CN104573866A - Method and system for predicting defects of electrical equipment - Google Patents
Method and system for predicting defects of electrical equipment Download PDFInfo
- Publication number
- CN104573866A CN104573866A CN201510009618.9A CN201510009618A CN104573866A CN 104573866 A CN104573866 A CN 104573866A CN 201510009618 A CN201510009618 A CN 201510009618A CN 104573866 A CN104573866 A CN 104573866A
- Authority
- CN
- China
- Prior art keywords
- defect
- defect analysis
- analysis variable
- power equipment
- duration
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 540
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004458 analytical method Methods 0.000 claims abstract description 287
- 239000011159 matrix material Substances 0.000 claims abstract description 39
- 238000006243 chemical reaction Methods 0.000 claims abstract description 17
- 230000007704 transition Effects 0.000 claims description 132
- 230000001186 cumulative effect Effects 0.000 claims description 28
- 238000013507 mapping Methods 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 15
- 238000001816 cooling Methods 0.000 claims description 14
- 230000002950 deficient Effects 0.000 claims description 13
- 239000000284 extract Substances 0.000 claims description 12
- 230000002045 lasting effect Effects 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 abstract description 15
- 230000000694 effects Effects 0.000 abstract description 8
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000008030 elimination Effects 0.000 description 4
- 238000003379 elimination reaction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for predicting defects of electrical equipment. The method is applied to N pieces of electrical equipment of the same type. The method comprises the steps of extracting the historical data of the electrical equipment within a time period, and obtaining K defect analysis variables meeting a predetermined condition; calculating the sum of duration of the electrical equipment under the same defect analysis variable and total duration under the K defect analysis variables, and further obtaining the initial probability of each defect state variable and a vector P(0) through combination; acquiring the total number of appearing times of the K defect analysis variables, determining the number of times of conversion of K*K defect analysis variables between every two adjacent time slices in M time slices obtained through equipartition, and further obtaining K*K conversion probabilities and a matrix P through combination; determining that the defect corresponding to the maximum value in P(1) is a predicated defect existing before new electrical equipment is used according to P(1)= P(0)*P. By the adoption of the method, possible defects of equipment can be detected accurately, labor intensity of equipment maintenance staff can be relieved, and the guiding effect of defect analysis on practical use is improved.
Description
Technical field
The present invention relates to electric power equipment management technical field, particularly relate to a kind of method and system predicting power equipments defect.
Background technology
Healthy power equipment ensures that electrical network normally runs and improves the basis of mains supply reliability.In actual motion, although some power equipment can continue to use, its running status generation exception or there is hidden danger, will cause shorten equipment life, the safety of the impact person, equipment and electrical network, thus degradation rough sledding under there is the quality of power supply.To sum up, the exception of above-mentioned power equipment or hidden danger are all referred to as defect.Therefore, for all kinds of defects in power equipment, need to find as early as possible, eliminate in time, avoid development of defects to be fault, cause the harsh conditions such as grid power blackout to occur.
At present, the analytical approach of power equipments defect is mainly comprised: to the statistics of the defects count of power equipment, defect defect elimination rate and defect elimination promptness rate, and according to the defects count of above-mentioned statistics, defect defect elimination rate and defect elimination promptness rate, power equipment overall fault rate is predicted.Although this analyses and prediction method can grasp generation and the state of development of equipment deficiency to a certain extent, shortcoming is: information is accurate not enough, cannot effective the carrying out of coaching device tour work.Such as, predicting the outcome of overall fault rate is the ratio that the number of devices that defect may occur in following certain batch of power equipment accounts for total quantity, but in actual production, can not the work of effective coaching device operation maintenance personnel.
Summary of the invention
Embodiment of the present invention technical matters to be solved is, a kind of method and system predicting power equipments defect is provided, the contingent defect of power equipment can be gone out by accurately predicting, power equipment operation maintenance personnel is helped to carry out emphasis tour and maintenance targetedly, decrease the labor capacity of power equipment operation maintenance personnel, improve power equipments defect analysis and effect is instructed to actual production work.
In order to solve the problems of the technologies described above, embodiments provide a kind of method predicting power equipments defect, it realizes on N number of of a sort power equipment, and described method comprises:
A, extract the historical data of N number of power equipment described in the time period, be met K defect classification of predetermined condition according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
B, in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
C, obtain described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine to be combined into matrix P by a described K*K transition probability further by the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively; Wherein, M is positive integer;
D, according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Wherein, described method comprises further:
Obtain a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
Wherein, the concrete steps of described step a comprise:
Extract the historical data of N number of power equipment described in the time period, and determine the total degree that in described historical data, each defect occurs;
The total degree sequential from large to small that each defect is occurred, filter out the defect that a front K-1 total degree is large, and classification corresponding for a described K-1 defect and classification that defect do not occur are set to defect analysis variable further as K the defect classification satisfied condition.
Wherein, the concrete steps of described step b comprise:
In described historical data, obtain the lasting time of origin of described N number of power equipment each defect analysis variable corresponding, under filtering out same defect analysis variable described N number of power equipment duration and add up, obtain the duration that K defect analysis variable is corresponding respectively;
The duration that K the defect analysis variable obtained described in cumulative is corresponding respectively, obtain total duration;
The duration that the described K obtained a defect analysis variable is corresponding respectively is all divided by with the total duration of described acquisition, obtains the probability that K defect analysis variable is corresponding respectively, and a described K probability is combined into vectorial P (0).
Wherein, the concrete steps of described step c comprise:
Obtain described K the total degree that defect analysis variable occurs respectively in described historical data;
Described K defect analysis variable is mapped between two, obtains K*K kind defect analysis variable transitions mode;
Is divided into M timeslice the described time period, sorts from small to large according to the time, determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair is answered in described every a part is as corresponding denominator, obtain the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, further a described K*K transition probability is combined into matrix P.
Wherein, described power equipment is transformer, described defect analysis variable comprise do not occur defect, leakage of oil, cooling system failure, instrument fault, operating mechanism exception and exterior mechanical damage.
The embodiment of the present invention further provides a kind of method predicting power equipments defect, and it realizes on N number of of a sort power equipment, and described method comprises:
S1, extract the historical data of N number of power equipment described in the time period, be met K defect classification of predetermined condition according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
S2, obtain described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine to be combined into matrix P by a described K*K transition probability further by the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively; Wherein, M is positive integer;
S3, obtain a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
Wherein, the concrete steps of described step S1 comprise:
Extract the historical data of N number of power equipment described in the time period, and determine the total degree that in described historical data, each defect occurs;
The total degree sequential from large to small that each defect is occurred, filter out the defect that a front K-1 total degree is large, and classification corresponding for a described K-1 defect and classification that defect do not occur are set to defect analysis variable further as K the defect classification satisfied condition.
Wherein, the concrete steps of described step S2 comprise:
Obtain described K the total degree that defect analysis variable occurs respectively in described historical data;
Described K defect analysis variable is mapped between two, obtains K*K kind defect analysis variable transitions mode;
Is divided into M timeslice the described time period, sorts from small to large according to the time, determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair is answered in described every a part is as corresponding denominator, obtain the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, further a described K*K transition probability is combined into matrix P.
Wherein, described method comprises further:
In described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
According to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Wherein, described in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, the concrete steps being combined into vectorial P (0) by a described K probability further comprise:
In described historical data, obtain the lasting time of origin of described N number of power equipment each defect analysis variable corresponding, under filtering out same defect analysis variable described N number of power equipment duration and add up, obtain the duration that K defect analysis variable is corresponding respectively;
The duration that K the defect analysis variable obtained described in cumulative is corresponding respectively, obtain total duration;
The duration that the described K obtained a defect analysis variable is corresponding respectively is all divided by with the total duration of described acquisition, obtains the probability that K defect analysis variable is corresponding respectively, and a described K probability is combined into vectorial P (0).
The embodiment of the present invention additionally provides a kind of system predicting power equipments defect, and it realizes on N number of of a sort power equipment, and described system comprises:
Determine defect analysis variable cell, for extracting the historical data of N number of power equipment described in the time period, K defect classification of predetermined condition is met according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Obtain probability unit, for in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
Obtain transition probability unit, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, matrix P is combined into further by a described K*K transition probability, wherein, M is positive integer,
New equipment prediction defective unit, for according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Wherein, described system also comprises:
Operational outfit prediction defective unit, for obtaining a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
The embodiment of the present invention further provides a kind of system predicting power equipments defect, and it realizes on N number of of a sort power equipment, and described system comprises:
Determine defect analysis variable cell, for extracting the historical data of N number of power equipment described in the time period, K defect classification of predetermined condition is met according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Obtain transition probability unit, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, matrix P is combined into further by a described K*K transition probability, wherein, M is positive integer,
Operational outfit prediction defective unit, for obtaining a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
Wherein, described system also comprises:
Obtain probability unit, for in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
New equipment prediction defective unit, for according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Implement the embodiment of the present invention, there is following beneficial effect:
In embodiments of the present invention, due to according to the historic defects information of similar power equipment and current operating situation, adopt Prediction of Markov algorithm, accurately predicting goes out power equipment (comprising does not come into operation and come into operation, and defect occurred) contingent defect, power equipment operation maintenance personnel can be helped to carry out emphasis tour and maintenance targetedly, reduce the labor capacity of power equipment operation maintenance personnel, improve power equipments defect analysis and effect is instructed to actual production work.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, the accompanying drawing obtaining other according to these accompanying drawings still belongs to category of the present invention.
The process flow diagram of the method for the prediction power equipments defect that Fig. 1 provides for the embodiment of the present invention;
The process flow diagram of the method for another prediction power equipments defect that Fig. 2 provides for the embodiment of the present invention;
The structural representation of the system of the prediction power equipments defect that Fig. 3 provides for the embodiment of the present invention;
The structural representation of the system of another prediction power equipments defect that Fig. 4 provides for the embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail.
As shown in Figure 1, the embodiment of the present invention provides a kind of method predicting power equipments defect, and it realizes on N number of of a sort power equipment, and described method comprises:
Step S101, extract the historical data of N number of power equipment described in the time period, be met K defect classification of predetermined condition according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Detailed process is, extracts the historical data of N number of power equipment in the time period, and determines the total degree that in historical data, each defect occurs;
The total degree sequential from large to small that each defect is occurred, filter out the defect that a front K-1 total degree is large, and classification corresponding for K-1 defect and classification that defect do not occur are set to defect analysis variable further as K the defect classification satisfied condition.
As an example, power equipment is transformer, its main cause that defect occurs includes but not limited to leakage of oil, cooling system failure, instrument fault, operating mechanism exception, exterior mechanical damage etc., therefore, when extracting the service data in multiple transformer 1 year, this service data comprises the defective data that there is above-mentioned defect.Count the total degree that in all transformers in the historical data, all defect occurs respectively, then all defect is sorted according to total degree is descending, filtering out and coming several, foremost defect is that leakage of oil, cooling system failure, instrument fault, operating mechanism exception and exterior mechanical damage, and using the defect classification filtered out and there is not defect classification as corresponding defect analysis variable, the order of defect analysis variable-definition for there is not defect, go out leakage of oil, cooling system failure, instrument fault, operating mechanism exception and exterior mechanical damage.
Step S102, in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
Detailed process is, in the historical data, obtain the lasting time of origin of N number of power equipment each defect analysis variable corresponding, filter out the duration of N number of power equipment under same defect analysis variable and add up, obtain the duration of K defect analysis variable correspondence respectively;
The duration that cumulative K the defect analysis variable obtained is corresponding respectively, obtain total duration;
Duration corresponding respectively for the K obtained a defect analysis variable is all divided by with the total duration obtained, obtains the probability that K defect analysis variable is corresponding respectively, and K probability is combined into vectorial P (0).
In embodiments of the present invention, K probability can be expressed as p
1(0), p
2(0) ... p
k(0), therefore vectorial P (0)=(p
1(0), p
2(0) ... p
k(0)).
For aforementioned transformer, p
1(0) probability that defect does not occur is represented, p
2(0) ... p
6(0) probability of the defects such as leakage of oil, cooling system failure, instrument fault, operating mechanism exception and exterior mechanical damage is represented respectively.The step calculating the probability of defect analysis variable is following (with p
1(0) be example):
There is not the duration of the duration of defect, the duration of cumulative all Leakage in Transformer oil, duration of cumulative all transformer cooling system accident defects, the duration of cumulative all transformer instrument faults, cumulative all transformer operating mechanisms exception in cumulative all transformers, till the result of the duration that all transformer exterior mechanicals that obtains adding up out damage;
The duration that above-mentioned six defect analysis variablees add up out is totally added again, thus obtains total duration;
All transformers be there is not the duration of defect as molecule, total duration is calculated as denominator, obtains p
1(0).
In like manner, p can be obtained according to said method
2(0) ... p
6, thus further form vectorial P (0)=(p (0)
1(0), p
2(0) ... p
6(0)).
Step S103, obtain described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine to be combined into matrix P by a described K*K transition probability further by the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively; Wherein, M is positive integer;
Detailed process is, obtains the total degree that K defect analysis variable occurs respectively in the historical data;
K defect analysis variable is mapped between two, obtains K*K kind defect analysis variable transitions mode;
M timeslice will be divided into the time period, sort from small to large according to the time, determine that between adjacent time sheet, N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair in every a part is answered is as corresponding denominator, obtain the transition probability that K*K kind defect analysis variable transitions mode is corresponding respectively, further K*K transition probability is combined into matrix P.
It should be noted that the demand in order to calculate, K defect analysis variable maps between two, and it comprises the mutual mapping of same defect analysis variable, and the leakage of oil variable mappings as transformer is identical leakage of oil variable, the matrix therefore formed.
Should be noted that, M the timeslice be divided into time period is little as far as possible, adjacent time sheet (a upper timeslice is to future time sheet) is occurred, and the number of times of defect class transitions meets for once, as above there is leakage of oil in a timeslice A transformer, but only there will be primary cooling system accident defect at future time sheet A transformer, instead of once above cooling system failure defect.
In embodiments of the present invention, the transition probability that K*K kind defect analysis variable transitions mode is corresponding respectively can be expressed as (p
11, p
12... p
1K; p
21, p
22... p
2K; ... p
k1, p
k2... p
kK), thus form matrix
Wherein, p
nnthe defect classification being expressed as the defect analysis variable of the same power equipment of adjacent time sheet corresponding is identical, n=1, and 2 ... K.
For aforementioned transformer, 1 year was divided according to 12 months, obtain 12 timeslices; p
11represent that the equipment deficiency state between upper and lower two months is all the transition probability that defect does not occur, p
12represent that the transition probability that defect and next timeslice there occurs leakage of oil defect does not occur a timeslice, therefore by that analogy, the transition probability that the defect analysis variable transitions mode of transformer is corresponding respectively can be expressed as (p
11, p
12... p
16; p
21, p
22... p
26; ... p
61, p
62... p
66).The step calculating the transition probability of defect analysis variable is following (there is not defect (p
11, p
12... p
16) be example):
Obtain the total degree that six defect analysis variablees occur respectively in the historical data, certainly now for (p
11, p
12... p
16), only need to determine that the total degree of defect appearance does not occur all transformers in the historical data;
There is not defect will map out six kinds of conversion regimes and be: defect does not occur and maps and defect does not occur, defect does not occur map leakage of oil, defect does not occur map cooling system failure, do not occur that defect maps instrument fault, that defect map operation mechanism does not occur is abnormal and defect does not occur map exterior mechanical and damage;
From sequence in one to Dec, determine that between adjacent time sheet, all transformers correspond to the number of times of above-mentioned six kinds of defect analysis variable transitions modes;
Using the number of times of above-mentioned six kinds of defect analysis variable transitions modes successively all as molecule, in historical data there is not the total degree of defect appearance as denominator in all transformers, obtains (p
11, p
12... p
16).
In like manner, (p can be obtained according to said method
21, p
22... p
26; ... p
61, p
62... p
66), thus form matrix further
Step S104, according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
By predict new power equipment come into operation before defect power equipment maintainer can be made to carry out emphasis tour and maintenance targetedly, reduce the labor capacity of power equipment operation maintenance personnel, improve power equipments defect analysis and effect is instructed to actual production work.
For aforementioned transformer,
The maximal value obtained in P (1) corresponds to cooling system failure defect, using the defect of cooling system failure defect as the transformer of prediction.
Predict in the embodiment of the present invention that transition matrix that the method for power equipments defect produces also has the failure prediction of the power equipment come into operation and effect is instructed to actual production work, and do not need the calculated amount increasing data to carry out failure prediction to current power equipment under certain condition, therefore described method comprises further:
Obtain a defect having come into operation the current generation of power equipment, and find in matrix P corresponding to the maximal value in K kind conversion regime according to the classification of this current defect, and using defect classification corresponding for the maximal value that finds next prediction defect as the power equipment of current generation defect.
As shown in Figure 2, embodiments provide the method for another kind of prediction power equipments defect, it realizes on N number of of a sort power equipment, and described method comprises:
Step S201, extract the historical data of N number of power equipment described in the time period, be met K defect classification of predetermined condition according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Detailed process is, extracts the historical data of N number of power equipment in the time period, and determines the total degree that in historical data, each defect occurs;
The total degree sequential from large to small that each defect is occurred, filter out the defect that a front K-1 total degree is large, and classification corresponding for K-1 defect and classification that defect do not occur are set to defect analysis variable further as K the defect classification satisfied condition.
Step S202, obtain described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine to be combined into matrix P by a described K*K transition probability further by the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively; Wherein, M is positive integer;
Detailed process is, obtains the total degree that K defect analysis variable occurs respectively in the historical data;
K defect analysis variable is mapped between two, obtains K*K kind defect analysis variable transitions mode;
M timeslice will be divided into the time period, sort from small to large according to the time, determine that between adjacent time sheet, N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair in every a part is answered is as corresponding denominator, obtain the transition probability that K*K kind defect analysis variable transitions mode is corresponding respectively, further K*K transition probability is combined into matrix P.
It should be noted that the demand in order to calculate, K defect analysis variable maps between two, and it comprises the mutual mapping of same defect analysis variable, and the leakage of oil variable mappings as transformer is identical leakage of oil variable, the matrix therefore formed.
Should be noted that, M the timeslice be divided into time period is little as far as possible, adjacent time sheet (a upper timeslice is to future time sheet) is occurred, and the number of times of defect class transitions meets for once, as above there is leakage of oil in a timeslice A transformer, but only there will be primary cooling system accident defect at future time sheet A transformer, instead of once above cooling system failure defect.
In embodiments of the present invention, the transition probability that K*K kind defect analysis variable transitions mode is corresponding respectively can be expressed as (p
11, p
12... p
1K; p
21, p
22... p
2K; ... p
k1, p
k2... p
kK), thus form matrix
Wherein, p
nnthe defect classification being expressed as the defect analysis variable of the same power equipment of adjacent time sheet corresponding is identical, n=1, and 2 ... K.
Step S203, obtain a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
By prediction come into operation power equipment come into operation before defect power equipment maintainer can be made to carry out emphasis tour and maintenance targetedly, reduce the labor capacity of power equipment operation maintenance personnel, improve power equipments defect analysis and effect is instructed to actual production work.
Predict in the embodiment of the present invention that new power equipment defect before being taken into use also has and instruct effect to actual production work, therefore described method comprises further:
Step S21, in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
Detailed process is, in the historical data, obtain the lasting time of origin of N number of power equipment each defect analysis variable corresponding, filter out the duration of N number of power equipment under same defect analysis variable and add up, obtain the duration of K defect analysis variable correspondence respectively;
The duration that cumulative K the defect analysis variable obtained is corresponding respectively, obtain total duration;
Duration corresponding respectively for the K obtained a defect analysis variable is all divided by with the total duration obtained, obtains the probability that K defect analysis variable is corresponding respectively, and K probability is combined into vectorial P (0).
In embodiments of the present invention, K probability can be expressed as p
1(0), p
2(0) ... p
k(0), therefore vectorial P (0)=(p
1(0), p
2(0) ... p
k(0)).
Step S22, according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Wherein, described in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, the concrete steps being combined into vectorial P (0) by a described K probability further comprise:
As shown in Figure 3, the embodiment of the present invention additionally provides a kind of system predicting power equipments defect, and it realizes on N number of of a sort power equipment, and described system comprises:
Determine defect analysis variable cell 110, for extracting the historical data of N number of power equipment described in the time period, K defect classification of predetermined condition is met according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Obtain probability unit 120, for in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
Obtain transition probability unit 130, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, matrix P is combined into further by a described K*K transition probability, wherein, M is positive integer,
New equipment prediction defective unit 140, for according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Wherein, system also comprises:
Operational outfit prediction defective unit 150, for the defect of the current generation of power equipment of having come into operation when acquisition one, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
Wherein, obtain probability unit 120 to comprise:
Obtain duration module 1201, for in described historical data, obtain the lasting time of origin of described N number of power equipment each defect analysis variable corresponding, under filtering out same defect analysis variable described N number of power equipment duration and add up, obtain the duration that K defect analysis variable is corresponding respectively;
Obtain total duration module 1202, the duration that K the defect analysis variable for obtaining described in cumulative is corresponding respectively, acquisition total duration;
Determine probability module 1203, all be divided by with the total duration of described acquisition for the duration that the described K obtained a defect analysis variable is corresponding respectively, obtain the probability that K defect analysis variable is corresponding respectively, and a described K probability is combined into vectorial P (0).
Wherein, obtain transition probability unit 130 to comprise:
Obtain defect total degree module 1301, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data;
Defect mapping block 1302, for mapping between two described K defect analysis variable, obtains K*K kind defect analysis variable transitions mode;
Obtain defect conversion times module 1303, for the described time period is divided into M timeslice, sort from small to large according to the time, determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Determine transition probability module 1304, for using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair is answered in described every a part is as corresponding denominator, obtain the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, further a described K*K transition probability is combined into matrix P.
As shown in Figure 4, the embodiment of the present invention additionally provides the system of another kind of prediction power equipments defect, and it realizes on N number of of a sort power equipment, and described system comprises:
Determine defect analysis variable cell 210, for extracting the historical data of N number of power equipment described in the time period, K defect classification of predetermined condition is met according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Obtain transition probability unit 220, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, matrix P is combined into further by a described K*K transition probability, wherein, M is positive integer,
Operational outfit prediction defective unit 230, for obtaining a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
Wherein, described acquisition transition probability unit 220 comprises:
Obtain defect total degree module 2201, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data;
Defect mapping block 2202, for mapping between two described K defect analysis variable, obtains K*K kind defect analysis variable transitions mode;
Obtain defect conversion times module 2203, for the described time period is divided into M timeslice, sort from small to large according to the time, determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Determine transition probability module 2204, for using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair is answered in described every a part is as corresponding denominator, obtain the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, further a described K*K transition probability is combined into matrix P.
Wherein, described system also comprises:
Obtain probability unit 240, for in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
New equipment prediction defective unit 250, for according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Wherein, described acquisition probability unit 240 comprises:
Obtain duration module 2401, for in described historical data, obtain the lasting time of origin of described N number of power equipment each defect analysis variable corresponding, under filtering out same defect analysis variable described N number of power equipment duration and add up, obtain the duration that K defect analysis variable is corresponding respectively;
Obtain total duration module 2402, the duration that K the defect analysis variable for obtaining described in cumulative is corresponding respectively, acquisition total duration;
Determine probability module 2403, all be divided by with the total duration of described acquisition for the duration that the described K obtained a defect analysis variable is corresponding respectively, obtain the probability that K defect analysis variable is corresponding respectively, and a described K probability is combined into vectorial P (0).
Implement the embodiment of the present invention, there is following beneficial effect:
In embodiments of the present invention, due to according to the historic defects information of similar power equipment and current operating situation, adopt Prediction of Markov algorithm, accurately predicting goes out power equipment (comprising does not come into operation and come into operation, and defect occurred) contingent defect, power equipment operation maintenance personnel can be helped to carry out emphasis tour and maintenance targetedly, reduce the labor capacity of power equipment operation maintenance personnel, improve power equipments defect analysis and effect is instructed to actual production work.
It should be noted that in said system embodiment, each included system unit is carry out dividing according to function logic, but is not limited to above-mentioned division, as long as can realize corresponding function; In addition, the concrete title of each functional unit, also just for the ease of mutual differentiation, is not limited to protection scope of the present invention.
One of ordinary skill in the art will appreciate that all or part of step realized in above-described embodiment method is that the hardware that can carry out instruction relevant by program has come, described program can be stored in a computer read/write memory medium, described storage medium, as ROM/RAM, disk, CD etc.
Above disclosedly be only present pre-ferred embodiments, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (15)
1. predict a method for power equipments defect, it is characterized in that, it realizes on N number of of a sort power equipment, and described method comprises:
A, extract the historical data of N number of power equipment described in the time period, be met K defect classification of predetermined condition according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
B, in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
C, obtain described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine to be combined into matrix P by a described K*K transition probability further by the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively; Wherein, M is positive integer;
D, according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
2. the method for claim 1, is characterized in that, described method comprises further:
Obtain a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
3. the method for claim 1, is characterized in that, the concrete steps of described step a comprise:
Extract the historical data of N number of power equipment described in the time period, and determine the total degree that in described historical data, each defect occurs;
The total degree sequential from large to small that each defect is occurred, filter out the defect that a front K-1 total degree is large, and classification corresponding for a described K-1 defect and classification that defect do not occur are set to defect analysis variable further as K the defect classification satisfied condition.
4. the method for claim 1, is characterized in that, the concrete steps of described step b comprise:
In described historical data, obtain the lasting time of origin of described N number of power equipment each defect analysis variable corresponding, under filtering out same defect analysis variable described N number of power equipment duration and add up, obtain the duration that K defect analysis variable is corresponding respectively;
The duration that K the defect analysis variable obtained described in cumulative is corresponding respectively, obtain total duration;
The duration that the described K obtained a defect analysis variable is corresponding respectively is all divided by with the total duration of described acquisition, obtains the probability that K defect analysis variable is corresponding respectively, and a described K probability is combined into vectorial P (0).
5. the method for claim 1, is characterized in that, the concrete steps of described step c comprise:
Obtain described K the total degree that defect analysis variable occurs respectively in described historical data;
Described K defect analysis variable is mapped between two, obtains K*K kind defect analysis variable transitions mode;
Is divided into M timeslice the described time period, sorts from small to large according to the time, determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair is answered in described every a part is as corresponding denominator, obtain the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, further a described K*K transition probability is combined into matrix P.
6. the method according to any one of claim 1 to 5, is characterized in that, described power equipment is transformer, described defect analysis variable comprise do not occur defect, leakage of oil, cooling system failure, instrument fault, operating mechanism exception and exterior mechanical damage.
7. predict a method for power equipments defect, it is characterized in that, it realizes on N number of of a sort power equipment, and described method comprises:
S1, extract the historical data of N number of power equipment described in the time period, be met K defect classification of predetermined condition according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
S2, obtain described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine to be combined into matrix P by a described K*K transition probability further by the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively; Wherein, M is positive integer;
S3, obtain a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
8. method as claimed in claim 7, it is characterized in that, the concrete steps of described step S1 comprise:
Extract the historical data of N number of power equipment described in the time period, and determine the total degree that in described historical data, each defect occurs;
The total degree sequential from large to small that each defect is occurred, filter out the defect that a front K-1 total degree is large, and classification corresponding for a described K-1 defect and classification that defect do not occur are set to defect analysis variable further as K the defect classification satisfied condition.
9. method as claimed in claim 7, it is characterized in that, the concrete steps of described step S2 comprise:
Obtain described K the total degree that defect analysis variable occurs respectively in described historical data;
Described K defect analysis variable is mapped between two, obtains K*K kind defect analysis variable transitions mode;
Is divided into M timeslice the described time period, sorts from small to large according to the time, determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode;
Using the number of times of each defect analysis variable transitions mode all as molecule, and determine the defect analysis variable that in every a part, main mapping pair is answered, and the total degree filtering out the defect analysis occurrences that main mapping pair is answered in described every a part is as corresponding denominator, obtain the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, further a described K*K transition probability is combined into matrix P.
10. method as claimed in claim 7, it is characterized in that, described method comprises further:
In described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
According to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
11. methods as claimed in claim 10, it is characterized in that, described in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, the concrete steps being combined into vectorial P (0) by a described K probability further comprise:
In described historical data, obtain the lasting time of origin of described N number of power equipment each defect analysis variable corresponding, under filtering out same defect analysis variable described N number of power equipment duration and add up, obtain the duration that K defect analysis variable is corresponding respectively;
The duration that K the defect analysis variable obtained described in cumulative is corresponding respectively, obtain total duration;
The duration that the described K obtained a defect analysis variable is corresponding respectively is all divided by with the total duration of described acquisition, obtains the probability that K defect analysis variable is corresponding respectively, and a described K probability is combined into vectorial P (0).
12. 1 kinds of systems predicting power equipments defect, it is characterized in that, it realizes on N number of of a sort power equipment, and described system comprises:
Determine defect analysis variable cell, for extracting the historical data of N number of power equipment described in the time period, K defect classification of predetermined condition is met according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Obtain probability unit, for in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
Obtain transition probability unit, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, matrix P is combined into further by a described K*K transition probability, wherein, M is positive integer,
New equipment prediction defective unit, for according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
13. systems as claimed in claim 12, it is characterized in that, described system also comprises:
Operational outfit prediction defective unit, for obtaining a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
14. 1 kinds of systems predicting power equipments defect, it is characterized in that, it realizes on N number of of a sort power equipment, and described system comprises:
Determine defect analysis variable cell, for extracting the historical data of N number of power equipment described in the time period, K defect classification of predetermined condition is met according to described historical data statistics, and using the described K obtained a defect classification all as defect analysis variable; Wherein, K, N are positive integer;
Obtain transition probability unit, for obtaining described K the total degree that defect analysis variable occurs respectively in described historical data, and the described time period is divided into M timeslice, sequentially determine that between adjacent time sheet, described N number of power equipment corresponds to the number of times of K*K kind defect analysis variable transitions mode, and according to the total degree of K defect analysis occurrences of described acquisition and the number of times of K*K kind defect analysis variable transitions mode, determine the transition probability that described K*K kind defect analysis variable transitions mode is corresponding respectively, matrix P is combined into further by a described K*K transition probability, wherein, M is positive integer,
Operational outfit prediction defective unit, for obtaining a defect having come into operation the current generation of power equipment, and find corresponding to the maximal value in K kind conversion regime in described matrix P according to the classification of described current defect, and using defect classification corresponding for the described maximal value found next prediction defect as the power equipment of described current generation defect.
15. systems as claimed in claim 14, it is characterized in that, described system also comprises:
Obtain probability unit, for in described historical data, all add up out the duration of described N number of power equipment under same defect analysis variable for each defect analysis variable, and the duration of cumulative K described N number of power equipment under same defect analysis variable and obtain total duration, and according to the described total duration that adds up out and duration corresponding to described each the defect analysis variable added up out, determine the probability of each defect state variable, be combined into vectorial P (0) by a described K probability further;
New equipment prediction defective unit, for according to formula P (1)=P (0) * P, determine the maximal value in P (1), and using defect classification corresponding for the described maximal value determined as the prediction defect before new power equipment comes into operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510009618.9A CN104573866B (en) | 2015-01-08 | 2015-01-08 | A kind of method and system for predicting power equipments defect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510009618.9A CN104573866B (en) | 2015-01-08 | 2015-01-08 | A kind of method and system for predicting power equipments defect |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104573866A true CN104573866A (en) | 2015-04-29 |
| CN104573866B CN104573866B (en) | 2017-12-08 |
Family
ID=53089881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510009618.9A Active CN104573866B (en) | 2015-01-08 | 2015-01-08 | A kind of method and system for predicting power equipments defect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104573866B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303296A (en) * | 2015-09-29 | 2016-02-03 | 国网浙江省电力公司电力科学研究院 | Electric power equipment full-life state evaluation method |
| CN105740975A (en) * | 2016-01-26 | 2016-07-06 | 云南电网有限责任公司电力科学研究院 | Data association relationship-based equipment defect assessment and prediction method |
| CN106845728A (en) * | 2017-02-14 | 2017-06-13 | 北京邮电大学 | The Forecasting Methodology and device of a kind of power transformer defect |
| CN109558979A (en) * | 2018-11-29 | 2019-04-02 | 广东电网有限责任公司 | Power equipments defect prediction technique and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011041741A2 (en) * | 2009-10-01 | 2011-04-07 | Edsa Micro Corporation | Microgrid model based automated real time simulation for market based electric power system optimization |
| CN102928720A (en) * | 2012-11-07 | 2013-02-13 | 广东电网公司 | Defect rate detecting method of oil immersed type main transformer |
| CN103177186A (en) * | 2013-03-21 | 2013-06-26 | 国家电网公司 | Electric return circuit fault probability forecasting method |
| CN103714401A (en) * | 2014-01-21 | 2014-04-09 | 国家电网公司 | Method for predicting distribution and transformation fault frequency of electric network |
| US20140163936A1 (en) * | 2012-12-11 | 2014-06-12 | International Business Machines Corporation | System and method for maintenance planning and failure prediction for equipment subject to periodic failure risk |
-
2015
- 2015-01-08 CN CN201510009618.9A patent/CN104573866B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011041741A2 (en) * | 2009-10-01 | 2011-04-07 | Edsa Micro Corporation | Microgrid model based automated real time simulation for market based electric power system optimization |
| CN102928720A (en) * | 2012-11-07 | 2013-02-13 | 广东电网公司 | Defect rate detecting method of oil immersed type main transformer |
| US20140163936A1 (en) * | 2012-12-11 | 2014-06-12 | International Business Machines Corporation | System and method for maintenance planning and failure prediction for equipment subject to periodic failure risk |
| CN103177186A (en) * | 2013-03-21 | 2013-06-26 | 国家电网公司 | Electric return circuit fault probability forecasting method |
| CN103714401A (en) * | 2014-01-21 | 2014-04-09 | 国家电网公司 | Method for predicting distribution and transformation fault frequency of electric network |
Non-Patent Citations (1)
| Title |
|---|
| 吕启深 等: "《基于贝叶斯网络和粗糙集约简的变压器故障诊断 》", 《中国电力》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303296A (en) * | 2015-09-29 | 2016-02-03 | 国网浙江省电力公司电力科学研究院 | Electric power equipment full-life state evaluation method |
| CN105303296B (en) * | 2015-09-29 | 2019-04-23 | 国网浙江省电力公司电力科学研究院 | A kind of power equipment life-cycle method for evaluating state |
| CN105740975A (en) * | 2016-01-26 | 2016-07-06 | 云南电网有限责任公司电力科学研究院 | Data association relationship-based equipment defect assessment and prediction method |
| CN105740975B (en) * | 2016-01-26 | 2019-08-27 | 云南电网有限责任公司电力科学研究院 | A kind of equipment deficiency assessment and prediction technique based on data correlation relation |
| CN106845728A (en) * | 2017-02-14 | 2017-06-13 | 北京邮电大学 | The Forecasting Methodology and device of a kind of power transformer defect |
| CN106845728B (en) * | 2017-02-14 | 2020-11-06 | 北京邮电大学 | Method and device for predicting defects of power transformer |
| CN109558979A (en) * | 2018-11-29 | 2019-04-02 | 广东电网有限责任公司 | Power equipments defect prediction technique and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104573866B (en) | 2017-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mohsenian-Rad et al. | Distribution synchrophasors: Pairing big data with analytics to create actionable information | |
| CN106384210B (en) | A kind of power transmission and transforming equipment maintenance prioritization method based on maintenance risk income | |
| CN103679293A (en) | Intelligent substation warning and aid decision making system | |
| CN110322135A (en) | A kind of method for real-time monitoring and system of grid equipment safe operation state | |
| CN104573866A (en) | Method and system for predicting defects of electrical equipment | |
| CN105184084A (en) | Fault type predicting method and system for automatic electric power measurement terminals | |
| CN103630768A (en) | Method for diagnosing transformer fault in transformer station | |
| CN113191687B (en) | Elastic power distribution network panoramic information visualization method and system | |
| CN102663535A (en) | Method and device for managing both technical performance and financial information of transformers | |
| CN107256449A (en) | A kind of relay protection device of intelligent substation state evaluation and appraisal procedure | |
| CN105425768A (en) | Electric power secondary equipment monitoring device and method | |
| CN105467971A (en) | Electric power secondary equipment monitoring system and method | |
| CN110646685B (en) | Comprehensive evaluation method for state of switch cabinet | |
| CN106295240A (en) | A kind of Condition Assessment for Power Transformer method based on fuzzy mathematics | |
| CN103559580A (en) | Power distribution network analysis system and method | |
| CN104506137A (en) | Equipment fault diagnosis method and apparatus | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN112763963A (en) | System and method for carrying out online monitoring on mutual inductor based on deep network | |
| CN103530708A (en) | Power transmission and distribution equipment hidden danger troubleshooting information management and decision support system | |
| CN104881754A (en) | Currency type quantitative risk transformer life-cycle management auxiliary decision system | |
| CN114252716A (en) | Power grid fault diagnosis method and device and storage medium | |
| CN105096217A (en) | Communication state prediction method and system of electric power measurement automation terminal | |
| CN107368979B (en) | Method and device for predicting disturbance event of weather-sensitive regional power distribution network | |
| CN117614137A (en) | Power distribution network optimization system based on multi-source data fusion | |
| CN105184657B (en) | Power supply risk assessment method and system for power system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee after: Shenzhen Power Supply Co.,Ltd. Country or region after: China Patentee after: China Southern Power Grid Digital Platform Technology (Guangdong) Co.,Ltd. Address before: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee before: Shenzhen Power Supply Co.,Ltd. Country or region before: China Patentee before: SHENZHEN COMTOP INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240315 Address after: 518101, 3rd Floor, Building 40, Baotian Industrial Zone, Chentian Community, Xixiang Street, Bao'an District, Shenzhen City, Guangdong Province Patentee after: China Southern Power Grid Digital Platform Technology (Guangdong) Co.,Ltd. Country or region after: China Address before: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee before: Shenzhen Power Supply Co.,Ltd. Country or region before: China Patentee before: China Southern Power Grid Digital Platform Technology (Guangdong) Co.,Ltd. |
|
| TR01 | Transfer of patent right |