CN109598052A - Intelligent electric meter life cycle prediction technique and device based on correlation analysis - Google Patents
Intelligent electric meter life cycle prediction technique and device based on correlation analysis Download PDFInfo
- Publication number
- CN109598052A CN109598052A CN201811440265.8A CN201811440265A CN109598052A CN 109598052 A CN109598052 A CN 109598052A CN 201811440265 A CN201811440265 A CN 201811440265A CN 109598052 A CN109598052 A CN 109598052A
- Authority
- CN
- China
- Prior art keywords
- indicate
- life cycle
- ammeter
- manufacturer
- intelligent electric
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of intelligent electric meter life cycle prediction technique and device based on correlation analysis, by the intelligent electric meter life cycle prediction technique based on correlation analysis according to unit factor to affect, manufacturer's factor to affect and fault type factor to affect be major parameter, and using neural network algorithm as parameter training auxiliary.This method process is as follows: firstly, calculating the cycle dependency of three verifying unit, ammeter manufacturer, failure cause factors；Then the prediction model of the prediction replacement cycle of ammeter, the every value occurred in initialization model are obtained；Weight is determined using heuristic iterative search later, is modified using the update weight mode based on neural network algorithm；Finally design Early-warning Model.It realizes the Accurate Prediction to the life cycle of intelligent electric meter and replaces the technical effect of early warning.
Description
Technical field
The present invention relates to the data mining technology fields in Computer Subject, and in particular to the intelligence based on correlation analysis
It can ammeter life cycle prediction technique and device.
Background technique
Intelligent electric energy meter is the ammeter for starting largely to spread in life application layer in recent years.With in world wide
The construction and correlation of " smart grid " and advanced measurement system (advanced metering infrastructure, AMI)
The propulsion of technology is just attract a large amount of meters manufacturer as the intelligent electric meter of its base components and core equipment.Intelligent electric meter
Need that there is high reliability and long life under normal operation, and can it is unattended under the conditions of can be continuously uninterrupted
Work.
In order to effectively manage intelligent electric meter and safeguard national electric energy, it is capable of the service life of Accurate Prediction and estimation intelligent electric meter
Characteristic becomes extremely important.Influence the credible sexual factor of intelligent electric meter reliability: function, complexity, design, manufacturing process, failure
Criterion, operating condition, installation maintenance etc..
In the prior art, some scholars have carried out correlative study to the maintenance of intelligent electric meter, wherein Chu Jianxin is " based on event
Hinder the repairable system maintenance cycle predicted method of statistical model " in a text, propose a kind of repairable system fault statistics model and dimension
Method is surveyed on the top for repairing the period, its basic principle is single sample parameter estimation of system local fault change rate, as in equipment
Application in maintenance management.This method can have the practicality in the maintenance cycle prediction of maintenance system, but intelligent electric meter this
For class is more likely in the equipment of rotation compared with maintenance, can not directly it apply.In addition, National Standard of the People's Republic of China
GB17215.911 --- in 200X/IEC/TR62059-11:2002, elaborate the credible basic conception of electrical measuring device.
But relevant analysis is not carried out to the life cycle of intelligent electric meter.
Summary of the invention
In view of this, the intelligent electric meter life cycle prediction technique that the present invention provides a kind of based on correlation analysis and
Device can not carry out Accurate Prediction to the life cycle of intelligent electric meter in the prior art to solve or at least partly solve
Technical problem.
In order to solve the above-mentioned technical problem, first aspect present invention provides the intelligent electric meter longevity based on correlation analysis
Order period forecasting method, comprising:
Step S1: calculating and verifies unit, ammeter manufacturer, the cycle dependency between three factors of failure cause, wherein
Cycle dependency specifically:It is former in identical failure that μ ', σ ' respectively indicate identical ammeter manufacturer
Because of different units, the average value and variance in each corresponding ammeter service life；
Step S2: according to cycle dependency, intelligent electric meter life cycle prediction model, the prediction model are constructed specifically:
Wherein, M indicates ammeter manufacturer total quantity, and N indicates failure cause total quantity, and W indicates unit total quantity, min (M, N)
It indicates to take the minimum value in M, N,
Wherein, ω1、ω2For weight factor, initial value 1.00,Indicate ammeter manufacturer j all electricity produced
Quantity weight life cycle mean value of the table in all units；ωDiIndicate the life cycle weighing factor of unit i；ωFjMainError
Indicate the life cycle weighing factor of the major failure reason of ammeter manufacturer j；ωDiCorrelationErrorIndicate the phase of unit i
The life cycle weighing factor of closing property failure cause；
Step S3: intelligent electric meter life cycle is predicted based on the intelligent electric meter life cycle prediction model.
In one embodiment, upon step s 2, the method also includes:
Based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is modified,
Based on revised weight factor, prediction model is optimized.
In one embodiment, the method also includes:
According to the prediction result obtained by prediction model, bimetry period and average error rate are obtained；
Based on bimetry period and average error rate, pre-warning time corresponding with intelligent electric meter is obtained；
Early warning is arranged according to pre-warning time to remind.
In one embodiment, weight parameter in step S2ωDi、ωFjMainErrorAnd ωDiCorrelationError's
Calculation is as follows:
Calculation method beWherein,Indicate manufacture intelligence
The record of the h articles ammeter of ammeter manufacturer j, maxNFjIndicate that the dominant record item number of Watch Factory j, maxError indicate that single batch permits
Perhaps maximum failure rate, default value 2%, ErrorFjhIndicate the h articles record of the failure ammeter quantity of Watch Factory j,
TErrorTimeIndicate the fault time of table, TInstallTimeIndicate the initial set-up time of ammeter,Indicate the number of factory j bug list
Amount；
ωDiCalculation method beWherein, TDiIndicate the life cycle of unit i,
Indicate the average life span period of all units, TDiCalculation are as follows:
Wherein,Indicate a articles ammeter quantity of unit i；max NiaIndicate the record strip number maximum value of unit i,Table
Show a articles life cycle record of unit i,Calculation method are as follows: Indicate using for unit i
The life cycle mean value of all ammeters, sum indicate total Board Lot；
ωFjMainErrorCalculation method be Indicate the main event of ammeter manufacturer j
Hinder the quantity weight life cycle mean value of reason, TallIndicate the mean value of the quantity weight life cycle mean value of all failure causes,Calculation method are as follows:max NFjMainErrorAmmeter manufacturer j
Major failure reason K life cycle dominant record quantity,Indicate the major failure reason of ammeter manufacturer j
The kth item of ammeter quantity records；
ωDiCorrelationErrorCalculation method it is as follows:Wherein,Indicate the quantity weight life cycle mean value of all failure causes,NAllErrorIt indicates
The maximum categorical measure of failure cause,Indicate the quantity weight life cycle of failure cause i, whereinTable
Show the quantity weight life cycle mean value of the dependent failure reason of ammeter manufacturer jMax N indicates the dependent failure reason of manufacturer j most
Big record strip number,Indicate i-th period rotation of failure cause j.
In one embodiment, the intelligent electric meter life cycle number of a true unit i ammeter manufacturer j is pre-defined
According toAs reference data, based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is repaired
Just specifically include:
Step S4.1: from all intelligent electric meter informations record obtained in advance, the ammeter for randomly selecting 2/3 is used as training
Set, then randomly select 2/3 from training set and be used as training sample set, in all intelligent electric meter informations record remaining 1/3
It is positive integer as being A referring to set, and referring to the individual amount in set；
Step S4.2: the formula in prediction model is utilizedWith
It is predicted, prediction object is referring to set
In individual, obtain predicted value
Step S4.3: judging whether the absolute value of the difference of predicted value and reference point is less than threshold value Δ, i.e.,
It is whether true, if set up, go to step S4.4；
Step S4.4: judgementIt is whether true, if set up, update ω2,If invalid, ω is updated1,
Step S4.5: judging whether prediction is completed referring to each of set individual, if completed, is terminated, if
It does not complete, then continues iteration, execute step S4.2.
Based on same inventive concept, second aspect of the present invention provides the intelligent electric meter service life based on correlation analysis
Period forecasting device, comprising:
Authentication module is calculated, for calculating and verifying unit, ammeter manufacturer, the period phase between three factors of failure cause
Guan Xing, wherein cycle dependency specifically:μ ', σ ' respectively indicate identical ammeter manufacturer in phase
The different unit of same failure cause, the average value and variance in each corresponding ammeter service life；
Model construction module, for constructing intelligent electric meter life cycle prediction model, the prediction mould according to cycle dependency
Type specifically:
Wherein, M indicates ammeter manufacturer total quantity, and N indicates failure cause total quantity, and W indicates unit total quantity, min (M, N)
It indicates to take the minimum value in M, N,
Wherein, ω1、ω2For weight factor, initial value 1.00,Indicate ammeter manufacturer j all electricity produced
Quantity weight life cycle mean value of the table in all units；ωDiIndicate the life cycle weighing factor of unit i；ωFjMainError
Indicate the life cycle weighing factor of the major failure reason of ammeter manufacturer j；ωDiCorrelationErrorIndicate the phase of unit i
The life cycle weighing factor of closing property failure cause；
Prediction module, it is pre- for being carried out based on the intelligent electric meter life cycle prediction model to intelligent electric meter life cycle
It surveys.
It in one embodiment, further include prediction model optimization module, for after constructing prediction model:
Based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is modified,
Based on revised weight factor, prediction model is optimized.
In one embodiment, further include early warning setup module, be specifically used for:
According to the prediction result obtained by prediction model, bimetry period and average error rate are obtained；
Based on bimetry period and average error rate, pre-warning time corresponding with intelligent electric meter is obtained；
Early warning is arranged according to pre-warning time to remind.
In one embodiment, weight parameter in model construction moduleωDi、ωFjMainErrorWith
ωDiCorrelationErrorCalculation it is as follows:
Calculation method beWherein,Indicate manufacture intelligence electricity
The record of the h articles ammeter of Watch Factory quotient j, maxNFjIndicate that the dominant record item number of Watch Factory j, maxError indicate that single batch allows
Maximum failure rate, default value 2%, ErrorFjhIndicate the h articles record of the failure ammeter quantity of Watch Factory j, TErrorTime
Indicate the fault time of table, TInstallTimeIndicate the initial set-up time of ammeter,Indicate the quantity of factory j bug list；
ωDiCalculation method beWherein, TDiIndicate the life cycle of unit i,
Indicate the average life span period of all units, TDiCalculation are as follows:
Wherein,Indicate a articles ammeter quantity of unit i；max NiaIndicate the record strip number maximum value of unit i,Table
Show a articles life cycle record of unit i,Calculation method are as follows: Indicate using for unit i
The life cycle mean value of all ammeters, sum indicate total Board Lot；
ωFjMainErrorCalculation method be Indicate the main event of ammeter manufacturer j
Hinder the quantity weight life cycle mean value of reason, TallIndicate the mean value of the quantity weight life cycle mean value of all failure causes,Calculation method are as follows:max NFjMainErrorAmmeter manufacturer j
Major failure reason K life cycle dominant record quantity,Indicate the major failure reason of ammeter manufacturer j
The kth item of ammeter quantity records；
ωDiCorrelationErrorCalculation method it is as follows:Wherein,Indicate the quantity weight life cycle mean value of all failure causes,NAllErrorIt indicates
The maximum categorical measure of failure cause,Indicate the quantity weight life cycle of failure cause i, whereinTable
Show the quantity weight life cycle mean value of the dependent failure reason of ammeter manufacturer jMax N indicates the dependent failure reason of manufacturer j most
Big record strip number,Indicate i-th period rotation of failure cause j.
Based on same inventive concept, third aspect present invention provides a kind of computer readable storage medium, deposits thereon
Computer program is contained, which is performed the method for realizing first aspect.
Said one or multiple technical solutions in the embodiment of the present application at least have following one or more technology effects
Fruit:
The invention proposes the intelligent electric meter life cycle prediction techniques based on correlation analysis, calculate and verify first
Unit, ammeter manufacturer, the cycle dependency between three factors of failure cause construct intelligence electricity then according to cycle dependency
Calendar life period forecasting model, then intelligent electric meter life cycle is predicted based on intelligent electric meter life cycle prediction model.
Due to it is proposed by the present invention be a kind of intelligent electric meter life cycle prediction technique based on correlation analysis, influenced according to unit
Factor, manufacturer's factor to affect and fault type factor to affect are major parameter, and using neural network algorithm as parameter
Training auxiliary, can obtain the prediction model in the bimetry period of ammeter, due to considering unit, ammeter manufacturer, failure original
Cycle dependency because between solves intelligent electric meter so as to realize to the Accurate Prediction of the life cycle of intelligent electric meter
The problem of in terms of because of long-term unattended bring reliability.
Further, weight is determined using heuristic iterative search, is weighed using the update based on neural network algorithm
Double recipe formula is modified, and can be optimized to the prediction model of building, be further increased the accuracy of prediction.
Further, the present invention is also provided with early warning mechanism, and when practical application, electric administrative department can use this model
Intelligent electric meter life cycle nearly when, carry out the regular sampling observation of intelligent electric meter.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the intelligent electric meter life cycle prediction technique stream based on correlation analysis in one embodiment of the present invention
Cheng Tu；
Fig. 2 is the method flow diagram for determining weight using heuristic iterative search based on neural network；
Fig. 3 is the structural frames of the intelligent electric meter life cycle prediction meanss based on correlation analysis in the embodiment of the present invention
Figure；
Fig. 4 is the structure chart of computer readable storage medium in the embodiment of the present invention.
Specific embodiment
Aiming at the problem that it is an object of the invention in terms of intelligent electric meter is because of long-term unattended bring reliability, and
A kind of base of the problem of existing method can not carry out Accurate Prediction to the life cycle of intelligent electric meter, proposition is based on related coefficient
The intelligent electric meter life cycle prediction technique and device of analysis.
To achieve the above object, central scope of the invention is as follows: the basic principle that maintenance data excavates calculates simultaneously
Unit, ammeter manufacturer, the cycle dependency between three factors of failure cause are verified, and is constructed based on after relevant parameter analysis
Prediction model, recycle prediction model predict intelligent electric meter life cycle.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Embodiment one
A kind of intelligent electric meter life cycle prediction technique based on correlation analysis is present embodiments provided, figure is referred to
1, this method comprises:
It is related step S1 to be first carried out: calculating and verifies unit, ammeter manufacturer, the period between three factors of failure cause
Property, wherein cycle dependency specifically:μ ', σ ' respectively indicate identical ammeter manufacturer identical
The different unit of failure cause, the average value and variance in each corresponding ammeter service life.
Specifically, correlation analysis is to study two or more to be in the phase between the stochastic variable of par
The statistical analysis technique of pass relationship.For example, between the height and weight of people；The phase between relative humidity and rainfall in air
The problem of pass relationship is all correlation analysis research.Correlation analysis passes through various correlation properties between discovery stochastic variable, Ke Yiying
For each field such as industrial or agricultural, the hydrology, meteorology, social economy and biology.
In the specific implementation process, the intelligent electric meter " in operation " of each power office provided present invention utilizes certain unit
Fault information data analyzes " using the unit of intelligent electric meter ", the performance for the table that " ammeter manufacturer " difference in turn results in
Variance factor.And thinks the difference of manufacturer, determine design, the difference of manufacturing process." fault type " can express intelligence
The difference of the possible first device component of ammeter." using the unit of ammeter " may cause the operation ring such as geographical environment, temperature, humidity
Border difference and installation maintenance condition difference.
Then it executes step S2: according to cycle dependency, constructing intelligent electric meter life cycle prediction model, the prediction model
Specifically:
Wherein, M indicates ammeter manufacturer total quantity, and N indicates failure cause total quantity, and W indicates unit total quantity, min (M, N)
It indicates to take the minimum value in M, N,
Otherwise
Wherein, ω1、ω2For weight factor, initial value 1.00,Indicate ammeter manufacturer j all electricity produced
Quantity weight life cycle mean value of the table in all units；ωDiIndicate the life cycle weighing factor of unit i；ωFjMainError
Indicate the life cycle weighing factor of the major failure reason of ammeter manufacturer j；ωDiCorrelationErrorIndicate the phase of unit i
The life cycle weighing factor of closing property failure cause, TDiFjFor weights influence parameter, it is however generally that,When only considering major failure reason,
Specifically, this step is initialized to the prediction model in the bimetry period of intelligent electric meter, to influence
Every weight parameter of life cycle is calculated.
Specifically, weight parameter in step S2ωDi、ωFjMainErrorAnd ωDiCorrelationErrorCalculation such as
Under:
Calculation method beWherein,Indicate manufacture intelligence electricity
The record of the h articles ammeter of Watch Factory quotient j, maxNFjIndicate that the dominant record item number of Watch Factory j, maxError indicate that single batch allows
Maximum failure rate, default value 2%, ErrorFjhIndicate the h articles record of the failure ammeter quantity of Watch Factory j, TErrorTime
Indicate the fault time of table, TInstallTimeIndicate the initial set-up time of ammeter,Indicate the quantity of factory j bug list；
ωDiCalculation method beWherein, TDiIndicate the life cycle of unit i,
Indicate the average life span period of all units, TDiCalculation are as follows:
Wherein,Indicate a articles ammeter quantity of unit i；max NiaIndicate the record strip number maximum value of unit i,Table
Show a articles life cycle record of unit i,Calculation method are as follows: Indicate using for unit i
The life cycle mean value of all ammeters, sum indicate total Board Lot；
ωFjMainErrorCalculation method be Indicate the main event of ammeter manufacturer j
Hinder the quantity weight life cycle mean value of reason, TallIndicate the mean value of the quantity weight life cycle mean value of all failure causes,Calculation method are as follows:max NFjMainErrorAmmeter manufacturer j
Major failure reason K life cycle dominant record quantity,Indicate the electricity of the major failure reason of ammeter manufacturer j
The kth item of table quantity records；
ωDiCorrelationErrorCalculation method it is as follows:Wherein,Indicate the quantity weight life cycle mean value of all failure causes,NAllErrorIt indicates
The maximum categorical measure of failure cause,Indicate the quantity weight life cycle of failure cause i, whereinTable
Show the quantity weight life cycle mean value of the dependent failure reason of ammeter manufacturer jMax N indicates the dependent failure reason of manufacturer j most
Big record strip number,Indicate i-th period rotation of failure cause j.
Next execute step S3: based on the intelligent electric meter life cycle prediction model to intelligent electric meter life cycle into
Row prediction.
Specifically, intelligent electric meter life cycle can then be predicted by the prediction model μ ' of building and σ ', in advance
Survey the life cycle that result is ammeter, such as 5 years, 10 years etc..
In order to improve the accuracy of prediction, in one embodiment, upon step s 2, the method also includes:
Based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is modified,
Based on revised weight factor, prediction model is optimized.
Specifically, weight factor can be determined using heuristic iterative search based on neural network.
In one embodiment, the intelligent electric meter life cycle number of a true unit i ammeter manufacturer j is pre-defined
According toAs reference data, based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is repaired
Just specifically include:
Step S4.1: from all intelligent electric meter informations record obtained in advance, the ammeter for randomly selecting 2/3 is used as training
Set, then randomly select 2/3 from training set and be used as training sample set, in all intelligent electric meter informations record remaining 1/3
It is positive integer as being A referring to set, and referring to the individual amount in set；
Step S4.2: the formula in prediction model is utilizedWith
It is predicted, prediction object is referring to set
In individual, obtain predicted value
Step S4.3: judging whether the absolute value of the difference of predicted value and reference point is less than threshold value Δ, i.e.,
It is whether true, if set up, go to step S4.4；
Step S4.4: judgementIt is whether true, if set up, update ω2,If invalid, ω is updated1,
Step S4.5: judging whether prediction is completed referring to each of set individual, if completed, is terminated, if
It does not complete, then continues iteration, execute step S4.2.
Specifically, Fig. 2 is referred to, for the method for using heuristic iterative search to determine weight based on neural network
Flow chart has pre-defined the intelligent electric meter life cycle data of a true unit i ammeter manufacturer jAs reference
Data.In specific implementation, individual variable X can be set, initial value 1 regard corresponding individual as prediction object, so
Afterwards by iteration, an individual often has been calculated, then X adds 1, completes until calculating referring to all individuals in set individual, then
Iteration is completed.It include the update condition and update mode of specific weight factor in iterative process.Pass through updated weight
The factor can then optimize prediction model, further increase prediction effect.In addition, after updating weight factor, also into one
Step verifies cycle dependency, and increases fuzzy warning model function, with the practicability of improvement method.
In one embodiment, the method also includes:
According to the prediction result obtained by prediction model, bimetry period and average error rate are obtained；
Based on bimetry period and average error rate, pre-warning time corresponding with intelligent electric meter is obtained；
Early warning is arranged according to pre-warning time to remind.
Specifically, in order to enable the prediction model in the present invention can be applied preferably, can by following manner come
It realizes: fuzzy warning model can be added in practice, if the bimetry period is A, average error rate B, then when the intelligence electricity
The pre-warning time of table is T=A-A*B.When automatic early-warning is reminded, to inspecting by random samples for intelligent electric meter.If the qualification rate of sampling observation reaches
To 95%, then present lot ammeter continues to use, otherwise with regard to carrying out rotation processing.
The invention proposes the intelligent electric meter life cycle prediction techniques based on correlation analysis, calculate and verify first
Unit, ammeter manufacturer, the cycle dependency between three factors of failure cause construct intelligence electricity then according to cycle dependency
Calendar life period forecasting model, then intelligent electric meter life cycle is predicted based on intelligent electric meter life cycle prediction model.
Due to it is proposed by the present invention be a kind of intelligent electric meter life cycle prediction technique based on correlation analysis, influenced according to unit
Factor, manufacturer's factor to affect and fault type factor to affect are major parameter, and using neural network algorithm as parameter
Training auxiliary, can obtain the prediction model in the bimetry period of ammeter, due to considering unit, ammeter manufacturer, failure original
Cycle dependency because between solves intelligent electric meter so as to realize to the Accurate Prediction of the life cycle of intelligent electric meter
The problem of in terms of because of long-term unattended bring reliability.
Based on the same inventive concept, present invention also provides with the intelligent electric meter based on correlation analysis in embodiment one
The corresponding device of life cycle prediction technique, detailed in Example two.
Embodiment two
A kind of intelligent electric meter life cycle prediction technique device based on correlation analysis is present embodiments provided, please be join
See Fig. 3, which includes:
Authentication module 301 is calculated, for calculating and verifying unit, ammeter manufacturer, the week between three factors of failure cause
Phase correlation, wherein cycle dependency specifically:μ ', σ ' respectively indicate identical ammeter manufacturer
In the different unit of identical failure cause, the average value and variance in each corresponding ammeter service life；
Model construction module 302, for constructing intelligent electric meter life cycle prediction model, this is pre- according to cycle dependency
Survey model specifically:
Wherein, M indicates ammeter manufacturer total quantity, and N indicates failure cause total quantity, and W indicates unit total quantity, min (M, N)
It indicates to take the minimum value in M, N,
Otherwise
Wherein, ω1、ω2For weight factor, initial value 1.00,Indicate ammeter manufacturer j all electricity produced
Quantity weight life cycle mean value of the table in all units；ωDiIndicate the life cycle weighing factor of unit i；ωFjMainError
Indicate the life cycle weighing factor of the major failure reason of ammeter manufacturer j；ωDiCorrelationErrorIndicate the phase of unit i
The life cycle weighing factor of closing property failure cause；
Prediction module 303, for based on the intelligent electric meter life cycle prediction model to intelligent electric meter life cycle into
Row prediction.
It in one embodiment, further include prediction model optimization module, for after constructing prediction model:
Based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is modified,
Based on revised weight factor, prediction model is optimized.
In one embodiment, further include early warning setup module, be specifically used for:
According to the prediction result obtained by prediction model, bimetry period and average error rate are obtained；
Based on bimetry period and average error rate, pre-warning time corresponding with intelligent electric meter is obtained；
Early warning is arranged according to pre-warning time to remind.
In one embodiment, weight parameter in model construction moduleωDi、ωFjMainErrorWith
ωDiCorrelationErrorCalculation it is as follows:
Calculation method beWherein,Indicate manufacture intelligence
The record of the h articles ammeter of ammeter manufacturer j, maxNFjIndicate that the dominant record item number of Watch Factory j, maxError indicate that single batch permits
Perhaps maximum failure rate, default value 2%, ErrorFjhIndicate the h articles record of the failure ammeter quantity of Watch Factory j,
TErrorTimeIndicate the fault time of table, TInstallTimeIndicate the initial set-up time of ammeter,Indicate the number of factory j bug list
Amount；
ωDiCalculation method beWherein, TDiIndicate the life cycle of unit i,
Indicate the average life span period of all units, TDiCalculation are as follows:
Wherein,Indicate a articles ammeter quantity of unit i；max NiaIndicate the record strip number maximum value of unit i,Table
Show a articles life cycle record of unit i,Calculation method are as follows: Indicate using for unit i
The life cycle mean value of all ammeters, sum indicate total Board Lot；
ωFjMainErrorCalculation method be Indicate that ammeter manufacturer j's is main
The quantity weight life cycle mean value of failure cause, TallIndicate the equal of the quantity weight life cycle mean value of all failure causes
Value,Calculation method are as follows:max NFjMainErrorAmmeter factory
The dominant record quantity of the life cycle of the major failure reason K of quotient j,Indicate the major failure reason of ammeter manufacturer j
Ammeter quantity kth item record；
ωDiCorrelationErrorCalculation method it is as follows:Wherein,Indicate the quantity weight life cycle mean value of all failure causes,NAllErrorIt indicates
The maximum categorical measure of failure cause,Indicate the quantity weight life cycle of failure cause i, whereinTable
Show the quantity weight life cycle mean value of the dependent failure reason of ammeter manufacturer jMax N indicates the dependent failure reason of manufacturer j most
Big record strip number,Indicate i-th period rotation of failure cause j.
By the device that the embodiment of the present invention two is introduced, to implement to be based on correlation analysis in the embodiment of the present invention one
Intelligent electric meter life cycle predict used by device, so based on the method that the embodiment of the present invention one is introduced, this field
Affiliated personnel can understand specific structure and the deformation of the device, so details are not described herein.All embodiment of the present invention one
Device used by method belongs to the range of the invention to be protected.
Embodiment three
Based on the same inventive concept, present invention also provides a kind of computer readable storage medium 400, Fig. 4 is referred to,
On be stored with computer program 411, the program be performed realize embodiment one in method.
By the computer readable storage medium that the embodiment of the present invention three is introduced, to implement base in the embodiment of the present invention one
The computer readable storage medium used by the intelligent electric meter life cycle of correlation analysis is predicted, so based on the present invention
The method that embodiment one is introduced, the affiliated personnel in this field can understand specific structure and the change of the computer readable storage medium
Shape, so details are not described herein.Computer readable storage medium used by all one the methods of the embodiment of the present invention all belongs to
In the range of the invention to be protected.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, those skilled in the art can carry out various modification and variations without departing from this hair to the embodiment of the present invention
The spirit and scope of bright embodiment.In this way, if these modifications and variations of the embodiment of the present invention belong to the claims in the present invention
And its within the scope of equivalent technologies, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. the intelligent electric meter life cycle prediction technique based on correlation analysis characterized by comprising
Step S1: calculating and verifies unit, ammeter manufacturer, the cycle dependency between three factors of failure cause, wherein the period
Correlation specifically:μ ', σ ' respectively indicate identical ammeter manufacturer identical failure cause not
Same unit, the average value and variance in each corresponding ammeter service life；
Step S2: according to cycle dependency, intelligent electric meter life cycle prediction model, the prediction model are constructed specifically:
Wherein, M indicates ammeter manufacturer total quantity, and N indicates failure cause total quantity, and W indicates unit total quantity, and min (M, N) is indicated
The minimum value in M, N is taken,
Wherein, ω1、ω2For weight factor, initial value 1.00,Indicate that ammeter manufacturer j all ammeters produced exist
The quantity weight life cycle mean value of all units；ωDiIndicate the life cycle weighing factor of unit i；ωFjMainErrorIt indicates
The life cycle weighing factor of the major failure reason of ammeter manufacturer j；ωDiCorrelationErrorIndicate the correlation of unit i
The life cycle weighing factor of failure cause；
Step S3: intelligent electric meter life cycle is predicted based on the intelligent electric meter life cycle prediction model.
2. the method as described in claim 1, which is characterized in that upon step s 2, the method also includes:
Based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is modified,
Based on revised weight factor, prediction model is optimized.
3. the method as described in claim 1, which is characterized in that the method also includes:
According to the prediction result obtained by prediction model, bimetry period and average error rate are obtained；
Based on bimetry period and average error rate, pre-warning time corresponding with intelligent electric meter is obtained；
Early warning is arranged according to pre-warning time to remind.
4. the method as described in claim 1, which is characterized in that weight parameter in step S2ωDi、ωFjMainErrorWith
ωDiCorrelationErrorCalculation it is as follows:
Calculation method be
Wherein,Indicate the record of the h articles ammeter of manufacture intelligent electric meter manufacturer j, max NFjIndicate the dominant record of Watch Factory j
Item number, max Error indicate the maximum failure rate that single batch allows, default value 2%, ErrorFjhIndicate the event of Watch Factory j
Hinder the h articles record of ammeter quantity, TErrorTimeIndicate the fault time of table, TInstallTimeIndicate the initial set-up time of ammeter,Indicate the quantity of factory j bug list；
ωDiCalculation method beWherein, TDiIndicate the life cycle of unit i,
Indicate the average life span period of all units, TDiCalculation are as follows:
Wherein,Indicate a articles ammeter quantity of unit i；max NiaIndicate the record strip number maximum value of unit i,Indicate single
The a articles life cycle record of position i,Calculation method are as follows: Indicate that using for unit i is all
The life cycle mean value of ammeter, sum indicate total Board Lot；
ωFjMainErrorCalculation method be Indicate that the major failure of ammeter manufacturer j is former
The quantity weight life cycle mean value of cause, TallIndicate the mean value of the quantity weight life cycle mean value of all failure causes,Calculation method are as follows:max NFjMainErrorAmmeter manufacturer j
Major failure reason K life cycle dominant record quantity,Indicate the major failure reason of ammeter manufacturer j
The kth item of ammeter quantity records；
ωDiCorrelationErrorCalculation method it is as follows:Wherein,It indicates
The quantity weight life cycle mean value of all failure causes,NAllErrorIndicate failure cause
Maximum categorical measure,Indicate the quantity weight life cycle of failure cause i, whereinIndicate ammeter manufacturer j
Dependent failure reason quantity weight life cycle mean value
Max N indicates the dominant record item number of the dependent failure reason of manufacturer j,Indicate the i-th of failure cause j
Period rotation.
5. method as claimed in claim 4, which is characterized in that the intelligence of a pre-defined true unit i ammeter manufacturer j
Ammeter life cycle dataAs referring to data, the update weight mode based on default neural network algorithm is to weight factor
ω1And ω2It is modified and specifically includes:
Step S4.1: from all intelligent electric meter informations record obtained in advance, 2/3 ammeter is randomly selected as training set
Conjunction, then randomly select 2/3 from training set and be used as training sample set, remaining 1/3 work in all intelligent electric meter informations records
It is positive integer to be A referring to set, and referring to the individual amount in set；
Step S4.2: the formula in prediction model is utilizedWithIt is predicted, prediction object is the individual in reference set,
Obtain predicted value
Step S4.3: judging whether the absolute value of the difference of predicted value and reference point is less than threshold value Δ, i.e.,Whether
It sets up, if set up, goes to step S4.4；
Step S4.4: judgementIt is whether true, if set up, update ω2,If invalid, ω is updated1,
Step S4.5: judge whether prediction is completed referring to each of set individual, if completed, is terminated, if not complete
At then continuing iteration, execute step S4.2.
6. the intelligent electric meter life cycle prediction meanss based on correlation analysis characterized by comprising
Authentication module is calculated, it is related for calculating and verifying unit, ammeter manufacturer, the period between three factors of failure cause
Property, wherein cycle dependency specifically:μ ', σ ' respectively indicate identical ammeter manufacturer identical
The different unit of failure cause, the average value and variance in each corresponding ammeter service life；
Model construction module, for constructing intelligent electric meter life cycle prediction model, prediction model tool according to cycle dependency
Body are as follows:
Wherein, M indicates ammeter manufacturer total quantity, and N indicates failure cause total quantity, and W indicates unit total quantity, and min (M, N) is indicated
The minimum value in M, N is taken,
Wherein, ω1、ω2For weight factor, initial value 1.00,Indicate that ammeter manufacturer j all ammeters produced exist
The quantity weight life cycle mean value of all units；ωDiIndicate the life cycle weighing factor of unit i；ωFjMainErrorIt indicates
The life cycle weighing factor of the major failure reason of ammeter manufacturer j；ωDiCorrelationErrorIndicate the correlation of unit i
The life cycle weighing factor of failure cause；
Prediction module, for being predicted based on the intelligent electric meter life cycle prediction model intelligent electric meter life cycle.
7. device as claimed in claim 6, which is characterized in that further include prediction model optimization module, for being predicted in building
After model:
Based on the update weight mode of default neural network algorithm to weight factor ω1And ω2It is modified,
Based on revised weight factor, prediction model is optimized.
8. method as claimed in claim 6, which is characterized in that further include early warning setup module, be specifically used for:
According to the prediction result obtained by prediction model, bimetry period and average error rate are obtained；
Based on bimetry period and average error rate, pre-warning time corresponding with intelligent electric meter is obtained；
Early warning is arranged according to pre-warning time to remind.
9. device as claimed in claim 8, which is characterized in that weight parameter in model construction moduleωDi、
ωFjMainErrorAnd ωDiCorrelationErrorCalculation it is as follows:
Calculation method beWherein,Indicate manufacture intelligent electric meter
The record of the h articles ammeter of manufacturer j, maxNFjIndicate that the dominant record item number of Watch Factory j, maxError indicate what single batch allowed
Maximum failure rate, default value 2%, ErrorFjhIndicate the h articles record of the failure ammeter quantity of Watch Factory j, TErrorTimeTable
Show the fault time of table, TInstallTimeIndicate the initial set-up time of ammeter,Indicate the quantity of factory j bug list；
ωDiCalculation method beWherein, TDiIndicate the life cycle of unit i,
Indicate the average life span period of all units, TDiCalculation are as follows:
Wherein,Indicate a articles ammeter quantity of unit i；max NiaIndicate the record strip number maximum value of unit i,Indicate single
The a articles life cycle record of position i,Calculation method are as follows: Indicate that using for unit i is all
The life cycle mean value of ammeter, sum indicate total Board Lot；
ωFjMainErrorCalculation method be Indicate the major failure of ammeter manufacturer j
The quantity weight life cycle mean value of reason, TallIndicate the mean value of the quantity weight life cycle mean value of all failure causes,Calculation method are as follows:max NFjMainErrorAmmeter manufacturer j
Major failure reason K life cycle dominant record quantity,Indicate the major failure reason of ammeter manufacturer j
The kth item of ammeter quantity records；
ωDiCorrelationErrorCalculation method it is as follows:Wherein,It indicates
The quantity weight life cycle mean value of all failure causes,NAllErrorIndicate failure cause
Maximum categorical measure,Indicate the quantity weight life cycle of failure cause i, whereinIndicate ammeter manufacturer
The quantity weight life cycle mean value of the dependent failure reason of j
Max N indicates the dominant record item number of the dependent failure reason of manufacturer j,Indicate the of failure cause j
I period rotation.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is performed
Realize the method as described in any one of claim 1 to 5 claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811440265.8A CN109598052B (en) | 2018-11-29 | 2018-11-29 | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811440265.8A CN109598052B (en) | 2018-11-29 | 2018-11-29 | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109598052A true CN109598052A (en) | 2019-04-09 |
| CN109598052B CN109598052B (en) | 2022-07-05 |
Family
ID=65959833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811440265.8A Active CN109598052B (en) | 2018-11-29 | 2018-11-29 | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598052B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261811A (en) * | 2019-07-05 | 2019-09-20 | 北京志翔科技股份有限公司 | Intelligent electric meter batch method for early warning and system |
| CN110287640A (en) * | 2019-07-03 | 2019-09-27 | 辽宁艾特斯智能交通技术有限公司 | Life prediction method, apparatus, storage medium and the electronic equipment of lighting apparatus |
| CN110967695A (en) * | 2019-10-28 | 2020-04-07 | 兰州大方电子有限责任公司 | Radar echo extrapolation short-term prediction method based on deep learning |
| CN115358347A (en) * | 2022-09-30 | 2022-11-18 | 山西虚拟现实产业技术研究院有限公司 | Method for predicting remaining life of intelligent electric meter under different subsystems |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708306A (en) * | 2012-06-19 | 2012-10-03 | 华北电网有限公司计量中心 | Prediction method for q-precentile life of intelligent meter |
| CN103018706A (en) * | 2012-11-16 | 2013-04-03 | 浙江省电力公司电力科学研究院 | Method and system for forecasting rotation cycle of intelligent electric meter |
| CN103383445A (en) * | 2013-07-16 | 2013-11-06 | 湖北省电力公司电力科学研究院 | System and method for forecasting service life and reliability of intelligent electric meter |
| CN105022019A (en) * | 2015-06-23 | 2015-11-04 | 国家电网公司 | Method of comprehensively estimating reliability of single-phase intelligent electric energy meter |
| CN106054105A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter reliability prediction correction model building method |
| KR20160140474A (en) * | 2015-05-27 | 2016-12-07 | 내셔날 쳉쿵 유니버시티 | Metrology sampling method with sampling rate decision scheme and computer program product thereof |
| CN108680890A (en) * | 2018-08-23 | 2018-10-19 | 重庆市计量质量检测研究院 | Intelligent electric energy meter life characteristics detection method |
| CN109344967A (en) * | 2018-08-31 | 2019-02-15 | 武汉大学 | A kind of intelligent electric meter life cycle prediction technique based on artificial neural network |
-
2018
- 2018-11-29 CN CN201811440265.8A patent/CN109598052B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708306A (en) * | 2012-06-19 | 2012-10-03 | 华北电网有限公司计量中心 | Prediction method for q-precentile life of intelligent meter |
| CN103018706A (en) * | 2012-11-16 | 2013-04-03 | 浙江省电力公司电力科学研究院 | Method and system for forecasting rotation cycle of intelligent electric meter |
| CN103383445A (en) * | 2013-07-16 | 2013-11-06 | 湖北省电力公司电力科学研究院 | System and method for forecasting service life and reliability of intelligent electric meter |
| KR20160140474A (en) * | 2015-05-27 | 2016-12-07 | 내셔날 쳉쿵 유니버시티 | Metrology sampling method with sampling rate decision scheme and computer program product thereof |
| CN105022019A (en) * | 2015-06-23 | 2015-11-04 | 国家电网公司 | Method of comprehensively estimating reliability of single-phase intelligent electric energy meter |
| CN106054105A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter reliability prediction correction model building method |
| CN108680890A (en) * | 2018-08-23 | 2018-10-19 | 重庆市计量质量检测研究院 | Intelligent electric energy meter life characteristics detection method |
| CN109344967A (en) * | 2018-08-31 | 2019-02-15 | 武汉大学 | A kind of intelligent electric meter life cycle prediction technique based on artificial neural network |
Non-Patent Citations (2)
| Title |
|---|
| 张强等: "智能电能表全生命周期质量跟踪策略探讨", 《东北电力技术》 * |
| 贺宁: "智能电表故障大数据分析探究", 《中小企业管理与科技(上旬刊)》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287640A (en) * | 2019-07-03 | 2019-09-27 | 辽宁艾特斯智能交通技术有限公司 | Life prediction method, apparatus, storage medium and the electronic equipment of lighting apparatus |
| CN110287640B (en) * | 2019-07-03 | 2023-10-13 | 辽宁艾特斯智能交通技术有限公司 | Lighting equipment service life prediction method and device, storage medium and electronic equipment |
| CN110261811A (en) * | 2019-07-05 | 2019-09-20 | 北京志翔科技股份有限公司 | Intelligent electric meter batch method for early warning and system |
| CN110967695A (en) * | 2019-10-28 | 2020-04-07 | 兰州大方电子有限责任公司 | Radar echo extrapolation short-term prediction method based on deep learning |
| CN115358347A (en) * | 2022-09-30 | 2022-11-18 | 山西虚拟现实产业技术研究院有限公司 | Method for predicting remaining life of intelligent electric meter under different subsystems |
| CN115358347B (en) * | 2022-09-30 | 2023-01-31 | 山西虚拟现实产业技术研究院有限公司 | Method for predicting remaining life of intelligent electric meter under different subsystems |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109598052B (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | Review of urban building energy modeling (UBEM) approaches, methods and tools using qualitative and quantitative analysis | |
| CN109598052A (en) | Intelligent electric meter life cycle prediction technique and device based on correlation analysis | |
| CN109614997A (en) | A kind of stealing Risk Forecast Method and device based on deep learning | |
| CN104200288B (en) | A kind of equipment fault Forecasting Methodology based on dependency relation identification between factor and event | |
| US20190139059A1 (en) | Demand forecasting device, demand forecasting method and non-transitory computer readable medium | |
| CN109740787A (en) | Training Building air conditioning load prediction model and the method and apparatus predicted with it | |
| CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
| CN106651007A (en) | Method and device for GRU-based medium and long-term prediction of irradiance of photovoltaic power station | |
| CN114493052B (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
| CN117335411B (en) | Medium-and-long-term power generation capacity prediction method for photovoltaic power station group | |
| Shin et al. | Spatiotemporal load-analysis model for electric power distribution facilities using consumer meter-reading data | |
| Otache et al. | ARMA modelling of Benue River flow dynamics: comparative study of PAR model | |
| Zelikman et al. | Short-term solar irradiance forecasting using calibrated probabilistic models | |
| CN103020733B (en) | Method and system for predicting single flight noise of airport based on weight | |
| CN109615414A (en) | House property predictor method, device and storage medium | |
| Ghassemi et al. | Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings | |
| Niska et al. | Evolving smart meter data driven model for short-term forecasting of electric loads | |
| Han et al. | Fengwu-ghr: Learning the kilometer-scale medium-range global weather forecasting | |
| Mahdi et al. | Using artificial neural networks to predict solar radiation for Duhok City, Iraq | |
| Zou et al. | Predicting the electric power consumption of office buildings based on dynamic and static hybrid data analysis | |
| Yang et al. | Short-term demand forecasting for bike sharing system based on machine learning | |
| JP7257276B2 (en) | Data prediction system and method | |
| Zhang et al. | Robust interval state estimation for distribution systems considering pseudo-measurement interval prediction | |
| Debdas et al. | Short-Term Load Forecasting Using Time Series Algorithm | |
| Wu et al. | Regional forecasting of fine particulate matter concentrations: A novel hybrid model based on principal component regression and EOF |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |