CN109598052B - Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis - Google Patents

Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis Download PDF

Info

Publication number
CN109598052B
CN109598052B CN201811440265.8A CN201811440265A CN109598052B CN 109598052 B CN109598052 B CN 109598052B CN 201811440265 A CN201811440265 A CN 201811440265A CN 109598052 B CN109598052 B CN 109598052B
Authority
CN
China
Prior art keywords
life cycle
meter
representing
manufacturer
failure
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.)
Active
Application number
CN201811440265.8A
Other languages
Chinese (zh)
Other versions
CN109598052A (en
Inventor
刘金硕
刘必为
李瞧
杨广益
李扬眉
李晨曦
田浩翔
柳凯
谢志国
冯阔
严鸿昌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN201811440265.8A priority Critical patent/CN109598052B/en
Publication of CN109598052A publication Critical patent/CN109598052A/en
Application granted granted Critical
Publication of CN109598052B publication Critical patent/CN109598052B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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

Abstract

The invention provides a method and a device for predicting the life cycle of an intelligent electric meter based on correlation coefficient analysis. The method comprises the following steps: firstly, calculating the periodic correlation of three factors of a verification unit, an ammeter manufacturer and a fault reason; then obtaining a prediction model of the prediction replacement period of the electric meter, and initializing the values of all items appearing in the model; then, determining the weight by adopting a heuristic method through iterative search, and correcting by using an updating weight mode based on a neural network algorithm; and finally designing an early warning model. The technical effects of accurate prediction of the service life cycle of the intelligent electric meter and replacement early warning are achieved.

Description

Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis
Technical Field
The invention relates to the technical field of data mining in computer science, in particular to a method and a device for predicting the life cycle of an intelligent electric meter based on correlation coefficient analysis.
Background
The intelligent electric energy meter is a novel electric energy meter which is popularized to a living application layer in a large quantity in recent years. With the worldwide development of the "smart grid" and Advanced Measurement Infrastructure (AMI) and related technologies, smart meters, which are their basic components and core devices, are attracting a large number of meter manufacturers. The smart meter needs to have high reliability and long service life under normal conditions and can continuously and uninterruptedly work under unattended conditions.
In order to effectively manage the smart meter and maintain the national power, it is very important to be able to accurately predict and estimate the life characteristics of the smart meter. Factors influencing reliability credibility of the intelligent electric meter are as follows: function, complexity, design, manufacturing process, failure criteria, operating conditions, installation maintenance, etc.
In the prior art, some scholars conduct relevant research on maintenance of the intelligent electric meter, wherein a new repairable system maintenance period prediction method based on a fault statistical model is built, and a top measurement method of the repairable system fault statistical model and the maintenance period is provided. The method has practical applicability in predicting the maintenance period of the maintainable system, but cannot be directly applied to equipment such as a smart meter which is more prone to rotation than maintenance. Furthermore, the basic concept of the credibility of electrical measuring devices is set forth in the national standard of the people's republic of China GB 17215.911-200X/IEC/TR 62059-11: 2002. But no relevant analysis is performed on the life cycle of the smart meter.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for predicting a life cycle of a smart meter based on correlation coefficient analysis, so as to solve or at least partially solve the technical problem in the prior art that the life cycle of the smart meter cannot be accurately predicted.
In order to solve the technical problem, a first aspect of the present invention provides a method for predicting a life cycle of a smart meter based on correlation coefficient analysis, including:
step S1: calculating and verifying the periodic correlation among three factors of a unit, an electric meter manufacturer and a fault reason, wherein the periodic correlation specifically comprises the following steps:
Figure BDA0001884522880000021
mu 'and sigma' respectively represent the average value and the variance of the service life of each corresponding ammeter in the same unit with different fault reasons of the same ammeter manufacturer;
step S2: according to the period correlation, a life cycle prediction model of the intelligent electric meter is constructed, and the prediction model specifically comprises the following steps:
Figure BDA0001884522880000022
wherein M represents the total number of the manufacturers of the electric meter, N represents the total number of the fault reasons, W represents the total number of units, min (M, N) represents the minimum value in M, N,
wherein, ω is1、ω2As a weighting factor, the initial value is 1.00,
Figure BDA0001884522880000023
representing the number weighted life cycle average of all meters produced by meter manufacturer j in all units; omegaDiLife cycle impact weight in units of i; omegaFjMainErrorLife cycle impact weight representing the primary cause of failure for meter manufacturer j; omegaDiCorrelationErrorLife cycle influence weight representing the correlation fault cause of unit i;
step S3: and predicting the life cycle of the intelligent electric meter based on the life cycle prediction model of the intelligent electric meter.
In one embodiment, after step S2, the method further comprises:
updating weight mode pair weight factor omega based on preset neural network algorithm1And ω2The correction is carried out so that the correction is carried out,
and optimizing the prediction model based on the corrected weight factor.
In one embodiment, the method further comprises:
obtaining a predicted life cycle and an average error rate according to a prediction result obtained through the prediction model;
acquiring early warning time corresponding to the intelligent ammeter based on the predicted life cycle and the average error rate;
and setting early warning reminding according to the early warning time.
In one embodiment, the weighting parameters in step S2
Figure BDA0001884522880000024
ωDi、ωFjMainErrorAnd ωDiCorrelationErrorThe calculation method of (c) is as follows:
Figure BDA0001884522880000031
is calculated by
Figure BDA0001884522880000032
Wherein the content of the first and second substances,
Figure BDA0001884522880000033
record, maxN, representing the h-th meter of the manufacturer j that manufactured the smart meterFjRepresents the maximum number of records of the meter factory j, maxError represents the maximum fault rate allowed by a single batch, the default value is 2 percent, and ErrorFjhH-th record, T, representing the number of faulty meters of meter factory jErrorTimeIndicating the time of failure, T, of the watchInstallTimeRepresents the initial installation time of the electricity meter,
Figure BDA0001884522880000034
indicating the number of plant j fault tables;
ωDiis calculated by
Figure BDA0001884522880000035
Wherein, TDiThe life cycle in units of i is expressed,
Figure BDA0001884522880000036
denotes the average life cycle, T, of all unitsDiThe calculation method is as follows:
Figure BDA0001884522880000037
wherein the content of the first and second substances,
Figure BDA0001884522880000038
the number of the a-th electric meters in the unit i is represented; max NiaThe maximum value of the number of records in the unit i,
Figure BDA0001884522880000039
the a-th life cycle record representing the unit i,
Figure BDA00018845228800000310
the calculation method comprises the following steps:
Figure BDA00018845228800000311
Figure BDA00018845228800000312
represents the life cycle average of all meters used in unit i, sum represents the total number of units;
ωFjMainErroris calculated by
Figure BDA00018845228800000313
Figure BDA00018845228800000314
Number weighted life cycle mean, T, representing the major cause of failure for meter manufacturer jallThe number representing all the causes of failure weights the mean of the life cycle averages,
Figure BDA00018845228800000315
the calculation method comprises the following steps:
Figure BDA00018845228800000316
max NFjMainErrorthe maximum number of records of life cycle of the main cause of failure K of meter manufacturer j,
Figure BDA00018845228800000317
a kth record of the number of meters indicating the main causes of failure for meter manufacturer j;
ωDiCorrelationErrorthe calculation method of (2) is as follows:
Figure BDA00018845228800000318
wherein the content of the first and second substances,
Figure BDA0001884522880000041
the quantity representing all the causes of failure is weighted by the life cycle average,
Figure BDA0001884522880000042
NAllErrorthe maximum number of categories representing the cause of the fault,
Figure BDA0001884522880000043
the number representing the cause of the fault i, weights the life cycle, wherein,
Figure BDA0001884522880000044
number weighted life cycle mean value representing correlation fault cause of meter manufacturer j
Figure BDA0001884522880000045
max N represents the maximum number of records of the correlation failure cause of the manufacturer j,
Figure BDA0001884522880000046
the ith cycle representing the cause of the fault j is rotated.
In one embodiment, the life cycle data of the smart meter of a real unit i-meter manufacturer j is predefined
Figure BDA0001884522880000047
As reference data, the weight factor omega is subjected to weight updating based on the updating weight mode of the preset neural network algorithm1And ω2The correction specifically includes:
step S4.1: randomly extracting 2/3 electric meters from all the pre-acquired intelligent electric meter information records to serve as a training set, then randomly extracting 2/3 electric meters from the training set to serve as a training sample set, and taking the rest 1/3 of all the intelligent electric meter information records as a reference set, wherein the number of individuals in the reference set is A and is a positive integer;
step S4.2: using formulas in predictive models
Figure BDA0001884522880000048
And
Figure BDA0001884522880000049
performing prediction by taking the prediction object as an individual in the reference set to obtain a predicted value
Figure BDA00018845228800000410
Step S4.3: determining whether the absolute value of the difference between the predicted value and the reference value is less than a threshold value delta, i.e.
Figure BDA00018845228800000411
If yes, go to step S4.4;
step S4.4: judgment of
Figure BDA00018845228800000412
If true, then ω is updated2，
Figure BDA00018845228800000413
If not, update ω1，
Figure BDA00018845228800000414
Step S4.5: and judging whether each individual in the reference set is predicted to be finished or not, if so, finishing, and if not, continuing iteration and executing the step S4.2.
Based on the same inventive concept, the second aspect of the present invention provides a device for predicting life cycle of a smart meter based on correlation coefficient analysis, comprising:
the calculation and verification module is used for calculating and verifying the periodic correlation among three factors, namely a unit, an electric meter manufacturer and a fault reason, wherein the periodic correlation specifically comprises the following steps:
Figure BDA0001884522880000051
mu 'and sigma' respectively represent the average value and the variance of the service life of each corresponding ammeter in the same unit with different fault reasons of the same ammeter manufacturer;
the model building module is used for building a life cycle prediction model of the intelligent electric meter according to the cycle correlation, and the prediction model specifically comprises the following steps:
Figure BDA0001884522880000052
wherein M represents the total number of the manufacturers of the electric meter, N represents the total number of the fault reasons, W represents the total number of units, min (M, N) represents the minimum value in M, N,
wherein, ω is1、ω2As a weighting factor, the initial value is 1.00,
Figure BDA0001884522880000053
representing the number weighted life cycle average of all meters produced by meter manufacturer j in all units; omegaDiLife cycle impact weight in units of i; omegaFjMainErrorLife cycle impact weight representing the primary cause of failure for meter manufacturer j; omegaDiCorrelationErrorLife cycle influence weight representing the correlation fault cause of unit i;
and the prediction module is used for predicting the service life of the intelligent electric meter based on the service life prediction model of the intelligent electric meter.
In one embodiment, the method further comprises a prediction model optimization module for, after building the prediction model:
updating weight mode pair weight factor omega based on preset neural network algorithm1And ω2The correction is carried out so that the correction is carried out,
and optimizing the prediction model based on the corrected weight factor.
In one embodiment, the system further comprises an early warning setting module, specifically configured to:
obtaining a predicted life cycle and an average error rate according to a prediction result obtained through the prediction model;
acquiring early warning time corresponding to the intelligent ammeter based on the predicted life cycle and the average error rate;
and setting early warning reminding according to the early warning time.
In one embodiment, the weight parameters in the model building module
Figure BDA0001884522880000054
ωDi、ωFjMainErrorAnd ωDiCorrelationErrorThe calculation method of (c) is as follows:
Figure BDA0001884522880000055
is calculated by
Figure BDA0001884522880000056
Wherein the content of the first and second substances,
Figure BDA0001884522880000057
record, maxN, representing the h-th meter of the manufacturer j that manufactured the smart meterFjRepresents the maximum number of records of the meter factory j, maxError represents the maximum fault rate allowed by a single batch, the default value is 2 percent, and ErrorFjhH-th record, T, representing the number of faulty meters of meter factory jErrorTimeIndicating the time of failure, T, of the watchInstallTimeRepresents the initial installation time of the electricity meter,
Figure BDA0001884522880000061
indicating the number of plant j fault tables;
ωDiis calculated by
Figure BDA0001884522880000062
Wherein, TDiThe life cycle in units of i is expressed,
Figure BDA0001884522880000063
denotes the average life cycle, T, of all unitsDiThe calculation method is as follows:
Figure BDA0001884522880000064
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0001884522880000065
the number of the a-th electric meters in the unit i is represented; max NiaThe maximum value of the number of records in the unit i,
Figure BDA0001884522880000066
the a-th life cycle record representing the unit i,
Figure BDA0001884522880000067
the calculation method comprises the following steps:
Figure BDA0001884522880000068
Figure BDA0001884522880000069
represents the life cycle average of all meters used in unit i, sum represents the total number of units;
ωFjMainErroris calculated by
Figure BDA00018845228800000610
Figure BDA00018845228800000611
Number weighted life cycle mean, T, representing the major cause of failure for meter manufacturer jallThe number representing all the causes of failure weights the mean of the life cycle averages,
Figure BDA00018845228800000612
the calculation method comprises the following steps:
Figure BDA00018845228800000613
max NFjMainErrorthe maximum number of records of life cycle of the main cause of failure K of meter manufacturer j,
Figure BDA00018845228800000614
a kth record of the number of meters indicating the main causes of failure for meter manufacturer j;
ωDiCorrelationErrorthe calculation method of (2) is as follows:
Figure BDA00018845228800000615
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA00018845228800000616
the quantity representing all the causes of failure is weighted by the life cycle average,
Figure BDA00018845228800000617
NAllErrorthe maximum number of categories representing the cause of the fault,
Figure BDA00018845228800000618
the number representing the cause of the fault i, weights the life cycle, wherein,
Figure BDA0001884522880000071
number weighted life cycle mean value representing correlation fault cause of meter manufacturer j
Figure BDA0001884522880000072
max N represents the maximum number of records of the correlation failure cause of the manufacturer j,
Figure BDA0001884522880000073
the ith cycle representing the cause of the fault j is rotated.
Based on the same inventive concept, a third aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed, performs the method of the first aspect.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
the invention provides a life cycle prediction method of an intelligent electric meter based on correlation coefficient analysis. The invention provides a life cycle prediction method of an intelligent ammeter based on correlation coefficient analysis, which can obtain a prediction model of the life cycle of the ammeter according to unit influence factors, manufacturer influence factors and fault type influence factors as main parameters and by taking a neural network algorithm as parameter training assistance.
Furthermore, a heuristic method is adopted to iteratively search and determine the weight, and an updating weight mode based on a neural network algorithm is used for correction, so that the constructed prediction model can be optimized, and the prediction accuracy is further improved.
Furthermore, the invention also provides an early warning mechanism, and when the intelligent ammeter is actually applied, a power management department can utilize the model to carry out regular sampling inspection on the intelligent ammeter when the service life cycle of the intelligent ammeter is close.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a life cycle prediction method for an intelligent electric meter based on correlation coefficient analysis according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for determining weights by iterative search using a heuristic approach based on neural networks;
FIG. 3 is a block diagram of an apparatus for predicting life cycle of a smart meter based on correlation coefficient analysis according to an embodiment of the present invention;
fig. 4 is a block diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
The invention aims to provide a method and a device for predicting the life cycle of an intelligent electric meter based on correlation coefficient analysis, aiming at the problems of reliability of the intelligent electric meter caused by long-term unattended operation and the problem that the life cycle of the intelligent electric meter cannot be accurately predicted by the conventional method.
In order to achieve the above object, the main concept of the present invention is as follows: by applying the basic principle of data mining, the periodic correlation among three factors of a unit, an ammeter manufacturer and a fault reason is calculated and verified, a prediction model based on relevant parameter analysis is constructed, and the service life of the intelligent ammeter is predicted by using the prediction model.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The embodiment provides a smart meter life cycle prediction method based on correlation coefficient analysis, please refer to fig. 1, and the method includes:
step S1 is first executed: calculating and verifying the periodic correlation among three factors of a unit, an electric meter manufacturer and a fault reason, wherein the periodic correlation specifically comprises the following steps:
Figure BDA0001884522880000081
the μ 'and σ' respectively represent the average value and the variance of the life of each electric meter corresponding to the same electric meter manufacturer in the same unit with different fault causes.
Specifically, correlation coefficient analysis is a statistical analysis method for studying the correlation between two or more equally positioned random variables. For example, between the height and weight of a person; the correlation between the relative humidity in the air and the rainfall is a problem of relevant analytical research. Correlation analysis can be applied to various fields such as industry and agriculture, hydrology, meteorology, social economy, biology and the like by finding various correlation characteristics among random variables.
In a specific implementation process, the method utilizes fault information data, provided by a certain unit, of the intelligent electric meters in the operation process of each power bureau, and analyzes the performance difference factors of the meters caused by the difference of the unit using the intelligent electric meters and the manufacturer of the intelligent electric meters. And the design and manufacturing process are different according to different manufacturers. The "fault type" can express the difference of possible element components of the intelligent electric meter. The "unit using the electricity meter" may cause differences in operating environments such as geographical environment, temperature, humidity, and the like, and differences in installation and maintenance conditions.
Then, step S2 is executed: according to the period correlation, a life cycle prediction model of the intelligent electric meter is constructed, and the prediction model specifically comprises the following steps:
Figure BDA0001884522880000091
wherein M represents the total number of the manufacturers of the electric meter, N represents the total number of the fault reasons, W represents the total number of units, min (M, N) represents the minimum value in M, N,
Figure BDA0001884522880000092
otherwise
Figure BDA0001884522880000093
Wherein, ω is1、ω2As a weighting factor, the initial value is 1.00,
Figure BDA0001884522880000094
representing the number weighted life cycle average of all meters produced by meter manufacturer j in all units; omegaDiLife cycle impact weight in units of i; omegaFjMainErrorLife cycle impact weight representing the primary cause of failure for meter manufacturer j; omegaDiCorrelationErrorLife cycle impact weight, T, representing the cause of a correlation failure in unit iDiFjFor the weight-influencing parameters, it is, in general,
Figure BDA0001884522880000095
when only the primary cause of the fault is considered,
Figure BDA0001884522880000096
specifically, the step is to initialize a prediction model of the life cycle of the smart meter and calculate various weight parameters influencing the life cycle.
Specifically, the weight parameter in step S2
Figure BDA0001884522880000097
ωDi、ωFjMainErrorAnd ωDiCorrelationErrorThe calculation method of (c) is as follows:
Figure BDA0001884522880000098
is calculated by
Figure BDA0001884522880000099
Wherein the content of the first and second substances,
Figure BDA00018845228800000910
record, maxN, representing the h-th meter of the manufacturer j that manufactured the smart meterFjRepresents the maximum number of records of the meter factory j, maxError represents the maximum fault rate allowed by a single batch, the default value is 2 percent, and ErrorFjhH-th record, T, representing the number of faulty meters of meter factory jErrorTimeIndicating the time of failure, T, of the watchInstallTimeRepresents the initial installation time of the electricity meter,
Figure BDA0001884522880000101
indicating the number of plant j fault tables;
ωDiis calculated by
Figure BDA0001884522880000102
Wherein, TDiThe life cycle in units of i is expressed,
Figure BDA0001884522880000103
denotes the average life cycle, T, of all unitsDiThe calculation method is as follows:
Figure BDA0001884522880000104
wherein the content of the first and second substances,
Figure BDA0001884522880000105
the number of the a-th electric meters in the unit i is represented; max NiaThe maximum value of the number of records in the unit i,
Figure BDA0001884522880000106
the a-th life cycle record representing the unit i,
Figure BDA0001884522880000107
the calculation method comprises the following steps:
Figure BDA0001884522880000108
Figure BDA0001884522880000109
represents the life cycle average of all meters used in unit i, sum represents the total number of units;
ωFjMainErroris calculated by
Figure BDA00018845228800001010
Figure BDA00018845228800001011
Number weighted life cycle mean, T, representing the major cause of failure for meter manufacturer jallThe number representing all the causes of failure weights the mean of the life cycle averages,
Figure BDA00018845228800001012
the calculation method comprises the following steps:
Figure BDA00018845228800001013
max NFjMainErrorthe maximum number of records of life cycle of the main cause of failure K of meter manufacturer j,
Figure BDA00018845228800001014
a kth record of the number of meters indicating the main causes of failure for meter manufacturer j;
ωDiCorrelationErrorthe calculation method of (2) is as follows:
Figure BDA00018845228800001015
wherein the content of the first and second substances,
Figure BDA00018845228800001016
the quantity representing all causes of failure weights the life cycle mean,
Figure BDA00018845228800001017
NAllErrorthe maximum number of categories representing the cause of the fault,
Figure BDA00018845228800001018
the number representing the cause of the fault i, weights the life cycle, wherein,
Figure BDA0001884522880000111
number weighted life cycle mean value representing correlation fault cause of meter manufacturer j
Figure BDA0001884522880000112
max N represents the maximum number of records of the correlation failure cause of the manufacturer j,
Figure BDA0001884522880000113
the ith cycle representing the cause of the fault j is rotated.
Step S3 is executed next: and predicting the life cycle of the intelligent electric meter based on the life cycle prediction model of the intelligent electric meter.
Specifically, the life cycle of the smart meter can be predicted through the constructed prediction models mu 'and sigma', and the prediction result is the life cycle of the smart meter, such as 5 years, 10 years and the like.
To improve the accuracy of the prediction, in one embodiment, after step S2, the method further comprises:
updating weight mode pair weight factor omega based on preset neural network algorithm1And ω2The correction is carried out so that the correction is carried out,
and optimizing the prediction model based on the corrected weight factor.
In particular, a heuristic method may be employed to iteratively search for the determined weight factors based on the neural network.
In one embodiment, the life cycle data of the smart meter of a real unit i-meter manufacturer j is predefined
Figure BDA0001884522880000119
As reference data, the weight factor omega is subjected to weight updating based on the updating weight mode of the preset neural network algorithm1And ω2The correction specifically includes:
step S4.1: randomly extracting 2/3 electric meters from all the pre-acquired intelligent electric meter information records to serve as a training set, then randomly extracting 2/3 electric meters from the training set to serve as a training sample set, and taking the rest 1/3 of all the intelligent electric meter information records as a reference set, wherein the number of individuals in the reference set is A and is a positive integer;
step S4.2: using formulas in predictive models
Figure BDA0001884522880000114
And
Figure BDA0001884522880000115
performing prediction by taking the prediction object as an individual in the reference set to obtain a predicted value
Figure BDA0001884522880000116
Step S4.3: determining whether the absolute value of the difference between the predicted value and the reference value is less than a threshold value delta, i.e.
Figure BDA0001884522880000117
If yes, go to step S4.4;
step S4.4: judgment of
Figure BDA0001884522880000118
If true, then ω is updated2，
Figure BDA0001884522880000121
If not, update ω1，
Figure BDA0001884522880000122
Step S4.5: and judging whether each individual in the reference set is predicted to be finished or not, if so, finishing, and if not, continuing iteration and executing the step S4.2.
Specifically, referring to fig. 2, a flowchart of a method for determining weights by using heuristic iterative search based on a neural network is shown, where life cycle data of a smart meter of a real unit i-meter manufacturer j is predefined
Figure BDA0001884522880000123
As reference data. In specific implementation, an individual variable X may be set, the initial value is 1, the corresponding individual is used as a prediction object, and then through iteration, every time an individual is calculated, X is added by 1, until all the individuals in the reference set are calculated, the iteration is completed. In the iterative process, the updating condition and the updating mode of the specific weight factor are included. Through the updated weight factors, the prediction model can be optimized, and the prediction effect is further improved. In addition, after the weight factor is updated, the periodic correlation is further verified, and a fuzzy early warning function is added, so that the practicability of the method is improved.
In one embodiment, the method further comprises:
obtaining a predicted life cycle and an average error rate according to a prediction result obtained through the prediction model;
acquiring early warning time corresponding to the intelligent ammeter based on the predicted life cycle and the average error rate;
and setting early warning reminding according to the early warning time.
In particular, in order to make the prediction model in the present invention better applicable, it can be realized by: in practical application, fuzzy early warning can be added, the predicted life cycle is set as A, the average error rate is set as B, and when the early warning time of the intelligent ammeter is T-A-B. When the automatic early warning is reminded, the intelligent electric meter is subjected to spot check. If the qualification rate of the spot check reaches 95%, the current batch of the electric meters are continuously used, otherwise, the rotation processing is carried out.
The invention provides a life cycle prediction method of an intelligent electric meter based on correlation coefficient analysis. The invention provides a life cycle prediction method of an intelligent ammeter based on correlation coefficient analysis, which takes a unit influence factor, a manufacturer influence factor and a fault type influence factor as main parameters and takes a neural network algorithm as parameter training assistance to obtain a prediction model of the life cycle of the ammeter.
Based on the same inventive concept, the application also provides a device corresponding to the method for predicting the life cycle of the smart meter based on the correlation coefficient analysis in the first embodiment, which is detailed in the second embodiment.
Example two
The present embodiment provides a smart meter life cycle prediction method and device based on correlation coefficient analysis, please refer to fig. 3, the device includes:
the calculation and verification module 301 is configured to calculate and verify a periodic correlation among three factors, namely a unit, an electric meter manufacturer, and a fault reason, where the periodic correlation specifically includes:
Figure BDA0001884522880000131
mu 'and sigma' respectively represent the average value and the variance of the service life of each corresponding ammeter in the same unit with different fault reasons of the same ammeter manufacturer;
the model building module 302 is configured to build a life cycle prediction model of the smart meter according to the cycle correlation, where the prediction model specifically includes:
Figure BDA0001884522880000132
wherein M represents the total number of the manufacturers of the electric meter, N represents the total number of the fault reasons, W represents the total number of units, min (M, N) represents the minimum value in M, N,
Figure BDA0001884522880000133
otherwise
Figure BDA0001884522880000134
Wherein, ω is1、ω2As a weighting factor, the initial value is 1.00,
Figure BDA0001884522880000135
representing the number weighted life cycle average of all meters produced by meter manufacturer j in all units; omegaDiLife cycle impact weight in units of i; omegaFjMainErrorLife cycle impact weight representing the primary cause of failure for meter manufacturer j; omegaDiCorrelationErrorLife cycle influence weight representing the correlation fault cause of unit i;
and the predicting module 303 is used for predicting the life cycle of the intelligent electric meter based on the life cycle prediction model of the intelligent electric meter.
In one embodiment, the method further comprises a prediction model optimization module for, after building the prediction model:
updating weight mode pair weight factor omega based on preset neural network algorithm1And ω2The correction is carried out so that the correction is carried out,
and optimizing the prediction model based on the corrected weight factor.
In one embodiment, the system further comprises an early warning setting module, specifically configured to:
obtaining a predicted life cycle and an average error rate according to a prediction result obtained through the prediction model;
acquiring early warning time corresponding to the intelligent ammeter based on the predicted life cycle and the average error rate;
and setting early warning reminding according to the early warning time.
In one embodiment, the weight parameters in the model building module
Figure BDA0001884522880000141
ωDi、ωFjMainErrorAnd ωDiCorrelationErrorThe calculation method of (c) is as follows:
Figure BDA0001884522880000142
is calculated by
Figure BDA0001884522880000143
Wherein the content of the first and second substances,
Figure BDA0001884522880000144
record, maxN, representing the h-th meter of the manufacturer j that manufactured the smart meterFjRepresents the maximum number of records of the meter factory j, maxError represents the maximum fault rate allowed by a single batch, the default value is 2 percent, and ErrorFjhH-th record, T, representing the number of faulty meters of meter factory jErrorTimeIndicating the time of failure, T, of the watchInstallTimeRepresents the time of initial installation of the electricity meter,
Figure BDA0001884522880000145
indicating the number of plant j fault tables;
ωDiis calculated by
Figure BDA0001884522880000146
Wherein, TDiThe life cycle in units of i is expressed,
Figure BDA0001884522880000147
denotes the average life cycle, T, of all unitsDiThe calculation method is as follows:
Figure BDA0001884522880000148
wherein the content of the first and second substances,
Figure BDA0001884522880000149
the number of the a-th electric meters in the unit i is represented; max NiaThe maximum value of the number of records in the unit i,
Figure BDA00018845228800001410
the a-th life cycle record representing the unit i,
Figure BDA00018845228800001411
the calculation method comprises the following steps:
Figure BDA00018845228800001412
Figure BDA00018845228800001413
represents the life cycle average of all meters used in unit i, sum represents the total number of units;
ωFjMainErroris calculated by
Figure BDA00018845228800001414
Figure BDA00018845228800001415
Number weighted life cycle mean, T, representing the major cause of failure for meter manufacturer jallThe number representing all the causes of failure weights the mean of the life cycle averages,
Figure BDA00018845228800001416
the calculation method comprises the following steps:
Figure BDA0001884522880000151
max NFjMainErrorthe maximum number of records of life cycle of the main cause of failure K of meter manufacturer j,
Figure BDA0001884522880000152
number of meters indicating the major cause of failure of meter manufacturer jk records are recorded;
ωDiCorrelationErrorthe calculation method of (2) is as follows:
Figure BDA0001884522880000153
wherein the content of the first and second substances,
Figure BDA0001884522880000154
the quantity representing all causes of failure weights the life cycle mean,
Figure BDA0001884522880000155
NAllErrorthe maximum number of categories representing the cause of the fault,
Figure BDA0001884522880000156
the number representing the cause of the fault i, weights the life cycle, wherein,
Figure BDA0001884522880000157
number weighted life cycle mean value representing correlation fault cause of meter manufacturer j
Figure BDA0001884522880000158
max N represents the maximum number of records of the correlation failure cause of the manufacturer j,
Figure BDA0001884522880000159
the ith cycle representing the cause of the fault j is rotated.
Since the device described in the second embodiment of the present invention is a device used for predicting the life cycle of the smart meter based on the correlation coefficient analysis in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and deformation of the device based on the method described in the first embodiment of the present invention, and thus the details are not described herein. All the devices adopted in the method of the first embodiment of the present invention belong to the protection scope of the present invention.
EXAMPLE III
Based on the same inventive concept, the present application further provides a computer-readable storage medium 400, please refer to fig. 4, on which a computer program 411 is stored, which when executed implements the method in the first embodiment.
Since the computer-readable storage medium introduced in the third embodiment of the present invention is a computer-readable storage medium used for implementing the correlation coefficient analysis-based smart meter life cycle prediction in the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, persons skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, and thus details are not described herein. The computer readable storage medium used in the method according to the embodiment of the present invention is within the scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.

Claims (6)

1. The intelligent ammeter life cycle prediction method based on correlation coefficient analysis is characterized by comprising the following steps:
step S1: calculating and verifying the periodic correlation among three factors of a unit, an electric meter manufacturer and a fault reason, wherein the periodic correlation specifically comprises the following steps:
Figure FDA0003653193760000011
mu 'and sigma' respectively represent the average value and the variance of the service life of each corresponding ammeter in the same unit with different fault reasons of the same ammeter manufacturer;
step S2: according to the period correlation, a life cycle prediction model of the intelligent electric meter is constructed, and the prediction model specifically comprises the following steps:
Figure FDA0003653193760000012
wherein M represents the total number of manufacturers of the electric meter, N represents the total number of fault causes, W represents the total number of units, min (M, N) represents the minimum value in M, N,
Figure FDA0003653193760000013
wherein, ω is1、ω2As a weighting factor, the initial value is 1.00,
Figure FDA0003653193760000014
representing the number weighted life cycle average of all meters produced by meter manufacturer i in all units;
Figure FDA0003653193760000015
represents the life cycle impact weight in units of K;
Figure FDA0003653193760000016
life cycle impact weight representing the major cause of failure for meter manufacturer i;
Figure FDA0003653193760000017
the life cycle of the correlation failure cause representing the unit K affects the weight, wherein, when only the primary failure cause is considered,
Figure FDA0003653193760000018
step S3: predicting the life cycle of the intelligent electric meter based on the life cycle prediction model of the intelligent electric meter;
after step S2, the method further includes:
updating weight mode pair weight factor omega based on preset neural network algorithm1And ω2The correction is carried out so that the correction is carried out,
optimizing the prediction model based on the corrected weight factor;
when the weight factor is corrected based on the updating weight mode of the preset neural network algorithm, real life cycle data of the intelligent electric meter of a unit K electric meter manufacturer i is predefined
Figure FDA0003653193760000019
The reference data specifically include: setting an individual variable X with an initial value of 1, taking the corresponding individual as a prediction object, then adding 1 to X through iteration after each individual is calculated until all the individuals in the reference set are calculated, and then finishing the iterationIn the iterative process, the updating condition and the updating mode of the specific weight factor are included;
after updating the weight factors, the method further comprises verifying the periodic correlation;
the method further comprises the following steps:
obtaining a predicted life cycle and an average error rate according to a prediction result obtained through the prediction model;
acquiring early warning time corresponding to the intelligent ammeter based on the predicted life cycle and the average error rate;
and setting early warning reminding according to the early warning time.
2. The method of claim 1, wherein the weight parameter in step S2
Figure FDA0003653193760000021
Figure FDA0003653193760000022
Figure FDA0003653193760000023
And
Figure FDA0003653193760000024
the calculation method of (c) is as follows:
Figure FDA0003653193760000025
is calculated by
Figure FDA0003653193760000026
Wherein the content of the first and second substances,
Figure FDA0003653193760000027
record, maxN, representing the h-th meter of the meter manufacturer iFiRepresents the maximum number of records of the meter manufacturer i, and maxError represents the maximum allowable number of a single batchHigh failure rate, default 2%, ErrorFihH-th record, T, indicating the number of faulty meters from the meter manufacturer iErrorTimeIndicating the time of failure, T, of the watchInstallTimeRepresents the initial installation time of the electricity meter,
Figure FDA0003653193760000028
representing the number of fault meters of a meter manufacturer i;
Figure FDA0003653193760000029
is calculated by
Figure FDA00036531937600000210
Wherein, TDkWhich represents the life cycle in units of K,
Figure FDA00036531937600000211
denotes the average life cycle, T, of all unitsDkThe calculation method is as follows:
Figure FDA00036531937600000212
Figure FDA00036531937600000213
the number of the a-th electric meters in the unit K is represented; maxNKaRepresents the maximum value of the number of recording pieces in the unit K,
Figure FDA00036531937600000214
the a-th life cycle record representing the unit K,
Figure FDA00036531937600000215
the calculation method comprises the following steps:
Figure FDA00036531937600000216
Figure FDA00036531937600000217
represents the life cycle average of all meters in units of K usage, sum represents the total number of units;
Figure FDA00036531937600000218
is calculated by
Figure FDA00036531937600000219
Figure FDA00036531937600000220
Number weighted life cycle average representing the major cause of failure for meter manufacturer i,
Figure FDA00036531937600000221
the number representing all the causes of failure weights the mean of the life cycle averages,
Figure FDA0003653193760000031
the calculation method comprises the following steps:
Figure FDA0003653193760000032
maxNFiMainErrorthe maximum number of records of life cycles of the main cause of failure of the meter manufacturer i,
Figure FDA0003653193760000033
a kth record of the number of meters indicating the major cause of failure for meter manufacturer i;
Figure FDA0003653193760000034
the calculation method of (2) is as follows:
Figure FDA0003653193760000035
wherein the content of the first and second substances,
Figure FDA0003653193760000036
the quantity representing all causes of failure weights the life cycle mean,
Figure FDA0003653193760000037
NAllErrorthe maximum number of categories representing the cause of the fault,
Figure FDA0003653193760000038
the number representing the cause of failure, j, weights the life cycle, where,
Figure FDA0003653193760000039
number weighted life cycle mean value representing relevant fault causes for meter manufacturer i
Figure FDA00036531937600000310
maxN represents the maximum number of records of the correlation failure cause of the manufacturer i,
Figure FDA00036531937600000311
indicating the i-th cycle rotation of meter manufacturer i.
3. The method of claim 2, wherein a real unit of smart meter life cycle data for K meter manufacturer i is predefined
Figure FDA00036531937600000312
As reference data, the weight factor omega is subjected to weight updating based on the updating weight mode of the preset neural network algorithm1And ω2The correction specifically includes:
step S4.1: randomly extracting 2/3 electric meters from all the pre-acquired intelligent electric meter information records to serve as a training set, then randomly extracting 2/3 electric meters from the training set to serve as a training sample set, and taking the rest 1/3 of all the intelligent electric meter information records as a reference set, wherein the number of individuals in the reference set is A and is a positive integer;
step S4.2: using formulas in predictive models
Figure FDA00036531937600000313
And
Figure FDA00036531937600000314
performing prediction by taking the prediction object as an individual in the reference set to obtain a predicted value
Figure FDA00036531937600000315
Step S4.3: determining whether the absolute value of the difference between the predicted value and the reference value is less than a threshold value delta, i.e.
Figure FDA00036531937600000316
If yes, go to step S4.4;
step S4.4: judgment of
Figure FDA0003653193760000041
If true, then ω is updated2，
Figure FDA0003653193760000042
If not, update ω1，
Figure FDA0003653193760000043
Step S4.5: and judging whether each individual in the reference set is predicted to be finished or not, if so, finishing, and if not, continuing iteration and executing the step S4.2.
4. Smart electric meter life cycle prediction device based on correlation coefficient analysis, its characterized in that includes:
the calculation and verification module is used for calculating and verifying the periodic correlation among three factors of a unit, an ammeter manufacturer and a fault reason, wherein the period isThe correlation is specifically:
Figure FDA0003653193760000044
mu 'and sigma' respectively represent the average value and the variance of the service life of each corresponding ammeter in the same unit with different fault reasons of the same ammeter manufacturer;
the model building module is used for building a life cycle prediction model of the intelligent electric meter according to the cycle correlation, and the prediction model specifically comprises the following steps:
Figure FDA0003653193760000046
wherein M represents the total number of manufacturers of the electric meter, N represents the total number of fault causes, W represents the total number of units, min (M, N) represents the minimum value in M, N,
Figure FDA0003653193760000047
wherein, ω is1、ω2As a weighting factor, the initial value is 1.00,
Figure FDA0003653193760000048
representing the number weighted life cycle average of all meters produced by meter manufacturer i in all units;
Figure FDA0003653193760000049
represents the life cycle impact weight in units of k;
Figure FDA00036531937600000410
life cycle impact weight representing the major cause of failure for meter manufacturer i;
Figure FDA00036531937600000411
life cycle influence weight representing the cause of a correlation failure in unit k, whereWhen only the primary cause of the fault is considered,
Figure FDA00036531937600000412
the prediction module is used for predicting the life cycle of the intelligent ammeter based on the life cycle prediction model of the intelligent ammeter;
the apparatus further comprises a weight modification module configured to:
updating weight mode pair weight factor omega based on preset neural network algorithm1And ω2The correction is carried out so that the correction is carried out,
optimizing the prediction model based on the corrected weight factor;
when the weight factor is corrected based on the updating weight mode of the preset neural network algorithm, real life cycle data of the intelligent electric meter of a unit K electric meter manufacturer i is predefined
Figure FDA00036531937600000413
The reference data specifically include: setting an individual variable X, setting the initial value to be 1, taking the corresponding individual as a prediction object, adding 1 to X through iteration after one individual is calculated, and completing the iteration until all the individuals in the reference set are calculated, wherein the iteration process comprises the specific updating condition and the specific updating mode of the weight factor;
the device also comprises a fuzzy early warning module used for:
obtaining a predicted life cycle and an average error rate according to a prediction result obtained through the prediction model;
acquiring early warning time corresponding to the intelligent ammeter based on the predicted life cycle and the average error rate;
and setting early warning reminding according to the early warning time.
5. The apparatus of claim 4, in which the weight parameters in the model building module
Figure FDA0003653193760000053
And
Figure FDA0003653193760000054
the calculation method of (c) is as follows:
Figure FDA0003653193760000055
is calculated by
Figure FDA0003653193760000056
Wherein the content of the first and second substances,
Figure FDA0003653193760000057
record, maxN, representing the h-th meter of the meter manufacturer iFiRepresents the maximum number of records of the manufacturer i of the electric meter, maxError represents the maximum fault rate allowed by a single batch, the default value is 2 percent, and ErrorFihH-th record, T, indicating the number of faulty meters from the meter manufacturer iErrorTimeIndicating the time of failure, T, of the watchInstallTimeRepresents the initial installation time of the electricity meter,
Figure FDA0003653193760000058
representing the number of fault meters of a meter manufacturer i;
Figure FDA0003653193760000059
is calculated by
Figure FDA00036531937600000510
Wherein, TDkWhich represents the life cycle in units of K,
Figure FDA00036531937600000511
denotes the average life cycle, T, of all unitsDkThe calculation method is as follows:
Figure FDA00036531937600000512
Figure FDA00036531937600000513
the number of the a-th electric meters in the unit K is represented; maxNKaRepresents the maximum value of the number of recording pieces in the unit K,
Figure FDA00036531937600000514
the a-th life cycle record representing the unit K,
Figure FDA00036531937600000515
the calculation method comprises the following steps:
Figure FDA00036531937600000516
Figure FDA00036531937600000517
represents the life cycle average of all meters in units of K usage, sum represents the total number of units;
Figure FDA00036531937600000518
is calculated by
Figure FDA00036531937600000519
Figure FDA00036531937600000520
Number weighted life cycle average representing the major cause of failure for meter manufacturer i,
Figure FDA00036531937600000521
the number representing all the causes of failure weights the mean of the life cycle averages,
Figure FDA00036531937600000522
the calculation method comprises the following steps:
Figure FDA00036531937600000523
maxNFiMainErrorthe maximum number of records of life cycles of the main cause of failure of the meter manufacturer i,
Figure FDA0003653193760000061
a kth record of the number of meters indicating the major cause of failure for meter manufacturer i;
Figure FDA0003653193760000062
the calculation method of (2) is as follows:
Figure FDA0003653193760000063
wherein the content of the first and second substances,
Figure FDA0003653193760000064
the quantity representing all the causes of failure is weighted by the life cycle average,
Figure FDA0003653193760000065
NAllErrorthe maximum number of categories representing the cause of the fault,
Figure FDA0003653193760000066
the number representing the cause of failure, j, weights the life cycle, where,
Figure FDA0003653193760000067
number weighted life cycle mean value representing relevant fault causes for meter manufacturer i
Figure FDA0003653193760000068
max N represents the maximum number of records of the cause of the correlation failure of the manufacturer i,
Figure FDA0003653193760000069
indicating electric meter manufacturing plantThe ith cycle of quotient i is rotated.
6. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed, implements the method of any one of claims 1 to 3.
CN201811440265.8A 2018-11-29 2018-11-29 Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis Active CN109598052B (en)

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 CN109598052A (en) 2019-04-09
CN109598052B true 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)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
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

Citations (3)

* Cited by examiner, † Cited by third party
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
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

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
TWI539298B (en) * 2015-05-27 2016-06-21 國立成功大學 Metrology sampling method with sampling rate decision scheme and computer program product thereof
CN106054105B (en) * 2016-05-20 2019-01-15 国网新疆电力公司电力科学研究院 A kind of reliability prediction correction model method for building up of intelligent electric meter
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
CN109344967B (en) * 2018-08-31 2021-09-14 武汉大学 Intelligent electric meter life cycle prediction method based on artificial neural network

Patent Citations (3)

* Cited by examiner, † Cited by third party
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
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

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
智能电能表全生命周期质量跟踪策略探讨;张强等;《东北电力技术》;20150920(第09期);全文 *
智能电表故障大数据分析探究;贺宁;《中小企业管理与科技(上旬刊)》;20160705(第07期);全文 *

Also Published As

Publication number Publication date
CN109598052A (en) 2019-04-09

Similar Documents

Publication Publication Date Title
CN109598052B (en) Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis
CN110442936B (en) Equipment fault diagnosis method, device and system based on digital twin model
JP2021064370A (en) Method and system for semi-supervised deep abnormality detection for large-scale industrial monitoring system based on time-series data utilizing digital twin simulation data
CN107506868B (en) Method and device for predicting short-time power load
CN107730127B (en) Relay storage degradation data prediction method based on output characteristic initial distribution
CN116757534B (en) Intelligent refrigerator reliability analysis method based on neural training network
CN114297036B (en) Data processing method, device, electronic equipment and readable storage medium
CN102708306A (en) Prediction method for q-precentile life of intelligent meter
CN109726865A (en) Customer charge probability density prediction technique, device and storage medium based on EMD-QRF
CN109344967B (en) Intelligent electric meter life cycle prediction method based on artificial neural network
KR20200008621A (en) Electrical Equipment Safety Evaluation System Using Artificial Intelligence Technique
Liu et al. Combined forecasting method of dissolved gases concentration and its application in condition-based maintenance
CN111178585A (en) Fault reporting amount prediction method based on multi-algorithm model fusion
KR20190123040A (en) Solar power generation prediction model management APPARATUS AND METHOD for setting the renewal cycle of the deep run-based solar power generation prediction model
CN112686481A (en) Runoff forecasting method and processor
CN113554466A (en) Short-term power consumption prediction model construction method, prediction method and device
Dong et al. Short-term building cooling load prediction model based on DwdAdam-ILSTM algorithm: A case study of a commercial building
CN116930609A (en) Electric energy metering error analysis method based on ResNet-LSTM model
CN116388150A (en) Matching short-term load prediction method based on digital twin and neural network technology
CN114329347A (en) Method and device for predicting metering error of electric energy meter and storage medium
Ghassemi et al. Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings
CN113589172A (en) Service life estimation method for power grid components
CN117330963A (en) Energy storage power station fault detection method, system and equipment
CN116960962A (en) Mid-long term area load prediction method for cross-area data fusion
CN112581311B (en) Method and system for predicting long-term output fluctuation characteristics of aggregated multiple wind power plants

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