CN106842106A - Electrical energy meter fault Forecasting Methodology and device - Google Patents
Electrical energy meter fault Forecasting Methodology and device Download PDFInfo
- Publication number
- CN106842106A CN106842106A CN201710100110.9A CN201710100110A CN106842106A CN 106842106 A CN106842106 A CN 106842106A CN 201710100110 A CN201710100110 A CN 201710100110A CN 106842106 A CN106842106 A CN 106842106A
- Authority
- CN
- China
- Prior art keywords
- failure
- energy meter
- electric energy
- fault
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention relates to electrical energy meter fault Forecasting Methodology and device.Methods described includes：The real-time running data of electric energy meter is obtained, the real-time running data is input into default breakdown judge model, judge whether to break down；If it is determined that breaking down, then the fault message that will currently determine is converted to the logical term being adapted with the fault diagnosis mining model for building in advance；The fault diagnosis mining model is the Association Rules Model that the historical failure information based on the electric energy meter is built using the algorithm of Mining Boolean Association Rules frequent item set；The corresponding logical term of current failure information is matched with the correlation rule in the fault diagnosis mining model, failure predication information corresponding with the electric energy meter current failure is drawn according to matching result.The present invention can effectively predict the operation troubles of electric energy meter.
Description
Technical field
The present invention relates to testing techniques of equipment field, more particularly to a kind of electrical energy meter fault Forecasting Methodology and electric energy meter are former
Barrier prediction meanss.
Background technology
Electric energy meter is the important component of intelligent grid, the meter of the clearing that carried on trade as power supply enterprise and power consumer
Measuring device has, and its operational reliability all has significance to both sides, therefore, it is necessary to be ensured by effective technology and management means
Its normal table runs.
Shown according to operating statistic situation, the risk of electric energy meter reliability service at the scene is mainly derived from the mistake of itself component
Electrical energy meter fault and the extremely caused abnormal operating condition of running environment caused by effect.But traditional quality management and control can only pass through
Electric energy meter install before experiment and install after operation sampling observation, periodic inspection come ensure electric energy meter by run, it is impossible to predict electric energy
The operation troubles of table, cause to be difficult in time, comprehensively grasp electric energy meter running status.
The content of the invention
Based on this, electrical energy meter fault Forecasting Methodology and device are the embodiment of the invention provides, can effectively predict electric energy meter
Operation troubles.
One aspect of the present invention provides electrical energy meter fault Forecasting Methodology, including：
The real-time running data of electric energy meter is obtained, the real-time running data is input into default breakdown judge model, sentenced
It is disconnected whether to break down；
If it is determined that breaking down, then the fault message that will currently determine is converted to and excavated with the fault diagnosis for building in advance
The adaptable logical term of model；The fault diagnosis mining model is the historical failure information based on the electric energy meter using excavation
The Association Rules Model that the algorithm of Boolean Association Rules frequent item set builds；
The corresponding logical term of current failure information is matched with the correlation rule in the fault diagnosis mining model,
Failure predication information corresponding with the electric energy meter current failure is drawn according to matching result.
Another aspect of the present invention provides a kind of electrical energy meter fault prediction meanss, including：
Information and Fault Identification module, the real-time running data for obtaining electric energy meter, by the real time execution number
According to default breakdown judge model is input into, judge whether to break down；
Modular converter, for if it is determined that breaking down, then the fault message that will currently determine is converted to and built in advance
The adaptable logical term of fault diagnosis mining model；The fault diagnosis mining model is the history event based on the electric energy meter
The Association Rules Model that barrier information is built using the algorithm of Mining Boolean Association Rules frequent item set；
Prediction module, for by the corresponding logical term of current failure information and associating in the fault diagnosis mining model
Rule is matched, and failure predication information corresponding with the electric energy meter current failure is drawn according to matching result.
The electrical energy meter fault Forecasting Methodology and device provided based on above-described embodiment, are detecting the real time fail of electric energy meter
During information, valuable information can be found from the gathered data of magnanimity by the fault diagnosis mining model of correlation rule, it is real
Show the prediction to electric energy meter operation troubles, can in time, comprehensively identify the event being likely to occur in electric energy meter running
Barrier.
Brief description of the drawings
Fig. 1 is the indicative flowchart of the electrical energy meter fault Forecasting Methodology of an embodiment；
Fig. 2 is the indicative flowchart of the electrical energy meter fault Forecasting Methodology of another embodiment；
Fig. 3 is the schematic diagram of the electrical energy meter fault prediction meanss of an embodiment.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the indicative flowchart of the electrical energy meter fault Forecasting Methodology of an embodiment；As shown in figure 1, in the present embodiment
Electrical energy meter fault Forecasting Methodology include step：
S11, obtains the real-time running data of electric energy meter, and the real-time running data is input into default breakdown judge mould
Type, judges whether to break down；
In one embodiment, be able to can also be collected by the service data of power information acquisition system Real-time Collection electric energy meter
The service data that electric energy meter is reported automatically in the process of running.Electric energy meter has self-checking function, can be by own hardware loop pair
The operating mode of each module is detected and is carried out reporting events, and such failure mainly has：On-load switch malfunction or tripping；ESAM is wrong
By mistake；Internal memory card initialization mistake；Clock battery voltage is low；Internal processes mistake；Holder failure or damage；Clock failure；Stop
Electricity is checked meter battery undervoltage.
In one embodiment, the failure of electric energy meter is including hardware fault, electricity exception and operation exception etc., wherein described
Hardware fault is for example：On-load switch malfunction or tripping, ESAM mistakes, internal memory card initialization mistake, Clock battery voltage are low, inside
Program error, holder failure or damage, clock failure and power cut-off recording battery undervoltage etc.；The electricity is abnormal for example：Fly
Walk with mutation failure, reversely active indicating value more than zero failure, clock not to failure, fall away failure and indicating value stops walking failure etc.；
The operation exception is for example：Power cut-off recording battery undervoltage failure, power-off fault, switching on failure, switch access state quantitative change position
Failure, game clock lid failure, open end button cover failure, stationary magnetic field interference failure and reset failure etc..
In one embodiment, the different failure of correspondence, can be judged by each self-corresponding breakdown judge model.
Multiple different breakdown judge models are pre-set, for judging whether electric energy meter occurs accordingly according to current service data
Failure.
In the embodiment of the present invention, the fault message determined by step S11 includes failure title and corresponding type
Information.
S12, however, it is determined that break down, then the fault message that will currently determine is converted to and the fault diagnosis for building in advance
The adaptable logical term of mining model；The fault diagnosis mining model is that the historical failure information based on the electric energy meter is used
The Association Rules Model that the algorithm of Mining Boolean Association Rules frequent item set builds；
In one embodiment, the fault diagnosis mining model is the historical failure information based on the electric energy meter, uses
The Association Rules Model that Apriori algorithm builds.Apriori algorithm is a kind of influential Mining Boolean Association Rules frequent episode
The algorithm of collection.Its core is the recursive algorithm for collecting thought based on two benches frequency.The correlation rule belongs to one-dimensional, list in classification
Layer, Boolean Association Rules.Herein, all supports are referred to as frequent item set more than the item collection of minimum support, and referred to as frequency collects.Should
The basic thought of algorithm is：Find out all of frequency collection first, the frequency that these item collections occur at least with predefined most ramuscule
Degree of holding is the same.Then Strong association rule is produced by frequency collection, these rules must are fulfilled for minimum support and Minimum support4.Then
The frequency collection found using the 1st step produces desired rule, produces the strictly all rules of the item only comprising set, each of which rule
Right part there was only one, use here it is middle rule definition.Once these rules are generated, then only those are more than use
The rule of the given Minimum support4 in family is just left to be come.Wherein, support support=P (AB), refers to event A and thing
The simultaneous probability of part B；Confidence level confidence=P (B | A)=P (AB)/P (A), refer to the basis of generation event A
The probability of upper generation event B.
Corresponding, the fault message that will currently determine is converted to and is adapted with the fault diagnosis mining model for building in advance
Logical term refer to the fault message that will currently determine and be converted to the logic that Apriori association rule algorithms can be recognized
.
S13, the corresponding logical term of current failure information is carried out with the correlation rule in the fault diagnosis mining model
Matching, failure predication information corresponding with the electric energy meter current failure is drawn according to matching result.
In the embodiment of the present invention, logic corresponding with current failure information can be obtained from the fault diagnosis mining model
Item matching degree highest correlation rule, failure predication corresponding with the electric energy meter current failure is drawn according to the correlation rule
As a result.
The electrical energy meter fault Forecasting Methodology that above-described embodiment is provided, when certain operation troubles occurs in electric energy meter, by electricity
The abnormal data that can be sent out on table forms fault message after being analyzed, then with extracted from historical failure data storehouse associate rule
Then matched, valuable letter can be found from the gathered data of magnanimity by the fault diagnosis mining model of correlation rule
Breath, realizes the prediction to electric energy meter operation troubles, and can in time, comprehensively identify be likely to occur in electric energy meter running
Failure.
In a preferred embodiment, default breakdown judge model includes：Fly away and mutation failure judgment models, clock event
Barrier judgment models, indicating value stop walking at least two in breakdown judge model.
Preferably, described flying away with mutation failure judgment models can be：
WF=220*3*Ib；
Wherein, WFIt is the working capacity of the electric energy meter, IbIt is the fundamental current of the electric energy meter, K is the default electricity
Can table fly away and mutation factor.It is corresponding, will be flown away and mutation failure judgment models described in service data input, work as K
During more than or equal to the first setting value, it is judged as occurring flying away and mutation failure.
Preferably, the clock failure judgment models can be：
Δ t=| tTerminal-tAmmeter|；
Wherein, Δ t is the difference of clock of power meter time and standard clock time, tTerminalIt is standard clock time, tAmmeterFor institute
State the clock time of electric energy meter.It is corresponding, the service data is input into the clock failure judgment models, when Δ t more than etc.
When the second setting value, it is judged as clock occur not to failure.
Preferably, the indicating value stops walking breakdown judge model can be：
w1=w1’；
w2=w2’；
Wherein, w1For the forward direction of today has work value, w1' there are work value, w for the forward direction of yesterday2Reversely there is work value for today,
w2' reversely there is work value for yesterday.It is corresponding, the service data is input into the indicating value and stops walking breakdown judge model, work as electricity
The energy table forward direction of adjacent two days has work value and reversely has work value constant, and the per day current value of described adjacent two days is more than
During equal to three setting values, it is judged as that indicating value occur stops walking failure.
In one embodiment, also including building electrical energy meter fault diagnosis mining model the step of, including：To default described
Fault message in the historical failure data storehouse of electric energy meter is sorted out, and is formedImplications, X be fault message set F
={ F1, F2..., FNIn item or item collection, Y be failure predication results set R={ R1, R2..., RNIn item or item collection；
Default minimum support and confidence level are read, institute is scanned using Apriori algorithm according to the minimum support and confidence level
The implications set in historical failure data storehouse is stated, frequent item set is obtained and is extracted correlation rule；According to the association rule for extracting
Then build the fault diagnosis mining model of the electric energy meter；Wherein, the electric energy meter is stored in the historical failure data storehouse
A plurality of historical failure information and the corresponding failure predication result of each bar fault message.
Based on above-described embodiment, with reference to shown in Fig. 2, below electrical energy meter fault Forecasting Methodology of the invention illustrate
It is bright：
1) historical failure data storehouse and the real time fail database of electric energy meter are pre-build, wherein, the historical failure number
According to a plurality of historical failure information and the corresponding failure predication result of each bar fault message that the electric energy meter is stored in storehouse.
2) electric energy meter basic data is gathered by acquisition channel by power information acquisition system.
3) service data is pre-processed, removes noise data therein；For example：To power information acquisition system
The electric energy meter basic data that collection comes up is pre-processed, and removes the data unrelated with electrical energy meter fault, there is the number of apparent error
According to the data repeated with attribute.
4) according to electrical energy meter fault judgment models, judge whether electric energy meter currently breaks down, and it is determined that sending failure
When fault data is stored in the real time fail database of electric energy meter.Specific method is exemplified below：
When carrying out electric energy meter and flying away with mutation failure data screening, judge using the following method
WF=220*3*Ib
Wherein WFIt is working capacity, IbIt is fundamental current, K flies away and mutation factor for ammeter.When K >=1, it is judged as flying
Walk and mutation failure.
When carry out clock of power meter not to fault data screen when, judge using the following method
Δ t=| tTerminal-tAmmeter|
Wherein Δ t is terminal clock and the difference of clock of power meter time, tTerminalIt is terminal clock time, tAmmeterIt is ammeter clock
Time.When Δ t >=3, it is judged as general clock of power meter not to failure；When 3≤Δ t≤15, when being judged as important ammeter
Clock is not to failure；When Δ t >=15, it is judged as serious ammeter clock not to failure.
When carrying out ammeter expression value and stopping walking fault data and screen, judge using the following method
w1=w1’
w2=w2’
I≥0.01A
Wherein w1For forward direction today has work value, w1' for yesterday forward direction have work value, w2Reversely to have work value, w today2' it is yesterday
Reversely there is work value day, I is per day current value.When the electric energy meter forward and reverse of two days has work value constant, and per day electricity
When flow valuve is more than or equal to 0.01A, it is judged as that electric energy meter indicating value stops walking failure.
When terminal affair is reported as following event, event is stored in Mishap Database：
On-load switch malfunction or tripping；ESAM mistakes；Internal memory card initialization mistake；Clock battery voltage is low；Internal processes
Mistake；Holder failure or damage；Clock failure；Power cut-off recording battery undervoltage；Have a power failure；Switching on；Switch access state quantitative change
Position；Game clock lid；Open end button cover；Disturb stationary magnetic field；Reset.
Further, the fault message that can be also stored into the real time fail database carries out conversion classification, is sorted out
For the fault type that fault diagnosis mining model is capable of identify that.Wherein, sorting out foundation includes：
Hardware fault：Electric energy meter has self-checking function, the operating mode of each module can be detected by own hardware loop
And reporting events are carried out, such failure mainly has：On-load switch malfunction or tripping；ESAM mistakes；Internal memory card initialization mistake；When
Clock cell voltage is low；Internal processes mistake；Holder failure or damage；Clock failure；Power cut-off recording battery undervoltage.
Electricity exception：It is mainly shown as that electric energy meter display waveform or electric energy metrical aspect are present not normal, such failure is main
Have：Electric energy meter flies away and mutation failure；Reversely active indicating value is more than zero failure to electric energy meter；Clock of power meter is not to failure；Electric energy
Table falls away failure；Ammeter expression value stops walking failure.
Operation exception：It is live to abnormal conditions caused by electric energy table handling, typically there is corresponding logout, such event
Barrier information mainly has：Power cut-off recording battery undervoltage；Have a power failure；Switching on；Switch access state quantitative change position；Game clock lid；Open end button cover；
Disturb stationary magnetic field；Reset.
Additionally, for the event of failure according to electric energy meter or terminal to report, corresponding fault message can be stored in described
Historical failure data storehouse.In historical failure data storehouse, the reporting events record of electric energy meter can be formed directly in fault message, and measure
The information such as amount, switching value are then according to corresponding breakdown judge pattern-recognition.
5) fault message in historical failure data storehouse is sorted out, is formedImplications, X is fault message
Set F={ F1, F2..., FNItem or item collection, Y be failure predication results set R={ R1, R2..., RNItem or item collection.
Wherein, sort out according to and step 4) in it is identical.
6) minimum support and confidence level of setting are read, historical failure data storehouse is scanned with Apriori algorithm and is searched
Rope frequent item set simultaneously extracts correlation rule.Idiographic flow is as follows：
In the implications set that first stage must be formed from step 5, all high frequency project team are found out.If support is more than
During equal to set minimum support threshold value, high frequency k- project team is set to, is typically expressed as Largek.Algorithm and from
Produce Largek+1 again in the project team of Largek, until cannot again find longer high frequency project team untill.Second stage exists
It is pass by this rule extraction when the confidence level that a rule is tried to achieve meets min confidence under the condition threshold of min confidence
Connection rule.Wherein, high frequency project team refers to that the frequency that a certain project team occurs is higher for all items.
7) after the completion of correlation rule is extracted, the fault diagnosis mining model of electric energy meter is formed, the fault diagnosis is excavated
Model links to the real time fail database of electric energy meter, and failure predication is carried out for the current failure for electric energy meter.
8) failure predication is carried out with electrical energy meter fault diagnosis mining model, exports failure predication result.
In a preferred embodiment, based on the current fault message determined draw corresponding failure predication information it
Afterwards, can also be by current failure information and its corresponding failure predication information Store to the historical failure data storehouse.It is corresponding,
The fault diagnosis mining model can be also updated according to new historical failure data storehouse according to the time cycle of setting,
To improve the accuracy of failure predication.
It should be noted that for foregoing each method embodiment, in order to simplicity is described, it is all expressed as a series of
Combination of actions, but those skilled in the art should know, and the present invention is not limited by described sequence of movement, because according to
According to the present invention, some steps can sequentially or simultaneously be carried out using other.Additionally, also any group can be carried out to above-described embodiment
Close, obtain other embodiments.
Based on above-described embodiment in electrical energy meter fault Forecasting Methodology identical thought, the present invention also provide electric energy meter therefore
Barrier prediction meanss, the device can be used to perform above-mentioned electrical energy meter fault Forecasting Methodology.For convenience of description, electrical energy meter fault prediction
In the structural representation of device embodiment, the part related to the embodiment of the present invention is illustrate only, those skilled in the art can
To understand, it is illustrated that the restriction of structure not structure twin installation, can include than illustrating more or less part, or combine certain
A little parts, or different part arrangements.
Fig. 3 is the schematic diagram of the electrical energy meter fault prediction meanss of one embodiment of the invention；As shown in figure 3, this reality
The electrical energy meter fault prediction meanss for applying example include：Information and Fault Identification module 310, modular converter 320 and modulus of conversion
Block 330, details are as follows for each module：
Described information is collected and Fault Identification module 310, the real-time running data for obtaining electric energy meter, will be described real-time
Service data is input into default breakdown judge model, judges whether to break down；
The modular converter 320, for if it is determined that break down, then the fault message that will currently determine be converted to in advance
The logical term that the fault diagnosis mining model for first building is adapted；The fault diagnosis mining model is based on the electric energy meter
The Association Rules Model that historical failure information is built using the algorithm of Mining Boolean Association Rules frequent item set；
The prediction module 330, for by the corresponding logical term of current failure information and the fault diagnosis mining model
In correlation rule matched, failure predication information corresponding with the electric energy meter current failure is drawn according to matching result.
In one embodiment, described information is collected and Fault Identification module 320, is additionally operable to be input into by the service data
Before default breakdown judge model, the service data is pre-processed, remove noise data therein.
In one embodiment, default breakdown judge model includes：Fly away and sentence with mutation failure judgment models, clock failure
Disconnected model, indicating value stop walking at least two in breakdown judge model.
In one embodiment, described electrical energy meter fault prediction meanss also include：Fault diagnosis mining model builds module,
Sort out for the fault message in the historical failure data storehouse to the default electric energy meter, formedImplications,
X is fault message set F={ F1, F2..., FNIn item or item collection, Y be failure predication results set R={ R1, R2...,
RNIn item or item collection；Default minimum support and confidence level are read, is used according to the minimum support and confidence level
Apriori algorithm scans the implications set in the historical failure data storehouse, obtains frequent item set and extracts correlation rule；Root
The fault diagnosis mining model of the electric energy meter is built according to the correlation rule for extracting；Wherein, in the historical failure data storehouse
Store a plurality of historical failure information and the corresponding failure predication result of each bar fault message of the electric energy meter.
It should be noted that in the implementation method of the electrical energy meter fault prediction meanss of above-mentioned example, the letter between each module
The contents such as breath interaction, implementation procedure, due to being based on same design, its technique effect for bringing with preceding method embodiment of the present invention
Identical with preceding method embodiment of the present invention, particular content can be found in the narration in the inventive method embodiment, no longer go to live in the household of one's in-laws on getting married herein
State.
Additionally, in the implementation method of the electrical energy meter fault prediction meanss of above-mentioned example, the logical partitioning of each functional module is only
Be for example, in practical application can as needed, for example for corresponding hardware configuration requirement or software realization
It is convenient to consider, above-mentioned functions distribution is completed by different functional modules, will the electrical energy meter fault prediction meanss inside
Structure is divided into different functional modules, to complete all or part of function described above.Wherein each function mould both can be with
Realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.
It will appreciated by the skilled person that all or part of flow in realizing above-described embodiment method, being can
Completed with instructing the hardware of correlation by computer program, described program can be stored in embodied on computer readable storage and be situated between
In matter, as independent production marketing or use.Described program upon execution, can perform as above-mentioned each method embodiment it is complete
Portion or part steps.Wherein, described storage medium can be magnetic disc, CD, read-only memory (Read-Only
Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiments.
Embodiment described above only expresses several embodiments of the invention, it is impossible to be interpreted as to the scope of the claims of the present invention
Limitation.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise,
Various modifications and improvements can be made, these belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention
Should be determined by the appended claims.
Claims (10)
1. a kind of electrical energy meter fault Forecasting Methodology, it is characterised in that including：
The real-time running data of electric energy meter is obtained, the real-time running data is input into default breakdown judge model, judgement is
No failure；
If it is determined that breaking down, then the fault message that will currently determine is converted to and the fault diagnosis mining model for building in advance
Adaptable logical term；The fault diagnosis mining model is that the historical failure information based on the electric energy meter uses Mining Boolean
The Association Rules Model that the algorithm of correlation rule frequent item set builds；
The corresponding logical term of current failure information is matched with the correlation rule in the fault diagnosis mining model, according to
Matching result draws failure predication information corresponding with the electric energy meter current failure.
2. electrical energy meter fault Forecasting Methodology according to claim 1, it is characterised in that collecting the service data of electric energy meter
Afterwards, before the service data being input into default breakdown judge model, also include：
The service data is pre-processed, noise data therein is removed.
3. electrical energy meter fault Forecasting Methodology according to claim 1, it is characterised in that default breakdown judge model bag
Include：Fly away stop walking with mutation failure judgment models, clock failure judgment models, indicating value in breakdown judge model at least two.
4. electrical energy meter fault Forecasting Methodology according to claim 3, it is characterised in that
Described flying away with mutation failure judgment models be：
WF=220*3*Ib；
WFIt is the working capacity of the electric energy meter, IbIt is the fundamental current of the electric energy meter, K is flying for the default electric energy meter
Walk and mutation factor；
The service data is input into default breakdown judge model, judges whether that failure includes：
To be flown away and mutation failure judgment models described in service data input, when K is more than or equal to the first setting value, judged
To occur flying away and mutation failure；
And/or,
The clock failure judgment models are：
Δ t=| tTerminal-tAmmeter|；
Wherein, Δ t is the difference of clock of power meter time and standard clock time, tTerminalIt is standard clock time, tAmmeterIt is the electricity
The clock time of energy table；
The service data is input into default breakdown judge model, judges whether that failure includes：
The service data is input into the clock failure judgment models, when Δ t is more than or equal to the second setting value, is judged as
Current clock is not to failure；
And/or,
The indicating value stops walking breakdown judge model：
w1=w1’；
w2=w2’；
Wherein, w1For the forward direction of today has work value, w1' there are work value, w for the forward direction of yesterday2Reversely there are work value, w for today2' be
The reverse of yesterday has work value；
The service data is input into default breakdown judge model, judges whether that failure includes：
The service data is input into the indicating value to stop walking breakdown judge model, when the electric energy meter forward direction of adjacent two days have work value and
Reversely have work value constant, and described adjacent two days per day current value be more than or equal to three setting values when, be judged as
Existing indicating value stops walking failure.
5. electrical energy meter fault Forecasting Methodology according to claim 1, it is characterised in that also include：
Fault message in the historical failure data storehouse of the default electric energy meter is sorted out, is formedImplications, X
It is fault message set F={ F1, F2..., FNIn item or item collection, Y be failure predication results set R={ R1, R2...,
RNIn item or item collection；
Default minimum support and confidence level are read, is swept using Apriori algorithm according to the minimum support and confidence level
The implications set in the historical failure data storehouse is retouched, frequent item set is obtained and is extracted correlation rule；According to the pass for extracting
Connection rule builds the fault diagnosis mining model of the electric energy meter；
Wherein, a plurality of historical failure information and each bar failure letter of the electric energy meter are stored in the historical failure data storehouse
Cease corresponding failure predication result.
6. electrical energy meter fault Forecasting Methodology according to claim 5, it is characterised in that the fault type includes：Hardware
Failure, electricity are abnormal, at least one in operation exception；
The hardware fault includes：On-load switch malfunction or tripping, ESAM mistakes, internal memory card initialization mistake, Clock battery electricity
Force down, internal processes mistake, holder failure or damage, clock failure and/or power cut-off recording battery undervoltage；
The electricity includes extremely：Fly away with mutation failure, reversely active indicating value more than zero failure, clock not to failure, fall away
Failure and/or indicating value stop walking failure；
The operation exception includes：Power cut-off recording battery undervoltage failure, power-off fault, switching on failure, switch access state amount
Failure, game clock lid failure are conjugated, end button cover failure, stationary magnetic field interference failure is opened and/or is reset failure.
7. according to any described electrical energy meter fault Forecasting Methodology of claim 1 to 6, it is characterised in that obtained according to matching result
Going out failure predication information corresponding with the electric energy meter current failure includes：
Logical term matching degree highest association rule corresponding with current failure information are obtained from the fault diagnosis mining model
Then, failure predication information corresponding with the electric energy meter current failure is drawn according to the correlation rule.
8. a kind of electrical energy meter fault prediction meanss, it is characterised in that including：
Information and Fault Identification module, the real-time running data for obtaining electric energy meter are defeated by the real-time running data
Enter default breakdown judge model, judge whether to break down；
Modular converter, for if it is determined that breaking down, then the fault message that will currently determine is converted to and the event for building in advance
The adaptable logical term of barrier diagnosis mining model；The fault diagnosis mining model is the historical failure letter based on the electric energy meter
The Association Rules Model that breath is built using the algorithm of Mining Boolean Association Rules frequent item set；
Prediction module, for by the correlation rule in the corresponding logical term of current failure information and the fault diagnosis mining model
Matched, failure predication information corresponding with the electric energy meter current failure is drawn according to matching result.
9. electrical energy meter fault prediction meanss according to claim 8, it is characterised in that described information is collected and Fault Identification
Module, was additionally operable to before the service data is input into default breakdown judge model, and pre- place is carried out to the service data
Reason, removes noise data therein；
And/or,
Default breakdown judge model includes：Fly away and stop walking event with mutation failure judgment models, clock failure judgment models, indicating value
In barrier judgment models at least two.
10. electrical energy meter fault prediction meanss according to claim 8 or 9, it is characterised in that also include：
Fault diagnosis mining model builds module, for the failure letter in the historical failure data storehouse to the default electric energy meter
Breath is sorted out, and is formedImplications, X be fault message set F={ F1, F2..., FNIn item or item collection, Y is
Failure predication results set R={ R1, R2..., RNIn item or item collection；Read default minimum support and confidence level, root
The implications set in the historical failure data storehouse is scanned using Apriori algorithm according to the minimum support and confidence level,
Obtain frequent item set and extract correlation rule；Mould is excavated according to the fault diagnosis that the correlation rule for extracting builds the electric energy meter
Type；
Wherein, a plurality of historical failure information and each bar failure letter of the electric energy meter are stored in the historical failure data storehouse
Cease corresponding failure predication result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710100110.9A CN106842106A (en) | 2017-02-23 | 2017-02-23 | Electrical energy meter fault Forecasting Methodology and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710100110.9A CN106842106A (en) | 2017-02-23 | 2017-02-23 | Electrical energy meter fault Forecasting Methodology and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106842106A true CN106842106A (en) | 2017-06-13 |
Family
ID=59134898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710100110.9A Pending CN106842106A (en) | 2017-02-23 | 2017-02-23 | Electrical energy meter fault Forecasting Methodology and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106842106A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107422175A (en) * | 2017-08-25 | 2017-12-01 | 中国电力科学研究院 | A kind of method and system for judging that power information acquisition system clock is abnormal |
| CN109038540A (en) * | 2018-06-12 | 2018-12-18 | 国网天津市电力公司 | A kind of supervisory control of substation information discriminating system based on big data analysis |
| CN110611531A (en) * | 2019-09-02 | 2019-12-24 | 锐捷网络股份有限公司 | Optical module fault diagnosis and early warning method, device and system |
| CN110703183A (en) * | 2019-11-13 | 2020-01-17 | 江苏方天电力技术有限公司 | Intelligent electric energy meter fault data analysis method and system |
| CN110888101A (en) * | 2019-12-05 | 2020-03-17 | 新奥数能科技有限公司 | Electric energy meter abnormity diagnosis method and device |
| CN110908844A (en) * | 2019-10-24 | 2020-03-24 | 珠海格力电器股份有限公司 | Arc fault detection method and device, computer readable storage medium and socket |
| CN110991668A (en) * | 2019-11-29 | 2020-04-10 | 合肥国轩高科动力能源有限公司 | Electric vehicle power battery monitoring data analysis method based on association rule |
| CN112053009A (en) * | 2020-09-30 | 2020-12-08 | 华人运通(江苏)技术有限公司 | Fault prediction method, device, system and storage medium |
| CN112286088A (en) * | 2020-09-25 | 2021-01-29 | 广东邮电职业技术学院 | Method and application system for online application of power equipment fault prediction model |
| CN112347072A (en) * | 2020-09-30 | 2021-02-09 | 宁波三星医疗电气股份有限公司 | Method for verifying data of power acquisition terminal |
| CN112748389A (en) * | 2019-10-31 | 2021-05-04 | 河南许继仪表有限公司 | On-site intelligent single-phase electric energy meter fault diagnosis instrument |
| CN116027253A (en) * | 2023-03-01 | 2023-04-28 | 广东电网有限责任公司广州供电局 | Electric energy meter fault self-diagnosis method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN104569886A (en) * | 2014-12-05 | 2015-04-29 | 胡乔林 | Calibrating method for signal detection equipment based on time-frequency parameter standard instrument |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN105630885A (en) * | 2015-12-18 | 2016-06-01 | 国网福建省电力有限公司泉州供电公司 | Abnormal power consumption detection method and system |
| CN106019084A (en) * | 2016-06-16 | 2016-10-12 | 上海交通大学 | Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method |
| CN106054104A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter fault real time prediction method based on decision-making tree |
| CN106154209A (en) * | 2016-07-29 | 2016-11-23 | 国电南瑞科技股份有限公司 | Electrical energy meter fault Forecasting Methodology based on decision Tree algorithms |
| CN106199494A (en) * | 2016-07-25 | 2016-12-07 | 国网上海市电力公司 | A kind of intelligent diagnosis system based on metering device fault |
-
2017
- 2017-02-23 CN CN201710100110.9A patent/CN106842106A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN104569886A (en) * | 2014-12-05 | 2015-04-29 | 胡乔林 | Calibrating method for signal detection equipment based on time-frequency parameter standard instrument |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN105630885A (en) * | 2015-12-18 | 2016-06-01 | 国网福建省电力有限公司泉州供电公司 | Abnormal power consumption detection method and system |
| CN106054104A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter fault real time prediction method based on decision-making tree |
| CN106019084A (en) * | 2016-06-16 | 2016-10-12 | 上海交通大学 | Power distribution and utilization data association-based medium-voltage power grid line fracture fault diagnosis method |
| CN106199494A (en) * | 2016-07-25 | 2016-12-07 | 国网上海市电力公司 | A kind of intelligent diagnosis system based on metering device fault |
| CN106154209A (en) * | 2016-07-29 | 2016-11-23 | 国电南瑞科技股份有限公司 | Electrical energy meter fault Forecasting Methodology based on decision Tree algorithms |
Non-Patent Citations (2)
| Title |
|---|
| 侯向丹等: "基于关联规则的电力仪表企业故障诊断", 《广西师范大学学报：自然科学版》 * |
| 王新刚等: "基于数据挖掘的智能电能表在线监测方法", 《电测与仪表》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107422175A (en) * | 2017-08-25 | 2017-12-01 | 中国电力科学研究院 | A kind of method and system for judging that power information acquisition system clock is abnormal |
| CN109038540A (en) * | 2018-06-12 | 2018-12-18 | 国网天津市电力公司 | A kind of supervisory control of substation information discriminating system based on big data analysis |
| CN110611531A (en) * | 2019-09-02 | 2019-12-24 | 锐捷网络股份有限公司 | Optical module fault diagnosis and early warning method, device and system |
| CN110908844B (en) * | 2019-10-24 | 2022-03-08 | 珠海格力电器股份有限公司 | Arc fault detection method and device, computer readable storage medium and socket |
| CN110908844A (en) * | 2019-10-24 | 2020-03-24 | 珠海格力电器股份有限公司 | Arc fault detection method and device, computer readable storage medium and socket |
| CN112748389A (en) * | 2019-10-31 | 2021-05-04 | 河南许继仪表有限公司 | On-site intelligent single-phase electric energy meter fault diagnosis instrument |
| CN110703183A (en) * | 2019-11-13 | 2020-01-17 | 江苏方天电力技术有限公司 | Intelligent electric energy meter fault data analysis method and system |
| CN110991668A (en) * | 2019-11-29 | 2020-04-10 | 合肥国轩高科动力能源有限公司 | Electric vehicle power battery monitoring data analysis method based on association rule |
| CN110888101A (en) * | 2019-12-05 | 2020-03-17 | 新奥数能科技有限公司 | Electric energy meter abnormity diagnosis method and device |
| CN112286088A (en) * | 2020-09-25 | 2021-01-29 | 广东邮电职业技术学院 | Method and application system for online application of power equipment fault prediction model |
| CN112347072A (en) * | 2020-09-30 | 2021-02-09 | 宁波三星医疗电气股份有限公司 | Method for verifying data of power acquisition terminal |
| CN112053009A (en) * | 2020-09-30 | 2020-12-08 | 华人运通(江苏)技术有限公司 | Fault prediction method, device, system and storage medium |
| CN112053009B (en) * | 2020-09-30 | 2023-08-01 | 华人运通(江苏)技术有限公司 | Fault prediction method, device, system and storage medium |
| CN116027253A (en) * | 2023-03-01 | 2023-04-28 | 广东电网有限责任公司广州供电局 | Electric energy meter fault self-diagnosis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106842106A (en) | Electrical energy meter fault Forecasting Methodology and device | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN105759201B (en) | High-voltage circuitbreaker self-diagnosing method based on exceptional sample identification | |
| CN109787979B (en) | Method for detecting electric power network event and invasion | |
| CN110855503A (en) | Fault cause determining method and system based on network protocol hierarchy dependency relationship | |
| CN107733357A (en) | The fault detection algorithm of battery panel in a kind of large-sized photovoltaic power station | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN110297207A (en) | Method for diagnosing faults, system and the electronic device of intelligent electric meter | |
| CN109409444B (en) | Multivariate power grid fault type discrimination method based on prior probability | |
| CN108663581A (en) | A kind of secondary equipment of intelligent converting station test method | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| Renga et al. | Data-driven exploratory models of an electric distribution network for fault prediction and diagnosis | |
| CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
| CN113395182B (en) | Intelligent network equipment management system and method with fault prediction | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN111143835B (en) | Non-invasive protection method for business logic of electric power metering system based on machine learning | |
| CN113093695A (en) | Data-driven SDN controller fault diagnosis system | |
| CN112803587A (en) | Intelligent inspection method for state of automatic equipment based on diagnosis decision library | |
| CN107092247A (en) | A kind of packaging production line method for diagnosing faults based on status data | |
| Catterson et al. | On-line transformer condition monitoring through diagnostics and anomaly detection | |
| Lan et al. | Unsupervised power system event detection and classification using unlabeled pmu data | |
| CN110210634A (en) | Based on big data driving Civil Aviation Engine fault diagnosis with it is health management system arranged | |
| CN107016410B (en) | Power information acquisition system method for diagnosing faults and trouble-shooter | |
| Nisi et al. | Transparently Mining Data from a Medium-voltage Distribution Network: A Prognostic-diagnostic Analysis. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |