CN110880062A - Method for determining state maintenance time of power distribution equipment - Google Patents

Method for determining state maintenance time of power distribution equipment Download PDF

Info

Publication number
CN110880062A
CN110880062A CN201911049328.1A CN201911049328A CN110880062A CN 110880062 A CN110880062 A CN 110880062A CN 201911049328 A CN201911049328 A CN 201911049328A CN 110880062 A CN110880062 A CN 110880062A
Authority
CN
China
Prior art keywords
equipment
cloud
index
value
matrix
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
CN201911049328.1A
Other languages
Chinese (zh)
Other versions
CN110880062B (en
Inventor
欧阳健娜
高立克
俞小勇
周扬珺
李珊
梁朔
陈绍南
黄伟翔
秦丽文
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.)
Electric Power Research Institute of Guangxi Power Grid Co Ltd
Original Assignee
Electric Power Research Institute of Guangxi Power Grid 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 Electric Power Research Institute of Guangxi Power Grid Co Ltd filed Critical Electric Power Research Institute of Guangxi Power Grid Co Ltd
Priority to CN201911049328.1A priority Critical patent/CN110880062B/en
Publication of CN110880062A publication Critical patent/CN110880062A/en
Application granted granted Critical
Publication of CN110880062B publication Critical patent/CN110880062B/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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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—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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method for determining state maintenance time of power distribution equipment, belongs to the technical field of power engineering, and solves the problems that conventional equipment maintenance of a power distribution network is mainly regular maintenance and after-repair, the utilization efficiency of maintenance resources is low, and fault prevention cannot be performed according to different equipment differences. The method comprises the steps of carrying out health state grade division according to equipment comprehensive deduction values, applying an entropy weight method to weight equipment state evaluation indexes, generating a health state cloud picture of equipment to be evaluated through a cloud model, and then calculating membership degrees between the health state cloud of the equipment to be evaluated and each health state grade cloud; and finally, inputting the membership vector, the times of failure, the operation records and other data into a long-term and short-term memory network for training, so as to realize the prediction of the next failure occurrence time of the equipment to be evaluated and reasonably plan the maintenance plan. And the reasonable planning of the operation equipment maintenance plan is realized according to the predicted fault occurrence time, the maintenance resources are effectively and reasonably utilized, and the equipment fault risk is reduced.

Description

Method for determining state maintenance time of power distribution equipment
The technical field is as follows:
the invention belongs to the technical field of electric power engineering, and particularly relates to a method for determining state maintenance time of power distribution equipment.
Background art:
the traditional equipment maintenance of distribution network is mostly regular maintenance and overhaul afterwards, overhauls the low and can't carry out the fault prevention to all kinds of equipment differences of resource utilization efficiency. Therefore, the state maintenance is carried out on the distribution equipment by utilizing the historical operating data and the test data of the distribution equipment, the maintenance blindness is avoided, the maintenance resources can be fully utilized, and the maintenance efficiency is improved.
The invention content is as follows:
the invention provides a method for determining the state maintenance time of power distribution equipment, which can solve the problems that the conventional equipment maintenance of a power distribution network is mostly regular maintenance and after-repair, the utilization efficiency of maintenance resources is low, and the fault prevention can not be performed according to the difference of various equipment.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for determining the state maintenance time of power distribution equipment comprises the following steps of 1, dividing the health degree into equipment grades: according to the comprehensive deduction value of the equipment, counting the similar voltage classeszDegree of health of table equipment
Figure 485668DEST_PATH_IMAGE001
（z=1,2,…Z) According to the degree of health
Figure 809333DEST_PATH_IMAGE001
Grading the health state of the equipment; step 2, determining the equipment state evaluation index weight by an entropy weight method, and solving the membership by a cloud model: after an entropy weight method is applied to weight the equipment state evaluation index, a health state cloud picture of the equipment to be evaluated is generated through a cloud model, and then membership degrees between the health state cloud of the equipment to be evaluated and the health state level clouds are calculated to obtain membership degree vectors; step 3, training a power distribution equipment fault occurrence time prediction model based on the long-term and short-term memory network: firstly, normalizing equipment operation record indexes in sample equipment state evaluation indexes to form a matrix
Figure 854650DEST_PATH_IMAGE002
Then the membership degree vector of the sample deviceδ z Number of failed times
Figure 515438DEST_PATH_IMAGE003
Matrix, matrix
Figure 487068DEST_PATH_IMAGE004
Inputting an LSTM neural network as an input sample for training;
step 4, predicting the next fault occurrence time of the equipment to be evaluated, and determining the maintenance time: according to the membership degree vector of the equipment to be evaluated
Figure 840689DEST_PATH_IMAGE005
Number of failed times
Figure 779826DEST_PATH_IMAGE006
And equipment operation record index normalization matrix
Figure 509884DEST_PATH_IMAGE007
Inputting the formed matrix into a trained LSTM neural network to calculate to obtain a predicted value of the next fault occurrence time of the equipment to be evaluated
Figure 834555DEST_PATH_IMAGE008
According to the formula
Figure 500023DEST_PATH_IMAGE009
Determining time to overhaul
Figure 785511DEST_PATH_IMAGE010
Wherein
Figure 679780DEST_PATH_IMAGE011
in order to plan the time for the overhaul,
Figure 734323DEST_PATH_IMAGE012
in order to maintain the required time for the maintenance,
Figure 570692DEST_PATH_IMAGE013
a safety margin time.
Further, step 1 is based on health degree
Figure 343476DEST_PATH_IMAGE014
The health status of the equipment is divided into four grades of normal, attention, abnormal and serious for use respectively
Figure 539971DEST_PATH_IMAGE015
、
Figure 714601DEST_PATH_IMAGE016
、
Figure 456292DEST_PATH_IMAGE017
、
Figure 716372DEST_PATH_IMAGE018
And (4) showing.
Further, by formula
Figure 952443DEST_PATH_IMAGE019
Cloud digital signatures for 4 health status levels were calculated,
Figure 981579DEST_PATH_IMAGE020
is the minimum value of the health status grade interval,
Figure 159751DEST_PATH_IMAGE021
is the maximum value of the health status grade interval,
Figure 641548DEST_PATH_IMAGE022
as equipment health status gradefThe expected value of (c) is,
Figure 179845DEST_PATH_IMAGE023
as equipment health status gradefThe entropy of the (c),
Figure 204433DEST_PATH_IMAGE024
as equipment health status gradefThe entropy of the first power,
Figure 678140DEST_PATH_IMAGE024
taking the mixture of 0.01, wherein,f=1,2,3,4, corresponding to four status levels, respectively
Figure 381654DEST_PATH_IMAGE015
、
Figure 225107DEST_PATH_IMAGE016
、
Figure 104201DEST_PATH_IMAGE017
、
Figure 748809DEST_PATH_IMAGE018
。
Further, the entropy weight method in step 2 is as follows,
firstly, constructing an equipment state evaluation index matrix: bynEvaluation of eachObjectmThe index matrix formed by the two-level indexes is as follows,
Figure 329832DEST_PATH_IMAGE025
，
Figure 85299DEST_PATH_IMAGE026
，
wherein,Xis composed of
Figure 553320DEST_PATH_IMAGE027
An index matrix constructed by the index values;X i is the first in the index matrixiAn index column vector, i.e.n(ii) evaluation of the objectiA vector consisting of individual evaluation indexes; is as followsi(ii) evaluation of the objectjA plurality of index values;xto be a set of indices, the index set,
Figure 103250DEST_PATH_IMAGE028
is the first in the index setjAn index;mis the index number;nthe number of the evaluation objects is;
secondly, the equipment state evaluation index normalization processing: the positive and negative indicators are normalized as follows
Figure 46935DEST_PATH_IMAGE029
，
Figure 232191DEST_PATH_IMAGE030
，
A normalized device status evaluation index matrix is obtained, as follows,
Figure 944932DEST_PATH_IMAGE031
，
thirdly, calculating the entropy value of each equipment state evaluation index: the calculation formula is as follows,
Figure 275551DEST_PATH_IMAGE032
，e j is as followsjEntropy values of the evaluation indicators, wherein,
Figure 706532DEST_PATH_IMAGE033
，
Figure 928435DEST_PATH_IMAGE034
is the firstiA sample device is arranged atjThe ratio of the scores on each index to the scores on the indexes of all the objects to be evaluated,
Figure 761262DEST_PATH_IMAGE035
，
fourthly, calculating the entropy weight of each equipment state evaluation index: the calculation formula is as follows,
Figure 528360DEST_PATH_IMAGE036
，w j is as followsjEntropy weights of the individual evaluation indexes.
Further, the cloud model in step 2 generates the cloud picture mainly as follows,
first, calculate the inverse cloud generator: first, thejExpectation of secondary index
Figure 181059DEST_PATH_IMAGE037
Entropy of
Figure 973696DEST_PATH_IMAGE038
Entropy of the sea
Figure 129871DEST_PATH_IMAGE039
The calculation formula of (a) is as follows,
Figure 458084DEST_PATH_IMAGE040
，
Figure 473445DEST_PATH_IMAGE041
，
Figure 178096DEST_PATH_IMAGE042
，
Figure 844569DEST_PATH_IMAGE043
，
wherein,S 2 is the variance of the received signal and the variance,Pin order to index the number of samples,
Figure 343684DEST_PATH_IMAGE044
the index value is a secondary index value; the digital characteristic parameters of the cloud model of the level of the target layer are obtained by combining the digital characteristics of the cloud model of the related indexes of each level, the calculation formula is shown as follows,
Figure 846340DEST_PATH_IMAGE045
，
Figure 89103DEST_PATH_IMAGE046
，
Figure 99829DEST_PATH_IMAGE047
；
second, calculate a forward cloud generator: is characterized by a number of
Figure 769845DEST_PATH_IMAGE048
Random generation by a forward cloud generatorNCloud drop of Chinese herbal medicine
Figure 759798DEST_PATH_IMAGE049
The method comprises the following specific steps:
a, in order to
Figure 540672DEST_PATH_IMAGE050
In the interest of expectation,
Figure 181738DEST_PATH_IMAGE051
for standard deviation, normally distributed random numbers are generated
Figure 22655DEST_PATH_IMAGE052
；
b, in order to
Figure 499904DEST_PATH_IMAGE053
In the interest of expectation,
Figure 84469DEST_PATH_IMAGE054
for standard deviation, normally distributed random numbers are generated
Figure 81506DEST_PATH_IMAGE055
；
c, to
Figure 93324DEST_PATH_IMAGE052
、
Figure 792290DEST_PATH_IMAGE055
As variables, into formulas
Figure 570759DEST_PATH_IMAGE056
Producing cloud droplets
Figure 796204DEST_PATH_IMAGE049
；
d, repeating steps a to c until generatingNUntil the cloud drops, according toNAnd drawing a cloud model diagram by the individual cloud droplets.
Further, the cloud of the sample device and the firstfThe intersection points of the cloud pictures with the same scale areKDripping from the root of Yun, and takingKThe mean value of the membership value of each cloud droplet is used as the membership of the equipment state value, as shown in the formula,
Figure 854290DEST_PATH_IMAGE057
whereinf1,2,3,4, thenzMembership vector of stage sample equipment
Figure 430764DEST_PATH_IMAGE058
。
Further, the training algorithm of the LSTM neural network in step 3 is a back propagation algorithm, and is divided into three steps, first, the output value of the LSTM memory module is calculated forward by combining the weight matrix, second, the error term of each memory module is calculated backward, and third, the gradient of each weight matrix used in the first step is calculated according to the corresponding residual error term, and the weight matrix is updated.
Further, after the sample data of each sample device is input into the LSTM neural network for training, the model training is finished; or the model training is finished when the training error is set to be less than 1 e-06.
Further, the output value of the LSTM memory module, namely the true value of the next fault occurrence time of the sample equipment, is calculated in the forward direction
Figure 983231DEST_PATH_IMAGE059
The calculation formula of (a) is as follows,
Figure 63182DEST_PATH_IMAGE060
，
Figure 557749DEST_PATH_IMAGE061
，
Figure 621520DEST_PATH_IMAGE062
，
Figure 476212DEST_PATH_IMAGE063
，
Figure 410670DEST_PATH_IMAGE064
，
Figure 76138DEST_PATH_IMAGE065
；
Figure 361625DEST_PATH_IMAGE066
in order to be a sigmoid function,
Figure 255894DEST_PATH_IMAGE067
is thattThe input matrix of the time of day,
Figure 310438DEST_PATH_IMAGE068
、
Figure 146807DEST_PATH_IMAGE069
、
Figure 654012DEST_PATH_IMAGE070
、
Figure 850507DEST_PATH_IMAGE071
representation and current input
Figure 25136DEST_PATH_IMAGE072
The weight matrix of the multiplication is used,
Figure 766827DEST_PATH_IMAGE073
、
Figure 26907DEST_PATH_IMAGE074
、
Figure 262979DEST_PATH_IMAGE075
、
Figure 292115DEST_PATH_IMAGE076
is shown andt-1 time output value
Figure 204707DEST_PATH_IMAGE077
The weight matrix of the multiplication is used,
Figure 952083DEST_PATH_IMAGE078
、
Figure 224802DEST_PATH_IMAGE079
、
Figure 108444DEST_PATH_IMAGE080
、
Figure 457517DEST_PATH_IMAGE081
respectively are the bias items of a forgetting gate, an input gate, a state unit and an output gate,
Figure 426610DEST_PATH_IMAGE082
、
Figure 4484DEST_PATH_IMAGE083
、
Figure 8212DEST_PATH_IMAGE084
respectively are the activation functions of a forgetting gate, an input gate and an output gate,
Figure 262607DEST_PATH_IMAGE085
、
Figure 718996DEST_PATH_IMAGE086
is a vector of state units and instantaneous states;
Figure 208883DEST_PATH_IMAGE087
the current output of the LSTM neural network is the real value of the next fault occurrence time of the sample device.
Compared with the prior art, the invention has the beneficial effects that:
the method utilizes historical operating data and test data of the power distribution equipment to be processed by an entropy weight method and a cloud model, inputs the processed data into an LSTM neural network for training, processes the data according to corresponding indexes of the equipment to be evaluated, and inputs the processed data into the LSTM neural network to predict the next fault occurrence time of the equipment to be evaluated and determine the maintenance time, thereby realizing reasonable planning of maintenance plans of the equipment in operation, avoiding the blindness of maintenance, fully utilizing maintenance resources, improving the maintenance efficiency and reducing the equipment fault risk.
Description of the drawings:
FIG. 1 is a flow chart of a method for determining a condition maintenance time of a power distribution device in accordance with the present invention;
FIG. 2 is a state evaluation index system for a distribution transformer in accordance with the present invention;
FIG. 3 is a diagram of a distribution line condition evaluation index system according to the present invention;
FIG. 4 illustrates an LSTM memory module structure according to the present invention;
FIG. 5 is an expanded view of the timing of the LSTM network of the present invention.
The specific implementation mode is as follows:
in order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following detailed description is made with reference to the accompanying drawings and specific examples, and specific embodiments of the present invention are described in detail as follows:
the invention provides a method for determining the state maintenance time of power distribution equipment, the flow of the method is shown in figure 1, the state maintenance of the power distribution equipment in question is actually graded into health states according to the comprehensive deduction value of the equipment; after the entropy weight method is used for weighting the equipment state evaluation index, a health state cloud picture of the equipment to be evaluated is generated through a cloud model, and then the membership degree between the health state cloud of the equipment to be evaluated and each health state grade cloud is calculated; and finally, inputting the membership vector, the times of failure, the operation records and other data into a long-term and short-term memory network for training, so as to realize the prediction of the next failure occurrence time of the equipment to be evaluated. The method mainly comprises the following steps:
step 1: and carrying out health state grade division according to the equipment comprehensive deduction value.
According to the comprehensive deduction value of the equipment, counting the similar voltage classeszDegree of health of table equipment
Figure 191752DEST_PATH_IMAGE001
（z=1,2,…Z) According to the degree of health
Figure 7261DEST_PATH_IMAGE001
The health grade of the equipment is divided into four grades of normal, attention, abnormal and serious, which are respectively used
Figure 560733DEST_PATH_IMAGE015
、
Figure 854311DEST_PATH_IMAGE016
、
Figure 193151DEST_PATH_IMAGE017
、
Figure 179561DEST_PATH_IMAGE018
Expressed that the corresponding value ranges are respectively [80, 100 ]]、[60，80)、[40，60)、[0，40)。
Step 2: and after the entropy weight method is used for weighting the equipment state evaluation index, generating a health state cloud picture of the equipment to be evaluated through a cloud model, and calculating the membership degree between the health state cloud of the equipment to be evaluated and each health state grade cloud. Normalizing each index of the sample equipment according to the formulas (4) and (5), inputting the normalized numerical value and the corresponding weight into a reverse cloud generator, calculating cloud digital characteristics according to the formulas (10) to (13), and generating a cloud picture through the forward cloud generator.
According to the range of the device state value [0, 1]And the corresponding relationship of the health status grade of the equipment,
Figure 485909DEST_PATH_IMAGE015
、
Figure 583178DEST_PATH_IMAGE016
、
Figure 275059DEST_PATH_IMAGE017
、
Figure 166792DEST_PATH_IMAGE018
the four state value ranges are respectively [0.8, 1 ]]0.6, 0.8), 0.4, 0.6, 0.4). Calculating the cloud digital characteristics of 4 health state grades by the formula (1), generating a corresponding cloud picture according to the step (2-2),
Figure 85069DEST_PATH_IMAGE020
is the minimum value of the health status grade interval,
Figure 595816DEST_PATH_IMAGE021
is the maximum value of the health status grade interval,
Figure 17570DEST_PATH_IMAGE022
as equipment health status gradefThe expected value of (c) is,
Figure 971882DEST_PATH_IMAGE023
as equipment health status gradefThe entropy of the (c),
Figure 377456DEST_PATH_IMAGE024
as equipment health status gradefThe entropy of the first power,
Figure 957473DEST_PATH_IMAGE024
taking the mixture of 0.01, wherein,f=1,2,3,4, corresponding to four status levels, respectively
Figure 420684DEST_PATH_IMAGE015
、
Figure 654219DEST_PATH_IMAGE016
、
Figure 156876DEST_PATH_IMAGE017
、
Figure 868480DEST_PATH_IMAGE018
The health status classification grade of the equipment and the corresponding digital characteristics of the cloud model are calculated and are shown in the table 1,
Figure 168223DEST_PATH_IMAGE019
（1）
Figure 572659DEST_PATH_IMAGE088
(1) the entropy weight method comprises the following calculation steps:
(1-1) constructing an equipment state evaluation index matrix:
bynAn evaluation objectmThe index matrix formed by the secondary indexes is shown as (2),
Figure 687246DEST_PATH_IMAGE025
（2）
Figure 77907DEST_PATH_IMAGE026
（3）
wherein,Xis composed of
Figure 594339DEST_PATH_IMAGE027
An index matrix constructed by the index values;X i is the first in the index matrixiAn index column vector, i.e.n(ii) evaluation of the objectiA vector consisting of individual evaluation indexes; is as followsi(ii) evaluation of the objectjA plurality of index values;xto be a set of indices, the index set,
Figure 559890DEST_PATH_IMAGE028
is the first in the index setjAn index;mis the index number;nthe number of the evaluation objects is;
(1-2) device status evaluation index normalization processing:
considering that the equipment state evaluation index system comprises both positive indexes and negative indexes (the higher the positive index value is, the better the negative index value is), the normalization processing is respectively carried out on the positive indexes and the negative indexes, as shown in formulas (4) and (5),
Figure 161773DEST_PATH_IMAGE029
（4）
Figure 621704DEST_PATH_IMAGE030
（5）
obtaining a normalized equipment state evaluation index matrix, as shown in (6),
Figure 258222DEST_PATH_IMAGE031
（6）
(1-3) entropy calculation of each equipment state evaluation index: the calculation is as shown in equation (7),
Figure 896139DEST_PATH_IMAGE032
（7）
e j is as followsjEntropy values of the evaluation indicators, wherein,
Figure 719738DEST_PATH_IMAGE033
，
Figure 983360DEST_PATH_IMAGE034
is the firstiA sample device is arranged atjThe ratio of the score on each index to the scores on the indexes of all the objects to be evaluated is shown in the formula (8)
Figure 943226DEST_PATH_IMAGE035
（8）
(1-4) calculating the entropy weight of each equipment state evaluation index: the calculation formula is shown as (9),
Figure 250579DEST_PATH_IMAGE036
（9）
w j is as followsjEntropy weights of the individual evaluation indexes.
(2) The cloud model comprises the following main steps: and (3) normalizing each index according to a formula for the sample equipment, inputting the normalized numerical value and the corresponding weight into a reverse cloud generator, calculating the cloud digital characteristics, and generating a cloud picture through the forward cloud generator.
(2-1) calculating a reverse cloud generator: first, thejExpectation of secondary index
Figure 827054DEST_PATH_IMAGE037
Entropy of
Figure 628788DEST_PATH_IMAGE038
Entropy of the sea
Figure 708740DEST_PATH_IMAGE039
The calculation formula of (a) is as follows,
Figure 954039DEST_PATH_IMAGE040
(10)
Figure 752230DEST_PATH_IMAGE041
(11)
Figure 92076DEST_PATH_IMAGE042
(12)
Figure 26534DEST_PATH_IMAGE043
(13)
wherein,S 2 is the variance of the received signal and the variance,Pin order to index the number of samples,
Figure 816635DEST_PATH_IMAGE044
the index value is a secondary index value; the digital characteristic parameters of the cloud model of the level of the target layer are obtained by combining the digital characteristics of the cloud model of the related indexes of each level, the calculation formula is shown as follows,
Figure 961178DEST_PATH_IMAGE045
(14)
Figure 494927DEST_PATH_IMAGE046
(15)
Figure 424837DEST_PATH_IMAGE047
(16)
(2-2) calculating a forward cloud generator: is characterized by a number of
Figure 120261DEST_PATH_IMAGE048
Random generation by a forward cloud generatorNCloud drop of Chinese herbal medicine
Figure 519143DEST_PATH_IMAGE049
The method comprises the following specific steps:
(2-2-1) with
Figure 325425DEST_PATH_IMAGE050
In the interest of expectation,
Figure 109842DEST_PATH_IMAGE051
for standard deviation, normally distributed random numbers are generated
Figure 241746DEST_PATH_IMAGE052
；
(2-2-2) with
Figure 360880DEST_PATH_IMAGE053
In the interest of expectation,
Figure 236432DEST_PATH_IMAGE054
for standard deviation, normally distributed random numbers are generated
Figure 140934DEST_PATH_IMAGE055
；
(2-2-3) with
Figure 912581DEST_PATH_IMAGE052
、
Figure 659957DEST_PATH_IMAGE055
As variables, into formulas
Figure 230878DEST_PATH_IMAGE056
Producing cloud droplets
Figure 724308DEST_PATH_IMAGE049
；
(2-2-4) repeating the steps (2-2-1) to (2-2-3) until the productionNUntil the cloud drops, according toNAnd drawing a cloud model diagram by the individual cloud droplets.
(2-2-5) cloud of sample device andfthe intersection points of the cloud pictures with the same scale areKDripping from the root of Yun, and takingKThe mean value of the membership value of each cloud droplet is used as the membership of the equipment state value, as shown in formula (17),
Figure 932435DEST_PATH_IMAGE057
(17)
wherein,f1,2,3,4, thenzMembership vector of stage sample equipment
Figure 635949DEST_PATH_IMAGE058
。
And step 3: the power distribution equipment fault occurrence time prediction model training based on the long-term and short-term memory network,
normalizing the operation record index (the 'operation record B' index in an equipment state evaluation index system, as shown in figures 2 and 3) of the sample equipment according to a formula to form a matrix
Figure 977937DEST_PATH_IMAGE002
Then the membership degree vector of the sample device
Figure 716086DEST_PATH_IMAGE089
Number of failed times
Figure 236061DEST_PATH_IMAGE003
Running record index normalization matrix
Figure 692450DEST_PATH_IMAGE004
As input samples, the LSTM neural network is input for training (the topology is shown in FIG. 4).
The training algorithm of the LSTM neural network is a back propagation algorithm and is divided into the following three steps, and when the sample data of each sample device is input into the LSTM neural network for training, the model training is finished; or the model training is finished when the training error is set to be less than 1e-06, the training error is the total training error of the sample set which is trained each time, the training error is not the training error of single sample data, and 1e-06 is a value obtained by experience and repeatability tests.
(3-1) calculating the output value of the LSTM memory module in the forward direction;
Figure 808435DEST_PATH_IMAGE060
(18)
Figure 666670DEST_PATH_IMAGE061
(19)
Figure 216600DEST_PATH_IMAGE062
(20)
Figure 770072DEST_PATH_IMAGE063
(21)
Figure 329230DEST_PATH_IMAGE064
(22)
Figure 901025DEST_PATH_IMAGE065
(23)
Figure 887436DEST_PATH_IMAGE066
wherein the function of sigmoid is the function of sigmoid,
Figure 193783DEST_PATH_IMAGE067
is thattThe input matrix of the time of day,
Figure 291052DEST_PATH_IMAGE068
、
Figure 592721DEST_PATH_IMAGE069
、
Figure 641710DEST_PATH_IMAGE070
、
Figure 28829DEST_PATH_IMAGE071
representation and current input
Figure 805156DEST_PATH_IMAGE072
The weight matrix of the multiplication is used,
Figure 492489DEST_PATH_IMAGE073
、
Figure 679757DEST_PATH_IMAGE074
、
Figure 757434DEST_PATH_IMAGE075
、
Figure 822604DEST_PATH_IMAGE076
is shown andt-1 time output value
Figure 98865DEST_PATH_IMAGE077
The weight matrix of the multiplication is used,
Figure 597979DEST_PATH_IMAGE078
、
Figure 100636DEST_PATH_IMAGE079
、
Figure 343398DEST_PATH_IMAGE080
、
Figure 864378DEST_PATH_IMAGE081
respectively are the bias items of a forgetting gate, an input gate, a state unit and an output gate,
Figure 534394DEST_PATH_IMAGE082
、
Figure 117822DEST_PATH_IMAGE083
、
Figure 39642DEST_PATH_IMAGE084
respectively are the activation functions of a forgetting gate, an input gate and an output gate,
Figure 290495DEST_PATH_IMAGE085
、
Figure 745792DEST_PATH_IMAGE086
is a vector of state units and instantaneous states;
Figure 82095DEST_PATH_IMAGE087
the current output of the LSTM neural network is the real value of the next fault occurrence time of the sample device.
(3-2) reverse calculation of error terms for each memory module
Figure 401081DEST_PATH_IMAGE090
The error term of LSTM proceeds in both directionsAnd (5) spreading. The error term propagating backwards in time, i.e. being calculatedt-1 error term at time instanttAt a time, the output value of LSTM is
Figure 647386DEST_PATH_IMAGE091
Definition oftThe error term of the time is
Figure 659204DEST_PATH_IMAGE092
WhereinEAs a loss function, then
Figure 545120DEST_PATH_IMAGE093
. From the formula of the full derivative
Figure 667797DEST_PATH_IMAGE094
About
Figure 784920DEST_PATH_IMAGE095
、
Figure 967640DEST_PATH_IMAGE096
、
Figure 419481DEST_PATH_IMAGE097
、
Figure 345848DEST_PATH_IMAGE098
The relationship of the four items is that,
Figure 816013DEST_PATH_IMAGE095
、
Figure 169634DEST_PATH_IMAGE096
、
Figure 797186DEST_PATH_IMAGE097
、
Figure 261666DEST_PATH_IMAGE098
is defined as follows, symbols "
Figure 337069DEST_PATH_IMAGE099
"denotes multiplication by element:
Figure 596012DEST_PATH_IMAGE100
(24)
Figure 133697DEST_PATH_IMAGE101
(25)
Figure 605130DEST_PATH_IMAGE102
(26)
Figure 784307DEST_PATH_IMAGE103
(27)
the substitution of each term by the partial derivative formula can be obtained:
Figure 745310DEST_PATH_IMAGE104
(28)
the formula is a formula for the error to reversely propagate to the last moment, so that the error term can be reversely propagated to any timekFormula for the time of day:
Figure 393460DEST_PATH_IMAGE105
(29)
definition is currently the first
Figure 465322DEST_PATH_IMAGE106
Layer of
Figure 470DEST_PATH_IMAGE107
Error term of layer is error function pair
Figure 132374DEST_PATH_IMAGE107
The inverse of the weighted input for the layer neurons, i.e.
Figure 2241DEST_PATH_IMAGE108
. Input of LSTM
Figure 268007DEST_PATH_IMAGE109
，
Figure 31563DEST_PATH_IMAGE110
To represent
Figure 209735DEST_PATH_IMAGE107
The activation function of the layer. Equation (30) is obtained using the fully-derived equation, which is a calculation to pass the error to the previous layer.
Figure 691532DEST_PATH_IMAGE111
(30)
(3-3) calculating the gradient of each weight matrix in (3-1) according to the corresponding residual error term, and updating the weight matrix, wherein the formula is as follows:
Figure 731294DEST_PATH_IMAGE112
(31)
Figure 614937DEST_PATH_IMAGE113
(32)
Figure 964009DEST_PATH_IMAGE114
(33)
Figure 933102DEST_PATH_IMAGE115
(34)
Figure 275091DEST_PATH_IMAGE116
(35)
Figure 385478DEST_PATH_IMAGE117
(36)
Figure 171031DEST_PATH_IMAGE118
(37)
Figure 361841DEST_PATH_IMAGE119
(38)
Figure 117308DEST_PATH_IMAGE120
(39)
Figure 834597DEST_PATH_IMAGE121
(40)
Figure 384527DEST_PATH_IMAGE122
(41)
Figure 203578DEST_PATH_IMAGE123
(42)
and 4, step 4: and predicting the next fault occurrence time of the equipment to be evaluated, and determining the overhaul time.
Generating a health state cloud chart of the equipment to be evaluated according to the cloud model in the step 2, and calculating a membership degree vector of the equipment to be evaluated according to a formula (17)
Figure 762736DEST_PATH_IMAGE005
(ii) a Normalizing the operation record indexes (shown in figures 2 and 3) of the equipment to be evaluated according to formulas (4) - (5) to form a matrix
Figure 101575DEST_PATH_IMAGE007
Then the membership degree vector of the equipment to be evaluated
Figure 822407DEST_PATH_IMAGE005
Number of failed times
Figure 987809DEST_PATH_IMAGE006
Running record index normalization matrix
Figure 960444DEST_PATH_IMAGE007
The formed matrix is substituted into the formulas (18) - (23), and the next fault occurrence time of the equipment to be evaluated is calculatedPredicted value of (2)
Figure 793271DEST_PATH_IMAGE008
The maintenance time is calculated according to the formula (43)
Figure 809637DEST_PATH_IMAGE010
，
Figure 462335DEST_PATH_IMAGE009
（43）
Wherein,
Figure 238662DEST_PATH_IMAGE011
in order to plan the time for the overhaul,
Figure 660416DEST_PATH_IMAGE011
the time required for maintenance and the time of a safety margin to ensure the reliability of the power supply
Figure 988629DEST_PATH_IMAGE013
。
According to the method, the historical operation data and the test data of the power distribution equipment are utilized to predict the next fault occurrence time of the equipment to be evaluated and determine the maintenance time, so that the reasonable planning of the maintenance plan of the in-operation equipment is realized, the maintenance blindness is avoided, the maintenance resources can be fully utilized, the maintenance efficiency is improved, and the equipment fault risk is reduced.
The above description of embodiments of the invention with reference to the drawings is not intended to be limiting, and those skilled in the art can make many variations without departing from the spirit of the invention and the scope of the appended claims, which fall within the scope of the invention.

Claims (9)

1. A method for determining the state maintenance time of power distribution equipment is characterized by comprising the following steps: the method comprises the following steps of,
step 1, the health degree is divided into equipment grades: according to the comprehensive deduction value of the equipment, counting the similar voltage classeszTable deviceDegree of health
Figure 351615DEST_PATH_IMAGE001
（z=1,2,…Z) According to the degree of health
Figure 416785DEST_PATH_IMAGE001
Grading the health state of the equipment;
step 2, determining the equipment state evaluation index weight by an entropy weight method, and solving the membership by a cloud model: after an entropy weight method is applied to weight the equipment state evaluation index, a health state cloud picture of the equipment to be evaluated is generated through a cloud model, and then membership degrees between the health state cloud of the equipment to be evaluated and the health state level clouds are calculated to obtain membership degree vectors;
step 3, training a power distribution equipment fault occurrence time prediction model based on the long-term and short-term memory network: firstly, normalizing equipment operation record indexes in sample equipment state evaluation indexes to form a matrix
Figure 161887DEST_PATH_IMAGE002
Then the membership degree vector of the sample deviceδ z Number of failed times
Figure 67526DEST_PATH_IMAGE003
Matrix, matrix
Figure 694817DEST_PATH_IMAGE004
Inputting an LSTM neural network as an input sample for training;
step 4, predicting the next fault occurrence time of the equipment to be evaluated, and determining the maintenance time: according to the membership degree vector of the equipment to be evaluated
Figure 62213DEST_PATH_IMAGE005
Number of failed times
Figure 130663DEST_PATH_IMAGE006
And equipment operation record index normalization matrix
Figure 800679DEST_PATH_IMAGE007
Inputting the formed matrix into a trained LSTM neural network to calculate to obtain a predicted value of the next fault occurrence time of the equipment to be evaluated
Figure 541364DEST_PATH_IMAGE008
According to the formula
Figure 791080DEST_PATH_IMAGE009
Determining time to overhaul
Figure 41933DEST_PATH_IMAGE010
Wherein
Figure 23795DEST_PATH_IMAGE011
in order to plan the time for the overhaul,
Figure 625678DEST_PATH_IMAGE012
in order to maintain the required time for the maintenance,
Figure 334877DEST_PATH_IMAGE013
a safety margin time.
2. The method of determining electrical distribution equipment condition repair time of claim 1, wherein: step 1 according to health degree
Figure 705815DEST_PATH_IMAGE014
The health status of the equipment is divided into four grades of normal, attention, abnormal and serious for use respectively
Figure 593000DEST_PATH_IMAGE015
、
Figure 682179DEST_PATH_IMAGE016
、
Figure 430954DEST_PATH_IMAGE017
、
Figure 656399DEST_PATH_IMAGE018
And (4) showing.
3. The method of determining electrical distribution equipment condition repair time of claim 2, wherein: is composed of
Figure 980064DEST_PATH_IMAGE019
Cloud digital signatures for 4 health status levels were calculated,
Figure 290960DEST_PATH_IMAGE020
is the minimum value of the health status grade interval,
Figure 341961DEST_PATH_IMAGE021
is the maximum value of the health status grade interval,
Figure 687492DEST_PATH_IMAGE022
as equipment health status gradefThe expected value of (c) is,
Figure 244375DEST_PATH_IMAGE023
as equipment health status gradefThe entropy of the (c),
Figure 917933DEST_PATH_IMAGE024
as equipment health status gradefThe entropy of the first power,
Figure 913571DEST_PATH_IMAGE024
taking the mixture of 0.01, wherein,f=1,2,3,4, corresponding to four status levels, respectively
Figure 751425DEST_PATH_IMAGE015
、
Figure 479210DEST_PATH_IMAGE016
、
Figure 764698DEST_PATH_IMAGE017
、
Figure 908234DEST_PATH_IMAGE018
。
4. The method of determining electrical distribution equipment condition repair time of claim 1, wherein: the entropy weighting method in step 2 is as follows,
firstly, constructing an equipment state evaluation index matrix: bynAn evaluation objectmThe index matrix formed by the two-level indexes is as follows,
Figure 228357DEST_PATH_IMAGE025
，
Figure 313994DEST_PATH_IMAGE026
，
wherein,Xis composed of
Figure 290040DEST_PATH_IMAGE027
An index matrix constructed by the index values;X i is the first in the index matrixiAn index column vector, i.e.n(ii) evaluation of the objectiA vector consisting of individual evaluation indexes; is as followsi(ii) evaluation of the objectjA plurality of index values;xto be a set of indices, the index set,
Figure 96322DEST_PATH_IMAGE028
is the first in the index setjAn index;mis the index number;nthe number of the evaluation objects is;
secondly, the equipment state evaluation index normalization processing: the positive and negative indicators are normalized as follows
Figure 146318DEST_PATH_IMAGE029
，
Figure 278222DEST_PATH_IMAGE030
，
A normalized device status evaluation index matrix is obtained, as follows,
Figure 164400DEST_PATH_IMAGE031
，
thirdly, calculating the entropy value of each equipment state evaluation index: the calculation formula is as follows,
Figure 977636DEST_PATH_IMAGE032
，e j is as followsjEntropy values of the evaluation indicators, wherein,
Figure 6772DEST_PATH_IMAGE033
，
Figure 450522DEST_PATH_IMAGE034
is the firstiA sample device is arranged atjThe ratio of the scores on each index to the scores on the indexes of all the objects to be evaluated,
Figure 932319DEST_PATH_IMAGE035
，
fourthly, calculating the entropy weight of each equipment state evaluation index: the calculation formula is as follows,
Figure 549245DEST_PATH_IMAGE036
，w j is as followsjEntropy weights of the individual evaluation indexes.
5. The method of determining electrical distribution equipment condition repair time of claim 4, wherein: the cloud model in step 2 generates a cloud picture mainly as follows,
first, calculate the inverse cloud generator: first, thejSecond stageExpectation of index
Figure 557522DEST_PATH_IMAGE037
Entropy of
Figure 296807DEST_PATH_IMAGE038
Entropy of the sea
Figure 672425DEST_PATH_IMAGE039
The calculation formula of (a) is as follows,
Figure 250299DEST_PATH_IMAGE040
，
Figure 457290DEST_PATH_IMAGE041
，
Figure 101898DEST_PATH_IMAGE042
，
Figure 699232DEST_PATH_IMAGE043
，
wherein,S 2 is the variance of the received signal and the variance,Pin order to index the number of samples,
Figure 454699DEST_PATH_IMAGE044
the index value is a secondary index value; the digital characteristic parameters of the cloud model of the level of the target layer are obtained by combining the digital characteristics of the cloud model of the related indexes of each level, the calculation formula is shown as follows,
Figure 250616DEST_PATH_IMAGE045
，
Figure 190759DEST_PATH_IMAGE046
，
Figure 400024DEST_PATH_IMAGE047
；
second, calculate a forward cloud generator: characterised by the numberIs composed of
Figure 834547DEST_PATH_IMAGE048
Random generation by a forward cloud generatorNCloud drop of Chinese herbal medicine
Figure 547288DEST_PATH_IMAGE049
The method comprises the following specific steps:
a, in order to
Figure 471382DEST_PATH_IMAGE050
In the interest of expectation,
Figure 794041DEST_PATH_IMAGE051
for standard deviation, normally distributed random numbers are generated
Figure 891310DEST_PATH_IMAGE052
；
b, in order to
Figure 599503DEST_PATH_IMAGE053
In the interest of expectation,
Figure 694498DEST_PATH_IMAGE054
for standard deviation, normally distributed random numbers are generated
Figure 612776DEST_PATH_IMAGE055
；
c, to
Figure 903949DEST_PATH_IMAGE052
、
Figure 325703DEST_PATH_IMAGE055
As variables, into formulas
Figure 857178DEST_PATH_IMAGE056
Producing cloud droplets
Figure 872539DEST_PATH_IMAGE049
；
d, repeating steps a to c until generatingNUntil the cloud drops, according toNAnd drawing a cloud model diagram by the individual cloud droplets.
6. The method of determining electrical distribution equipment condition repair time of claim 5, wherein: cloud and second sample devicefThe intersection points of the cloud pictures with the same scale areKDripping from the root of Yun, and takingKThe mean value of the membership value of each cloud droplet is used as the membership of the equipment state value, as shown in the formula,
Figure 842769DEST_PATH_IMAGE057
whereinf1,2,3,4, thenzMembership vector of stage sample equipment
Figure 10707DEST_PATH_IMAGE058
。
7. The method of determining electrical distribution equipment condition repair time of claim 1, wherein: the training algorithm of the LSTM neural network in the step 3 is a back propagation algorithm and is divided into three steps, firstly, the output value of the LSTM memory module is calculated forward by combining the weight matrix, secondly, the error item of each memory module is calculated backward, thirdly, the gradient of each weight matrix used in the first step is calculated according to the corresponding residual error item, and the weight matrix is updated.
8. The method of determining electrical distribution equipment condition repair time of claim 7, wherein: after the sample data of each sample device is input into the LSTM neural network for training, the model training is finished; or the model training is finished when the training error is set to be less than 1 e-06.
9. The method of determining electrical distribution equipment condition repair time of claim 7, wherein: forward computing output value of LSTM memory module, namely when next fault of sample equipment occursTrue value of (1) in (2)
Figure 509822DEST_PATH_IMAGE059
The calculation formula of (a) is as follows,
Figure 340374DEST_PATH_IMAGE060
，
Figure 458503DEST_PATH_IMAGE061
，
Figure 120429DEST_PATH_IMAGE062
，
Figure 915078DEST_PATH_IMAGE063
，
Figure 29665DEST_PATH_IMAGE064
，
Figure 13801DEST_PATH_IMAGE065
；
Figure 405599DEST_PATH_IMAGE066
in order to be a sigmoid function,
Figure 246516DEST_PATH_IMAGE067
is thattThe input matrix of the time of day,
Figure 474498DEST_PATH_IMAGE068
、
Figure 59063DEST_PATH_IMAGE069
、
Figure 305367DEST_PATH_IMAGE070
、
Figure 972978DEST_PATH_IMAGE071
representation and current input
Figure 62157DEST_PATH_IMAGE072
The weight matrix of the multiplication is used,
Figure 325779DEST_PATH_IMAGE073
、
Figure 754486DEST_PATH_IMAGE074
、
Figure 937206DEST_PATH_IMAGE075
、
Figure 139779DEST_PATH_IMAGE076
is shown andt-1 time output value
Figure 331726DEST_PATH_IMAGE077
The weight matrix of the multiplication is used,
Figure 287044DEST_PATH_IMAGE078
、
Figure 906244DEST_PATH_IMAGE079
、
Figure 907698DEST_PATH_IMAGE080
、
Figure 762391DEST_PATH_IMAGE081
respectively are the bias items of a forgetting gate, an input gate, a state unit and an output gate,
Figure 900111DEST_PATH_IMAGE082
、
Figure 893475DEST_PATH_IMAGE083
、
Figure 805061DEST_PATH_IMAGE084
respectively are the activation functions of a forgetting gate, an input gate and an output gate,
Figure 338811DEST_PATH_IMAGE085
、
Figure 268721DEST_PATH_IMAGE086
is a vector of state units and instantaneous states;
Figure 964144DEST_PATH_IMAGE087
the current output of the LSTM neural network is the real value of the next fault occurrence time of the sample device.
CN201911049328.1A 2019-10-31 2019-10-31 Method for determining state maintenance time of power distribution equipment Active CN110880062B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911049328.1A CN110880062B (en) 2019-10-31 2019-10-31 Method for determining state maintenance time of power distribution equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911049328.1A CN110880062B (en) 2019-10-31 2019-10-31 Method for determining state maintenance time of power distribution equipment

Publications (2)

Publication Number Publication Date
CN110880062A true CN110880062A (en) 2020-03-13
CN110880062B CN110880062B (en) 2022-07-08

Family

ID=69728229

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911049328.1A Active CN110880062B (en) 2019-10-31 2019-10-31 Method for determining state maintenance time of power distribution equipment

Country Status (1)

Country Link
CN (1) CN110880062B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111652395A (en) * 2020-06-12 2020-09-11 成都国铁电气设备有限公司 Health assessment method for high-speed railway contact network equipment
CN112884174A (en) * 2021-02-05 2021-06-01 上海市市政工程管理咨询有限公司 Daily maintenance information management method and system for road
CN113221441A (en) * 2020-12-24 2021-08-06 山东鲁能软件技术有限公司 Method and device for health assessment of power plant equipment
CN113408759A (en) * 2021-07-07 2021-09-17 大连理工大学 Method for preventive maintenance of distributed energy supply system equipment based on entropy theory
CN114970904A (en) * 2022-07-26 2022-08-30 中铁电气化勘测设计研究院有限公司 Digital adjustment method for contact network operation and maintenance resources based on defect processing
CN117571347A (en) * 2023-10-20 2024-02-20 河北白沙烟草有限责任公司 Equipment health state monitoring and evaluating method and device and electronic equipment

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103177186A (en) * 2013-03-21 2013-06-26 国家电网公司 Electric return circuit fault probability forecasting method
CN103279671A (en) * 2013-06-03 2013-09-04 南京大学 Urban water disaster risk prediction method based on RBF (radial basis function) neural network-cloud model
CN105590146A (en) * 2016-02-29 2016-05-18 上海带来科技有限公司 Power plant device intelligent prediction overhaul method and power plant device intelligent prediction overhaul system based on big data
CN106056218A (en) * 2016-05-11 2016-10-26 国电南瑞科技股份有限公司 Equipment monthly maintenance scheduling optimization method considering overload and transient stability constraint
CN106251042A (en) * 2016-07-19 2016-12-21 广西电网有限责任公司电力科学研究院 A kind of method that distribution transformer is carried out health state evaluation
CN206312210U (en) * 2016-08-11 2017-07-07 中国南方电网有限责任公司电网技术研究中心 State evaluation system of power distribution network equipment
CN106961349A (en) * 2017-02-20 2017-07-18 江苏大学 A kind of sensor fault identifying system and method based on data fusion
CN106997513A (en) * 2017-04-11 2017-08-01 广西电网有限责任公司电力科学研究院 The distribution net equipment state evaluation system analyzed based on big data
CN107769972A (en) * 2017-10-25 2018-03-06 武汉大学 A kind of power telecom network equipment fault Forecasting Methodology based on improved LSTM
CN108037378A (en) * 2017-10-26 2018-05-15 上海交通大学 Running state of transformer Forecasting Methodology and system based on long memory network in short-term
CN109490726A (en) * 2018-11-23 2019-03-19 广西电网有限责任公司南宁供电局 Electric power transformer insulated state evaluating method based on Clouds theory
CN109583520A (en) * 2018-12-27 2019-04-05 云南电网有限责任公司玉溪供电局 A kind of state evaluating method of cloud model and genetic algorithm optimization support vector machines
US20190138903A1 (en) * 2017-11-08 2019-05-09 International Business Machines Corporation Reducing the cost of n modular redundancy for neural networks
CN110070060A (en) * 2019-04-26 2019-07-30 天津开发区精诺瀚海数据科技有限公司 A kind of method for diagnosing faults of bearing apparatus
CN110210169A (en) * 2019-06-14 2019-09-06 中铁高新工业股份有限公司 A kind of shield machine failure prediction method based on LSTM
CN110264053A (en) * 2019-06-10 2019-09-20 广西电网有限责任公司电力科学研究院 A kind of distribution network reliability evaluation method for considering Strategies of Maintenance and failure rate being influenced
CN110348513A (en) * 2019-07-10 2019-10-18 北京华电天仁电力控制技术有限公司 A kind of Wind turbines failure prediction method based on deep learning

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103177186A (en) * 2013-03-21 2013-06-26 国家电网公司 Electric return circuit fault probability forecasting method
CN103279671A (en) * 2013-06-03 2013-09-04 南京大学 Urban water disaster risk prediction method based on RBF (radial basis function) neural network-cloud model
CN105590146A (en) * 2016-02-29 2016-05-18 上海带来科技有限公司 Power plant device intelligent prediction overhaul method and power plant device intelligent prediction overhaul system based on big data
CN106056218A (en) * 2016-05-11 2016-10-26 国电南瑞科技股份有限公司 Equipment monthly maintenance scheduling optimization method considering overload and transient stability constraint
CN106251042A (en) * 2016-07-19 2016-12-21 广西电网有限责任公司电力科学研究院 A kind of method that distribution transformer is carried out health state evaluation
CN206312210U (en) * 2016-08-11 2017-07-07 中国南方电网有限责任公司电网技术研究中心 State evaluation system of power distribution network equipment
CN106961349A (en) * 2017-02-20 2017-07-18 江苏大学 A kind of sensor fault identifying system and method based on data fusion
CN106997513A (en) * 2017-04-11 2017-08-01 广西电网有限责任公司电力科学研究院 The distribution net equipment state evaluation system analyzed based on big data
CN107769972A (en) * 2017-10-25 2018-03-06 武汉大学 A kind of power telecom network equipment fault Forecasting Methodology based on improved LSTM
CN108037378A (en) * 2017-10-26 2018-05-15 上海交通大学 Running state of transformer Forecasting Methodology and system based on long memory network in short-term
US20190138903A1 (en) * 2017-11-08 2019-05-09 International Business Machines Corporation Reducing the cost of n modular redundancy for neural networks
CN109490726A (en) * 2018-11-23 2019-03-19 广西电网有限责任公司南宁供电局 Electric power transformer insulated state evaluating method based on Clouds theory
CN109583520A (en) * 2018-12-27 2019-04-05 云南电网有限责任公司玉溪供电局 A kind of state evaluating method of cloud model and genetic algorithm optimization support vector machines
CN110070060A (en) * 2019-04-26 2019-07-30 天津开发区精诺瀚海数据科技有限公司 A kind of method for diagnosing faults of bearing apparatus
CN110264053A (en) * 2019-06-10 2019-09-20 广西电网有限责任公司电力科学研究院 A kind of distribution network reliability evaluation method for considering Strategies of Maintenance and failure rate being influenced
CN110210169A (en) * 2019-06-14 2019-09-06 中铁高新工业股份有限公司 A kind of shield machine failure prediction method based on LSTM
CN110348513A (en) * 2019-07-10 2019-10-18 北京华电天仁电力控制技术有限公司 A kind of Wind turbines failure prediction method based on deep learning

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
OUYANG JIANNA 等: "Modeling and Analysis of Microgrid Cluster Simulation Based on RTDS", 《2018 2ND IEEE CONFERENCE ON ENERGY INTERNET AND ENERGY SYSTEM INTEGRATION (EI2)》 *
WU LIFANG: "Study on the R TDS Simulation Platform of Parallel Injection Hybrid Active Power Filter", 《2018 2ND IEEE CONFERENCE ON ENERGY INTERNET AND ENERGY SYSTEM INTEGRATION (EI2)》 *
刘华新等: "基于融合理论的风电机组状态评价正态云模型", 《太阳能学报》 *
朱见伟 等: "基于云理论的变压器多重故障诊断及短期预测策略", 《电气技术》 *
梁朔 等: "基于风险评估的配电设备状态检修决策方法", 《电力系统及其自动化学报》 *
熊卫红等: "基于云理论及熵权法的变压器潜在故障风险评估方法", 《电力自动化设备》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111652395A (en) * 2020-06-12 2020-09-11 成都国铁电气设备有限公司 Health assessment method for high-speed railway contact network equipment
CN113221441A (en) * 2020-12-24 2021-08-06 山东鲁能软件技术有限公司 Method and device for health assessment of power plant equipment
CN113221441B (en) * 2020-12-24 2022-12-02 山东鲁能软件技术有限公司 Method and device for health assessment of power plant equipment
CN112884174A (en) * 2021-02-05 2021-06-01 上海市市政工程管理咨询有限公司 Daily maintenance information management method and system for road
CN113408759A (en) * 2021-07-07 2021-09-17 大连理工大学 Method for preventive maintenance of distributed energy supply system equipment based on entropy theory
CN114970904A (en) * 2022-07-26 2022-08-30 中铁电气化勘测设计研究院有限公司 Digital adjustment method for contact network operation and maintenance resources based on defect processing
CN114970904B (en) * 2022-07-26 2022-11-29 中铁电气化勘测设计研究院有限公司 Digital adjustment method for contact network operation and maintenance resources based on defect processing
CN117571347A (en) * 2023-10-20 2024-02-20 河北白沙烟草有限责任公司 Equipment health state monitoring and evaluating method and device and electronic equipment
CN117571347B (en) * 2023-10-20 2024-09-20 河北白沙烟草有限责任公司 Equipment health state monitoring and evaluating method and device and electronic equipment

Also Published As

Publication number Publication date
CN110880062B (en) 2022-07-08

Similar Documents

Publication Publication Date Title
CN110880062A (en) Method for determining state maintenance time of power distribution equipment
CN103413174B (en) Based on the short-term wind speed multistep forecasting method of degree of depth learning method
El-Keib et al. Application of artificial neural networks in voltage stability assessment
CN104951836A (en) Posting predication system based on nerual network technique
CN109242149A (en) A kind of student performance early warning method and system excavated based on educational data
CN107133695A (en) A kind of wind power forecasting method and system
CN108732528A (en) A kind of digitalized electrical energy meter method for diagnosing faults based on depth confidence network
CN104636801A (en) Transmission line audible noise prediction method based on BP neural network optimization
CN106022954A (en) Multiple BP neural network load prediction method based on grey correlation degree
Shan et al. Reliability analysis of power distribution network based on PSO-DBN
CN110059913A (en) A kind of quantitative estimation method counted and the power failure of future-state is planned
CN104133143A (en) Power grid line fault diagnosis system and method based on Hadoop cloud computing platform
Zhou et al. Transient stability assessment based on gated graph neural network with imbalanced data in Internet of Energy
CN116911459A (en) Multi-input multi-output ultra-short-term power load prediction method suitable for virtual power plant
Handoyo et al. The fuzzy inference system with rule bases generated by using the fuzzy C-means to predict regional minimum wage in Indonesia
Cui et al. Short-time series load forecasting by seq2seq-lstm model
Zhou et al. Statistics-based method for large-scale group decision-making with incomplete linguistic distribution fuzzy information: Incorporating reliability and entropy
Chen et al. Prediction of critical clearing time for transient stability based on ensemble extreme learning machine regression model
Yu et al. Research on the stochastic hybrid multi-attribute decision making method based on prospect theory
Zeng et al. HHA: An attentive prediction model for academic abnormality
CN104537416A (en) Fault diagnosis method based on HBF neural network observer
Selvi et al. Artificial neural network approach for on-line ATC estimation in deregulated power system
Changsheng et al. A Temporal Convolutional Knowledge Tracing Model Integrating Forgetting Factors and Item Response Theory
Zhang et al. Electricity price forecasting method based on quantum immune optimization BP neural network algorithm
Xu et al. Graduate enrollment prediction by an error back propagation algorithm based on the multi-experiential particle swarm optimization

Legal Events

Date Code Title Description
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