CN113625109A - Intelligent diagnosis method and device for power line faults - Google Patents
Intelligent diagnosis method and device for power line faults Download PDFInfo
- Publication number
- CN113625109A CN113625109A CN202110890777.XA CN202110890777A CN113625109A CN 113625109 A CN113625109 A CN 113625109A CN 202110890777 A CN202110890777 A CN 202110890777A CN 113625109 A CN113625109 A CN 113625109A
- Authority
- CN
- China
- Prior art keywords
- fault
- probability
- transmission line
- data
- icing
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention relates to an intelligent diagnosis method and device for power line faults in the technical field of power transmission lines, wherein the device comprises an online monitoring module, a judgment module, a historical database, a data module and a correction module; the method comprises the following steps of S101, judging that the overhead transmission line with the fault is provided with a distributed device; s102, acquiring traveling wave characteristics acquired by a distributed device; s103, analyzing and processing the traveling wave characteristics, and calculating to obtain the fault probability P1(ii) a S104, combining online monitoring data to correct P1Preliminarily determining a fault reason; s105, acquiring a power frequency waveform acquired by the distributed device; s106, analyzing and processing the power frequency waveform, and calculating to obtain the fault probability P2(ii) a S107, on-line monitoring data correction P is combined2And further determining the fault reason. The invention solves the problems that the efficiency of analyzing the fault cause of the overhead transmission line is low and the safe and stable operation of the overhead transmission line is seriously influenced.
Description
Technical Field
The invention relates to the technical field of power transmission lines, in particular to an intelligent power line fault diagnosis method and device.
Background
At present, when the transmission line fault is diagnosed, the types of the transmission line faults and the positions of the fault points are analyzed one by adopting an elimination method based on manual experience, a comprehensive analysis and diagnosis technology of a system is lacked, and particularly, under the condition of multi-source information, clear fault reasons cannot be given, so that the analysis and the searching efficiency of the transmission line faults are low, and the safe and stable operation of the transmission line is seriously influenced.
The transmission line faults mainly comprise faults caused by lightning stroke, mountain fire, weather, ice coating, bird damage faults and the like. The identification of the cause of a fault requires mining and analyzing the characteristics of a specific fault on the basis of understanding various fault principles and processes, so as to form the basis for identifying the cause, and therefore, fault mechanism analysis needs to be performed on various fault types. Meanwhile, the occurrence of faults is related to the operating environment of the power transmission line, and the characteristics of different types of faults are represented differently on the wave recording data, so that external factors such as weather, time, seasons and the like at the line occurrence moment and internal factors represented by the wave recording data such as reclosing conditions, non-periodic component characteristics of fault phase current and transition resistance are mined on the basis of principle analysis, and characteristic rules are searched, so that a data source is provided for the establishment of a subsequent classification model.
Disclosure of Invention
The invention provides an intelligent power line fault diagnosis method and device for overcoming the problems in the prior art, and aims to solve the problems that the analysis and search efficiency of power line faults is low, and the safe and stable operation of a power line is seriously influenced.
In order to achieve the purpose, the invention adopts the following technical scheme:
an electric power line fault intelligent diagnosis device, comprising:
the online monitoring module is used for online monitoring the overhead transmission line to obtain online monitoring data;
the judging module is used for acquiring online monitoring data of the online monitoring module and judging whether the online monitoring data comprises a fault waveform;
the historical database is used for storing historical fault data of the overhead transmission line;
the data module is used for acquiring historical fault data of a historical database, online monitoring data of the judging module and a judging result, and processing the online monitoring data according to the judging result and the historical fault data to obtain a fault probability corresponding to the fault reason of the overhead transmission line;
and the correction module is used for acquiring the fault probability of the data module, correcting the fault probability to obtain the corrected fault probability, and judging a specific fault reason according to the corrected fault probability.
Preferably, the online monitoring module monitors specific time, fault waveform, fault phase number, line reclosing state, lightning stroke information, mountain fire information, meteorological information and icing information when the overhead transmission line fails on line, wherein the fault waveform when the overhead transmission line fails is realized by installing a distributed fault monitoring device and a transmission line corridor environment monitoring device on the overhead transmission line.
The invention also provides an intelligent power line fault diagnosis method, which is applied to the intelligent power line fault diagnosis device and comprises the following steps:
s101, judging whether the overhead power transmission line with the fault is provided with a distributed fault monitoring device and a power transmission line corridor environment monitoring device, if so, executing a step S102, otherwise, executing a step S201;
s102, acquiring traveling wave characteristics of fault waveforms at fault moments acquired by the distributed fault monitoring devices and the power transmission line corridor environment monitoring devices;
s103, inputting the traveling wave characteristics into a Support Vector Machine (SVM) algorithm, and calculating to obtain the fault probability P1Output the probability of failure P1And judging P1If the value is larger than 0.5, executing the step 104, otherwise executing the step 105;
s104. due to P1If the lightning stroke is larger than 0.5, the lightning stroke occurs in the overhead transmission line at the fault moment, lightning stroke information when the overhead transmission line fails is monitored on line, lightning current data are obtained, and the lightning current data are analyzed to obtain a correction function f1By modifying the function f1Multiplied by the probability of failure P1Correcting to obtain fault probability P11The failure cause of the overhead transmission line is determined to be lightning stroke failure;
s105, acquiring power frequency waveform characteristics of the distributed fault monitoring device and the power transmission line corridor environment monitoring device at the fault moment;
s106, inputting the power frequency waveform characteristics into a Support Vector Machine (SVM) algorithm, and calculating to obtain the fault probability P2Output the probability of failure P2；
S107, on-line monitoring of mountain fire information, meteorological information and icing information when the overhead power transmission line fails to work, obtaining mountain fire data, meteorological data and icing data, analyzing the mountain fire data, the meteorological data and the icing data to obtain a correction function f of the mountain fire fault2,Correction function f for meteorological faults3Correction function f for icing faults4(ii) a Correction function f of mountain fire fault2Multiplied by the probability of failure P2Obtaining the correction probability P of the forest fire fault21Correction function f of meteorological data3Multiplied by the probability of failure P2Obtaining a correction probability P of a meteorological fault22Correction function f for icing faults4Multiplied by the probability of failure P2Obtaining a corrected probability P of icing faults23(ii) a Finally, the calculated correction probability P is calculated21、P22、P23Sorting according to sizeAnd judging the specific fault reason of the overhead transmission line.
Further, the step S201 includes:
s201, monitoring lightning stroke information when the overhead transmission line breaks down on line, executing a step S202 if lightning stroke occurs, and executing a step S203 if no lightning stroke occurs;
s202, setting fault probability P3Monitoring lightning stroke information when the overhead transmission line has faults on line to obtain lightning current data, analyzing the lightning current data to obtain a correction function f1By modifying the function f1Multiplied by the probability of failure P3Correcting to obtain fault probability P31The failure cause of the overhead transmission line is determined to be lightning stroke failure;
s203, online monitoring of specific time, fault phase number, line reclosing state and meteorological information when the overhead transmission line is in fault to obtain online monitoring data;
s204, obtaining historical fault data of a historical database, inputting the historical fault data and online monitoring data into a Bayesian network, and calculating to obtain a mountain fire fault probability P of the non-lightning fault4Weather failure probability P5Probability of icing failure P6And probability of bird trouble P7A probability distribution of (a);
s205, on-line monitoring of mountain fire information, meteorological information and icing information when the overhead power transmission line fails to work, obtaining mountain fire data, meteorological data and icing data, analyzing the mountain fire data, the meteorological data and the icing data to obtain a correction function f of the mountain fire fault2,Correction function f for meteorological faults3Correction function f for icing faults4(ii) a Correction function f of mountain fire fault2Multiplying by the probability of mountain fire fault P4Obtaining a corrected probability P41Correction function f of meteorological data3Multiplying by the weather failure probability P5Obtaining a corrected probability P51Correction function f for icing faults4Multiplied by the icing fault probability P6Obtaining a corrected probability P61(ii) a Finally, P obtained by calculation41、P51、P61Sorting by size, in combination with bird trouble fault P7And comprehensively judging the specific fault reason of the overhead transmission line.
Further, the correction function f in step S104 and step S2021Comprises the following steps: f. of1A + (1-a), wherein
a is a correction parameter, A is the amplitude of the lightning current nearest to the fault position of the overhead transmission line, and D is the distance between the fault position of the overhead transmission line and the nearest lightning current.
Further, the correction function f in step S107 and step S2052Comprises the following steps: f. of2B + (1-b), wherein
b is a correction parameter, T is the temperature of the mountain fire point closest to the fault position of the overhead transmission line, and E is the distance between the fault position of the overhead transmission line and the closest mountain fire point.
Further, the correction function f in step S107 and step S2053Comprises the following steps: f. of3C + (1-c), wherein
c＝[min(W,12)+2]/14
c is a correction parameter, and W is the maximum wind speed of the overhead line corridor when the overhead transmission line fails.
Further, the correction function f in step S107 and step S2054Comprises the following steps: f. of4D + (1-d), wherein
d＝0.5log(H+1)
d is a correction parameter, and H is the maximum icing thickness when the overhead transmission line fails.
Further, the substituted bayesian network in step S204 is specifically:
wherein j is 2, 3, 4 and 5, which respectively correspond to a mountain fire fault, a meteorological fault, an icing fault and a bird damage fault;
a is 1, 2, 3, 4 and 5, which respectively correspond to sunny days, cloudy days, rainy days, snowy days and foggy days;
b is 1, 2 and 3, and respectively corresponds to reclosure success, reclosure failure and no action;
c is 1, 2 and 3, and corresponds to a single-phase fault, a two-phase fault and a three-phase fault respectively;
d is 1-12, which respectively corresponds to 1-12 months of the month;
e is 0-23, corresponding to 0-23 hours of the time respectively;
f is 1-12 and respectively corresponds to 1-12 levels of wind power;
when j is 2, the weather of the online monitored overhead transmission line when the fault occurs is A, the reclosing state is B, the fault phase number is C, the month number at the time point is D, the time point is E, the wind power grades are F and P (V)2) The ratio of the number of all mountain fire faults which occur in the history fault data to the total number of the faults which occur in the history is P (A | V)2) The ratio of the number of times with weather A in all mountain fire fault times to all mountain fire fault times is shown;
the same calculation results in P (B | V)2)、P(C|V2)、P(D|V2)、P(E|V2)、P(F|V2) Then, summing all the calculated proportions to obtain the mountain fire fault proportion V2Then, the calculation of the time when j is 3, 4, 5 is started, and the weather fault ratio V is obtained3Icing fault ratio V4And bird trouble ratio V5。
Further, after substituting the bayesian network in step S204, the method further comprises the following calculation formula:
the mountain fire fault probability P4＝V2/(V2+V3+V4+V5)；
The weather failure probability P5＝V3/(V2+V3+V4+V5)；
The icing fault probability P6＝V4/(V2+V3+V4+V5)；
The bird trouble probability P7＝V5/(V2+V3+V4+V5)。
The invention has the following beneficial effects:
1. the invention firstly utilizes traveling wave characteristics to judge whether the overhead transmission line is struck by lightning or not for the overhead transmission line provided with the distributed fault monitoring device and the transmission line corridor environment monitoring device, and if the overhead transmission line is struck by lightning, a lightning positioning system is utilized to correct the lightning fault probability of the overhead transmission line, so that the lightning fault result is more authoritative; and if the power frequency characteristic is not the lightning stroke, further calculating the power frequency characteristic of the fault, then correcting the probability of the fault reason matching through monitoring information of power transmission line corridors such as mountain fire, ice coating, weather and the like, and outputting a diagnosis result.
2. According to the method, for the overhead transmission line which is not provided with the distributed fault monitoring device and the transmission line corridor environment monitoring device, the probability corresponding to various fault reason types is calculated by directly utilizing information such as fault time, reclosing state, fault phase number and the like of online monitoring and historical statistics, and the diagnosis result is given by correcting in combination with the transmission line corridor monitoring information.
3. The invention accurately positions the transmission line fault, carries out the analysis of the line tripping fault reason, can greatly reduce the line inspection workload and can improve the power supply reliability.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a structural diagram of an intelligent power line fault diagnosis apparatus according to this embodiment.
Fig. 2 is a first flowchart of an intelligent power line fault diagnosis method according to this embodiment.
Fig. 3 is a second flowchart of an intelligent power line fault diagnosis method according to this embodiment.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The specific embodiment of the invention is as follows:
as shown in fig. 1, the intelligent power line fault diagnosis device of the present embodiment includes:
the online monitoring module 1 is used for online monitoring the overhead transmission line to obtain online monitoring data;
the judging module 2 is used for acquiring online monitoring data of the online monitoring module 1 and judging whether the online monitoring data comprises a fault waveform;
the historical database 3 is used for storing historical fault data of the overhead transmission line;
the data module 4 is used for acquiring historical fault data of the historical database 3, online monitoring data and a judgment result of the judgment module 2, and processing the online monitoring data according to the judgment result and the historical fault data to obtain a fault probability corresponding to the fault reason of the overhead transmission line;
and the correcting module 5 is used for acquiring the fault probability of the data module 4, correcting the fault probability to obtain the corrected fault probability, and judging a specific fault reason according to the corrected fault probability.
Preferably, the online monitoring module 1 monitors specific time, fault waveform, fault phase number, line reclosing state, lightning stroke information, mountain fire information, meteorological information and icing information when the overhead transmission line fails on line, wherein the fault waveform when the overhead transmission line fails is realized by installing a distributed fault monitoring device and a transmission line corridor environment monitoring device on the overhead transmission line.
As shown in fig. 2, a first flow of the power line fault intelligent diagnosis method of this embodiment includes:
s101, judging whether the overhead power transmission line with the fault is provided with a distributed fault monitoring device and a power transmission line corridor environment monitoring device, if so, executing a step S102, otherwise, executing a step S201;
s102, acquiring traveling wave characteristics of fault waveforms at fault moments acquired by the distributed fault monitoring devices and the power transmission line corridor environment monitoring devices;
s103, inputting the traveling wave characteristics into a Support Vector Machine (SVM) algorithm, and calculating to obtain the fault probability P1Output the probability of failure P1And judging P1If the value is larger than 0.5, executing the step 104, otherwise executing the step 105;
s104. due to P1If the lightning stroke is larger than 0.5, the lightning stroke occurs in the overhead transmission line at the fault moment, lightning stroke information when the overhead transmission line fails is monitored on line, lightning current data are obtained, and the lightning current data are analyzed to obtain a correction function f1By modifying the function f1Multiplied by the probability of failure P1Correcting to obtain fault probability P11The failure cause of the overhead transmission line is determined to be lightning stroke failure;
s105, acquiring power frequency waveform characteristics of the distributed fault monitoring device and the power transmission line corridor environment monitoring device at the fault moment;
s106, inputting the power frequency waveform characteristics into a Support Vector Machine (SVM) algorithm, and calculating to obtain the fault probability P2Output the probability of failure P2；
S107, on-line monitoring of mountain fire information, meteorological information and icing information when the overhead power transmission line fails to work, obtaining mountain fire data, meteorological data and icing data, analyzing the mountain fire data, the meteorological data and the icing data to obtain a correction function f of the mountain fire fault2,Correction function f for meteorological faults3Correction function f for icing faults4(ii) a Correction function f of mountain fire fault2Multiplied by the probability of failure P2Obtaining the correction probability P of the forest fire fault21Correction function f of meteorological data3Multiplied by the probability of failure P2Obtaining a correction probability P of a meteorological fault22Correction function f for icing faults4Multiplied by the probability of failure P2Obtaining a corrected probability P of icing faults23(ii) a Finally, the calculated correction probability P is calculated21、P22、P23And sequencing according to the sizes, and comprehensively judging the specific fault reasons of the overhead transmission line.
As shown in fig. 3, a second flow of the intelligent power line fault diagnosis method of the present embodiment includes:
s201, monitoring lightning stroke information when the overhead transmission line breaks down on line, executing a step S202 if lightning stroke occurs, and executing a step S203 if no lightning stroke occurs;
s202, setting fault probability P3Monitoring lightning stroke information when the overhead transmission line has faults on line to obtain lightning current data, analyzing the lightning current data to obtain a correction function f1By modifying the function f1Multiplied by the probability of failure P3Correcting to obtain fault probability P31The failure cause of the overhead transmission line is determined to be lightning stroke failure;
s203, online monitoring of specific time, fault phase number, line reclosing state and meteorological information when the overhead transmission line is in fault to obtain online monitoring data;
s204, acquiring calendarHistorical fault data of a historical database are input into a Bayesian network, and the mountain fire fault probability P of the non-lightning fault is calculated4Weather failure probability P5Probability of icing failure P6And probability of bird trouble P7A probability distribution of (a);
s205, on-line monitoring of mountain fire information, meteorological information and icing information when the overhead power transmission line fails to work, obtaining mountain fire data, meteorological data and icing data, analyzing the mountain fire data, the meteorological data and the icing data to obtain a correction function f of the mountain fire fault2,Correction function f for meteorological faults3Correction function f for icing faults4(ii) a Correction function f of mountain fire fault2Multiplying by the probability of mountain fire fault P4Obtaining a corrected probability P41Correction function f of meteorological data3Multiplying by the weather failure probability P5Obtaining a corrected probability P51Correction function f for icing faults4Multiplied by the icing fault probability P6Obtaining a corrected probability P61(ii) a Finally, P obtained by calculation41、P51、P61Sorting by size, in combination with bird trouble fault P7And comprehensively judging the specific fault reason of the overhead transmission line.
Further, the correction function f in step S104 and step S2021Comprises the following steps: f. of1A + (1-a), wherein
a is a correction parameter, A is the amplitude of the lightning current nearest to the fault position of the overhead transmission line, and D is the distance between the fault position of the overhead transmission line and the nearest lightning current.
Further, the correction function f in step S107 and step S2052Comprises the following steps: f. of2B + (1-b), wherein
b is a correction parameter, T is the temperature of the mountain fire point closest to the fault position of the overhead transmission line, and E is the distance between the fault position of the overhead transmission line and the closest mountain fire point.
Further, the correction function f in step S107 and step S2053Comprises the following steps: f. of3C + (1-c), wherein
c＝[min(W,12)+2]/14
c is a correction parameter, and W is the maximum wind speed of the overhead line corridor when the overhead transmission line fails.
Further, the correction function f in step S107 and step S2054Comprises the following steps: f. of4D + (1-d), wherein
d＝0.5log(H+1)
d is a correction parameter, and H is the maximum icing thickness when the overhead transmission line fails.
Further, the substituted bayesian network in step S204 is specifically:
wherein j is 2, 3, 4 and 5, which respectively correspond to a mountain fire fault, a meteorological fault, an icing fault and a bird damage fault;
a is 1, 2, 3, 4 and 5, which respectively correspond to sunny days, cloudy days, rainy days, snowy days and foggy days;
b is 1, 2 and 3, and respectively corresponds to reclosure success, reclosure failure and no action;
c is 1, 2 and 3, and corresponds to a single-phase fault, a two-phase fault and a three-phase fault respectively;
d is 1-12, which respectively corresponds to 1-12 months of the month;
e is 0-23, corresponding to 0-23 hours of the time respectively;
f is 1-12 and respectively corresponds to 1-12 levels of wind power;
when j is 2, the weather of the online monitored overhead transmission line when the overhead transmission line fails is A, the reclosing state is B, the number of failed phases is C, and the number of months at the time point isD. The time point is E, the wind power class is F, P (V)2) The ratio of the number of all mountain fire faults which occur in the history fault data to the total number of the faults which occur in the history is P (A | V)2) The ratio of the number of times with weather A in all mountain fire fault times to all mountain fire fault times is shown;
the same calculation results in P (B | V)2)、P(C|V2)、P(D|V2)、P(E|V2)、P(F|V2) Then, summing all the calculated proportions to obtain the mountain fire fault proportion V2Then, the calculation of the time when j is 3, 4, 5 is started, and the weather fault ratio V is obtained3Icing fault ratio V4And bird trouble ratio V5。
Further, after substituting the bayesian network in step S204, the method further comprises the following calculation formula:
the mountain fire fault probability P4＝V2/(V2+V3+V4+V5)；
The weather failure probability P5＝V3/(V2+V3+V4+V5)；
The icing fault probability P6＝V4/(V2+V3+V4+V5)；
The bird trouble probability P7＝V5/(V2+V3+V4+V5)。
For example, when a certain overhead transmission line fails, it is monitored on line that the area where the overhead transmission line is located when the failure occurs is a clear day, the reclosing state of the overhead transmission line is successful, the number of failed phases of the overhead transmission line is two, the month at the time is 4 months, the time at the time is 0 point, and the maximum wind power level of the corridor of the overhead transmission line is 5 levels, that is, a is 1, B is 1, C is 2, D is 4, E is 0, and F is 5.
Then substituting the Bayesian grid, and sequentially calculating j to be 2, 3, 4 and 5, namely respectively corresponding to the conditions of the mountain fire fault, the weather fault, the icing fault and the bird trouble fault, specifically as follows:
failure of mountain fire：j＝2，P(V2) The ratio of the number of all mountain fire faults which occur in the history fault data to the total number of the faults which occur in the history is P (A | V)2) The proportion of the number of times of weather in sunny days in all mountain fire fault times is P (B | V)2) The proportion of the number of times of successful reclosure of the overhead transmission line in all the mountain fire fault times to all the mountain fire fault times is P (C | V)2) The proportion of the number of the fault phases of the overhead transmission line in all the mountain fire fault times, which is two phases, to the number of all the mountain fire fault times, is P (D | V)2) P (E | V) is the ratio of the number of times of the failure occurrence in the month of 4 months to the number of times of the failure occurrence in all the mountain fires2) P (F | V) is the proportion of the number of times of 0 point of the occurrence time of the fault in all mountain fire fault numbers to the number of times of all mountain fire faults2) And the ratio of the number of times that the maximum wind power level of the corridor of the overhead transmission line is 5 in all the mountain fire fault times to all the mountain fire fault times is calculated. Summing all the calculated proportions to obtain the mountain fire fault proportion V2I.e. by
V2＝P(V2)+P(A|V2)+P(B|V2)+P(C|V2)+P(D|V2)+P(E|V2)+P(F|V2)。
Weather failure: j is 3, P (V)3) The ratio of the number of all weather faults which have occurred in the history fault data to the total number of the faults in the history is P (A | V)3) The proportion of the times of weather in sunny days in all weather fault times to all weather fault times is P (B | V)3) The proportion of the number of times of successful reclosing of the overhead transmission line in all weather fault times, P (C | V)3) The ratio of the number of fault phases of the overhead transmission line in all the weather fault times to the number of fault phases of two phases is P (D | V)3) The proportion of the number of failures occurring in the month of 4 months to the number of failures in all weather conditions is P (E | V)3) The proportion of the number of times of the fault occurrence time point 0 in all the weather fault times to all the weather fault times is P (F | V)3) For all weather failure timesThe number of times that the maximum wind power level of the empty power transmission line corridor is 5 grades accounts for the proportion of the number of times of all meteorological faults. Summing all the calculated proportions to obtain a meteorological fault proportion V3I.e. by
V3＝P(V3)+P(A|V3)+P(B|V3)+P(C|V3)+P(D|V3)+P(E|V3)+P(F|V3)。
Ice coating failure: j is 4, P (V)4) P (A | V) is the ratio of the number of all ice coating faults which have occurred historically in the historical fault data to the total number of faults which have occurred historically4) The proportion of the number of times of weather sunny day in all the icing fault times is P (B | V)4) The proportion of the number of times of successful reclosing times of the overhead transmission line in all icing fault times is P (C | V)4) The proportion of the number of the fault phases of the overhead transmission line in all the icing fault times, which is two phases, to all the icing fault times is P (D | V)4) P (E | V) is the ratio of the number of times of the failure occurrence in 4 months to the number of times of the failure occurrence in all the icing4) P (F | V) is the proportion of the number of the ice coating faults in the total number of the ice coating faults, wherein the number of the ice coating faults at the time point of occurrence is 0 point4) And the proportion of the number of times that the maximum wind power level of the corridor of the overhead transmission line is 5 in all the icing fault times to all the icing fault times is determined. Summing the calculated proportions to obtain an icing fault proportion V4I.e. by
V4＝P(V4)+P(A|V4)+P(B|V4)+P(C|V4)+P(D|V4)+P(E|V4)+P(F|V4)。
Bird trouble failure: j is 5, P (V)5) P (A | V) is the ratio of the number of all bird faults which have occurred in the history fault data to the total number of the faults in the history5) The proportion of the times of weather sunny days in all bird trouble times, P (B | V)5) The proportion of the number of times of successful reclosing of the overhead transmission line in all bird trouble faults is P (C | V)5) For all bird pestsThe proportion of the number of the fault phases of the overhead transmission line in the number of the faults to the number of the faults of all birds is P (D | V)5) P (E | V) is the ratio of the number of times of the bird trouble failure in all the numbers of times of the bird trouble failure in the month of 5 months5) P (F | V) is the ratio of the number of times of 0 point of the occurrence time of the fault in all bird faults to the number of times of all bird faults5) The proportion of the number of the overhead transmission line corridor with the maximum wind power level of 5 in all the bird trouble failure numbers to all the bird trouble failure numbers is disclosed. Summing all the calculated proportions to obtain a bird damage fault proportion V5I.e. by
V5＝P(V5)+P(A|V5)+P(B|V5)+P(C|V5)+P(D|V5)+P(E|V5)+P(F|V5)。
I.e. mountain fire fault probability P4＝V2/(V2+V3+V4+V5)；
Weather failure probability P5＝V3/(V2+V3+V4+V5)；
Probability of icing failure P6＝V4/(V2+V3+V4+V5)；
Probability of bird trouble P7＝V5/(V2+V3+V4+V5)。
Finally, P obtained by calculation4、P5、P6、P7And sequencing according to the sizes, and comprehensively judging to obtain the fault reason of the overhead transmission line fault.
In the description of the present invention, it is to be understood that the terms "intermediate", "length", "upper", "lower", "front", "rear", "vertical", "horizontal", "inner", "outer", "radial", "circumferential", and the like, indicate orientations and positional relationships that are based on the orientations and positional relationships shown in the drawings, are used for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and therefore, are not to be construed as limiting the present invention.
In the present invention, unless otherwise expressly stated or limited, the first feature may be "on" the second feature in direct contact with the second feature, or the first and second features may be in indirect contact via an intermediate. "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; may be mechanically coupled, may be electrically coupled or may be in communication with each other; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The above description is for the purpose of illustrating embodiments of the invention and is not intended to limit the invention, and it will be apparent to those skilled in the art that any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention shall fall within the protection scope of the invention.
Claims (10)
1. An intelligent power line fault diagnosis device, comprising:
the online monitoring module is used for online monitoring the overhead transmission line to obtain online monitoring data;
the judging module is used for acquiring online monitoring data of the online monitoring module and judging whether the online monitoring data comprises a fault waveform;
the historical database is used for storing historical fault data of the overhead transmission line;
the data module is used for acquiring historical fault data of a historical database, online monitoring data of the judging module and a judging result, and processing the online monitoring data according to the judging result and the historical fault data to obtain a fault probability corresponding to the fault reason of the overhead transmission line;
and the correction module is used for acquiring the fault probability of the data module, correcting the fault probability to obtain the corrected fault probability, and judging a specific fault reason according to the corrected fault probability.
2. The power line fault intelligent diagnosis device according to claim 1, wherein the online monitoring module monitors specific time, fault waveform, fault phase number, line reclosing state, lightning stroke information, mountain fire information, meteorological information and icing information when the overhead power transmission line is in fault online, wherein the fault waveform when the overhead power transmission line is in fault online is monitored by installing a distributed fault monitoring device on the overhead power transmission line and a power transmission line corridor environment monitoring device.
3. An intelligent power line fault diagnosis method applied to the intelligent power line fault diagnosis device according to claims 1-2, comprising:
s101, judging whether the overhead power transmission line with the fault is provided with a distributed fault monitoring device and a power transmission line corridor environment monitoring device, if so, executing a step S102, otherwise, executing a step S201;
s102, acquiring traveling wave characteristics of fault waveforms at fault moments acquired by the distributed fault monitoring devices and the power transmission line corridor environment monitoring devices;
s103, inputting the traveling wave characteristics into a Support Vector Machine (SVM) algorithm, and calculating to obtain the fault probability P1Output the probability of failure P1And judging P1If the value is larger than 0.5, executing the step 104, otherwise executing the step 105;
s104. due to P1If the lightning stroke is larger than 0.5, the lightning stroke occurs in the overhead transmission line at the fault moment, lightning stroke information when the overhead transmission line is in fault is monitored on line, lightning current data are obtained, and the lightning current is analyzedThe current data is obtained as a correction function f1By modifying the function f1Multiplied by the probability of failure P1Correcting to obtain fault probability P11The failure cause of the overhead transmission line is determined to be lightning stroke failure;
s105, acquiring power frequency waveform characteristics of the distributed fault monitoring device and the power transmission line corridor environment monitoring device at the fault moment;
s106, inputting the power frequency waveform characteristics into a Support Vector Machine (SVM) algorithm, and calculating to obtain the fault probability P2Output the probability of failure P2；
S107, on-line monitoring of mountain fire information, meteorological information and icing information when the overhead power transmission line fails to work, obtaining mountain fire data, meteorological data and icing data, analyzing the mountain fire data, the meteorological data and the icing data to obtain a correction function f of the mountain fire fault2,Correction function f for meteorological faults3Correction function f for icing faults4(ii) a Correction function f of mountain fire fault2Multiplied by the probability of failure P2Obtaining the correction probability P of the forest fire fault21Correction function f of meteorological data3Multiplied by the probability of failure P2Obtaining a correction probability P of a meteorological fault22Correction function f for icing faults4Multiplied by the probability of failure P2Obtaining a corrected probability P of icing faults23(ii) a Finally, the calculated correction probability P is calculated21、P22、P23And sequencing according to the sizes, and comprehensively judging the specific fault reasons of the overhead transmission line.
4. The method according to claim 3, wherein the step S201 comprises:
s201, monitoring lightning stroke information when the overhead transmission line breaks down on line, executing a step S202 if lightning stroke occurs, and executing a step S203 if no lightning stroke occurs;
s202, setting fault probability P3Monitoring lightning stroke information when the overhead transmission line has faults on line to obtain lightning current data, analyzing the lightning current data to obtain a correction function f1By modifying the function f1Multiplied by the probability of failure P3Correcting to obtain fault probability P31The failure cause of the overhead transmission line is determined to be lightning stroke failure;
s203, online monitoring of specific time, fault phase number, line reclosing state and meteorological information when the overhead transmission line is in fault to obtain online monitoring data;
s204, obtaining historical fault data of a historical database, inputting the historical fault data and online monitoring data into a Bayesian network, and calculating to obtain a mountain fire fault probability P of the non-lightning fault4Weather failure probability P5Probability of icing failure P6And probability of bird trouble P7A probability distribution of (a);
s205, on-line monitoring of mountain fire information, meteorological information and icing information when the overhead power transmission line fails to work, obtaining mountain fire data, meteorological data and icing data, analyzing the mountain fire data, the meteorological data and the icing data to obtain a correction function f of the mountain fire fault2,Correction function f for meteorological faults3Correction function f for icing faults4(ii) a Correction function f of mountain fire fault2Multiplying by the probability of mountain fire fault P4Obtaining a corrected probability P41Correction function f of meteorological data3Multiplying by the weather failure probability P5Obtaining a corrected probability P51Correction function f for icing faults4Multiplied by the icing fault probability P6Obtaining a corrected probability P61(ii) a Finally, P obtained by calculation41、P51、P61Sorting by size, in combination with bird trouble fault P7And comprehensively judging the specific fault reason of the overhead transmission line.
5. The method according to claim 4, wherein the correction function f in step S104 and step S2021Comprises the following steps: f. of1A + (1-a), wherein
a is a correction parameter, A is the amplitude of the lightning current nearest to the fault position of the overhead transmission line, and D is the distance between the fault position of the overhead transmission line and the nearest lightning current.
6. Method according to claim 4, characterized in that the correction function f in steps S107 and S2052Comprises the following steps: f. of2B + (1-b), wherein
b is a correction parameter, T is the temperature of the mountain fire point closest to the fault position of the overhead transmission line, and E is the distance between the fault position of the overhead transmission line and the closest mountain fire point.
7. Method according to claim 4, characterized in that the correction function f in steps S107 and S2053Comprises the following steps: f. of3C + (1-c), wherein
c＝[min(W,12)+2]/14
c is a correction parameter, and W is the maximum wind speed of the overhead line corridor when the overhead transmission line fails.
8. Method according to claim 4, characterized in that the correction function f in steps S107 and S2054Comprises the following steps: f. of4D + (1-d), wherein
d＝0.5log(H+1)
d is a correction parameter, and H is the maximum icing thickness when the overhead transmission line fails.
9. The method according to claim 4, wherein the substituted Bayesian network in step S204 is specifically:
wherein j is 2, 3, 4 and 5, which respectively correspond to a mountain fire fault, a meteorological fault, an icing fault and a bird damage fault;
a is 1, 2, 3, 4 and 5, which respectively correspond to sunny days, cloudy days, rainy days, snowy days and foggy days;
b is 1, 2 and 3, and respectively corresponds to reclosure success, reclosure failure and no action;
c is 1, 2 and 3, and corresponds to a single-phase fault, a two-phase fault and a three-phase fault respectively;
d is 1-12, which respectively corresponds to 1-12 months of the month;
e is 0-23, corresponding to 0-23 hours of the time respectively;
f is 1-12 and respectively corresponds to 1-12 levels of wind power;
when j is 2, the weather of the online monitored overhead transmission line when the fault occurs is A, the reclosing state is B, the fault phase number is C, the month number at the time point is D, the time point is E, the wind power grades are F and P (V)2) The ratio of the number of all mountain fire faults which occur in the history fault data to the total number of the faults which occur in the history is P (A | V)2) The ratio of the number of times with weather A in all mountain fire fault times to all mountain fire fault times is shown;
the same calculation results in P (B | V)2)、P(C|V2)、P(D|V2)、P(E|V2)、P(F|V2) Then, summing all the calculated proportions to obtain the mountain fire fault proportion V2Then, the calculation of the time when j is 3, 4, 5 is started, and the weather fault ratio V is obtained3Icing fault ratio V4And bird trouble ratio V5。
10. The method according to claim 9, wherein after substituting the bayesian network in step S204, the method further comprises the following calculation formula:
the mountain fire fault probability P4＝V2/(V2+V3+V4+V5)；
The weather failure probability P5＝V3/(V2+V3+V4+V5)；
The icing fault probability P6＝V4/(V2+V3+V4+V5)；
The bird trouble probability P7＝V5/(V2+V3+V4+V5)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110890777.XA CN113625109A (en) | 2021-08-04 | 2021-08-04 | Intelligent diagnosis method and device for power line faults |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110890777.XA CN113625109A (en) | 2021-08-04 | 2021-08-04 | Intelligent diagnosis method and device for power line faults |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113625109A true CN113625109A (en) | 2021-11-09 |
Family
ID=78382590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110890777.XA Pending CN113625109A (en) | 2021-08-04 | 2021-08-04 | Intelligent diagnosis method and device for power line faults |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113625109A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114696467A (en) * | 2022-05-31 | 2022-07-01 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing fault tripping event of high-voltage transmission long line |
| CN115932477A (en) * | 2022-12-28 | 2023-04-07 | 国网湖北省电力有限公司电力科学研究院 | Multi-source information fused method and system for diagnosing fault cause of overhead transmission line |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871004A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network failure cause analyzing method based on expert system and D-S evidence theory |
| CN104992055A (en) * | 2015-06-16 | 2015-10-21 | 哈尔滨工业大学 | Pollution-flashover-caused trip probability calculation method of overhead lines in sand and dust environment |
| CN105868872A (en) * | 2016-05-30 | 2016-08-17 | 东北大学 | Power distribution network lightning disaster failure prediction method |
| CN106651128A (en) * | 2016-11-16 | 2017-05-10 | 国家电网公司 | Power transmission and transformation system risk early warning method |
| CN109655712A (en) * | 2019-01-14 | 2019-04-19 | 中国电力科学研究院有限公司 | A kind of distribution network line fault analysis of causes method and system |
| CN112149554A (en) * | 2020-09-21 | 2020-12-29 | 广东电网有限责任公司清远供电局 | Fault classification model training method, fault detection method and related device |
-
2021
- 2021-08-04 CN CN202110890777.XA patent/CN113625109A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871004A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network failure cause analyzing method based on expert system and D-S evidence theory |
| CN104992055A (en) * | 2015-06-16 | 2015-10-21 | 哈尔滨工业大学 | Pollution-flashover-caused trip probability calculation method of overhead lines in sand and dust environment |
| CN105868872A (en) * | 2016-05-30 | 2016-08-17 | 东北大学 | Power distribution network lightning disaster failure prediction method |
| CN106651128A (en) * | 2016-11-16 | 2017-05-10 | 国家电网公司 | Power transmission and transformation system risk early warning method |
| CN109655712A (en) * | 2019-01-14 | 2019-04-19 | 中国电力科学研究院有限公司 | A kind of distribution network line fault analysis of causes method and system |
| CN112149554A (en) * | 2020-09-21 | 2020-12-29 | 广东电网有限责任公司清远供电局 | Fault classification model training method, fault detection method and related device |
Non-Patent Citations (4)
| Title |
|---|
| SHUAI YANG 等: "Failure probability estimation of overhead transmission lines considering the spatial and temporal variation in severe weather", J. MOD. POWER SYST. CLEAN ENERGY * |
| 王友明: "基于故障录波数据和气象信息的架空输电线路故障类型辨识方法研究", 万方硕士论文 * |
| 申元 等: "基于BP神经网络的输电线路故障原因辨识研究", 智能电网 * |
| 黄志都 等: "输电线路故障类型辨识研究", 电工技术 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114696467A (en) * | 2022-05-31 | 2022-07-01 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing fault tripping event of high-voltage transmission long line |
| CN115932477A (en) * | 2022-12-28 | 2023-04-07 | 国网湖北省电力有限公司电力科学研究院 | Multi-source information fused method and system for diagnosing fault cause of overhead transmission line |
| CN115932477B (en) * | 2022-12-28 | 2024-01-23 | 国网湖北省电力有限公司电力科学研究院 | Multi-source information fusion overhead transmission line fault cause diagnosis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113533906B (en) | Intelligent overhead transmission line fault type diagnosis method and system | |
| CN111555716B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
| US9048693B2 (en) | Method and apparatus for detecting impairment of a solar array | |
| CN113625109A (en) | Intelligent diagnosis method and device for power line faults | |
| CN107037279B (en) | A kind of shunt capacitor monitoring system and method | |
| US9568514B2 (en) | Power quality event localization by multiple indexes | |
| CN105134510A (en) | State monitoring and failure diagnosis method for wind generating set variable pitch system | |
| CN111082749B (en) | Photovoltaic string running state identification method, device and storage medium | |
| CN114898232B (en) | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic group string data analysis | |
| CN115639840A (en) | Unmanned aerial vehicle inspection method based on photovoltaic power station operation and maintenance analysis | |
| CN106845822B (en) | Icing-galloping-prevention technically improved project efficiency evaluation method and system | |
| CN114997745A (en) | Photovoltaic fault diagnosis tracing method based on depth feature extraction | |
| Li et al. | A line-fault cause analysis method for distribution network based on decision-making tree and machine learning | |
| CN113688987A (en) | Training method of photovoltaic monitoring model, monitoring method of photovoltaic equipment and equipment | |
| CN116383914B (en) | Multi-dimensional information analysis-based power system fault judging device and method | |
| CN117131321A (en) | Electric energy data acquisition method | |
| CN112711905A (en) | Wind power plant current collection line protection method based on clustering algorithm | |
| CN116208091A (en) | Fault diagnosis and early warning method for distributed photovoltaic power station equipment | |
| CN113033018A (en) | GIS maintenance decision intelligent recommendation method based on comprehensive state evaluation | |
| CN115219853B (en) | Fault early warning processing method and system for current collection line of wind power plant | |
| Aljafari | Reliability investigation of long photovoltaic string generators under electrical fault scenarios | |
| CN115932477B (en) | Multi-source information fusion overhead transmission line fault cause diagnosis method and system | |
| CN116094179B (en) | AC/DC flexible distribution network medium-voltage line fault analysis processing system | |
| CN114200243B (en) | Intelligent diagnosis method and system for faults of low-voltage transformer area | |
| CN116125189A (en) | Wind power plant collector line fault positioning method |
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 |