method based on D-S evidence theory | |
| CN104503399B (en) | The regimental Wind turbines status monitoring of one kind collection and fault diagnosis platform | |
| CN104020754B (en) | Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system | |
| Liu et al. | Knowledge-based system for distribution system outage locating using comprehensive information | |
| CN107463998A (en) | A kind of power equipment O＆M service system and method based on cloud service platform | |
| CN107798395A (en) | A kind of power grid accident signal automatic diagnosis method and system | |
| CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN108287327A (en) | Metering automation terminal fault diagnostic method based on Bayes's classification | |
| CN103023028A (en) | Rapid grid failure positioning method based on dependency graph of entities | |
| CN109308587A (en) | The reliability analysis system and its intelligent diagnosing method of electric automobile charging pile | |
| CN102800030A (en) | Comprehensive reliability interactive iteration assessment method for regional power grid relay protection equipment | |
| CN109615273A (en) | A kind of electric car electrically-charging equipment method for evaluating state and system | |
| CN113740666B (en) | Method for positioning root fault of storm alarm in power system of data center | |
| CN103888300B (en) | Network failure analysis system and method in Web service system | |
| CN113159517B (en) | Three-dimensional visual power grid operation data analysis system | |
| CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
| CN108446202A (en) | A kind of judgment method of the safe condition of calculator room equipment | |
| CN104865959B (en) | A kind of fault self-diagnosis method of fire-fighting power supply control system | |
| CN109981359A (en) | A kind of intelligent substation remote control anomaly analysis diagnostic method and device | |
| CN111539642B (en) | Object-oriented power plant data acquisition and processing system and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |