CN105676067A - Fault diagnosis method and system of power transmission lines - Google Patents
Fault diagnosis method and system of power transmission lines Download PDFInfo
- Publication number
- CN105676067A CN105676067A CN201610051024.9A CN201610051024A CN105676067A CN 105676067 A CN105676067 A CN 105676067A CN 201610051024 A CN201610051024 A CN 201610051024A CN 105676067 A CN105676067 A CN 105676067A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- typical
- wave data
- module
- 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
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
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Locating Faults (AREA)
Abstract
The invention discloses a fault diagnosis method of power transmission lines. The method comprises simulated waveform data of typical fault forms is obtained and stored in a simulated waveform database of the typical fault forms, and the simulated waveform database of the typical fault forms also comprises simulation time of the simulated waveform data; the two ends of a distributed fault monitor obtain practical detection data, and the practical detection data is stored in a practical waveform database of the typical fault forms; a fault positioning module obtains obtaining time difference of the practical waveform database of the typical fault forms, and determines a position where a fault occurs; and a fault identification module obtains practical waveform data and the simulated waveform data of the typical fault forms, characteristic quantities of the practical waveform data and the simulated waveform data are extracted and compared, and a fault identification result is obtained via analysis. The fault can be positioned and identified rapidly and accurately, and the fault type is determined.
Description
Technical field
The present invention relates to transmission line malfunction diagnostic techniques field, more specifically, relate to a kind of transmission line malfunction diagnostic method and system.
Background technology
In recent years, China's power system development is rapid, and since the power system development strategy implementation that particularly " national network, transferring electricity from the west to the east, north and south supply mutually " and extra-high voltage grid and intelligent grid are built, power system capacity increases year by year, rack is more and more closeer, and overhead line structures are more and more higher. So, the transmission line of electricity trip accident that a variety of causes causes is also increasing, once transmission line of electricity trips, if that deals with improperly or process is likely to result in whole system instability not in time, even result in bulk power grid collapse and cause large area blackout, to industrial and agricultural production, particularly new and high technology manufacturing enterprise brings huge economic loss, causes great inconvenience to the routine work of people and life.
For the infringement that circuit and electrical network are caused by prevention and reduction fault, it should search in time after fault occurs and make treatment measures targetedly. The protective relaying devices such as at present conventional failure wave-recording and travelling wave ranging can to a certain degree reduce trouble shoot scope, the on-Line Monitor Device such as the thunder and lightning that such as adopts, icing, filth, mountain fire. But the differentiation of failure cause and nature of trouble then fully relies on manually, it is easy to erroneous judgement occur and fails to judge, affecting the eliminating of fault.
Visible, how to be quickly accurately positioned trouble point, accurate recognition fault, be those skilled in the art's problem demanding prompt solutions.
Summary of the invention
It is an object of the invention to provide a kind of transmission line malfunction diagnostic method and system, with quickly accurate to fault location and identification of defective, it is determined that fault type.
In order to solve above-mentioned technical problem, the present invention provides following technical scheme:
A kind of transmission line malfunction diagnostic method provided by the invention, described method includes:
Obtain typical fault morphological Simulation Wave data, storing described typical fault morphological Simulation Wave data to typical fault morphological Simulation waveform database, described typical fault morphological Simulation waveform database also includes the simulated time of described typical fault morphological Simulation Wave data;
The two ends of distributed fault monitoring device obtain actually detected data respectively, and described actually detected data are stored to typical fault form actual waveform data base, described detection data are (P1, and (P2 T1), T2), wherein: P represents the Wave data that detection receives, T represents that detection receives the moment of Wave data;
Fault location module obtains T1 and the T2 of described typical fault form actual waveform data base, calculates the difference of T1 and T2, it is determined that the position that fault occurs;
Fault identification module obtains described actual waveform data and described typical fault morphological Simulation Wave data, extract described actual waveform data and the characteristic quantity of described typical fault morphological Simulation Wave data respectively, contrast its characteristic quantity, analyze and obtain fault identification result.
Preferably, in above-mentioned transmission line malfunction diagnostic method, described method also includes:
10 corresponding for each fault form in described typical fault morphological Simulation waveform database up-to-date Wave datas are stored to typical fault form actual waveform data base, sets up training sample set;
Typical fault is carried out digital coding, described in carry out the difference of the identical figure place of digital coding and the bigger number of difference replaces the classifications of described typical fault;
By described training sample set input fault waveform pretreatment and Characteristic Extraction module, it is thus achieved that characteristic quantity set;
Set up BP neural network algorithm model, utilize described training sample set and described characteristic quantity set to carry out BP neural network algorithm model training;
The characteristic quantity of described actual waveform data is brought described BP neural network algorithm model into, it is thus achieved that the real figure that the characteristic quantity of described actual waveform data is corresponding encodes, and analyzes and obtains fault identification result.
Preferably, in above-mentioned transmission line malfunction diagnostic method, the real figure that the characteristic quantity of described acquisition described actual waveform data is corresponding encodes, and analyzes acquisition fault identification result and includes:
With the digital coding of described typical fault, described real figure coding is calculated Euclidean distance respectively, and the typical fault that the minimum described digital coding of wherein said Euclidean distance is corresponding is fault identification result.
Preferably, in above-mentioned transmission line malfunction diagnostic method, described training sample set or described actual waveform data are carried out effective section identification by described fault waveform pretreatment and Characteristic Extraction module, described effective section identification is using the beginning as effective section of the travelling wave current amplitude of the Wave data moment more than 1A, using amplitude less than moment of 50A persistent period 500 microsecond as the end of effective section.
Preferably, in above-mentioned transmission line malfunction diagnostic method, described method also includes:
Artificial acquisition physical fault type;
Judge that whether described fault identification result and described physical fault type be identical;
If it is not, then increase training sample set number, it is added into described training sample set by described actual waveform data;
If it is, when the sample number of described physical fault type is more than 10, then concentrated by described training sample and deduct one of them sample, when the sample number of described physical fault type is equal to 10, then keep described training sample set constant.
Transmission line malfunction diagnostic method provided by the invention, utilize fault that the characteristic that moment travelling wave signal changes occurs, adopt distributed fault monitoring device detection travelling wave signal, then travelling wave signal data are processed, the difference receiving signal time according to distributed fault monitoring device determines the position that fault occurs, the characteristic quantity of the fault waveform data detected Yu typical fault morphological Simulation Wave data pair is contrasted, it is thus achieved that fault identification result, namely obtain the type broken down. Transmission line malfunction diagnostic method provided by the invention is quickly accurate to fault location and identification of defective, it is determined that fault type.
Based on the transmission line malfunction diagnostic method of above-mentioned offer, present invention also offers a kind of transmission line malfunction diagnostic system, described system includes distributed fault detection system, data reception module, data memory module and fault diagnosis module;
The traveling wave data of described distributed fault detection system acquisition instant of failure, and by the transmission of described traveling wave data to described data reception module, described traveling wave data include Wave data and gather the Wave data time;
Described data reception module is used for receiving described traveling wave data, and sends described traveling wave data to described data memory module;
Described data memory module includes typical fault form actual waveform data base and typical fault morphological Simulation waveform database, described typical fault form actual waveform data base is used for storing described traveling wave data, described typical fault morphological Simulation waveform database is used for storing analog waveform data, and described analog waveform data include fault simulation Wave data, corresponding fault form, simulated time;
Described fault diagnosis module includes fault location module and fault identification module, for judging generation position and the fault type of fault corresponding to described Wave data.
Preferably, in above-mentioned transmission line malfunction diagnostic system, described system also includes web display module, and the input of described web display module connects the outfan of described fault diagnosis module.
Preferably, in above-mentioned transmission line malfunction diagnostic system, described system also includes lightning location system, line ice coating monitoring system, circuit filth monitoring system or forest fire monitoring system, and the outfan of described lightning location system, line ice coating monitoring system, circuit filth monitoring system or forest fire monitoring system connects the input of described data memory module respectively.
Preferably, in above-mentioned transmission line malfunction diagnostic system, the input of described web display module connects the outfan of described lightning location system, line ice coating monitoring system, circuit filth monitoring system or forest fire monitoring system respectively.
Preferably, in above-mentioned transmission line malfunction diagnostic system, described fault diagnosis module also includes fault waveform pretreatment and Characteristic Extraction module, and described fault waveform pretreatment and Characteristic Extraction module are used for processing described Wave data or described fault simulation Wave data.
Based on transmission line malfunction diagnostic method provided by the invention, transmission line malfunction diagnostic system provided by the invention, distributed fault detection system is adopted to obtain the traveling wave data of instant of failure, and send data to data reception module, data reception module sends data to data memory module, typical fault form actual waveform data base in data memory module is used for storage line wave datum, and the typical fault morphological Simulation waveform database in data memory module stores analog waveform data, fault diagnosis module includes fault location module and fault traveling wave data are carried out fault and the judgement of position and fault type occurs by fault identification module respectively. transmission line malfunction diagnostic system provided by the invention is conducive to fault location and the quickly accurate of Fault Identification to confirm.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme in the embodiment of the present invention, below the accompanying drawing used required during embodiment is described is briefly described, apparently, for those of ordinary skills, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the structure flow chart of the transmission line malfunction diagnostic method that the embodiment of the present invention one provides;
Fig. 2 is the structure flow chart of the transmission line malfunction diagnostic method that the embodiment of the present invention two provides;
Fig. 3 is the basic structure schematic diagram of the transmission line malfunction diagnostic system that the embodiment of the present invention provides.
Detailed description of the invention
A kind of transmission line malfunction diagnostic method of embodiment of the present invention offer and system, it is possible to quickly accurate to fault location and identification of defective, it is determined that fault type.
In order to make those skilled in the art be more fully understood that the technical scheme in the embodiment of the present invention, and it is understandable to enable the above-mentioned purpose of the embodiment of the present invention, feature and advantage to become apparent from, below in conjunction with accompanying drawing, the technical scheme in the embodiment of the present invention is described in further detail.
Embodiment one
With reference to accompanying drawing 1, the figure shows transmission line malfunction diagnostic method provided by the invention, it specifically includes that
S101: obtain typical fault morphological Simulation Wave data, described typical fault morphological Simulation Wave data is stored to typical fault morphological Simulation waveform database.
Obtain typical fault form, described typical fault form is thunderbolt, icing, filthy, the reasons such as mountain fire cause fault, obtain the fault waveform data that typical fault form is corresponding, so can adopt analog form simulated failure Wave data, the typical fault Wave data collected or simulated failure Wave data are referred to as fault simulation Wave data, set up typical fault morphological Simulation waveform database, fault simulation Wave data is preserved to typical fault morphological Simulation waveform database, typical fault morphological Simulation waveform database also stores acquisition time or the simulated time of typical fault morphological Simulation Wave data simultaneously, and the fault form to correspondence.
S102: the two ends of distributed fault monitoring device obtain actually detected data respectively, and described actually detected data are stored to typical fault form actual waveform data base.
Transmission line of electricity is installed distributed fault monitoring device, especially on emphasis Monitoring Line, distributed fault monitoring device can complete field monitoring terminal and be installed on line conductor every 20～30 kilometers, can closely catch the travelling wave signal of instant of failure, and the transmission line malfunction monitored is occurred the transient state in moment and steady state fault signal and uploads to data center. Setting up typical fault form actual waveform data base, distributed fault is monitored device and preserves the actually detected data measured to typical fault form actual waveform data base, actually detected data include fault actual waveform data and fault time.
Such as, when fault occurs time, the distributed fault monitoring device being distributed in fault two ends obtains detection data, remembers that described detection data are for (P1, and (P2 T1), T2), wherein: P represents the Wave data that detection receives, T represents that detection receives the moment of Wave data, (P1, T1) and (P2, T2) be the data that the monitoring point that same fault is different detects, data are preserved to typical fault form actual waveform data base.
S103: fault location module obtains T1 and the T2 of described typical fault form actual waveform data base, calculates the difference of T1 and T2, it is determined that the position that fault occurs.
Fault location module obtains the (P1 of a certain fault, and (P2 T1), T2), calculate T1, the difference of T2, obtain the distance L between the monitoring point at two ends, trouble point, set fault and the A point between two monitoring points occurs, A respectively L1 and the L2 of the distance from monitoring point, known traveling wave spread speed in the line is V (light velocity), by L1=(L+ (T1-T2) * V)/2 and L2=(L-(T1-T2) * V)/2, the value of L1 and L2 can be obtained, the generation position of fault is so may determine that according to the installation of distributed fault monitoring device.
S104: fault identification module obtains described actual waveform data and described typical fault morphological Simulation Wave data, extract described actual waveform data and the characteristic quantity of described typical fault morphological Simulation Wave data respectively, contrast its characteristic quantity, analyze and obtain fault identification result.
Fault identification module obtains actual waveform data and typical fault morphological Simulation Wave data, extract the characteristic quantity of actual waveform data and typical fault morphological Simulation Wave data, carry out the contrast of characteristic quantity, analyze and obtain fault identification result, namely the fault form that actual waveform data are corresponding, finally obtains fault type.
Transmission line malfunction diagnostic method provided by the invention, utilize fault that the characteristic that moment travelling wave signal changes occurs, adopt distributed fault monitoring device detection travelling wave signal, then travelling wave signal data are processed, the difference receiving signal time according to distributed fault monitoring device determines the position that fault occurs, the characteristic quantity of the fault waveform data detected Yu typical fault morphological Simulation Wave data pair is contrasted, it is thus achieved that fault identification result, namely obtain the type broken down. Transmission line malfunction diagnostic method provided by the invention is quickly accurate to fault location and identification of defective, it is determined that fault type.
Embodiment two
In conjunction with the embodiments one, optimize further and obtain embodiment two, in conjunction with accompanying drawing 2, it can be seen that embodiment two basic structure provided by the invention, statement is made in the place different from embodiment one with regard to embodiment two. It also includes:
S201: 10 corresponding for each the fault form in described typical fault morphological Simulation waveform database up-to-date Wave datas are stored to typical fault form actual waveform data base, sets up training sample set.
Inquire about described typical fault morphological Simulation waveform database, the fault waveform obtaining 10 up-to-date simulations of every kind of typical fault form according to simulated time is stored in described typical fault form actual waveform data base, as primary data, wherein fault simulation Wave data correspondence fault actual waveform data, simulated time correspondence fault time
S202: typical fault is carried out digital coding, described in carry out the difference of the identical figure place of digital coding and the bigger number of difference replaces the classifications of described typical fault.
Replace all kinds of fault forms with not bigger the counting of the difference of phase equal-order digits and value difference, for instance replace lightning fault forms with 1000, replace icing fault forms with 2000, by the 3000 filthy fault forms of filthy replacement, replace mountain fire fault forms with 4000. Numeral is used to represent, convenient operation.
S203: by described training sample set input fault waveform pretreatment and Characteristic Extraction module, it is thus achieved that characteristic quantity set.
By described initial training sample set input fault waveform pretreatment and Characteristic Extraction module, obtain combining by the characteristic quantity of described typical fault typoiogical classification.
S204: set up BP neural network algorithm model, utilizes described training sample set and described characteristic quantity set to carry out BP neural network algorithm model training.
Set up BP neural network algorithm model, described typical fault form is arranged digital coding respectively, using the combination of described characteristic quantity as input layer, using the digital coding of each corresponding fault form as desired output, hidden layer is set to one layer, and the fault form of diagnosis output is as output layer. Wherein, node in hidden layer being set to 5, frequency of training is set to 50000, and precision is set to 0.00001, and learning rate is set to 0.01.
S205: the characteristic quantity of described actual waveform data is brought into described BP neural network algorithm model, it is thus achieved that the real figure that the characteristic quantity of described actual waveform data is corresponding encodes, and analyzes and obtains fault identification result.
The characteristic quantity of actual waveform data is brought into described BP neural network algorithm model, export the real figure coding that the characteristic quantity obtaining actual waveform data is corresponding, the coding obtained is obtained fault type with the contrast of known malfunction coding, namely analyzes and obtain fault identification result.
Further optimisation technique scheme, encodes real figure the digital coding contrast of typical fault form agreement, calculates Euclidean distance with digital coding respectively, using fault form corresponding for digital coding minimum for Euclidean distance as fault identification result. For the real figure coding deviation malfunction coding that prevention obtains, it is simple to the judgement of fault, it is preferable that Euclidean distance judges, it is also possible to select additive method.
For reducing the complexity of identification, it is easy to unified Analysis, described training sample set or described actual waveform data are carried out effective section identification by fault waveform pretreatment and Characteristic Extraction module, using the beginning as effective section of the travelling wave current amplitude of the described each sample waveform data moment more than 1A, using amplitude less than moment of 50A persistent period 500 microsecond as the end of effective section.
For ensureing the accuracy of identification, also including training sample set is constantly updated in the transmission line malfunction diagnostic method that the embodiment of the present invention provides, it specifically includes that
Artificial acquisition physical fault type. In time there is new fault, artificial line walking determines the accurate form of fault after processing, and by typical fault form actual waveform data base described in result of determination typing, updates initial training sample set simultaneously.
Judge that whether described fault identification result and described physical fault type be identical; If it is not, then increase training sample set number, it is added into described training sample set by described actual waveform data; If it is, when the sample number of described physical fault type is more than 10, then concentrated by described training sample and deduct one of them sample, when the sample number of described physical fault type is equal to 10, then keep described training sample set constant.
Described kainogenesis fault increases to training sample after manually determining exact failure form concentrate, remove the sample obtained from described typical fault morphological Simulation waveform database of a corresponding fault form simultaneously. after the sample obtained from described typical fault morphological Simulation waveform database of all corresponding fault forms is all replaced, by the described kainogenesis fault exact failure form through manually determining with described in fault identification result comparison, if both are inconsistent, then number of training corresponding for described exact failure form is added 1, namely the artificial result of determination of kainogenesis fault is added, if both results are consistent and the number of training of corresponding fault form is more than 10, then the number of training of corresponding fault form is subtracted 1, namely a sample broken down at first is removed, if both results are consistent and the number of training of corresponding fault form is equal to 10, then the number of training of corresponding fault form is constant, so obtain new training sample set.
Updating training sample set is to adapt to environmental change, improves precision in real time. Because the change of climate change and circuit surrounding environment change meeting causing trouble reason, standard in recent years can be more accurate than the standard of time earlier, so obtain the training sample of closing to reality more, it is simple to quickly accurate to fault location and identification of defective, it is determined that fault type.
The transmission line malfunction diagnostic method that basic inventive embodiments provides, the embodiment of the present invention additionally provides a kind of transmission line malfunction diagnostic system, with reference to accompanying drawing 3, it mainly includes distributed fault detection system 101, data reception module 2, data memory module 3 and fault diagnosis module 4, distributed fault detection is, the 101 traveling wave data gathering instant of failure, and traveling wave data are transmitted to data reception module 2, traveling wave data include Wave data and gather the Wave data time; Data reception module 2 is used for receiving traveling wave data, and sends traveling wave data to data memory module 3; Data memory module 3 includes typical fault form actual waveform data base 302 and typical fault morphological Simulation waveform database 301, typical fault form actual waveform data base 302 is for storage line wave datum, typical fault morphological Simulation waveform database 301 is used for storing analog waveform data, and analog waveform data include fault simulation Wave data, corresponding fault form, simulated time; Fault diagnosis module 4 includes fault location module 401 and fault identification module 402, for judging generation position and the fault type of fault corresponding to Wave data.
Further optimisation technique scheme, transmission line malfunction diagnostic system provided by the invention, the input also including web display module 5, web display module 5 connects the outfan of fault diagnosis module 4, for the displaying of various identification results and transmission line of electricity situation.
For good, in conjunction with transmission line of electricity, other detect systematic difference, the transmission line malfunction diagnostic system that the embodiment of the present invention provides includes lightning location system 102, line ice coating monitoring system 103, circuit filth monitoring system 104 or forest fire monitoring system 105, lightning location system 102, line ice coating monitoring system 103, the outfan of circuit filth monitoring system 104 or forest fire monitoring system 105 connects the input of data memory module 3 respectively, be conducive to the application of set multiple systems, merge thus reaching multi-dimensional data, fault location precision improves, the purpose of the automatic identification of fault form, process decision-making for transmission line malfunction and reliable basis is provided.
Lightning location system 102 monitors, by installing the mode of acquisition station throughout the country, position and the lightning current that thunder and lightning occurs in real time, it is provided that the inquiry of lightning fault location; Line ice coating monitoring system 103 by monitoring line ice coating thickness near shaft tower, value of thrust etc. in the mode of electric power line pole tower installing terminal; Circuit filth monitoring system 104 by monitoring the salt density value near shaft tower, grey close value etc. in the mode of electric power line pole tower installing terminal; Forest fire monitoring system 105 by monitoring temperature near shaft tower, humidity etc. in the mode of electric power line pole tower installing terminal. Ambient conditions time various fault occurs can be obtained, it is simple to the determination of fault and analysis by lightning location system 102, line ice coating monitoring system 103, circuit filth monitoring system 104 or forest fire monitoring system 105.
The input of web display module 5 connects the outfan of lightning location system 102, line ice coating monitoring system 103, circuit filth monitoring system 104 or forest fire monitoring system 105 respectively. The displaying of its testing result can be carried out, it is simple to staff checks.
Other detection systems of transmission line of electricity provided by the invention obtain fault diagnosis module and also include fault waveform pretreatment and Characteristic Extraction module 403, fault waveform pretreatment and Characteristic Extraction module 403 are used for processing described Wave data or described fault simulation Wave data, extract the characteristic quantity of Wave data or fault simulation Wave data.
Each embodiment in this specification all adopts the mode gone forward one by one to describe, between each embodiment identical similar part mutually referring to, what each embodiment stressed is the difference with other embodiments.
Invention described above embodiment, is not intended that limiting the scope of the present invention. Any amendment, equivalent replacement and improvement etc. made within the spirit and principles in the present invention, should be included within protection scope of the present invention.
Claims (10)
1. a transmission line malfunction diagnostic method, it is characterised in that described method includes:
Obtain typical fault morphological Simulation Wave data, storing described typical fault morphological Simulation Wave data to typical fault morphological Simulation waveform database, described typical fault morphological Simulation waveform database also includes the simulated time of described typical fault morphological Simulation Wave data;
The two ends of distributed fault monitoring device obtain actually detected data respectively, and described actually detected data are stored to typical fault form actual waveform data base, described detection data are (P1, and (P2 T1), T2), wherein: P represents the Wave data that detection receives, T represents that detection receives the moment of Wave data;
Fault location module obtains T1 and the T2 of described typical fault form actual waveform data base, calculates the difference of T1 and T2, it is determined that the position that fault occurs;
Fault identification module obtains described actual waveform data and described typical fault morphological Simulation Wave data, extract described actual waveform data and the characteristic quantity of described typical fault morphological Simulation Wave data respectively, contrast its characteristic quantity, analyze and obtain fault identification result.
2. transmission line malfunction diagnostic method according to claim 1, it is characterised in that described method also includes:
10 corresponding for each fault form in described typical fault morphological Simulation waveform database up-to-date Wave datas are stored to typical fault form actual waveform data base, sets up training sample set;
Typical fault is carried out digital coding, described in carry out the difference of the identical figure place of digital coding and the bigger number of difference replaces the classifications of described typical fault;
By described training sample set input fault waveform pretreatment and Characteristic Extraction module, it is thus achieved that characteristic quantity set;
Set up BP neural network algorithm model, utilize described training sample set and described characteristic quantity set to carry out BP neural network algorithm model training;
The characteristic quantity of described actual waveform data is brought described BP neural network algorithm model into, it is thus achieved that the real figure that the characteristic quantity of described actual waveform data is corresponding encodes, and analyzes and obtains fault identification result.
3. transmission line malfunction diagnostic method according to claim 2, it is characterised in that the real figure that the characteristic quantity of described acquisition described actual waveform data is corresponding encodes, analyzes acquisition fault identification result and includes:
With the digital coding of described typical fault, described real figure coding is calculated Euclidean distance respectively, and the typical fault that the minimum described digital coding of wherein said Euclidean distance is corresponding is fault identification result.
4. transmission line malfunction diagnostic method according to claim 2, it is characterized in that, described training sample set or described actual waveform data are carried out effective section identification by described fault waveform pretreatment and Characteristic Extraction module, described effective section identification is using the beginning as effective section of the travelling wave current amplitude of the Wave data moment more than 1A, using amplitude less than moment of 50A persistent period 500 microsecond as the end of effective section.
5. transmission line malfunction diagnostic method according to claim 2, it is characterised in that described method also includes:
Artificial acquisition physical fault type;
Judge that whether described fault identification result and described physical fault type be identical;
If it is not, then increase training sample set number, it is added into described training sample set by described actual waveform data;
If it is, when the sample number of described physical fault type is more than 10, then concentrated by described training sample and deduct one of them sample, when the sample number of described physical fault type is equal to 10, then keep described training sample set constant.
6. a transmission line malfunction diagnostic system, it is characterised in that described system includes distributed fault detection system, data reception module, data memory module and fault diagnosis module;
The traveling wave data of described distributed fault detection system acquisition instant of failure, and by the transmission of described traveling wave data to described data reception module, described traveling wave data include Wave data and gather the Wave data time;
Described data reception module is used for receiving described traveling wave data, and sends described traveling wave data to described data memory module;
Described data memory module includes typical fault form actual waveform data base and typical fault morphological Simulation waveform database, described typical fault form actual waveform data base is used for storing described traveling wave data, described typical fault morphological Simulation waveform database is used for storing analog waveform data, and described analog waveform data include fault simulation Wave data, corresponding fault form, simulated time;
Described fault diagnosis module includes fault location module and fault identification module, for judging generation position and the fault type of fault corresponding to described Wave data.
7. transmission line malfunction diagnostic system according to claim 6, it is characterised in that described system also includes web display module, the input of described web display module connects the outfan of described fault diagnosis module.
8. transmission line malfunction diagnostic system according to claim 7, it is characterized in that, described system also includes lightning location system, line ice coating monitoring system, circuit filth monitoring system or forest fire monitoring system, and the outfan of described lightning location system, line ice coating monitoring system, circuit filth monitoring system or forest fire monitoring system connects the input of described data memory module respectively.
9. transmission line malfunction diagnostic system according to claim 8, it is characterized in that, the input of described web display module connects the outfan of described lightning location system, line ice coating monitoring system, circuit filth monitoring system or forest fire monitoring system respectively.
10. the transmission line malfunction diagnostic system according to claim 6-9 any one, it is characterized in that, described fault diagnosis module also includes fault waveform pretreatment and Characteristic Extraction module, and described fault waveform pretreatment and Characteristic Extraction module are used for processing described Wave data or described fault simulation Wave data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610051024.9A CN105676067A (en) | 2016-01-26 | 2016-01-26 | Fault diagnosis method and system of power transmission lines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610051024.9A CN105676067A (en) | 2016-01-26 | 2016-01-26 | Fault diagnosis method and system of power transmission lines |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105676067A true CN105676067A (en) | 2016-06-15 |
Family
ID=56303175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610051024.9A Pending CN105676067A (en) | 2016-01-26 | 2016-01-26 | Fault diagnosis method and system of power transmission lines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105676067A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106950466A (en) * | 2017-04-19 | 2017-07-14 | 上海紫通信息科技有限公司 | Earth fault inverting method of testing |
| CN107356834A (en) * | 2017-08-21 | 2017-11-17 | 赵崇征 | Electronic components discrimination method and device |
| CN108120900A (en) * | 2017-12-22 | 2018-06-05 | 北京映翰通网络技术股份有限公司 | A kind of electrical power distribution network fault location method and system |
| CN108663600A (en) * | 2018-05-09 | 2018-10-16 | 广东工业大学 | A kind of method for diagnosing faults, device and storage medium based on power transmission network |
| CN109062740A (en) * | 2018-06-05 | 2018-12-21 | 北京电子工程总体研究所 | A kind of auxiliary Check System and method based on direct fault location |
| CN109270407A (en) * | 2018-11-16 | 2019-01-25 | 国网山东省电力公司电力科学研究院 | Extra high voltage direct current transmission line failure cause discrimination method based on Multi-source Information Fusion |
| CN109584232A (en) * | 2018-11-28 | 2019-04-05 | 成都天衡智造科技有限公司 | Equipment use state on-line monitoring method, system and terminal based on image recognition |
| CN109633370A (en) * | 2018-12-08 | 2019-04-16 | 国网山东省电力公司德州供电公司 | A kind of electric network failure diagnosis method based on fault message coding and fusion method |
| CN110187233A (en) * | 2019-05-23 | 2019-08-30 | 国家电网有限公司 | Holographic sensor, transmission line malfunction method of disposal and terminal device |
| CN110726898A (en) * | 2018-07-16 | 2020-01-24 | 北京映翰通网络技术股份有限公司 | Power distribution network fault type identification method |
| CN110726899A (en) * | 2019-10-22 | 2020-01-24 | 广西电网有限责任公司电力科学研究院 | Power transmission line span checking method |
| CN110988560A (en) * | 2019-12-20 | 2020-04-10 | 中国人民解放军陆军军医大学第一附属医院 | Medical equipment fault detection system and method based on real-time current |
| CN111398714A (en) * | 2020-04-01 | 2020-07-10 | 深圳市中电电力技术股份有限公司 | Multi-data fusion power quality fault diagnosis method and system |
| CN111404603A (en) * | 2020-06-03 | 2020-07-10 | 广东电网有限责任公司佛山供电局 | Communication network fault rapid positioning method based on maximum matching degree |
| CN113109633A (en) * | 2021-06-16 | 2021-07-13 | 武汉华瑞伏安电力科技有限公司 | Power transmission line lightning stroke monitoring method and system based on distributed traveling wave positioning technology |
| CN113189448A (en) * | 2021-04-29 | 2021-07-30 | 广东电网有限责任公司清远供电局 | Method and device for detecting fault type of power transmission line |
-
2016
- 2016-01-26 CN CN201610051024.9A patent/CN105676067A/en active Pending
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106950466A (en) * | 2017-04-19 | 2017-07-14 | 上海紫通信息科技有限公司 | Earth fault inverting method of testing |
| CN107356834A (en) * | 2017-08-21 | 2017-11-17 | 赵崇征 | Electronic components discrimination method and device |
| CN108120900A (en) * | 2017-12-22 | 2018-06-05 | 北京映翰通网络技术股份有限公司 | A kind of electrical power distribution network fault location method and system |
| CN108120900B (en) * | 2017-12-22 | 2020-02-11 | 北京映翰通网络技术股份有限公司 | Power distribution network fault positioning method and system |
| CN108663600A (en) * | 2018-05-09 | 2018-10-16 | 广东工业大学 | A kind of method for diagnosing faults, device and storage medium based on power transmission network |
| CN108663600B (en) * | 2018-05-09 | 2020-11-10 | 广东工业大学 | Fault diagnosis method and device based on power transmission network and storage medium |
| CN109062740A (en) * | 2018-06-05 | 2018-12-21 | 北京电子工程总体研究所 | A kind of auxiliary Check System and method based on direct fault location |
| CN110726898A (en) * | 2018-07-16 | 2020-01-24 | 北京映翰通网络技术股份有限公司 | Power distribution network fault type identification method |
| CN110726898B (en) * | 2018-07-16 | 2022-02-22 | 北京映翰通网络技术股份有限公司 | Power distribution network fault type identification method |
| CN109270407A (en) * | 2018-11-16 | 2019-01-25 | 国网山东省电力公司电力科学研究院 | Extra high voltage direct current transmission line failure cause discrimination method based on Multi-source Information Fusion |
| CN109270407B (en) * | 2018-11-16 | 2022-02-25 | 国网山东省电力公司电力科学研究院 | Extra-high voltage direct current transmission line fault reason identification method based on multi-source information fusion |
| CN109584232A (en) * | 2018-11-28 | 2019-04-05 | 成都天衡智造科技有限公司 | Equipment use state on-line monitoring method, system and terminal based on image recognition |
| CN109633370A (en) * | 2018-12-08 | 2019-04-16 | 国网山东省电力公司德州供电公司 | A kind of electric network failure diagnosis method based on fault message coding and fusion method |
| CN110187233A (en) * | 2019-05-23 | 2019-08-30 | 国家电网有限公司 | Holographic sensor, transmission line malfunction method of disposal and terminal device |
| CN110726899A (en) * | 2019-10-22 | 2020-01-24 | 广西电网有限责任公司电力科学研究院 | Power transmission line span checking method |
| CN110726899B (en) * | 2019-10-22 | 2021-08-24 | 广西电网有限责任公司电力科学研究院 | Power transmission line span checking method |
| CN110988560A (en) * | 2019-12-20 | 2020-04-10 | 中国人民解放军陆军军医大学第一附属医院 | Medical equipment fault detection system and method based on real-time current |
| CN111398714A (en) * | 2020-04-01 | 2020-07-10 | 深圳市中电电力技术股份有限公司 | Multi-data fusion power quality fault diagnosis method and system |
| CN111404603A (en) * | 2020-06-03 | 2020-07-10 | 广东电网有限责任公司佛山供电局 | Communication network fault rapid positioning method based on maximum matching degree |
| CN111404603B (en) * | 2020-06-03 | 2020-11-27 | 广东电网有限责任公司佛山供电局 | Communication network fault rapid positioning method based on maximum matching degree |
| CN113189448A (en) * | 2021-04-29 | 2021-07-30 | 广东电网有限责任公司清远供电局 | Method and device for detecting fault type of power transmission line |
| CN113109633A (en) * | 2021-06-16 | 2021-07-13 | 武汉华瑞伏安电力科技有限公司 | Power transmission line lightning stroke monitoring method and system based on distributed traveling wave positioning technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105676067A (en) | Fault diagnosis method and system of power transmission lines | |
| CN103337831B (en) | A kind of out-of-step solution method with adaptation function | |
| CN106855603A (en) | Feeder line fault independent positioning method, detecting terminal, main website, alignment system | |
| CN106771867A (en) | Feeder line fault independent positioning method, detecting terminal, main website, alignment system | |
| CN113533906B (en) | Intelligent overhead transmission line fault type diagnosis method and system | |
| CN106358212B (en) | The detection method and device of indoor distributed system | |
| WO2020162937A1 (en) | Automated model validation system for electrical grid | |
| CN103776492A (en) | OPGW condition monitoring system | |
| CN111835006B (en) | Low-voltage transformer area topology identification method based on voltage curve and least square | |
| CN110645940A (en) | Dynamic prediction system and method for clearance distance between wire and tree | |
| CN105279612A (en) | Poisson distribution-based power transmission line tripping risk assessment method | |
| CN105279565A (en) | Lightning early warning method and lightning early warning system | |
| CN110390117B (en) | Numerical simulation method and system for thunderstorm electrification process | |
| CN107222169B (en) | A kind of photovoltaic array real time monitoring and fault detection method based on outlier detection | |
| CN115186974A (en) | Power distribution network power supply quality comprehensive evaluation method and system based on business middling station | |
| CN116780758A (en) | On-line monitoring system and method for multi-sensor data fusion of power transmission line | |
| CN205622328U (en) | Join in marriage power system fault online intelligent diagnostic system | |
| CN117406137B (en) | Method and system for monitoring lightning leakage current of power transmission line | |
| CN105425105A (en) | Method and system for comprehensive positioning of fault line of power grid | |
| CN204256103U (en) | A kind of monitoring system of the transmission line travelling wave localization of fault based on mobile Internet | |
| CN113688987A (en) | Training method of photovoltaic monitoring model, monitoring method of photovoltaic equipment and equipment | |
| CN112016739A (en) | Fault detection method and device, electronic equipment and storage medium | |
| CN116484554A (en) | Topology identification method, device, equipment and medium for power distribution network | |
| US11379091B2 (en) | Operation support device and operation support method | |
| CN110645939A (en) | System and method for dynamically predicting relative vertical distance between two wires |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160615 |