CN111415093A - Distribution transformer fault early warning method based on multi-factor and dynamic weight - Google Patents

Distribution transformer fault early warning method based on multi-factor and dynamic weight Download PDF

Info

Publication number
CN111415093A
CN111415093A CN202010210326.2A CN202010210326A CN111415093A CN 111415093 A CN111415093 A CN 111415093A CN 202010210326 A CN202010210326 A CN 202010210326A CN 111415093 A CN111415093 A CN 111415093A
Authority
CN
China
Prior art keywords
factor
fault
distribution transformer
data
factors
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
Application number
CN202010210326.2A
Other languages
Chinese (zh)
Other versions
CN111415093B (en
Inventor
魏清
章宗源
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.)
Jiangsu Zhongkun Data Technology Co ltd
Original Assignee
Jiangsu Zhongkun Data Technology Co ltd
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 Jiangsu Zhongkun Data Technology Co ltd filed Critical Jiangsu Zhongkun Data Technology Co ltd
Priority to CN202010210326.2A priority Critical patent/CN111415093B/en
Publication of CN111415093A publication Critical patent/CN111415093A/en
Application granted granted Critical
Publication of CN111415093B publication Critical patent/CN111415093B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention discloses a distribution transformer fault early warning method based on multiple factors and dynamic weight, which is characterized by comprising the following steps of 1: collecting historical fault data and normal data of the distribution transformer, and step 2: processing historical fault data and normal data, and 3: carrying out factor analysis of distribution transformer fault early warning, and step 4: establishing a functional relation between each factor and the fault rate of the distribution transformer, and step 5: obtaining the fault probability P of the distribution transformer according to the corresponding fault probability function and weight of each factor, and 6: and substituting the historical fault data and the normal data into the verification fault probability. The effect of realizing fault early warning on the distribution transformer and reducing the influence on the early warning when factors are missing or uncertain is achieved; because the functional relation between each factor and the distribution transformer fault is mutually independent, the addition and the deletion of the distribution transformer fault early warning system factor are convenient.

Description

Distribution transformer fault early warning method based on multi-factor and dynamic weight
Technical Field
The invention relates to the field of distribution transformer fault early warning, in particular to a distribution transformer fault early warning method based on multiple factors and dynamic weight.
Background
The distribution network is the important pivot between electric power system and the user, and distribution transformer has the effect of lifting at all in the distribution network, if can be through the excavation to distribution transformer operation data and external influence factor, realize the early warning to distribution transformer trouble risk, with the preventive maintenance of better realization to the distribution network, ensure the normal operating of distribution network. In the actual distribution transformer fault early warning, the problems that how to find factors really related to the early warning result from mass data and when part of influencing factors are missing or uncertain, the fault early warning is difficult to continue and a correct result is obtained are faced. Most of the existing distribution transformer fault early warning is performed by empirical fault analysis and fault reason theoretical analysis of operation and maintenance personnel, and the fault tolerance is still insufficient for multi-latitude fusion of the fault reasons of the distribution transformer and guarantee of the fault tolerance when characteristic factors are lost. The determination of the characteristic factor weight is generally evaluated according to experience or organization experts, although the opinions of a plurality of experts are concentrated, the rationality of the weight is difficult to keep and the actual operation difficulty is high by directly giving each index weight through scoring.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a distribution transformer fault early warning method based on multiple factors and dynamic weight, and solves the problems that most distribution transformer fault early warnings stay in empirical fault analysis of operation and maintenance personnel, the multiple latitudes of the distribution transformer fault reasons are fused, the characteristic factor weight cannot objectively reflect the actual situation, and the fault tolerance is still ensured to be insufficient when the characteristic factor is lost.
In order to solve the technical problems, the invention provides a fault early warning method of a distribution transformer based on multiple factors and dynamic weight, which is characterized in that the operation data and external influence factors of the distribution transformer are comprehensively considered; determining the weight of the factors by analyzing the correlation between the fault factors and the faults in the historical fault data; discarding missing or uncertain factors, and recalculating the weights of the other factors by using a sequence relation method so as to enable the fault early warning to be continuously carried out; the method comprises the following steps:
step 1: collecting historical fault data and normal data of the distribution transformer, wherein the historical fault data refers to data in a specified time period before the distribution transformer breaks down, and the normal data refers to data of the distribution transformer in a normal operation time period; presetting a fault early warning factor of a distribution transformer;
step 2: processing historical fault data and normal data, wherein the processing comprises data cleaning, data attribute transformation and abnormal sample elimination;
the data cleaning refers to finding and correcting recognizable errors in data, including checking data consistency and processing invalid values and missing values;
the data attribute transformation is to transform time series data, the time series data comprises current, voltage and power, the unbalance degree of the current and the voltage in a time period is calculated, and the load rate is calculated by using the power:
voltage unbalance degree:
Figure BDA0002422570830000021
in the formula of Umax、UminRespectively representing the maximum value and the minimum value of the three-phase voltage;
current unbalance degree:
Figure BDA0002422570830000022
in the formula Imax、IminRespectively representing the maximum value and the minimum value of the three-phase current;
load factor η:
Figure BDA0002422570830000023
in the formula PTIs the actual capacity, is the power data that can be acquired in real time; pRThe rated capacity of the transformer;
and step 3: analyzing the influence degree of different factors on the fault of the distribution transformer, thereby determining the selection of the factors and the corresponding weight, and setting the weight of the fault early warning factor of the distribution transformer as wkWherein k is a positive integer, wkWeight representing the k-th factor；
And 4, step 4: establishing a functional relation between each factor and the fault rate of the distribution transformer, wherein the functions are independent; let the factor be Al，A2，…，AnThen the corresponding function is y1，y2，…，yn；
And 5: obtaining the fault probability P of the distribution transformer according to the corresponding fault probability function and weight of each factor,
Figure BDA0002422570830000024
step 6: and (4) substituting the historical fault data and the normal data into the verification fault probability, and if the result has a problem, adjusting the functional relation between the weight value in the step 3 and each factor and the fault probability in the step 4.
In the step 1, the factors of the distribution transformer fault early warning include current, voltage, power, temperature, rainfall, wind speed, humidity, operation age and thunderstorm.
In the step 3, the weight of the fault factor of the distribution transformer is determined by using a sequence relation analysis method, and the calculation steps are as follows:
s 1: determining an order relation, and sequencing importance of the factors, wherein the more important the factors are, the more advanced the order relation is, specifically: for the set of factors Al，A2，…，An}，AkThe k factor in the factor set is shown, the most important factor is selected first and is marked as A1(ii) a Selecting the most important factor from the rest factors and marking the factor as A2(ii) a By analogy, the last factor is marked as AnDetermining the order relation according to the magnitude of the correlation between each factor in the historical fault data and the fault rate;
and (3) calculating the correlation between each factor in the historical fault data and the fault rate by adopting a Pearson correlation analysis method:
Figure BDA0002422570830000031
x represents a dimension influence factor, Y is the fault rate of the distribution transformer, the correlation degree between indexes is determined according to the magnitude of the correlation coefficient, the indexes with the correlation lower than a threshold value are removed through sorting;
s 2: giving out the ratio judgment of the relative importance degree among the factors; factor Ak-1And AkThe ratio of the importance levels of (a) to (b) is judged as:
Figure BDA0002422570830000032
in the formula: w is akRepresenting the ranking weight, r, of the k-th factorkIs a ratio of the degrees of importance; according to the correlation between different factors and fault rate and referring to rkAssignment reference table decision rkThe value of (A) is as follows:
rkassignment reference table
Figure BDA0002422570830000033
s 3: calculating the ranking weight of each factor:
Figure BDA0002422570830000034
wk-1＝rkwk，(k＝2,3,...,n-1,n)
Figure BDA0002422570830000035
wk(k 1, 2.., n-1, n) is a factor al，A2，…，AnThe corresponding weight.
In the step 4, through interpolation least square fitting, the temperature and the fault probability present a quadratic function relationship:
y＝0.001322x2-0.04628x+0.405；
the operating life and the fault rate of the distribution transformer accord with a Weibull distribution function, and the operating life is divided into three stages: less than 3 years, between 3-25 years, more than 25 years, the following functional relationships are established:
Figure BDA0002422570830000041
the relationship between the voltage unbalance, the current unbalance and the load rate and the fault of the distribution transformer is analyzed by adopting a random gradient descent model.
In the step 5, if a certain factor is invalid or missing, the factor is discarded, the weight of the influence of the remaining factor on the distribution transformer is recalculated by using the sequence relation method in the step 3, and the failure probability of the distribution transformer is determined by using the remaining factor when the sum of the weights of the invalid and missing factors does not exceed a specified threshold.
In the step 5, under the condition that the weight sum of the invalid and missing factors does not exceed the threshold value of 0.75, the residual factors are continuously utilized to judge the fault probability of the distribution transformer.
The invention achieves the following beneficial effects:
(1) the invention obtains the weight of each factor to the fault by analyzing the influence condition of the distribution transformer fault influence factor to the transformer fault, establishes the functional relation between each influence factor and the distribution transformer fault, abandons the factor when the factor is missing or uncertain, readjusts the weight of other factors, realizes the fault early warning of the distribution transformer, and reduces the influence of the missing factor or uncertain on the early warning;
(2) because the functional relation between each factor and the distribution transformer fault is mutually independent, the addition and the deletion of the distribution transformer fault early warning system factor are convenient.
Drawings
FIG. 1 is a schematic flow diagram of a method of an exemplary embodiment of the present invention;
fig. 2 is a flow chart of weighting based on order relationships in an exemplary embodiment of the invention.
Detailed Description
The invention will be further described with reference to the drawings and the exemplary embodiments:
as shown in fig. 1, a method for early warning a fault of a distribution transformer based on multiple factors and dynamic weights includes the following steps: step 1: collecting historical fault data and normal data of the distribution transformer, wherein the historical fault data refers to data in a specified time period before the distribution transformer breaks down, and the normal data refers to data of the distribution transformer in a normal operation time period; relevant factors for presetting distribution transformer fault early warning include current, voltage, power, temperature, rainfall, wind speed, humidity, operation age and thunderstorm.
Step 2: processing historical fault data and normal data, wherein the processing comprises data cleaning, data attribute transformation and abnormal sample elimination;
the data cleaning refers to finding and correcting recognizable errors in data, including checking data consistency and processing invalid values and missing values;
voltage operating data as shown in the table, there is data missing from line 172 to line 174, for which case these 3 lines of data will be automatically detected and rejected;
in the following table, lines 482, 485, 488 and 491, although there are values, the obvious values are incorrect, and in this case, the judgment is performed according to the voltage threshold value and the previous and subsequent values, and invalid values are eliminated;
Figure BDA0002422570830000051
the data attribute transformation is to transform time series data, wherein the time series data comprise current, voltage and power, calculate the unbalance degree of the current and the voltage in a time period, and calculate the load rate by using the power. The voltage or current imbalance can cause no-load loss and load loss of the transformer, the load rate can represent whether the transformer is overloaded or not and the severity of the overload, the voltage is replaced by the voltage imbalance degree in the subsequent fault probability calculation, the current is replaced by the current imbalance degree, and the power is replaced by the load rate
Voltage unbalance degree:
Figure BDA0002422570830000052
in the formula of Umax、UminRespectively representing the maximum value and the minimum value of the three-phase voltage;
current unbalance degree:
Figure BDA0002422570830000053
in the formula Imax、IminRespectively representing the maximum value and the minimum value of the three-phase current;
load factor η:
Figure BDA0002422570830000054
in the formula PTIs the actual capacity, is the power data that can be acquired in real time; pRIs the rated capacity of the transformer.
And step 3: analyzing the influence degree of different factors on the fault of the distribution transformer, thereby determining the selection of the factors and the corresponding weight, and setting the weight of the fault early warning factor of the distribution transformer as wkWherein k is a positive integer, wkA weight representing a kth factor;
as shown in fig. 2, in step 3, the weights of the fault factors of the distribution transformer are determined by using a sequence relation analysis method, and the calculation steps are as follows:
s 1: determining an order relation, and sequencing importance of the factors, wherein the more important the factors are, the more advanced the order relation is, specifically: for the set of factors Al，A2，…，AnThe most important factor is selected first and marked as A1(ii) a Selecting the most important factor from the rest factors and marking the factor as A2(ii) a By analogy, the last factor is marked as AnDetermining the order relation according to the correlation between each factor in the historical fault data and the fault rate;
the correlation between the factors such as temperature, rainfall, current, voltage and the like in the historical fault case and the fault rate of the distribution transformer is calculated by adopting a Pearson correlation analysis method,
Figure BDA0002422570830000061
x represents a plurality of dimensionality influence factors such as temperature, operation life, rainfall and the like, Y is the fault rate of the distribution transformer, the correlation degree between indexes is determined according to the size of the correlation coefficient, the indexes are sorted, and irrelevant indexes are removed. Calculated correlations between temperature and humidity and failure rate are 0.62 and 0.60 respectively, temperature is more important than humidity, whereas correlation between thunderstorm and failure rate is 0.43, which is lower, and this index is not used.
s 2: giving out the ratio judgment of the relative importance degree among the factors; factor Ak-1And AkThe ratio of the importance levels of (a) to (b) is judged as:
Figure BDA0002422570830000062
in the formula: w is akRepresenting the ranking weight, r, of the k-th factorkR is determined by referring to the table according to the correlation between different factors and the failure rate as a ratio of the degree of importancekThe value of (a).
rkAssignment reference table
Figure BDA0002422570830000063
s 3: calculating the ranking weight of each factor:
Figure BDA0002422570830000071
wk-1＝rkwk，(k＝2,3,...,n-1,n)
Figure BDA0002422570830000072
wk(k 1, 2.., n-1, n) is the factor al，A2，…，AnThe corresponding weight.
And 4, step 4: establishing a functional relationship between each factor and the failure rate of the distribution transformer, eachThe functions are independent of each other; let the factor be Al，A2，…，AnThen the corresponding function is y1，y2，…，yn。
And (3) analyzing the influence rule of temperature, wind speed, rainfall and humidity on the distribution transformer independently. Taking temperature as an example, the temperature fault probability reflects the quantitative influence of different temperatures on the reliability of the distribution transformer, and because the distribution transformer is influenced badly by overhigh or overlow temperature, the temperature fault probability curve has the characteristics of high two sides and low middle. Assuming that the temperature variation range is-10 to 45 ℃, the temperature and the fault probability present a quadratic function relationship through interpolation least square fitting,
y＝0.001322x2-0.04628x+0.405
the operation period and the fault rate of the distribution transformer accord with a Weibull distribution function, the operation period is divided into three stages according to actual conditions, the operation period is less than 3 years, between 3 and 25 years and more than 25 years, and the following functional relationship is established:
Figure BDA0002422570830000073
the relationship between the voltage unbalance, the current unbalance and the load rate and the fault of the distribution transformer is analyzed by adopting a random gradient descent model.
And 5: obtaining the fault probability P of the distribution transformer according to the corresponding fault probability function and weight of each factor,
Figure BDA0002422570830000074
and if a certain factor is invalid or missing, discarding the factor, and recalculating the influence weight of the remaining factors on the distribution transformer by using the sequence relation method in the step 3.
The weighted sum of the invalid and missing factors continues to use the remaining factors to determine the probability of failure of the distribution transformer without exceeding the threshold of 0.75.
Step 6: and substituting historical fault data and normal data into the verification, if the result is accurate, ending the verification, and if the result is not accurate, adjusting the functional relation between the weight value in the step 3 and the factor and fault probability in the step 4.
The invention is mainly used for providing a distribution transformer fault early warning method based on multiple factors and dynamic weight, the influence condition of the distribution transformer fault influence factors on the transformer fault is analyzed, the weight of each factor on the fault is obtained, the functional relation between each influence factor and the distribution transformer fault is established, when the factor is lost or uncertain, the factor is abandoned, and the weight of the other factors is recalculated by using a sequence relation method, so that the fault early warning can be continuously carried out, the fault early warning on the distribution transformer is realized, and the influence on the early warning when the factor is lost or uncertain is reduced; because the functional relation between each factor and the distribution transformer fault is mutually independent, the addition and the deletion of the distribution transformer fault early warning system factor are convenient.
The above embodiments do not limit the present invention in any way, and all other modifications and applications that can be made to the above embodiments in equivalent ways are within the scope of the present invention.

Claims (6)

1. A distribution transformer fault early warning method based on multiple factors and dynamic weight is characterized by comprising the following steps:
step 1: collecting historical fault data and normal data of the distribution transformer, wherein the historical fault data refers to data in a specified time period before the distribution transformer breaks down, and the normal data refers to data of the distribution transformer in a normal operation time period; presetting a fault early warning factor of a distribution transformer;
step 2: processing historical fault data and normal data, wherein the processing comprises data cleaning, data attribute transformation and abnormal sample elimination;
the data cleaning refers to finding and correcting recognizable errors in data, including checking data consistency and processing invalid values and missing values;
the data attribute transformation is to transform time series data, the time series data comprises current, voltage and power, the unbalance degree of the current and the voltage in a time period is calculated, and the load rate is calculated by using the power:
voltage unbalance degree:
Figure FDA0002422570820000011
in the formula of Umax、UminRespectively representing the maximum value and the minimum value of the three-phase voltage;
current unbalance degree:
Figure FDA0002422570820000012
in the formula Imax、IminRespectively representing the maximum value and the minimum value of the three-phase current;
load factor η:
Figure FDA0002422570820000013
in the formula PTIs the actual capacity, is the power data that can be acquired in real time; pRThe rated capacity of the transformer;
and step 3: analyzing the influence degree of different factors on the fault of the distribution transformer, thereby determining the selection of the factors and the corresponding weight, and setting the weight of the fault early warning factor of the distribution transformer as wkWherein k is a positive integer, wkA weight representing a kth factor;
and 4, step 4: establishing a functional relation between each factor and the fault rate of the distribution transformer, wherein the functions are independent; let the factor be Al，A2，…，AnThen the corresponding function is y1，y2，…，yn；
And 5: obtaining the fault probability P of the distribution transformer according to the corresponding fault probability function and weight of each factor,
Figure FDA0002422570820000014
step 6: and (4) substituting the historical fault data and the normal data into the verification fault probability, if the result has a problem, adjusting the weight value in the step (3), and adjusting the functional relation between each factor and the fault probability in the step (4).
2. The multi-factor and dynamic weight-based distribution transformer fault early warning method as claimed in claim 1, wherein: in the step 1, the factors of the distribution transformer fault early warning include current, voltage, power, temperature, rainfall, wind speed, humidity, operation age and thunderstorm.
3. The multi-factor and dynamic weight-based distribution transformer fault early warning method as claimed in claim 2, wherein: in the step 3, the weight of the fault factor of the distribution transformer is determined by using a sequence relation analysis method, and the calculation steps are as follows:
s 1: determining an order relation, and sequencing importance of the factors, wherein the more important the factors are, the more advanced the order relation is, specifically: for the set of factors Al，A2，…，An}，AkThe k factor in the factor set is shown, the most important factor is selected first and is marked as A1(ii) a Selecting the most important factor from the rest factors and marking the factor as A2(ii) a By analogy, the last factor is marked as AnDetermining the order relation according to the magnitude of the correlation between each factor in the historical fault data and the fault rate;
and (3) calculating the correlation between each factor in the historical fault data and the fault rate by adopting a Pearson correlation analysis method:
Figure FDA0002422570820000021
x represents a dimension influence factor, Y is the fault rate of the distribution transformer, the correlation degree between indexes is determined according to the magnitude of the correlation coefficient, the indexes with the correlation lower than a threshold value are removed through sorting;
s 2: giving out the ratio judgment of the relative importance degree among the factors; factor Ak-1And AkThe ratio of the importance levels of (a) to (b) is judged as:
Figure FDA0002422570820000022
in the formula: w is akRepresenting the ranking weight, r, of the k-th factorkIs a ratio of the degrees of importance; according to the correlation between different factors and fault rate and referring to rkAssignment reference table decision rkThe value of (A) is as follows:
rkassignment reference table
Figure FDA0002422570820000023
s 3: calculating the ranking weight of each factor:
Figure FDA0002422570820000031
wk-1＝rkwk，(k＝2,3,...,n-1,n)
Figure FDA0002422570820000032
wk(k 1, 2.., n-1, n) is a factor al，A2，…，AnThe corresponding weight.
4. The multi-factor and dynamic weight-based distribution transformer fault early warning method as claimed in claim 3, wherein: in the step 4, through interpolation least square fitting, the temperature and the fault probability present a quadratic function relationship:
y＝0.001322x2-0.04628x+0.405；
the operating life and the fault rate of the distribution transformer accord with a Weibull distribution function, and the operating life is divided into three stages: less than 3 years, between 3-25 years, more than 25 years, the following functional relationships are established:
Figure FDA0002422570820000033
the relationship between the voltage unbalance, the current unbalance and the load rate and the fault of the distribution transformer is analyzed by adopting a random gradient descent model.
5. The multi-factor and dynamic weight-based distribution transformer fault early warning method of claim 4, wherein: in the step 5, if a certain factor is invalid or missing, the factor is discarded, the weight of the influence of the remaining factor on the distribution transformer is recalculated by using the sequence relation method in the step 3, and the failure probability of the distribution transformer is determined by using the remaining factor when the sum of the weights of the invalid and missing factors does not exceed a specified threshold.
6. The multi-factor and dynamic weight-based distribution transformer fault early warning method of claim 5, wherein: in the step 5, under the condition that the weight sum of the invalid and missing factors does not exceed the threshold value of 0.75, the residual factors are continuously utilized to judge the fault probability of the distribution transformer.
CN202010210326.2A 2020-03-24 2020-03-24 Multi-factor and dynamic weight-based distribution transformer fault early warning method Active CN111415093B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010210326.2A CN111415093B (en) 2020-03-24 2020-03-24 Multi-factor and dynamic weight-based distribution transformer fault early warning method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010210326.2A CN111415093B (en) 2020-03-24 2020-03-24 Multi-factor and dynamic weight-based distribution transformer fault early warning method

Publications (2)

Publication Number Publication Date
CN111415093A true CN111415093A (en) 2020-07-14
CN111415093B CN111415093B (en) 2023-05-23

Family

ID=71491483

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010210326.2A Active CN111415093B (en) 2020-03-24 2020-03-24 Multi-factor and dynamic weight-based distribution transformer fault early warning method

Country Status (1)

Country Link
CN (1) CN111415093B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111999605A (en) * 2020-09-16 2020-11-27 珠海许继芝电网自动化有限公司 Power distribution network fault tolerance judgment method and device based on fault correlation analysis
CN112288180A (en) * 2020-11-05 2021-01-29 国电南京自动化股份有限公司 Comprehensive order dispatching method and system for distribution network maintenance work order
CN112463906A (en) * 2020-12-03 2021-03-09 国网黑龙江省电力有限公司电力科学研究院 Fault distribution analysis method for distribution transformer in high and cold regions
CN112836359A (en) * 2021-01-21 2021-05-25 红塔烟草(集团)有限责任公司 Safety evaluation method for power supply and distribution equipment of cigarette production enterprise
CN114422884A (en) * 2021-11-26 2022-04-29 北京智芯微电子科技有限公司 Distribution transformer fault sample collection method, device and system
CN115268350A (en) * 2022-09-27 2022-11-01 江苏永鼎股份有限公司 Fault early warning method and system for voltage stabilizing transformer
CN117040137A (en) * 2023-10-09 2023-11-10 国网山东省电力公司聊城供电公司 Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data
CN117040137B (en) * 2023-10-09 2024-05-07 国网山东省电力公司聊城供电公司 Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104200288A (en) * 2014-09-18 2014-12-10 山东大学 Equipment fault prediction method based on factor-event correlation recognition
CN105787648A (en) * 2016-02-19 2016-07-20 国网浙江省电力公司金华供电公司 Distribution transformer health state evaluation method based on real-time operation information
CN107145475A (en) * 2017-05-16 2017-09-08 国网四川省电力公司电力科学研究院 A kind of bushing shell for transformer probability of malfunction computational methods based on Fuzzy-valued

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104200288A (en) * 2014-09-18 2014-12-10 山东大学 Equipment fault prediction method based on factor-event correlation recognition
CN105787648A (en) * 2016-02-19 2016-07-20 国网浙江省电力公司金华供电公司 Distribution transformer health state evaluation method based on real-time operation information
CN107145475A (en) * 2017-05-16 2017-09-08 国网四川省电力公司电力科学研究院 A kind of bushing shell for transformer probability of malfunction computational methods based on Fuzzy-valued

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111999605A (en) * 2020-09-16 2020-11-27 珠海许继芝电网自动化有限公司 Power distribution network fault tolerance judgment method and device based on fault correlation analysis
CN111999605B (en) * 2020-09-16 2023-11-07 珠海许继芝电网自动化有限公司 Power distribution network fault tolerance judging method and device based on fault correlation analysis
CN112288180A (en) * 2020-11-05 2021-01-29 国电南京自动化股份有限公司 Comprehensive order dispatching method and system for distribution network maintenance work order
CN112463906A (en) * 2020-12-03 2021-03-09 国网黑龙江省电力有限公司电力科学研究院 Fault distribution analysis method for distribution transformer in high and cold regions
CN112836359A (en) * 2021-01-21 2021-05-25 红塔烟草(集团)有限责任公司 Safety evaluation method for power supply and distribution equipment of cigarette production enterprise
CN112836359B (en) * 2021-01-21 2024-05-07 红塔烟草(集团)有限责任公司 Safety evaluation method for power supply and distribution equipment of cigarette production enterprises
CN114422884A (en) * 2021-11-26 2022-04-29 北京智芯微电子科技有限公司 Distribution transformer fault sample collection method, device and system
CN115268350A (en) * 2022-09-27 2022-11-01 江苏永鼎股份有限公司 Fault early warning method and system for voltage stabilizing transformer
CN117040137A (en) * 2023-10-09 2023-11-10 国网山东省电力公司聊城供电公司 Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data
CN117040137B (en) * 2023-10-09 2024-05-07 国网山东省电力公司聊城供电公司 Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data

Also Published As

Publication number Publication date
CN111415093B (en) 2023-05-23

Similar Documents

Publication Publication Date Title
CN111415093A (en) Distribution transformer fault early warning method based on multi-factor and dynamic weight
CN105930976B (en) Node voltage sag severity comprehensive evaluation method based on weighted ideal point method
CN110988422A (en) Electricity stealing identification method and device and electronic equipment
CN112668943A (en) Distribution line health state assessment method and system
CN111582700B (en) Method for calculating fault rate of power distribution network equipment
CN110298012B (en) Test data and operation and maintenance information-based medium and low voltage XLPE cable service life assessment method
CN112001644A (en) Power distribution network operation reliability detection method, device, terminal and storage medium
CN117421687B (en) Method for monitoring running state of digital power ring main unit
CN110705859A (en) PCA-self-organizing neural network-based method for evaluating running state of medium and low voltage distribution network
CN111598457B (en) Method and device for determining quality of power wireless network
CN108510147A (en) A kind of Comprehensive assessment of power quality method based on residual error volatility model
CN110991876A (en) Primary and secondary fusion on-column switch inspection strategy based on state assessment
CN117394337A (en) Power grid load early warning method and system thereof
CN106529582A (en) Prior probability assessment method aiming at introducing expert assessment in Bayesian network
CN107563641B (en) Disaster-resistant multi-scene differentiation planning method for power distribution network considering disaster preference
CN107834563B (en) Method and system for processing voltage sag
CN109784777B (en) Power grid equipment state evaluation method based on time sequence information fragment cloud similarity measurement
CN111240306A (en) Self-adaptive distribution transformer fault diagnosis system and diagnosis method thereof
CN116151799A (en) BP neural network-based distribution line multi-working-condition fault rate rapid assessment method
CN110781959A (en) Power customer clustering method based on BIRCH algorithm and random forest algorithm
CN115879799A (en) Transformer substation electric energy quality analysis method
CN108596450B (en) Power grid risk early warning method and system
CN115389833A (en) Automatic capacity checking method for 315kV and below voltage class distribution transformer
CN113052473B (en) Power grid risk analysis method based on fault rate and static safety analysis
CN114764535A (en) Power data processing method, device and equipment for simulation and storage medium

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