CN110533331A - A kind of fault early warning method and system based on transmission line of electricity data mining - Google Patents
A kind of fault early warning method and system based on transmission line of electricity data mining Download PDFInfo
- Publication number
- CN110533331A CN110533331A CN201910818412.9A CN201910818412A CN110533331A CN 110533331 A CN110533331 A CN 110533331A CN 201910818412 A CN201910818412 A CN 201910818412A CN 110533331 A CN110533331 A CN 110533331A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- data
- characteristic
- electricity
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 138
- 230000005611 electricity Effects 0.000 title claims abstract description 60
- 238000007418 data mining Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000007257 malfunction Effects 0.000 claims abstract description 68
- 230000007613 environmental effect Effects 0.000 claims abstract description 25
- 238000012706 support-vector machine Methods 0.000 claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 24
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000007726 management method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 239000011248 coating agent Substances 0.000 claims description 10
- 238000000576 coating method Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 208000025274 Lightning injury Diseases 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 7
- 241000607479 Yersinia pestis Species 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 238000013501 data transformation Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 13
- 230000008901 benefit Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 239000012212 insulator Substances 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000003915 air pollution Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 102000008297 Nuclear Matrix-Associated Proteins Human genes 0.000 description 1
- 108010035916 Nuclear Matrix-Associated Proteins Proteins 0.000 description 1
- 241001282153 Scopelogadus mizolepis Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036449 good health Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 210000000299 nuclear matrix Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000005201 scrubbing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000005619 thermoelectricity Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The present invention proposes a kind of fault early warning method based on transmission line of electricity data mining, comprising: acquisition transmission line malfunction characteristic, the transmission line malfunction characteristic includes electric characteristic data, mechanical characteristics data and environmental characteristic data;Obtain transmission line malfunction type;According to different transmission line malfunction types, electric characteristic data, mechanical characteristics data and environmental characteristic data are based on, the failure accumulated value of different transmission line malfunction types is obtained;The failure accumulated value size for comparing different transmission line malfunction types judges transmission line of electricity physical fault type, and application support vector machines assesses risk class, it is ensured that transmission line of electricity stable operation.
Description
Technical field
The invention belongs to technical field of electric power transmission, in particular to a kind of fault early warning method based on transmission line of electricity data mining
And system.
Background technique
Domestic not mature transmission line status on-line monitoring and fault pre-alarming scheme.It is realized using direct monitoring technology
The research of transmission line of electricity different faults reason identification still in its infancy, is not yet realized based on wideband voltage, current measurement
Malfunction quantitative analysis, monitoring technology.
Due to a variety of causes such as geographical conditions and history, between Chinese natural energy resources distribution and Regional Economic Development degree
There is imbalances, are especially embodied in power industry, and in order to eliminate this situation, China is since at the beginning of 21 century, active development
Western water power, thermoelectricity resource construct extensive north and south supply mutually, transferring electricity from the west to the east channel, establish the power networking system in the whole nation, enable
Source grown place and the relation between supply and demand on load output ground are balanced, and resource between nationwide especially eastern and western regions is realized
With the optimization supply and configuration of the energy, it is connected with each other via AC or DC transmission line of electricity, interregional partial electric grid is connected,
It gradually forms and passes through from east to west, indulge the power supply network of the big scale of construction alternating current-direct current mixed connection across north and south.
In order to reduce the use of the non-renewable resources such as coal, the renewable resources such as wind energy, solar energy are now by extensive benefit
With still, wind energy and solar energy are all unstable, introduce biggish harmonic wave to electric system.
Increasingly complex, the whole world has gradually formed an energy internet system now.Electric system becomes more
Complicated and fragile, any one equipment fault, line fault and human error all may cause multiple regions electric system die
Barrier brings tremendous influence for economy, production and living, needs a kind of method that can carry out early warning to transmission line malfunction.
Carry out the repair based on condition of component work premised on monitoring on-line at first in the U.S.;Japan comes into effect from the eighties in last century
Repair based on condition of component work based on state analysis and on-line monitoring;The many national adoption status analyses in Europe and on-line monitoring skill
Art improves the overhaul efficiency of electrical equipment;Research of the JPS company of Japan in terms of the monitoring control of transmission line of electricity, includes line
The monitoring of road fault location, weather environment monitoring, line temperature report, ground resistance measurement, wire tension, audible noise etc..
Summary of the invention
In view of the above-mentioned problems, the present invention proposes a kind of fault early warning method and system based on transmission line of electricity data mining.
The present invention proposes a kind of fault early warning method based on transmission line of electricity data mining, comprising:
Transmission line malfunction characteristic is acquired, the transmission line malfunction characteristic includes electric characteristic data, power
Learn characteristic and environmental characteristic data;
Obtain transmission line malfunction type;
According to different transmission line malfunction types, electric characteristic data, mechanical characteristics data and environmental characteristic data are based on,
Obtain the failure accumulated value of different transmission line malfunction types;
The failure accumulated value size for comparing different transmission line malfunction types, judges transmission line of electricity physical fault type.
Preferably, the failure accumulated value is obtained by following formula:
Wherein
In formula,
Y is the failure accumulated value of transmission line malfunction;
wijIndicate the weight of i-th of electric characteristic data or mechanical characteristics data under j fault type, wij∈ [1,10], xi
Indicate i-th of electric characteristic data or the mechanical characteristics data normalization factor, xi∈ (0,1), H indicate corrected parameter, wjkIndicate j
The weight of k-th of environmental characteristic data, w under fault typejk∈ [1,10].
Preferably, it using the transmission line malfunction characteristic Training Support Vector Machines, is closed based on the fault type
The fault signature data of connection, the risk class of the fault type is assessed based on support vector machines.
Preferably, the transmission line malfunction characteristic be taken from enterprise resource planning, transmission of electricity automated system,
Transmission line online monitoring system, information acquisition system, production management system, Meteorological Information System, transmission of electricity GIS-Geographic Information System,
Intelligent shared monitoring system of distribution transformer.
Preferably, the transmission line malfunction characteristic of acquisition is pre-processed, including data cleansing, data transformation,
Data integration and outliers are rejected, wherein are carried out using k-means clustering algorithm to the transmission line malfunction characteristic
Data cleansing.
Preferably, the convolutional neural networks include input layer, convolutional layer, active coating, pond layer and full articulamentum;
Input layer is used to receive pretreated transmission line malfunction characteristic, and to transmission line malfunction characteristic
It is normalized;
The convolutional layer transmission line malfunction characteristic after normalized for identification;
Active coating is used to carry out Nonlinear Processing to the transmission line malfunction characteristic after identification;
Pond layer extracts most representative data for screening to the data after Nonlinear Processing;
Full articulamentum is for being summarized and being exported to the data that pond layer extracts.
The invention also provides a kind of fault early warning systems based on transmission line of electricity data mining, including acquisition module, event
Hinder identification module and Risk-warning module;
Acquisition module includes electrical for acquiring transmission line malfunction characteristic, the transmission line malfunction characteristic
Characteristic, mechanical characteristics data and environmental characteristic data;
Acquisition module is also used to obtain transmission line malfunction type, and the fault type includes lightning stroke, icing, bird pest, dirt
Sudden strain of a muscle and mountain fire;
Fault identification module is used to be carried out according to the transmission line malfunction characteristic using convolutional neural networks algorithm
Fault type recognition;
Risk-warning module uses the transmission line malfunction characteristic Training Support Vector Machines, the support vector machines
Model is established using Radial basis kernel function, and is based on the associated fault signature data of the fault type, assesses the failure classes
The risk class of type.
Preferably, acquisition module is specifically used for online from enterprise resource planning, transmission of electricity automated system, transmission line of electricity
Monitoring system, information acquisition system, production management system, Meteorological Information System, transmission of electricity GIS-Geographic Information System and intelligent shared match
Change monitoring system acquires the transmission line malfunction characteristic.
Preferably, acquisition module includes pretreatment unit, and pretreatment unit includes data cleansing unit, data transformation list
Member, data integration unit and outliers culling unit, wherein data cleansing unit is used to use k-means clustering algorithm pair
The transmission line malfunction characteristic carries out data cleansing.
Preferably, fault identification module includes normalization unit, activation unit, pond unit and full connection unit;
Normalization unit is for being normalized pretreated transmission line malfunction characteristic;
Unit is activated to be used to carry out Nonlinear Processing to the transmission line malfunction characteristic after normalization;
Pond unit extracts most representative data for screening to the data after Nonlinear Processing;
Full connection unit is for being summarized and being exported to the data that pond layer extracts.
Fault early warning method based on transmission line of electricity data mining of the invention acquires transmission line malfunction characteristic,
Transmission line malfunction data are from enterprise resource planning, transmission of electricity automated system, transmission line online monitoring system, letter
Acquisition system, production management system etc. are ceased, failure is identified using convolutional neural networks algorithm, and applies support vector machines
Assess risk class, it is ensured that transmission line of electricity stable operation.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Pointed structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 shows the project entire block diagram of the fault early warning system based on transmission line of electricity data mining;
Fig. 2 shows the structures of the fault early warning method according to an embodiment of the present invention based on transmission line of electricity data mining to show
It is intended to;
Fig. 3 shows the structural schematic diagram of convolutional neural networks according to an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention clearly and completely illustrated, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 shows the project entire block diagram of the fault early warning system based on transmission line of electricity data mining, by high-precision
Sensor obtain transmission line of electricity electric characteristic data, the information of mechanical characteristics data and environmental characteristic data;By online
Monitoring system and the information transmission system, transfer data to backstage, first pass around data scrubbing, data transformation, data integration and
Outliers, which are rejected, obtains effective data.During convolutional neural networks algorithm is applied to data identification and classification, know
Other transmission line status, the limiting value obtained according to historical data base are then alarmed, and provide as reference more than this reference value
Fault type.
Transmission line malfunction type mainly includes lightning stroke, icing, bird pest, pollution flashover, mountain fire etc., and one is proposed in the present embodiment
Kind of fault early warning method, can accurate measurements go out transmission line malfunction type, for accurate measurements to fault type, need to acquire
Characteristic it is different, transmission line malfunction feature is as shown in table 1;
Table 1
As shown in Table 1, early warning is carried out to different faults and needs to acquire different data, in the present embodiment, main acquisition electricity
Gas characteristic, mechanical characteristics data and environmental characteristic data:
Electric characteristic data include transmission line of electricity attribute, lightning conducter data, transmission line insulator, insulator attribute and hang
Extension mode, shaft tower type, insulator attribute, route height off the ground, pollution prevention device installation data, fire equipment information;
Mechanical characteristics data include wire tension, conductor galloping amplitude, arc sag deviation, shaft tower slope, normal load;
Environmental characteristic data include meteorological data, geographic information data, periphery magnetic field and electric field, environmental resistivity, lightning stroke
Record, meteorological data, ice covering thickness, ambient wind velocity, icing failure logging, regional characteristic, vegetative coverage, season and time prevent
Bird equipment installation data, birds active behavior, route bird dodge record, industrial environment distribution, air pollution data, filthy ingredient point
Analysis, route dirt collection rate, route pollution flashover record, Vegetation condition, the distribution of circuit network massif, forest fire classes, mountain fire failure
Record.
Above-mentioned electric characteristic data, mechanical characteristics data and environmental characteristic data are collected in existing transmission line management system
System, Management System of Power Line include Enterprise Resources Plan (ERP) system, transmission of electricity automated system, transmission line of electricity on-line monitoring
System, information acquisition system, Meteorological Information System, production management system, transmission of electricity GIS-Geographic Information System and intelligent shared distribution transforming prison
Examining system, table 2 show the collectable data of part Management System of Power Line:
Table 2
Since above-mentioned electric characteristic data, mechanical characteristics data and environmental characteristic data are taken from not homologous ray, data knot
Structure is different, and partial data needs to pre-process data there are certain repetition and intersection, specifically includes data cleansing, number
It is rejected according to conversion, data integration and outliers.
Data cleansing: including the processing of data vacancy value, data outliers processing, the processing of Data duplication value.Data vacancy value
Processing is mainly rejected or is supplemented to some absent field missing in initial data in record missing and record;Data are different
The characteristics of constant value processing is according to initial data, the data excessive to deviation that establish relevant regulations are rejected or are replaced;Number
According to repetition values handle be according to data itself the characteristics of, duplicate data are rejected.
For example, establishing the voltage set U={ u of monitoring point1, u2, u3…uk…um, wherein m is target prison in transmission line of electricity
The total number of survey grid network monitoring point, ukFor the voltage of k-th of monitoring point of target monitoring network in the transmission line of electricity, by acquisition
Monitoring point voltage value is put into set, if Or ukFor null value or there are two identical uk, then u is rejectedk。
Data transformation: original data are converted to be easy to analyze and apply form, main contents include latent structure,
Data staging and data quantization etc. such as quantify the hierarchical analysis of location information, put into operation time construction feature attribute, weather data
Deng.By taking monthly mean temperature as an example, the monthly mean temperature of the prefecture-level city focuses primarily upon the 6-9 month month higher than 30 DEG C according to statistics,
Monthly mean temperature is focusing primarily upon the 3-5 month, the 10-11 month 20 DEG C -30 DEG C of month;The moon of the monthly mean temperature at 10 DEG C -20 DEG C
Part focuses primarily upon the 1-2 month, December, therefore monthly mean temperature can be divided into 3 grades;The result analyzed from data is it is found that transmission of electricity
The fault condition of route and environment temperature are closely related, and at all seasons in be time to time change.
Data integration: data statistics is carried out, data are merged into some unified database, transmission line malfunction risk
Data needed for early warning are from different Management System of Power Line, it is therefore desirable to and conjunction for statistical analysis to initial data
And.
Outliers are rejected: by may also contain abnormal sample in aforementioned pretreated initial data, with same number
Widely different according to the most data of concentration, this data are referred to as outliers, can be used it is based on statistics, based on neighbouring
Value or the method based on cluster, are identified and are rejected, finally obtain valid data.
The data of acquisition are cleaned using k-means clustering algorithm in the present embodiment, K-means clustering algorithm is one
Simple, the efficient clustering algorithm of kind.It is that data set is divided in groups, each other with the object in cluster according to the similitude of data
Similar, the object in different clusters is different.Use cluster ciCentroid (mean value for distributing to the object of the cluster) represent the cluster, cluster ci's
Quality can use (the cluster c that is deteriorated in clusteriIn error between all objects and centroid ci quadratic sum) measurement, be defined as
In formula, E indicates the error sum of squares of all data records, and p represents data record, dist (p, ci) indicate object p
∈ciC is represented with the clusteriDifference.Assuming that the nearest center for arriving object p is cp, cpBe assigned to cpAverage distance between object
lcp, define ratio and outliers judged according to ratio R and are rejected.
5 kinds of fault types, respectively lightning stroke, icing, bird pest, pollution flashover and mountain fire are set.
Referring to Fig. 3, convolutional neural networks are made of input layer, convolutional layer, active coating, pond layer and full articulamentum.
Convolutional neural networks need learning training, therefore initially set up the sample set for training convolutional neural networks, obtain
Training data is taken, the training data used is power transmission line electrical characteristic, mechanical characteristics data and environmental characteristic data
Data are operated normally, the historical data of certain period of time is read from multiple Management System of Power Line, is then gone through in all
Training data of the good health data of operating status as building convolutional neural networks is screened in history data;And for different
Fault type makes different sample object values.
Training data imported into deep learning program and is trained by the frame for building convolutional neural networks (CNN), leads to
The adjustment to training parameter is crossed, training process is completed.
Specifically, convolutional neural networks training process is to update power to transmitting, then back transfer error before first passing through first
Value parameter, so that training error reaches minimum;Forward direction transmitting is exactly that training data is input to input layer, is handled through input layer
Sequence is handled through convolutional layer, active coating, pond layer and full articulamentum again afterwards, final output, that is, connection is calculated
Connection weight between each neuron, back transfer error are exactly to calculate output error, root to the output result of transmitting according to preceding
According to output error back transfer, error distribution is given to all units of each layer, so that the error signal of all units of each layer is obtained, into
And correct the weight of each unit.
Trained convolutional neural networks are subjected to fault identification to transmission line of electricity, recognition result is provided, obtains failure classes
Type.
Each layer of convolutional neural networks is illustrated below.
Input layer
Input layer (Input Layer) receives pretreated data, and data are normalized, due to each number
According to influence degree and its value range have substantial connection, so all data are normalized as the following formula,
For the data after normalization, x is the data of acquisition, xmaxAnd xminThe respectively maximum value and minimum value of data.
Convolutional layer
The data of input layer can be transmitted to a series of convolution algorithms by convolutional network, and convolution algorithm is similar to the mistake of filtering
Journey is slided in data using predefined convolution kernel, the part that convolution kernel slides into is multiplied with former data,
Overall to be added again, the result of addition will form a new matrix, thus realize feature extraction, the calculation formula of convolutional layer
It is as follows:
In formula, l indicates the number of levels of this layer network,L j-th of characteristic pattern of layer is represented, m is one of input feature vector figure
Set, bjFor the corresponding bias term of feature each in convolutional layer, xj-1Indicate one layer of output, xjIndicate the defeated of current layer
Out.
Active coating
The feature that active coating (Activation Layer) is responsible for extracting convolutional layer activates, since convolution operation is
The linear changing relation differed by input matrix with convolution nuclear matrix needs active coating to carry out nonlinear mapping to it.
Active coating is mainly made of activation primitive, i.e. nested nonlinear function on the basis of convolutional layer exports result, allows output
Characteristic pattern have non-linear relation, non-linear transform function is usually sigmoid function, function expression are as follows:
Pond layer
Pond layer is also known as down-sampled layer (Downsampling Layer), and the effect of pond layer is to the spy in receptive field
Sign is screened, and most representative feature in region is extracted, and can be effectively reduced output characteristic dimension, and then reduce model
Required parameter amount;Mean value pond is used in the present embodiment, input, output and pond matrix dimensionality meet m=n/k.It can
Feature extraction is carried out again, shown in the following formula of neuron calculation method:
Wherein
In formula, k is pond matrix dimensionality.
Full articulamentum
Full articulamentum is responsible for summarizing the feature that convolutional neural networks study is extracted and result exports, by multidimensional
Feature input is mapped as two-dimensional feature output, and higher-dimension indicates that sample batch, low-dimensional usually correspond to task object, and full articulamentum is defeated
Function out are as follows:
Wherein
In formula, y is the failure accumulated value of transmission line malfunction, wijIndicate j fault type under i-th of electric characteristic data or
The weight of mechanical characteristics data, wij∈ [1,10], xiIndicate i-th of electric characteristic data or mechanical characteristics data normalization because
Son, xi∈ (0,1), H indicate corrected parameter, wjkIndicate the weight of k-th of environmental characteristic data under j fault type, wjk∈ [1,
10].X indicate f () argument of function, it is exemplary such as:
It, will be under different faults type based on collected electric characteristic data, mechanical characteristics data and environmental characteristic data
All fault signature data being related to, which are put into above-mentioned formula, to be calculated, and obtains the y value of each fault type, and acquisition one is maximum
Y value, the corresponding fault type of maximum y value are the failure that transmission line of electricity actually occurs at this time.
Illustratively, the y value that fault type is lightning stroke is calculated, j=1, the electric characteristic data of acquisition include lightning conducter number
According to, i=1, mechanical characteristics data include wire tension, i=2, and environmental characteristic data include environmental resistivity, k=1, at this time y=
f[Hw11f(w11x1+w21x2)], enabling the y value being calculated is y1;
The y value that fault type is icing is calculated, j=2, the electric characteristic data of acquisition include transmission line insulator, i=
1, mechanical characteristics data packet parantheses hangs down deviation, i=2, and environmental characteristic data include ambient wind velocity, k=1, at this time y=f [Hw21f
(w12x1+w22x2)], enabling the y value being calculated is y2;
The y value that fault type is bird pest is calculated, j=3, the electric characteristic data of acquisition include fringing field data, i=1,
Environmental characteristic data include birds active behavior, k=1, at this time y=f [Hw31f(w13x1)], enabling the y value being calculated is y3;
The y value that fault type is bird pest is calculated, j=4, the electric characteristic data of acquisition include insulator attribute, i=1, ring
Border characteristic includes that industrial environment is distributed, k=1, air pollution data, k=2, at this time y=f [(Hw41+Hw42)f
(w14x1)], enabling the y value being calculated is y4;
The y value that fault type is mountain fire is calculated, j=5, the electric characteristic data of acquisition include route height off the ground, i=1,
Environmental characteristic data include Vegetation condition, k=1, the distribution of circuit network massif, k=2, at this time y=f [(Hw51+Hw52)f
(w15x1)], enabling the y value being calculated is y5;
Y1, y2, y3, y4 and y5 are compared, obtain y1 maximum, then the fault type of transmission line of electricity is lightning stroke at this time.
After convolutional neural networks identify the failure of transmission line of electricity, needs to calculate out of order risk class, provide early warning
As a result, carrying out transmission line of electricity Risk-warning based on RBF-SVM in the present embodiment, specifically the related data for calculating the failure is mentioned
It takes out, is input in RBF-SVM model, situation is exported according to RBF-SVM, it is determined whether issue early warning.
Support vector machines (SVM) is that the technology of Classification and Identification is used in data mining, and a support vector machines constructs one
Hyperplane or higher dimensional space, for classifying, returning or other tasks.The training that one good separating resulting passes through what class of leaving one's post
The hyperplane of the nearest maximum distance of data point (i.e. function surplus) realizes that, because surplus is bigger, the extensive error of classifier is smaller.
For the present embodiment using the support vector machines for being based on Radial basis kernel function (RBF), Radial basis kernel function is multilayer
Feed forward type network provides a kind of effective means for machine learning, has more good generalization ability, also has and calculate error
The advantages that small, convergence is rapidly, there is no local minimum points
Radial basis kernel function
Regression function based on Radial basis kernel function construction are as follows:
Transmission line of electricity risk class is divided into normal, average risk and serious risk three grades, root in the present embodiment
According to the SVM prediction transmission line malfunction risk class after training.
The sample set for Training Support Vector Machines is initially set up, and for normal, average risk and serious risk three
Grade carries out Characteristic Extraction;Characteristic quantity includes transmission line of electricity attribute, meteorological data, geographic information data, environmental resistivity, week
Side magnetic field and electric field, lightning conducter data, geographical coordinate etc..
Part sample data is randomly selected as training data, using remaining sample data as examination sample data.
The characteristic quantity of extraction is normalized, and by after normalized characteristic quantity construct the input space to
Amount.
Using input space vector as input, corresponding three risk class of input space vector result as export,
It establishes RBF-SVM disaggregated model and RBF-SVM disaggregated model is trained according to training sample data.
The RBF-SVM disaggregated model after training is evaluated and verified according to sample data is screened, if evaluation and verifying
Result precision it is high, and obtain expected effect, then can be using this model as failure risk grade separation model, if to evaluation
It is dissatisfied with the model after verifying, then it can reselect sample or increase sample size and adjustment relevant parameter etc. and re-start
The building and training of model.
Finally, the event that convolutional neural networks identify will be passed through after obtaining trained RBF-SVM disaggregated model
RBF-SVM disaggregated model after the correlated characteristic amount input training of barrier, obtains risk class.
Fault early warning system based on transmission line of electricity data mining of the invention, including acquisition module, fault identification module
With Risk-warning module;
Acquisition module is for acquiring transmission line malfunction influence factor data;
Fault identification module is used for according to the transmission line malfunction influence factor data, using convolutional neural networks algorithm
Carry out fault type recognition;
Risk-warning module uses the transmission line malfunction influence factor data Training Support Vector Machines, is based on failure institute
The associated failure influence factor data of fault type are stated, the risk class of the fault type is assessed.
Acquisition module is specifically used for from enterprise resource planning, transmission of electricity automated system, transmission line of electricity on-line monitoring system
System, information acquisition system, production management system, Meteorological Information System, transmission of electricity GIS-Geographic Information System and intelligent shared distribution transformer monitoring
Transmission line malfunction influence factor data described in system acquisition.
Acquisition module includes pretreatment unit, and pretreatment unit includes data cleansing unit, data conversion unit, data set
At unit and outliers culling unit, wherein data cleansing unit is used for using k-means clustering algorithm to the power transmission line
Road failure influence factor data carry out data cleansing.
Fault identification module includes normalization unit, activation unit, pond unit and full connection unit;
Normalization unit is for being normalized pretreated transmission line malfunction influence factor data;
Unit is activated to be used to carry out Nonlinear Processing to the transmission line malfunction influence factor data after normalization;
Pond unit extracts most representative data for screening to the data after Nonlinear Processing;
Full connection unit is for being summarized and being exported to the data that pond layer extracts.
Although the present invention is described in detail referring to the foregoing embodiments, those skilled in the art should manage
Solution: it is still possible to modify the technical solutions described in the foregoing embodiments, or to part of technical characteristic into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The spirit and scope of scheme.
Claims (10)
1. a kind of fault early warning method based on transmission line of electricity data mining characterized by comprising
Transmission line malfunction characteristic is acquired, the transmission line malfunction characteristic includes electric characteristic data, mechanics spy
Levy data and environmental characteristic data;
Obtain transmission line malfunction type;
According to different transmission line malfunction types, electric characteristic data, mechanical characteristics data and environmental characteristic data are based on, are obtained
The failure accumulated value of different transmission line malfunction types;
The failure accumulated value size for comparing different transmission line malfunction types, judges transmission line of electricity physical fault type.
2. the fault early warning method according to claim 1 based on transmission line of electricity data mining, which is characterized in that by with
Lower formula obtains the failure accumulated value:
Wherein
In formula,
Y is the failure accumulated value of transmission line malfunction;
wijIndicate the weight of i-th of electric characteristic data or mechanical characteristics data under j fault type, wij∈ [1,10];
xiIndicate i-th of electric characteristic data or the mechanical characteristics data normalization factor, xi∈ (0,1);
H indicates corrected parameter;
wjkIndicate the weight of k-th of environmental characteristic data under j fault type, wjk∈ [1,10].
3. the fault early warning method according to claim 1 based on transmission line of electricity data mining, which is characterized in that use institute
Transmission line malfunction characteristic Training Support Vector Machines are stated, the associated fault signature data of the fault type is based on, is based on
Support vector machines assesses the risk class of the fault type.
4. the fault early warning method according to claim 1 based on transmission line of electricity data mining, which is characterized in that described defeated
Line fault characteristic be taken from enterprise resource planning, transmission of electricity automated system, transmission line online monitoring system,
Information acquisition system, production management system, Meteorological Information System, transmission of electricity GIS-Geographic Information System and intelligent shared distribution transformer monitoring system
System.
5. the fault early warning method according to claim 1 based on transmission line of electricity data mining, which is characterized in that acquisition
Transmission line malfunction characteristic pre-processed, including data cleansing, data transformation, data integration and outliers are picked
It removes, wherein data cleansing is carried out to the transmission line malfunction characteristic using k-means clustering algorithm.
6. the fault early warning method according to claim 5 based on transmission line of electricity data mining, which is characterized in that the volume
Product neural network includes input layer, convolutional layer, active coating, pond layer and full articulamentum;
Input layer returns transmission line malfunction characteristic for transmission line malfunction characteristic after reception pretreatment
One change processing;
The convolutional layer transmission line malfunction characteristic after normalized for identification;
Active coating is used to carry out Nonlinear Processing to the transmission line malfunction characteristic after identification;
Pond layer extracts most representative data for screening to the data after Nonlinear Processing;
Full articulamentum is for being summarized and being exported to the data that pond layer extracts.
7. a kind of fault early warning system based on transmission line of electricity data mining, which is characterized in that including acquisition module, fault identification
Module and Risk-warning module;
For acquisition module for acquiring transmission line malfunction characteristic, the transmission line malfunction characteristic includes electric characteristic
Data, mechanical characteristics data and environmental characteristic data;
Acquisition module is also used to obtain transmission line malfunction type, the fault type include lightning stroke, icing, bird pest, pollution flashover and
Mountain fire;
Fault identification module is used for according to the transmission line malfunction characteristic, carries out failure using convolutional neural networks algorithm
Type identification;
Risk-warning module uses the transmission line malfunction characteristic Training Support Vector Machines, and the support vector machines uses
Radial basis kernel function establishes model, and is based on the associated fault signature data of the fault type, assesses the fault type
Risk class.
8. the fault early warning system according to claim 7 based on transmission line of electricity data mining, which is characterized in that acquisition mould
Block is specifically used for from enterprise resource planning, transmission of electricity automated system, transmission line online monitoring system, information collection system
System, production management system, Meteorological Information System, transmission of electricity GIS-Geographic Information System and the acquisition of intelligent shared monitoring system of distribution transformer are described defeated
Line fault characteristic.
9. the fault early warning system according to claim 7 based on transmission line of electricity data mining, which is characterized in that acquisition mould
Block includes pretreatment unit, and pretreatment unit includes data cleansing unit, data conversion unit, data integration unit and the sample that peels off
This culling unit, wherein data cleansing unit is used for using k-means clustering algorithm to the transmission line malfunction characteristic
Carry out data cleansing.
10. the fault early warning system according to claim 9 based on transmission line of electricity data mining, which is characterized in that failure
Identification module includes normalization unit, activation unit, pond unit and full connection unit;
Normalization unit is for being normalized pretreated transmission line malfunction characteristic;
Unit is activated to be used to carry out Nonlinear Processing to the transmission line malfunction characteristic after normalized;
Pond unit extracts most representative data for screening to the data after Nonlinear Processing;
Full connection unit is for being summarized and being exported to the data that pond layer extracts.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910818412.9A CN110533331B (en) | 2019-08-30 | 2019-08-30 | Fault early warning method and system based on transmission line data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910818412.9A CN110533331B (en) | 2019-08-30 | 2019-08-30 | Fault early warning method and system based on transmission line data mining |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110533331A true CN110533331A (en) | 2019-12-03 |
CN110533331B CN110533331B (en) | 2024-03-15 |
Family
ID=68666025
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910818412.9A Active CN110533331B (en) | 2019-08-30 | 2019-08-30 | Fault early warning method and system based on transmission line data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110533331B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111144447A (en) * | 2019-12-09 | 2020-05-12 | 国网新疆电力有限公司电力科学研究院 | Power grid peak-valley time interval division method for preventing peak regulation risk caused by new energy output |
CN112232370A (en) * | 2020-09-16 | 2021-01-15 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Fault analysis and prediction method for engine |
CN112417763A (en) * | 2020-11-25 | 2021-02-26 | 杭州凯达电力建设有限公司 | Defect diagnosis method, device and equipment for power transmission line and storage medium |
CN112508429A (en) * | 2020-12-16 | 2021-03-16 | 常州大学 | Fault diagnosis method for cathode protection system of buried pipeline based on convolutional neural network |
CN113033889A (en) * | 2021-03-19 | 2021-06-25 | 国网河北省电力有限公司邢台供电分公司 | High-voltage transmission line fault prediction method and device and terminal equipment |
CN113205487A (en) * | 2021-04-12 | 2021-08-03 | 武汉大学 | Cable state detection method based on residual error network fusion heterogeneous data |
CN113538371A (en) * | 2021-07-14 | 2021-10-22 | 贵州电网有限责任公司 | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering |
CN115061009A (en) * | 2022-06-01 | 2022-09-16 | 国网浙江省电力有限公司嘉兴供电公司 | Power transmission line fault analysis and early warning method |
CN117633479A (en) * | 2024-01-26 | 2024-03-01 | 国网湖北省电力有限公司 | Method and system for analyzing and processing faults of charging piles |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105974270A (en) * | 2016-07-22 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Power transmission line fault type diagnosis method and system |
CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
CN108133225A (en) * | 2017-10-23 | 2018-06-08 | 南京南瑞集团公司 | A kind of icing flashover fault early warning method based on support vector machines |
CN108959732A (en) * | 2018-06-15 | 2018-12-07 | 西安科技大学 | A kind of transmission line malfunction kind identification method based on convolutional neural networks |
CN109188198A (en) * | 2018-08-30 | 2019-01-11 | 武汉大学 | A kind of fault data matching process based on convolutional neural networks |
CN109270407A (en) * | 2018-11-16 | 2019-01-25 | 国网山东省电力公司电力科学研究院 | Extra high voltage direct current transmission line failure cause discrimination method based on Multi-source Information Fusion |
US20190094286A1 (en) * | 2017-09-26 | 2019-03-28 | Siemens Aktiengesellschaft | Method and apparatus for automatic localization of a fault |
CN109739209A (en) * | 2018-12-11 | 2019-05-10 | 深圳供电局有限公司 | A kind of electric network failure diagnosis method based on Classification Data Mining |
-
2019
- 2019-08-30 CN CN201910818412.9A patent/CN110533331B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105974270A (en) * | 2016-07-22 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Power transmission line fault type diagnosis method and system |
CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
US20190094286A1 (en) * | 2017-09-26 | 2019-03-28 | Siemens Aktiengesellschaft | Method and apparatus for automatic localization of a fault |
CN108133225A (en) * | 2017-10-23 | 2018-06-08 | 南京南瑞集团公司 | A kind of icing flashover fault early warning method based on support vector machines |
CN108959732A (en) * | 2018-06-15 | 2018-12-07 | 西安科技大学 | A kind of transmission line malfunction kind identification method based on convolutional neural networks |
CN109188198A (en) * | 2018-08-30 | 2019-01-11 | 武汉大学 | A kind of fault data matching process based on convolutional neural networks |
CN109270407A (en) * | 2018-11-16 | 2019-01-25 | 国网山东省电力公司电力科学研究院 | Extra high voltage direct current transmission line failure cause discrimination method based on Multi-source Information Fusion |
CN109739209A (en) * | 2018-12-11 | 2019-05-10 | 深圳供电局有限公司 | A kind of electric network failure diagnosis method based on Classification Data Mining |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111144447B (en) * | 2019-12-09 | 2022-05-31 | 国网新疆电力有限公司电力科学研究院 | Power grid peak-valley time interval division method for preventing peak regulation risk caused by new energy output |
CN111144447A (en) * | 2019-12-09 | 2020-05-12 | 国网新疆电力有限公司电力科学研究院 | Power grid peak-valley time interval division method for preventing peak regulation risk caused by new energy output |
CN112232370A (en) * | 2020-09-16 | 2021-01-15 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Fault analysis and prediction method for engine |
CN112417763A (en) * | 2020-11-25 | 2021-02-26 | 杭州凯达电力建设有限公司 | Defect diagnosis method, device and equipment for power transmission line and storage medium |
CN112508429A (en) * | 2020-12-16 | 2021-03-16 | 常州大学 | Fault diagnosis method for cathode protection system of buried pipeline based on convolutional neural network |
CN113033889A (en) * | 2021-03-19 | 2021-06-25 | 国网河北省电力有限公司邢台供电分公司 | High-voltage transmission line fault prediction method and device and terminal equipment |
CN113205487A (en) * | 2021-04-12 | 2021-08-03 | 武汉大学 | Cable state detection method based on residual error network fusion heterogeneous data |
CN113538371A (en) * | 2021-07-14 | 2021-10-22 | 贵州电网有限责任公司 | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering |
CN113538371B (en) * | 2021-07-14 | 2022-05-17 | 贵州电网有限责任公司 | Power distribution network overhead line icing thickness monitoring method for improving K-means clustering |
CN115061009A (en) * | 2022-06-01 | 2022-09-16 | 国网浙江省电力有限公司嘉兴供电公司 | Power transmission line fault analysis and early warning method |
CN115061009B (en) * | 2022-06-01 | 2024-05-31 | 国网浙江省电力有限公司嘉兴供电公司 | Power transmission line fault analysis and early warning method |
CN117633479A (en) * | 2024-01-26 | 2024-03-01 | 国网湖北省电力有限公司 | Method and system for analyzing and processing faults of charging piles |
CN117633479B (en) * | 2024-01-26 | 2024-04-09 | 国网湖北省电力有限公司 | Method and system for analyzing and processing faults of charging piles |
Also Published As
Publication number | Publication date |
---|---|
CN110533331B (en) | 2024-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110533331A (en) | A kind of fault early warning method and system based on transmission line of electricity data mining | |
Kezunovic et al. | Big data analytics for future electricity grids | |
CN109871976A (en) | A kind of prediction technique of power quality containing distributed power distribution network based on cluster and neural network | |
CN112749904B (en) | Power distribution network fault risk early warning method and system based on deep learning | |
CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
CN102934312B (en) | Energy production system and control thereof | |
CN113962659A (en) | Cloud computing-based smart power grid big data information management system and method | |
CN106017551A (en) | Intelligent transmission line integrated monitoring analysis and early warning method | |
CN106777984A (en) | A kind of method that photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm | |
CN106817708B (en) | A kind of inspection cluster construction method and device | |
Eseye et al. | Short-term wind power forecasting using a double-stage hierarchical hybrid GA-ANN approach | |
Kankanala et al. | Regression models for outages due to wind and lightning on overhead distribution feeders | |
Xie et al. | Short-term power load forecasting model based on fuzzy neural network using improved decision tree | |
CN113220751A (en) | Metering system and evaluation method for multi-source data state quantity | |
CN206620100U (en) | A kind of monitoring system of photovoltaic plant | |
Ju et al. | The use of edge computing-based internet of things big data in the design of power intelligent management and control platform | |
CN113313289B (en) | Power grid weather early warning system based on multiple data sources | |
CN108876144A (en) | A kind of pre- site selecting method of substation based on deep learning algorithm | |
CN112016739A (en) | Fault detection method and device, electronic equipment and storage medium | |
Hu et al. | Operational reliability evaluation method based on big data technology | |
CN108038518A (en) | A kind of photovoltaic generation power based on meteorological data determines method and system | |
Vargas et al. | Methodology for microgrid/smart farm systems: Case of study applied to indigenous mapuche communities | |
CN105958474A (en) | Power transmission line dynamic capacity increasing method and system used for power grid regulation and control system | |
Luo et al. | Loss-of-load state identification using self-organizing map | |
KR102422807B1 (en) | Renewable Energy Fusion Type Smart Farm Integrated Management System |
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 |