CN106779505B - Power transmission line fault early warning method and system based on big data driving - Google Patents
Power transmission line fault early warning method and system based on big data driving Download PDFInfo
- Publication number
- CN106779505B CN106779505B CN201710111397.5A CN201710111397A CN106779505B CN 106779505 B CN106779505 B CN 106779505B CN 201710111397 A CN201710111397 A CN 201710111397A CN 106779505 B CN106779505 B CN 106779505B
- Authority
- CN
- China
- Prior art keywords
- fault
- early warning
- time sequence
- transmission line
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000005065 mining Methods 0.000 claims abstract description 63
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 44
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims description 18
- 238000003745 diagnosis Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000013213 extrapolation Methods 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims 2
- 208000025274 Lightning injury Diseases 0.000 description 27
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 13
- 238000012360 testing method Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- General Engineering & Computer Science (AREA)
- Water Supply & Treatment (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a transmission line fault early warning method and system based on big data driving. Collecting relevant information of a power transmission line, wherein the relevant information of the power transmission line comprises electric quantity, meteorological data, fault event sequence information and power grid topological data; extracting the characteristics of the relevant information of the power transmission line, and further constructing a fault factor mining database and a fault distinguishing characteristic database; performing fault factor index mining on data in a current fault factor mining database based on a naive Bayesian algorithm, and further performing abnormal state tracking on abnormal fault factors; and transmitting the fault factor index of the abnormal fault factor to a fault discrimination feature library, matching the early warning information time sequence generated in real time in the fault discrimination feature library with a preset fault standard time sequence based on a time sequence similarity fault matching method, outputting early warning information corresponding to the matched early warning information time sequence, and performing fault early warning.
Description
Technical Field
The invention belongs to the field of intelligent power utilization, and particularly relates to a transmission line fault early warning method and system based on big data driving.
Background
With the development of social economy, the dependence on electric power is stronger and stronger, and large-scale power failure accidents often begin from the fault of a certain line of a power grid and are continuously expanded along with the strong relevance of power grid topology and the existing fragile links. For some areas where the power grid is weak, a single line fault may result in a loss of load.
At present, aiming at the related research of the transmission line faults, most achievements only rely on the existing data to diagnose the faults, and in fact, the problems of single uploaded data, large quantity, poor comprehensiveness and the like exist in an electric power system, so that comprehensiveness and predictability of fault prediction are difficult to realize by means of the data, information response timeliness is poor, and the work of tracking and predicting development trends of abnormal conditions of a line is difficult to perform. Under the premise of not improving the electricity price transfer economic pressure, advanced intelligent technology is urgently needed to be applied to early warning the transmission line fault, differentiation operation and maintenance are carried out, the line fault occurrence probability is reduced, and the improvement of the power supply reliability is facilitated.
Disclosure of Invention
In order to solve the problem of remote fault early warning of the power transmission line, the invention provides a power transmission line fault early warning method based on big data driving.
The invention discloses a big data drive-based power transmission line fault early warning method, which comprises the following steps:
collecting relevant information of the power transmission line, wherein the relevant information of the power transmission line comprises electric quantity, meteorological data, fault event sequence information and power grid topological data;
extracting the characteristics of the relevant information of the power transmission line, and further constructing a fault factor mining database and a fault distinguishing characteristic database;
performing fault factor index mining on data in a current fault factor mining database based on a naive Bayesian algorithm, and further performing abnormal state tracking on abnormal fault factors;
and transmitting the fault factor index of the abnormal fault factor to a fault discrimination feature library, matching the early warning information time sequence generated in real time in the fault discrimination feature library with a preset fault standard time sequence based on a time sequence similarity fault matching method, outputting early warning information corresponding to the matched early warning information time sequence, and performing fault early warning.
The electric quantity of the invention refers to the voltage and current of the transmission line and the resistance information on the transmission line.
The fault event sequence information of the invention refers to the time sequence information of the fault events of the power transmission line.
The fault factors of the present invention are target classes, such as: meteorological data factors or transmission line equipment factors; the fault factor index is a numerical value of the predicted occurrence of the target class.
Further, the invention constructs a fault factor mining database and a fault discrimination feature database based on the extracted features by a naive Bayes algorithm and a time series similarity fault matching algorithm respectively.
Aiming at the problems existing in the development of remote fault diagnosis of the power transmission line, the invention provides a solution scheme which comprises the following steps: the method comprises the steps of fully utilizing a big data technology to process existing massive data, mining the data by adopting a naive Bayesian algorithm to predict a fault factor index, then combining collectable electric quantity, meteorological data, fault event sequence information and power grid topological data, realizing fault early warning on a power transmission line by a fault matching algorithm based on time sequence similarity, and pushing early warning information to assist scheduling and operation and maintenance, making a solution in advance, rapidly processing faults and accelerating power grid recovery.
Further, the method further comprises: and pushing the early warning information to a power transmission line operation and maintenance server, determining a fault factor and a fault judgment characteristic of the early warning information, and feeding back the fault factor and the fault judgment characteristic to a fault factor mining database and a fault judgment characteristic database respectively to improve the fault early warning accuracy in a closed-loop feedback mode.
Further, the method further comprises: and displaying the output early warning information in various forms, namely displaying the fault characteristic analysis, and uniformly displaying the fault reason, the fault position and the diagnosis result. Therefore, the output early warning information can be checked more intuitively.
Further, the process of matching the early warning information time sequence generated in real time in the fault discrimination feature library with the fault standard time sequence based on the time sequence similarity fault matching method comprises the following steps:
and solving the similarity between the early warning information time sequence and the fault standard time sequence, comparing the similarity with a preset similarity threshold, and outputting early warning information corresponding to the early warning information time sequence which is greater than or equal to the preset similarity threshold.
According to the invention, the similarity between the early warning information time sequence and the fault standard time sequence is compared with the preset similarity threshold, so that the early warning information can be accurately and quickly acquired.
Further, the similarity between the early warning information time sequence and the standard time sequence is measured by calculating the edit distance between the early warning information time sequence and the standard time sequence.
Wherein the difference between the recognition result and the standard answer is judged using the edit distance. Different errors may reflect problems with the identification system.
The invention also provides a transmission line fault early warning system based on big data driving.
The invention relates to a big data drive-based power transmission line fault early warning system, which comprises:
the data acquisition module is used for acquiring relevant information of the power transmission line, wherein the relevant information of the power transmission line comprises electric quantity, meteorological data, fault event sequence information and power grid topological data;
the fault judgment index system building module is used for extracting the characteristics of the related information of the power transmission line so as to build a fault factor mining database and a fault judgment characteristic database;
the fault factor index mining module is used for mining the fault factor index of the data in the current fault factor mining database based on a naive Bayesian algorithm so as to track the abnormal state of the abnormal fault factor; the fault factor is a target class, and the fault factor index is a numerical value of the target class predicted occurrence;
and the fault early warning output module is used for transmitting the fault factor index to the fault discrimination feature library, matching an early warning information time sequence generated in the fault discrimination feature library in real time with a preset fault standard time sequence based on a time sequence similarity fault matching method, outputting early warning information corresponding to the matched early warning information time sequence and carrying out fault early warning.
In the fault discrimination index system construction module, a fault factor mining database and a fault discrimination feature database are constructed on the basis of extracted features by a naive Bayes algorithm and a time series similarity fault matching algorithm respectively.
Further, the system further comprises: and the early warning information pushing module is used for pushing the early warning information to the power transmission line operation and maintenance server, determining the fault factor and the fault distinguishing characteristic of the early warning information, and then feeding the fault factor and the fault distinguishing characteristic back to the fault factor mining database and the fault distinguishing characteristic database respectively, so that the fault early warning accuracy is improved in a closed-loop feedback mode.
Further, the system further comprises: and the display module is used for displaying the output early warning information in various forms, and displaying the early warning information in a fault characteristic analysis mode, and uniformly displaying fault reasons, fault positions and diagnosis results.
Further, the fault warning output module further includes:
the similarity calculation module is used for calculating the similarity between the early warning information time sequence and the fault standard time sequence;
and the similarity comparison module is used for solving the similarity between the early warning information time sequence and the fault standard time sequence, comparing the similarity with a preset similarity threshold value and outputting early warning information corresponding to the early warning information time sequence which is greater than or equal to the preset similarity threshold value.
Further, in the similarity calculation module, the similarity between the warning information time sequence and the standard time sequence is measured by calculating the edit distance between the warning information time sequence and the standard time sequence.
Compared with the prior art, the invention has the beneficial effects that:
(1) the fault factor mining method based on the naive Bayes algorithm and the fault matching algorithm based on the time series similarity are adopted to construct the fault early warning model, the fault factor mining and the fault matching algorithm complement each other, the fault factor mining improves the comprehensiveness and the foresight of fault prediction by predicting fault factor indexes to assist the time series similarity fault matching, the relevance of characteristic items of the naive Bayes algorithm is avoided based on the time series similarity fault matching, and the combination of the two can effectively realize the abnormal tracking and fault early warning of the power transmission line.
(2) In order to greatly improve the storage density, data positioning and running speed, the invention carries out real-time data processing on massive time sequence data by a large data processing cluster, and improves the stability and reliability of data processing.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of transmission line early warning model data processing;
FIG. 2 is a process diagram for constructing a fault discrimination indicator architecture;
FIG. 3 is a flow chart of fault factor mining data based on a naive Bayes algorithm;
FIG. 4 is a data flow diagram of a time series similarity based fault matching method;
FIG. 5 is a flow chart of an embodiment of a big data drive-based transmission line fault early warning method;
fig. 6 is a schematic structural diagram of an embodiment of a big data driving-based power transmission line fault early warning system according to the present invention;
fig. 7 is a schematic structural diagram of a second embodiment of a big data drive-based transmission line fault early warning system of the present invention;
fig. 8 is a schematic structural diagram of a transmission line fault early warning system based on big data driving according to an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiment of the invention provides a transmission line fault early warning method based on big data driving. The invention aims to solve the problem of remote fault early warning of a power transmission line, provides an early warning analysis method based on big data drive, mainly aims at the strong requirement of real-time data processing, selects a naive Bayes algorithm to realize fault factor index mining, combines the existing detectable data, carries out fault early warning on the running condition of the power transmission line based on time sequence similarity fault matching, and meets the requirement of making a solution in advance. The scheme mainly relies on a naive Bayes algorithm and a time sequence similarity algorithm to construct an early warning model, and the remote fault early warning service of the power transmission line is completed.
The invention discloses a big data drive-based power transmission line fault early warning method, which comprises the following steps:
a, collecting historical data and real-time data related to the power transmission line serving for each professional information management system of the power grid, collecting meteorological data, environmental data and data change information recorded in the power grid fault process of all current branches of a line and a bus accessed by a fault recording device, and determining data resources and detection targets.
B, based on information acquisition data, hierarchically combing fault features, and constructing a fault discrimination index system, wherein the fault discrimination index system mainly comprises a fault factor mining database and a fault discrimination feature database;
the invention constructs a fault factor mining database of fault factor mining based on a naive Bayesian algorithm, and constructs a fault discrimination feature library based on a time series similarity fault matching algorithm.
C, defining the information quantity and the control quantity of each fault based on a naive Bayes algorithm, determining a training sample set and a testing sample set, performing fault factor index mining on feature data given by a fault factor mining database, and performing abnormal state tracking on abnormal index fault factors, wherein the fault factors are target classes, such as: meteorological data, environmental data; the fault factor index is a numerical value of the predicted occurrence of the target class.
And D, transmitting the fault factor index of the abnormal fault factor to a fault discrimination feature library, forming an early warning time sequence by the feature items containing the unified time scale reference in the fault discrimination feature library according to the time sequence based on a time sequence similarity fault matching method, carrying out similarity matching with the fault standard time sequence, and generating fault early warning information when the power transmission line reaches a preset similarity threshold index value.
As shown in fig. 1, the big data driving-based power transmission line fault early warning method of the present invention further includes the following steps:
and E, testing the power transmission line fault early warning model built in the step C and the step D by using a test sample set, wherein the accuracy and the recall rate of the model are mainly included:
evaluating the power transmission line fault early warning model by the model test;
f, pushing the fault early warning information in a mode of short messages, mails or system interface window pop-up, and making a field fault solution in advance by the transmission line operation and maintenance responsible party according to the information to complete fault processing;
g, feeding back a fault sample, namely feeding back the diagnosis condition of the power transmission line, the information of the protection device and the fault reason according to on-site confirmation, continuously enriching a fault judgment index system and updating the fault prediction accuracy;
and H, displaying a visual result, namely displaying the data in various forms based on the abnormal tracking and fault early warning information, and mainly showing the fault characteristic analysis and unified display of fault reasons, fault positions and diagnosis results.
As shown in fig. 2, the generation process of constructing the fault discrimination index system in step B is as follows:
B1. based on information acquisition data serving as an original data set A, an original feature set containing N features, S being a selected feature set and initially being an empty set, F being a feature set to be selected and initially containing N features;
B2. computing
Mutual information I (a) with the target class cjC), find max [ D ]]Characteristic of being true and is noted asj *(j ═ 1,2, L, N), let F- { aj *}→Fj，{aj *}→SjRepeating the steps until F is an empty set, at which time SNThe features in (1) are arranged in descending order along with the increment of j according to the relevance of the feature items and the target class;
B3. will SNCharacteristic item a in (1)j(j ═ 1) and the rest items are mutually informed in sequence, and the characteristic item a is obtainedj(j 1) redundancy set R with each termj(j equals 1), let j equals j +1, repeat this step until j > N, obtain redundancy two-dimensional set R equals { R between each characteristic item at this moment1,R2...RN}；
B4. Initializing correlation threshold based on trial and error method
And the correlation can be corrected according to the verification of the accuracy of the fault early warning model of the modelSex threshold
Will SNAbove a correlation threshold
The characteristic items of (A) are attributed to a fault factor mining database;
B5. setting an initialization redundancy threshold value gamma according to the maximum correlation minimum redundancy criterion, and for the characteristic item a in the fault factor mining databasej(j equals 1), and the redundancy set R is formedjAnd (j is equal to 1), transferring the characteristic items with the numerical values larger than gamma and existing in the fault factor mining database into a fault distinguishing characteristic library, repeating the step until the characteristic items in the fault factor mining database are traversed, and thus obtaining the fault factor mining database and the fault distinguishing characteristic library.
It should be noted that the generation process of building the fault determination index system in fig. 2 is an embodiment, and there are other methods to build the fault determination index system, such as: and arranging the extracted fault features according to a preset sequence, and acquiring a fault factor mining database and a fault distinguishing feature database without performing redundancy processing.
And a data indexing method can be adopted, namely, the fault characteristics are indexed, and then redundant data are processed through indexing to obtain a fault factor mining database and a fault distinguishing characteristic database.
Wherein, the measure index related to the step B is defined as follows: given two characteristic items ajAnd akN, with a probability density of p (a)j) And p (a)k) The joint probability density is p (a)j,ak) Then a isjAnd akMutual information I (a) betweenj,ak) Is defined as
The measure indexes of the correlation and the redundancy are respectively defined as
Dj＝I(aj,c) (4)
Rj,k＝I(aj,ak) (5)
The two measurement indexes are considered comprehensively, and the maximum correlation minimum redundancy criterion is as follows:
max(Dj-Rj.k)，γ＝Rj.k (6)
wherein c is the object class, I (a)jAnd c) is a characteristic termjAnd the mutual information between object classes c, I (a)j,ak) As a characteristic item ajAnd feature item akD represents the correlation between the feature items and the object categories, and R represents the redundancy between the feature items.
As shown in fig. 3, the generation process of fault factor mining based on the naive bayes algorithm in the step C is as follows:
C1. defining x ═ a according to the characteristic items determined by the fault factor mining database1,a2,...,ai,...,amIs an item to be classified, where x is a fault factor to be mined, aiIs a characteristic item;
C2. determining a set C ═ y of fault factor classes to be mined1,y2In which y1For the fault factor to occur true, y2The fault factor occurrence is false;
C3. taking historical data with definite fault occurrence conditions of the conventional power transmission line as a known classified item set to be classified, namely determining a training sample set and a testing sample set;
C4. the conditional probability estimates of the individual feature items under the classes are obtained statistically, i.e.
When a certain feature item in a certain category does not appear, the phenomenon that P (a | y) ═ 0 is generated, so that the prediction quality of the model is greatly reduced, in order to solve the problem, under the premise that the number of training sample sets is large enough, Laplace calibration is introduced, and 1 is added to the count of all feature items in each category;
C5. the following derivation is made according to bayes' theorem:
since the denominator is constant for all classes, it is sufficient to maximize the numerator, which is further simplified:
P(yi|x)∝P(yi)P(a1|yi)P(a2|yi) (9)
C6. the method comprises the steps of putting sample data to be detected into a fault factor mining model, realizing fault factor mining by adopting a naive Bayes algorithm, providing a prediction value for time sequence similarity fault matching, and solving the probability ratio of fault occurrence index to fault non-occurrence index in the link for avoiding that simple binary classification does not meet the precision requirement of the next link:
C7. when the fault factor generation index is high, the abnormal state is continuously tracked and detected, and the abnormal characteristic factor index changing in real time is transmitted to the input characteristic based on the time series similarity fault matching algorithm in the fault judgment characteristic library.
It should be noted that the generation process of the fault factor mining based on the naive bayes algorithm in fig. 3 is an embodiment, and other calibration methods may be introduced in step C3 to calibrate the training sample set.
As shown in fig. 4, the generation process of performing fault early warning based on the time series similarity fault matching method in step D is as follows:
D1. according to input characteristics which are determined by a fault distinguishing characteristic library and based on a time series similarity fault matching algorithm, real-time characteristic data acquisition is carried out on the field data of the power transmission line and the fault factor index;
D2. generating from real-time characteristic dataForming a corresponding early warning information time sequence, wherein the time sequence is an ordered set of recorded values of certain information quantity and time node composition elements and is recorded as X ═ { X ═1＝(v1,t1),x2＝(v2,t2),...,xn＝(vn,tn) In which xi＝(vi,ti) Representing a time sequence at tiThe recorded information of the moment is vi(ii) a 1,2, …, n represents the sequence of occurrence of the fault events, and the sequence of fault events is synchronized with the sequence of time nodes, i.e.
i,j∈1,2...n)；
D3. Aiming at each early warning information time sequence, selecting an early warning type according to the fault factor index of the early warning information time sequence;
D4. determining an early warning fault area according to the reverse extrapolation of the abnormal fault factor index of the power transmission line, namely real-time characteristic data acquired on the site of fault factor mining based on a naive Bayes algorithm;
D5. clustering induction is carried out on the characteristic information collected by the historical fault cases, and a fault standard time sequence Y can be obtained as the following { Y ═ Y }1,y2...ynAnd setting a fault event weight xi ═ xi1,ξ2,...ξnH, confidence threshold α;
D6. acquiring the early warning information time sequence X ═ { X in real time1,x2...xmAnd the standard time sequence Y ═ Y1,y2...ynMatching is carried out, and the editing distance is used for measuring so as to obtain the time sequence similarity, and the editing distance D between the sequence X and the sequence Ym,nCan be prepared from0,0The result of the recursive calculation is that,
in the formula, when xi∈yjWhen, L (x)i,yi) 0, otherwise, L (x)i,yi)＝1；
D7. Similarity D of fault event weight xi and time sequencem,nMultiplying, accumulating the m fault event values to obtain a transmission line fault confidence coefficient alpha, and comparing the confidence coefficient alpha with a set confidence coefficient threshold alpha0By comparison, if α < α0And generating and pushing the power transmission line fault early warning indication of the type measured in the region.
It should be noted that the generation process of performing fault early warning based on the time series similarity fault matching method in fig. 4 is an embodiment.
In another embodiment, in step D6, the warning information time series X obtained in real time is { X ═ X1,x2...xmAnd the standard time sequence Y ═ Y1,y2...ynMatching is carried out, and the Euclidean distance, the cosine distance or the Manhattan distance are used for measuring so as to obtain the similarity of the time sequence.
The scheme of the invention is to implement a background platform by taking a certain power grid as a method, wherein data mainly come from an intelligent substation, an intelligent ammeter, a real-time monitoring system, a field mobile overhaul system, a measurement and control integrated system, remote signaling data and remote measuring data of the Internet and environmental data containing meteorological information. The big data server operation environment and configuration: the operating system is CentOS el7X86_64GNU/Linux, and the CPU is
To
E3-1230v5 and updated CPU, the memory is 8G or more, the client running environment and configuration are as follows: the operating system is Windows7, 8, 1064 bit operating system, the CPU is the sixth generation intelligence
Kurui foodTMi7-6700T processor or multi-core CP with main frequency above 3.6GHzU, memory is 4G and above.
Referring to fig. 5, a specific implementation process of the case of the method for performing a line a-phase single-phase grounding due to a lightning strike as a cause of a fault according to the present invention is described, which includes the following steps:
according to the statistical data of the power transmission line fault from 1 month to 6 months in 2013, the trip times in the whole year in 2013 are 1311 times, wherein the lightning stroke accounts for 46.3%, the lightning stroke fault case 607 is obtained, the lightning stroke fault case 324 in the last half year in 2014 is obtained in the same way, the sample cases in which rainfall occurs but lightning stroke does not occur in the area are collected as normal sample cases, the total number is 103827, and relevant data collection is carried out on the samples;
based on sample acquisition data, fault features are sorted hierarchically, a fault discrimination index system is constructed, firstly, a fault factor mining database based on naive Bayesian algorithm fault factor mining is constructed, and a correlation threshold value is set as
The method for mining the database containing the feature items 15 by the fault factors comprises the first step of constructing a redundancy threshold gamma of a fault discrimination feature library based on time sequence similarity matching [ 91644342326221211155555 ]]*10-4Besides the lightning stroke index mined in the previous step, the fault distinguishing feature library also comprises a feature item 6.
Taking the annual lightning stroke fault case 607 and the normal sample case 69236 in 2013 as a training sample set, and taking the last half-year lightning stroke fault case 324 and the normal sample case 34591 in 2014 as a test sample set;
feature item definition x ═ { a } determined from the fault discrimination feature library1,a2,...,ai,...,amIs an item to be classified, where x is a fault factor to be mined, aiDetermining a set C ═ y of fault factor classes to be mined for the feature items1,y2In which y1For the fault factor to occur true, y2For the fault factor is false, the conditional probability estimation of each characteristic item of the training sample set under each category is counted as 2The prior probability of index mining of lightning stroke fault factors occurring in 014 is shown as follows by using characteristic data of lightning stroke fault encountered by a certain 220kV power transmission line A phase in 2014:
in addition, the probability of occurrence of a lightning stroke fault event is 0.0087, and the probability of non-occurrence of the lightning stroke fault event is 0.9913, which can be obtained through history data training;
test sample data is put into a fault factor mining process, the calculated probability of lightning stroke occurrence and non-occurrence of the sample is finally obtained, and the characteristic data of the A-phase lightning stroke fault of a certain 220kV power transmission line in 2014 is used for example explanation
Therefore, the failure factor occurrence index is obtained as the probability ratio of failure occurrence and failure non-occurrence, namely the lightning stroke index:
putting the lightning stroke fault factor index data into a fault discrimination feature library, and setting a lightning stroke index threshold value theta by a training sample set0＝1.34，θ＜θ0If the lightning stroke index is abnormal, carrying out real-time tracking detection on the abnormal state, and continuously updating the data of the fault discrimination feature library;
receiving input features of a time series similarity-based fault matching method determined by a fault discrimination feature library, and generating a corresponding early warning information time series according to real-time feature data, wherein the time series is an ordered set of elements consisting of recorded values of certain electrical quantity and time nodesAnd, is denoted as X ═ X1＝(v1,t1),x2＝(v2,t2),...,x7＝(v7,t7)}；
Aiming at the generated early warning information time sequence, selecting a lightning early warning type according to the fault factor index, and performing reverse deduction by the power transmission line fault factor index, namely determining an early warning fault area by real-time characteristic data acquired on the site by fault factor mining based on a naive Bayes algorithm;
based on the characteristic information cluster analysis collected from the 2013 lightning stroke fault case 607, a standard lightning stroke fault time sequence Y ═ { Y ═ Y }can be obtained1,y2...y7The weight of the fault event is ξ ═ {1,98,16,12,0.01,10,1}, and the confidence threshold value is α0＝126；
Acquiring a lightning stroke fault early warning information time sequence X ═ X in real time1,x2...x7And a standard lightning stroke fault time sequence Y ═ Y1,y2...y7Alignment, edit distance D between sequence X and sequence Y7,7The data of the A phase of a certain 220kV power transmission line suffering from lightning stroke fault in 2014 are exemplified by the data obtained by the formula (5)
Similarity D of fault event weight xi and time sequence7,7Correspondingly multiplying, and accumulating the numerical values of 7 fault events to obtain the fault confidence coefficient alpha of the transmission line, which is 10 and alpha is less than alpha0Outputting lightning stroke fault early warning indication of the transmission line in the region;
as described in the above steps 4 to 9, the lightning stroke fault case 324 and the non-lightning stroke case 34591 in the first half of 2014 are taken as test sample sets, and the test evaluation is performed on the established early warning model, and the results are shown as follows
| Predicting no lightning strike | Predicted to be a lightning strike | Total number of tests | |
| Actual lightning strike occurrence | 57 | 267 | 324 |
| Actual lightning stroke does not occur | 34453 | 138 | 34591 |
| Total number of tests | 34510 | 405 | 34915 |
Evaluating model indexes:
the data can be obtained, and the fault factor mining based on the naive Bayes algorithm is combined with the fault matching algorithm based on the time sequence similarity, so that the transmission line fault can be well predicted;
the lightning stroke fault early warning result is pushed, a field fault solution is formulated in advance in an auxiliary mode, fault sample feedback is carried out according to field confirmation after fault processing is completed, the diagnosis condition of the power transmission line, the information of a protection device and the fault reason are fed back, a fault judgment index system is enriched continuously, and the fault prediction accuracy is updated;
and displaying a visual result, displaying the data in various forms based on the abnormal tracking and fault early warning information, mainly showing the fault characteristic analysis and unified display of fault reasons, fault positions and diagnosis results, and providing visual data display for the follow-up improvement of the power transmission line service.
As shown in fig. 6, the power transmission line fault early warning system based on big data driving of the present invention includes:
the data acquisition module is used for acquiring relevant information of the power transmission line, wherein the relevant information of the power transmission line comprises electric quantity, meteorological data, fault event sequence information and power grid topological data;
the fault discrimination index system construction module is used for extracting the characteristics of the related information of the power transmission line and constructing a fault factor mining database and a fault discrimination characteristic database on the basis of the extracted characteristics by a naive Bayes algorithm and a time series similarity fault matching algorithm;
the fault factor index mining module is used for mining the fault factor index of the data in the current fault factor mining database based on a naive Bayesian algorithm so as to track the abnormal state of the abnormal fault factor; the fault factor is a target class, and the fault factor index is a numerical value of the target class predicted occurrence;
and the fault early warning output module is used for transmitting the fault factor index to the fault discrimination feature library, matching an early warning information time sequence generated in the fault discrimination feature library in real time with a preset fault standard time sequence based on a time sequence similarity fault matching method, outputting early warning information corresponding to the matched early warning information time sequence and carrying out fault early warning.
Wherein, trouble early warning output module still includes:
the similarity calculation module is used for calculating the similarity between the early warning information time sequence and the fault standard time sequence;
and the similarity comparison module is used for solving the similarity between the early warning information time sequence and the fault standard time sequence, comparing the similarity with a preset similarity threshold value and outputting early warning information corresponding to the early warning information time sequence which is greater than or equal to the preset similarity threshold value.
Further, in the similarity calculation module, the similarity between the warning information time sequence and the standard time sequence is measured by calculating the edit distance between the warning information time sequence and the standard time sequence.
In another embodiment, as shown in fig. 7, the system further comprises: and the early warning information pushing module is used for pushing the early warning information to the power transmission line operation and maintenance server, determining the fault factor and the fault distinguishing characteristic of the early warning information, and then feeding the fault factor and the fault distinguishing characteristic back to the fault factor mining database and the fault distinguishing characteristic database respectively, so that the fault early warning accuracy is improved in a closed-loop feedback mode.
In another embodiment, as shown in fig. 8, the system further comprises: and the display module is used for displaying the output early warning information in various forms, and displaying the early warning information in a fault characteristic analysis mode, and uniformly displaying fault reasons, fault positions and diagnosis results.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (11)
1. A transmission line fault early warning method based on big data drive is characterized by comprising the following steps:
collecting relevant information of the power transmission line, wherein the relevant information of the power transmission line comprises electric quantity, meteorological data, fault event sequence information and power grid topological data;
extracting the characteristics of the relevant information of the power transmission line, and further constructing a fault factor mining database and a fault distinguishing characteristic database;
performing fault factor index mining on data in a current fault factor mining database based on a naive Bayesian algorithm, and further performing abnormal state tracking on abnormal fault factors;
transmitting the fault factor index of the abnormal fault factor to a fault discrimination feature library, matching an early warning information time sequence generated in real time in the fault discrimination feature library with a fault standard time sequence based on a time sequence similarity fault matching algorithm, outputting early warning information corresponding to the matched early warning information time sequence, and performing fault early warning;
the method for carrying out fault early warning based on the time sequence similarity fault matching method comprises the following steps:
D1. according to input characteristics which are determined by a fault distinguishing characteristic library and based on a time series similarity fault matching algorithm, real-time characteristic data acquisition is carried out on the field data of the power transmission line and the fault factor index;
D2. generating a corresponding early warning information time sequence according to the real-time characteristic data;
D3. aiming at each early warning information time sequence, selecting an early warning type according to the fault factor index of the early warning information time sequence;
D4. determining an early warning fault area according to the reverse extrapolation of the abnormal fault factor index of the power transmission line, namely real-time characteristic data acquired on the site of fault factor mining based on a naive Bayes algorithm;
clustering and inducing are carried out on the characteristic information collected by the historical fault cases, a fault standard time sequence is obtained, and the weight of a fault event and a confidence coefficient threshold value are set;
matching the early warning information time sequence acquired in real time with the fault standard time sequence, measuring by editing distance to acquire the similarity of the time sequence,
and multiplying the weight of the fault event by the similarity of the time sequence, accumulating the numerical value of the fault event to obtain the fault confidence coefficient of the power transmission line, comparing the fault confidence coefficient with a set confidence coefficient threshold, and if the fault confidence coefficient is smaller than the confidence coefficient threshold, generating the fault early warning indication of the power transmission line of the type measured in the region and pushing the fault early warning indication.
2. The big data drive-based transmission line fault early warning method as claimed in claim 1, wherein the method further comprises: and pushing the early warning information to a power transmission line operation and maintenance server, determining a fault factor and a fault judgment characteristic of the early warning information, and feeding back the fault factor and the fault judgment characteristic to a fault factor mining database and a fault judgment characteristic database respectively to improve the fault early warning accuracy in a closed-loop feedback mode.
3. The big data drive-based transmission line fault early warning method as claimed in claim 1, wherein the method further comprises: and displaying the output early warning information in various forms, namely displaying the fault characteristic analysis, and uniformly displaying the fault reason, the fault position and the diagnosis result.
4. The electric transmission line fault early warning method based on big data drive as claimed in claim 1, wherein the process of matching the early warning information time series generated in real time in the fault discrimination feature library with the fault standard time series based on the time series similarity fault matching method comprises:
and solving the similarity between the early warning information time sequence and the fault standard time sequence, comparing the similarity with a preset similarity threshold, and outputting early warning information corresponding to the early warning information time sequence which is greater than or equal to the preset similarity threshold.
5. The electric transmission line fault early warning method based on big data drive as claimed in claim 1, wherein the process of matching the early warning information time series generated in real time in the fault discrimination feature library with the fault standard time series based on the time series similarity fault matching method further comprises:
and constructing a fault factor mining database based on a naive Bayesian algorithm, and constructing a fault discrimination feature database based on a time series similarity fault matching algorithm.
6. The utility model provides a transmission line trouble early warning system based on big data drive which characterized in that includes:
the data acquisition module is used for acquiring relevant information of the power transmission line, wherein the relevant information of the power transmission line comprises electric quantity, meteorological data, fault event sequence information and power grid topological data;
the fault judgment index system building module is used for extracting the characteristics of the relevant information of the power transmission line so as to build a fault factor mining database and a fault judgment characteristic database;
the fault factor index mining module is used for mining the fault factor index of the data in the current fault factor mining database based on a naive Bayesian algorithm so as to track the abnormal state of the abnormal fault factor;
the fault early warning output module is used for transmitting the fault factor index of the abnormal fault factor to the fault distinguishing feature library, matching an early warning information time sequence generated in real time in the fault distinguishing feature library with a preset fault standard time sequence based on a time sequence similarity fault matching method, outputting early warning information corresponding to the matched early warning information time sequence and carrying out fault early warning;
the generation process of fault early warning based on the time series similarity fault matching method comprises the following steps:
D1. according to input characteristics which are determined by a fault distinguishing characteristic library and based on a time series similarity fault matching algorithm, real-time characteristic data acquisition is carried out on the field data of the power transmission line and the fault factor index;
D2. generating a corresponding early warning information time sequence according to the real-time characteristic data;
D3. aiming at each early warning information time sequence, selecting an early warning type according to the fault factor index of the early warning information time sequence;
D4. determining an early warning fault area according to the reverse extrapolation of the abnormal fault factor index of the power transmission line, namely real-time characteristic data acquired on the site of fault factor mining based on a naive Bayes algorithm;
clustering and inducing are carried out on the characteristic information collected by the historical fault cases, a fault standard time sequence is obtained, and the weight of a fault event and a confidence coefficient threshold value are set;
matching the early warning information time sequence acquired in real time with the standard time sequence, measuring by editing distance to acquire the similarity of the time sequence,
and multiplying the weight of the fault event by the similarity of the time sequence, accumulating the numerical value of the fault event to obtain the fault confidence coefficient of the power transmission line, comparing the fault confidence coefficient with a set confidence coefficient threshold, and if the fault confidence coefficient is smaller than the confidence coefficient threshold, generating the fault early warning indication of the power transmission line of the type measured in the region and pushing the fault early warning indication.
7. The big data drive-based transmission line fault early warning system according to claim 6, wherein the system further comprises: and the early warning information pushing module is used for pushing the early warning information to the power transmission line operation and maintenance server, determining the fault factor and the fault distinguishing characteristic of the early warning information, and then feeding the fault factor and the fault distinguishing characteristic back to the fault factor mining database and the fault distinguishing characteristic database respectively, so that the fault early warning accuracy is improved in a closed-loop feedback mode.
8. The big data drive-based transmission line fault early warning system according to claim 6, wherein the system further comprises: and the display module is used for displaying the output early warning information in various forms, and displaying the early warning information in a fault characteristic analysis mode, and uniformly displaying fault reasons, fault positions and diagnosis results.
9. The big data drive-based transmission line fault early warning system of claim 6, wherein the fault early warning output module further comprises:
the similarity calculation module is used for calculating the similarity between the early warning information time sequence and the fault standard time sequence;
and the similarity comparison module is used for solving the similarity between the early warning information time sequence and the fault standard time sequence, comparing the similarity with a preset similarity threshold value and outputting early warning information corresponding to the early warning information time sequence which is greater than or equal to the preset similarity threshold value.
10. The big-data-drive-based power transmission line fault early warning system according to claim 8, wherein in the similarity calculation module, the similarity between the early warning information time sequence and the standard time sequence is measured by calculating an edit distance between the early warning information time sequence and the standard time sequence.
11. The big data drive-based transmission line fault early warning system of claim 6, wherein the fault early warning output module further comprises:
in the fault discrimination index system construction module, a fault factor mining database is constructed based on a naive Bayesian algorithm, and a fault discrimination feature database is constructed based on a time series similarity fault matching algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710111397.5A CN106779505B (en) | 2017-02-28 | 2017-02-28 | Power transmission line fault early warning method and system based on big data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710111397.5A CN106779505B (en) | 2017-02-28 | 2017-02-28 | Power transmission line fault early warning method and system based on big data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106779505A CN106779505A (en) | 2017-05-31 |
| CN106779505B true CN106779505B (en) | 2021-04-02 |
Family
ID=58959703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710111397.5A Active CN106779505B (en) | 2017-02-28 | 2017-02-28 | Power transmission line fault early warning method and system based on big data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779505B (en) |
Families Citing this family (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085170A (en) * | 2017-06-23 | 2017-08-22 | 盛秀群 | Extra high voltage direct current transmission line based on big data is maked an inspection tour and reponse system |
| CN107478963A (en) * | 2017-09-30 | 2017-12-15 | 山东海兴电力科技有限公司 | Single-phase ground fault line selecting method of small-electric current grounding system based on power network big data |
| CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
| CN107807309A (en) * | 2017-10-27 | 2018-03-16 | 广东电网有限责任公司中山供电局 | A kind of transmission line malfunction method for early warning and system based on big data |
| CN107784115B (en) * | 2017-11-09 | 2019-01-22 | 福建省特种设备检验研究院 | A kind of special equipment failure analysis methods and system based on editing distance algorithm |
| CN108228428B (en) * | 2018-02-05 | 2021-09-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN109445406B (en) * | 2018-10-18 | 2021-05-18 | 西南交通大学 | Industrial control system safety detection method based on scene test and transaction search |
| CN109214595A (en) * | 2018-10-23 | 2019-01-15 | 中核核电运行管理有限公司 | Nuclear power plant's main pump three-level seal failure prediction technique based on big data analysis |
| CN109389181B (en) * | 2018-10-30 | 2020-11-24 | 全球能源互联网研究院有限公司 | Association rule generation method and device for power grid abnormal event |
| CN109596913B (en) * | 2018-11-26 | 2021-06-15 | 国网冀北电力有限公司 | Charging pile fault cause diagnosis method and device |
| CN109586239B (en) * | 2018-12-10 | 2020-03-31 | 国网四川省电力公司电力科学研究院 | Real-time diagnosis and fault early warning method for intelligent substation |
| CN110210632A (en) * | 2019-05-31 | 2019-09-06 | 国网河北省电力有限公司沧州供电分公司 | Failure emergency processing method, device and terminal based on ubiquitous electric power Internet of Things |
| CN110502499A (en) * | 2019-06-26 | 2019-11-26 | 中电万维信息技术有限责任公司 | Data fault event-handling method and maintenance system based on bayesian algorithm |
| CN110442657A (en) * | 2019-08-05 | 2019-11-12 | 北京远舢智能科技有限公司 | A kind of intelligent management platform based on big data |
| CN110457654A (en) * | 2019-08-08 | 2019-11-15 | 哈尔滨理工大学 | A kind of airborne equipment Reliability Prediction Method based on field data |
| CN110533331B (en) * | 2019-08-30 | 2024-03-15 | 广东电网有限责任公司江门供电局 | Fault early warning method and system based on transmission line data mining |
| CN110599030B (en) * | 2019-09-10 | 2022-06-07 | 江苏方天电力技术有限公司 | Electric power risk early warning method based on positive and negative feature library weighted matching |
| CN110806743A (en) * | 2019-12-05 | 2020-02-18 | 成都天玙兴科技有限公司 | Equipment fault detection and early warning system and method based on artificial intelligence |
| CN111444240A (en) * | 2020-03-26 | 2020-07-24 | 北京国网富达科技发展有限责任公司 | Power transmission line fault early warning method and device |
| CN111506478A (en) * | 2020-04-17 | 2020-08-07 | 上海浩方信息技术有限公司 | Method for realizing alarm management control based on artificial intelligence |
| CN111539478A (en) * | 2020-04-26 | 2020-08-14 | 成都见田科技有限公司 | Intelligent diagnosis method, system and diagnosis equipment for elevator faults |
| CN111722952A (en) * | 2020-05-25 | 2020-09-29 | 中国建设银行股份有限公司 | Fault analysis method, system, equipment and storage medium of business system |
| CN111709668A (en) * | 2020-07-07 | 2020-09-25 | 广西电网有限责任公司 | Power grid equipment parameter risk identification method and device based on data mining technology |
| CN111985719B (en) * | 2020-08-27 | 2023-07-25 | 华中科技大学 | Power load prediction method based on improved long-term and short-term memory network |
| CN112231348B (en) * | 2020-09-02 | 2022-08-09 | 浙江大华技术股份有限公司 | Rule engine intelligent automatic inspection method, system, electronic equipment and device |
| CN112415331B (en) * | 2020-10-27 | 2024-04-09 | 中国南方电网有限责任公司 | Power grid secondary system fault diagnosis method based on multi-source fault information |
| CN112598883B (en) * | 2021-02-07 | 2021-12-31 | 国网江苏省电力有限公司苏州供电分公司 | Power transmission line lightning-fall probability early warning method and early warning system based on Bayesian network |
| CN113052224B (en) * | 2021-03-19 | 2022-07-22 | 国网河南省电力公司电力科学研究院 | Interactive fusion method and system for power and meteorological multi-source data |
| CN113467349B (en) * | 2021-05-13 | 2024-06-14 | 河北工程大学 | Intelligent identification premonitory warning system for potential safety hazard of power transmission line |
| CN113159641B (en) * | 2021-05-17 | 2023-01-20 | 广东电网有限责任公司 | Power failure handling plan, system, terminal and storage medium based on matching degree factor |
| CN114217168B (en) * | 2021-12-07 | 2024-06-04 | 云南电网有限责任公司保山供电局 | Efficient fault diagnosis method for power transmission line based on optimal characteristic selection of recording data |
| CN114488923A (en) * | 2021-12-23 | 2022-05-13 | 浙江中控技术股份有限公司 | PLC control method, system and controller for realizing time scheduling function |
| CN114994451B (en) * | 2022-08-08 | 2022-10-11 | 山东交通职业学院 | Ship electrical equipment fault detection method and system |
| CN115361061A (en) * | 2022-08-24 | 2022-11-18 | 中铁电气化局集团有限公司 | Optical fiber fault monitoring method |
| CN117148047B (en) * | 2023-10-30 | 2024-01-12 | 国网江苏省电力有限公司南通供电分公司 | Power distribution fault positioning method and system based on multidimensional data |
| CN117688505B (en) * | 2024-02-04 | 2024-04-19 | 河海大学 | Prediction method and system for vegetation large-range regional negative abnormality |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573989A (en) * | 2015-01-28 | 2015-04-29 | 国家电网公司 | Transmission line fault probability assessment method based on historical fault information |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8571696B2 (en) * | 2009-06-10 | 2013-10-29 | Fisher-Rosemount Systems, Inc. | Methods and apparatus to predict process quality in a process control system |
| CN103996077B (en) * | 2014-05-22 | 2018-01-05 | 中国南方电网有限责任公司电网技术研究中心 | A kind of electrical equipment malfunction Forecasting Methodology based on multidimensional time-series |
| CN106017551A (en) * | 2016-05-16 | 2016-10-12 | 国网河南省电力公司电力科学研究院 | Intelligent transmission line integrated monitoring analysis and early warning method |
-
2017
- 2017-02-28 CN CN201710111397.5A patent/CN106779505B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573989A (en) * | 2015-01-28 | 2015-04-29 | 国家电网公司 | Transmission line fault probability assessment method based on historical fault information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106779505A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779505B (en) | Power transmission line fault early warning method and system based on big data driving | |
| CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| CN109583520B (en) | State evaluation method of cloud model and genetic algorithm optimization support vector machine | |
| CN108898311A (en) | A kind of data quality checking method towards intelligent distribution network repairing dispatching platform | |
| CN108664700A (en) | Acceleration degradation information Fusion Modeling Method based on uncertain data Envelope Analysis | |
| CN112688431A (en) | Power distribution network load overload visualization method and system based on big data | |
| CN112415331A (en) | Power grid secondary system fault diagnosis method based on multi-source fault information | |
| CN116467674A (en) | Intelligent fault processing fusion updating system and method for power distribution network | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN113420162A (en) | Equipment operation chain state monitoring method based on knowledge graph | |
| CN116468426A (en) | Power grid fault determining method and storage medium based on Apriori algorithm | |
| CN109739197A (en) | A kind of multi-state failure prediction method of chemical spent material processing equipment | |
| Xu et al. | Fault diagnosis and identification of malfunctioning protection devices in a power system via time series similarity matching | |
| CN103268329B (en) | Plasma panel manufacturing process data digging system | |
| CN117034149A (en) | Fault processing strategy determining method and device, electronic equipment and storage medium | |
| CN115908082A (en) | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes | |
| CN110766248A (en) | Workshop human factor reliability evaluation method based on SHEL and interval intuition fuzzy evaluation | |
| JP2005038098A (en) | Apparatus using data mining, and method for monitoring and executing operation state of facility or transaction | |
| CN115600695A (en) | Fault diagnosis method of metering equipment | |
| Lin et al. | Design and implementation of a CPS‐based predictive maintenance and automated management platform | |
| CN104731955A (en) | Methods and systems for diagnostic standard establishment and intelligent diagnosis of wind generation set oil monitoring | |
| CN110703183A (en) | Intelligent electric energy meter fault data analysis method and system | |
| CN116862209B (en) | New energy automobile charging facility management method and system | |
| Huang et al. | Research on Monitoring and Diagnosis Technology of Data Anomaly in Distribution Network | |
| CN116739532B (en) | Energy project management method, system, terminal equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |