CN107609569B - Power distribution network ground fault positioning method based on multi-dimensional feature vectors - Google Patents

Power distribution network ground fault positioning method based on multi-dimensional feature vectors Download PDF

Info

Publication number
CN107609569B
CN107609569B CN201710643117.5A CN201710643117A CN107609569B CN 107609569 B CN107609569 B CN 107609569B CN 201710643117 A CN201710643117 A CN 201710643117A CN 107609569 B CN107609569 B CN 107609569B
Authority
CN
China
Prior art keywords
fault
distribution network
power distribution
ground fault
ground
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710643117.5A
Other languages
Chinese (zh)
Other versions
CN107609569A (en
Inventor
戴义波
张建良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Inhand Network Technology Co ltd
Original Assignee
Beijing Inhand Network Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Inhand Network Technology Co ltd filed Critical Beijing Inhand Network Technology Co ltd
Priority to CN201710643117.5A priority Critical patent/CN107609569B/en
Publication of CN107609569A publication Critical patent/CN107609569A/en
Application granted granted Critical
Publication of CN107609569B publication Critical patent/CN107609569B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention discloses a power distribution network ground fault positioning method based on a multi-dimensional characteristic vector and a positioning detection system based on the method. The method for positioning the ground fault of the power distribution network forms a machine learning item for training a ground fault judgment model according to the fault characteristic vector sent by the power distribution network detection terminal and by combining the topological structure of the power distribution network in the main station area and the fed-back actual fault processing result, trains the existing ground fault judgment model, and enables the existing ground fault judgment model to be continuously perfect and output a more accurate fault positioning result.

Description

Power distribution network ground fault positioning method based on multi-dimensional feature vectors
Technical Field
The invention relates to the technical field of power detection, in particular to a power distribution network ground fault positioning method based on a multi-dimensional characteristic vector and a positioning detection system based on the method.
Background
CN103728532 discloses a method for locating a ground fault by installing a special distribution automation feeder terminal in a distribution line sectionalizing switch. According to the method, the distribution automation feeder terminals collect zero-sequence voltage 3U0 and zero-sequence current 3I0, then 3U0 and 3I0 are subjected to a series of processing and feature extraction, then the positions of switches where the current distribution automation feeder terminals are located relative to a ground fault point are judged by using preset fault judgment rules, and finally a fault section is located by combining a plurality of distribution automation feeder terminals.
According to the technical scheme, only fault information collected by a single terminal is used for judging when a fault is judged, comprehensive judgment of the fault information collected by a plurality of terminals is not effectively utilized, higher judgment accuracy can be achieved by comparing and judging characteristics among the plurality of terminals when a ground fault is utilized, the terminal only outputs semaphore information (0 or 1) on a fault path, the fault characteristic information is discarded after the fault judgment is completed, further analysis on the fault cannot be performed afterwards, meanwhile, updating of a preset fault judgment rule in the terminal can be completed only by updating a terminal program, a large amount of terminals need to be updated, and the terminals are in a work stop state for a period of time in the updating process.
CN104101812 discloses a fault detection and positioning method and system for a low-current grounding power distribution network. The system consists of a feeder line monitoring unit, a communication terminal and a system main station. And after the feeder line monitoring unit detects the suspected ground fault, the other two phases of transmission data are wirelessly and synchronously triggered. The system main station and the communication terminal adopt GPS time service, and the communication terminal and the feeder line monitoring unit carry out time service through a time division multiplexing wireless communication network. The system main station gathers the fault recording data of the three-phase feeder line monitoring unit of a plurality of points through the communication terminal, then extracts the transient signal of zero sequence voltage and zero sequence current from the recording in the main station, calculates the characteristic value, includes: amplitude, average value, differential value, integral value and combination thereof, transient zero sequence active power and zero sequence reactive power, calculating the similarity of transient zero sequence voltage and zero sequence current signal waveforms of each position, and preferentially judging each position on the screened suspected fault line according to the difference between the characteristic values and waveform similarity of the transient zero sequence voltage and zero sequence current before and after the ground fault point to locate the ground fault point.
However, in order to capture enough ground fault information, the fault recording will use a higher sampling rate, and usually a single recording will reach a size of tens of kbytes, thereby causing the following problems: 1. the recording transmission needs a long time, and has certain influence on the real-time performance of fault judgment; 2. in a season with high fault, multiple line faults may occur in a short time in the same main station region, and a large amount of data flow may rush into the main station in a period of time because collection of a single recording often passes through dozens of data interactions, so that the main station is required to have the capacity of processing a large amount of data flow for a long time, and the requirement on the performance of the main station is high; 3. most of the current power distribution terminals with fault recording adopt wireless networks and master station communication, a large amount of recording data can generate not small wireless charges, and the operation cost is high.
Disclosure of Invention
Based on the various defects in the prior art, one of the technical effects to be achieved by the invention is to comprehensively utilize the fault characteristics reported by a plurality of detection terminals to realize the positioning of the ground fault.
The invention also aims to achieve the technical purpose that the data interaction between the detection terminal and the data processing main station is maintained at a lower data volume level so as to ensure that the data processing main station cannot cause the paralysis of the main station due to the inrush of a large amount of data when a plurality of ground faults occur in the area under the jurisdiction of the data processing main station, and simultaneously, the data communication charge between the detection terminal and the data processing main station can be reduced.
In order to solve the technical problem, the invention provides a power distribution network ground fault positioning system, which comprises a power distribution network detection terminal 1 and a master station 2, wherein the master station is provided with a plurality of program modules, and the program modules comprise:
a fault feature collection unit 21 that receives a fault feature vector transmitted from the power distribution network detection terminal;
the power distribution network topology information storage part 22 is used for storing physical position descriptions of all power distribution network detection terminals 1 in the main station jurisdiction and the topology structure of the power distribution network in the main station jurisdiction;
the fault event collecting part 23 is used for classifying and collecting the fault characteristic vectors, and collecting the fault characteristic vectors uploaded by the power distribution network detection terminals under the same bus into a ground fault event according to the power distribution network topological structure;
a ground fault determination unit 24 that performs fault determination using a ground fault determination model based on the ground fault event data and outputs a fault location result;
a failure processing policy generation unit 25 for generating a policy corresponding to the failure processing based on the failure positioning result;
a failure processing information feedback unit 26 for receiving an actual processing result of the failure event;
a matching information storage unit 27 for matching the fed-back actual failure processing result with the ground fault event generated by the failure feature aggregation unit to form a machine learning entry;
and a fault determination model generation unit 28 that performs machine learning training on the ground fault determination model based on the machine learning entries and updates the ground fault determination model in the ground fault determination unit 24 based on the training result.
In one embodiment, the method used for machine learning training is decision tree, support vector machine, random forest, CNN, or RNN.
According to another aspect of the present invention, the present invention further provides a method for locating a ground fault of a power distribution network, which is characterized in that the method includes:
the power distribution network detection terminal uploads the fault characteristic vector to the master station;
generating a ground fault event by utilizing the fault characteristic vector, the distribution network topological structure and the distribution network detection terminal physical position;
inputting the fault grounding event into a grounding fault judgment model for fault judgment, and outputting a fault positioning result;
generating a fault processing strategy according to the fault positioning result, and feeding back an actual fault processing result;
matching the fed-back actual fault processing result with the ground fault event generated by the fault characteristic collection part so as to form a machine learning item;
and training the grounding fault judgment model by using the machine learning items, and updating the fault judgment model.
In one embodiment, after receiving the fault characteristic vector, the master station performs an interaction protocol for data communication with the power distribution network detection terminal, and simultaneously analyzes the fault characteristic vector data.
In one embodiment, the method used for training is decision tree, support vector machine, random forest, CNN, or RNN.
According to another aspect of the present invention, there is also provided a power distribution network detection terminal suitable for the ground fault location system of the present invention, wherein the power distribution network detection terminal includes:
the ground fault recording module can record faults according to the operation parameters of the power distribution network;
and the fault feature extraction module is used for performing feature extraction operation on the expected power distribution operation parameters according to the fault recording so as to obtain fault feature vectors.
In one embodiment, the parameters for recording the ground fault include three-phase current, three-phase voltage, three-phase ground electric field, zero sequence current or zero sequence voltage of the power distribution network.
In one embodiment, the operation of the fault feature extraction module for feature extraction on the recorded wave comprises amplitude, average value, differential value, integral value, steady state zero sequence active power, zero sequence reactive power or zero sequence current spectrum.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow diagram of a method according to an embodiment of the invention;
FIG. 2 is a flow chart of a method according to an example of the invention;
FIG. 3 is a schematic diagram of a training process for machine learning according to an example of the invention;
FIG. 4 is a schematic diagram of a decision process for a decision tree prediction model according to an example of the invention;
fig. 5 is a schematic diagram of a fault feature vector extraction process according to an example of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings.
First embodiment
Fig. 1 is a schematic system structure diagram of an embodiment of the distribution network ground fault location system of the present invention. This embodiment will be described with reference to fig. 1.
The distribution network ground fault positioning system of this embodiment includes: the system comprises a power distribution network detection terminal 1 and a main station 2, wherein the power distribution network detection terminal 1 is distributed and arranged at different positions of a power distribution network line and comprises but not limited to FTUs, DTUs, intelligent switches or fault indicators. When a ground fault occurs in the power distribution network, the power distribution network detection terminal carries out fault recording on one or more parameters of three-phase current, three-phase voltage, three-phase ground electric field, zero sequence current and zero sequence voltage of the power distribution network, and processes fault recording data to extract fault characteristics, wherein the processing of the fault recording data comprises but is not limited to calculating amplitude, average value, differential value, integral value, steady state zero sequence active power, zero sequence reactive power or zero sequence current frequency spectrum and the like of the recording data. And combining a plurality of fault characteristics to form a fault characteristic vector, wherein the fault characteristic vector is basic data information for the ground fault positioning judgment of the power distribution network ground fault positioning system.
The master station of this embodiment is provided with a plurality of program modules, and each program module includes a plurality of instructions for performing corresponding data processing. The plurality of program modules includes:
and a fault feature collection unit 21 for receiving the fault feature vector transmitted from the power distribution network detection terminal, including an interaction protocol for data communication with the power distribution network detection terminal and analysis of fault feature vector data.
And the power distribution network topology information storage part 22 is used for storing the physical position description of all the power distribution network detection terminals 1 in the main station area and the topology structure of the power distribution network in the area. For example, a PMIS system in a distribution automation system may be employed.
And a fault event collecting unit 23 configured to collect all fault feature vectors by classifying them according to the fault feature vectors input by the fault feature collecting unit 21 and the physical positions of the power distribution network detection terminals corresponding to the fault feature vectors provided by the power distribution network topology information storage unit 22, and collect the fault feature vectors uploaded by the power distribution network detection terminals on the same bus as a ground fault event according to the power distribution network topology structure, where the ground fault event data includes the fault feature vectors uploaded by the power distribution network detection terminals on the same bus and the power distribution network line topology structure of the bus.
And a ground fault determination unit 24 for performing a fault determination by using a ground fault determination model incorporated therein based on the ground fault event data outputted from the fault event collection unit 23, and outputting a fault location result.
And a failure processing strategy generating unit 25 for generating a strategy for processing the failure based on the failure location result outputted from the failure determining unit 24, and outputting the processing strategy to the power maintenance personnel.
In the present embodiment, the ground fault determination model of fault determination unit 24 is continuously refined through machine learning methods including, but not limited to, using decision trees, support vector machines, random forests, CNNs, or RNNs. The program modules for performing ground fault model machine learning include:
the failure processing information feedback unit 26 is configured to allow the grid maintenance worker to input an actual processing result of a certain failure event to the failure processing information feedback unit 26.
And a matching information storage unit 27 for matching the ground fault event outputted from the fault event aggregation unit 23 with the result of the actual fault processing to form a complete piece of information and sending the complete piece of information to the fault determination model generation unit 28.
And a failure determination model generation unit 28 that performs machine learning based on the ground fault event transmitted from the matching information storage unit 27 and the result information of the actual failure processing, and completes the ground fault determination model.
Fig. 2 is a flowchart of a method for locating a ground fault of a power distribution network according to this embodiment, which is described in detail below with reference to fig. 2.
Step 100, when an earth fault occurs in the power distribution network, detecting the earth fault by a power distribution network detection terminal, carrying out fault recording on one or more parameters of three-phase current, three-phase voltage, three-phase ground-to-earth electric field, zero-sequence current and zero-sequence voltage of the power distribution network by the power distribution network detection terminal, and processing fault recording data to extract fault characteristics, wherein the processing of the fault recording data comprises but is not limited to calculating amplitude, average value, differential value, integral value, steady-state zero-sequence active power, zero-sequence reactive power or zero-sequence current frequency spectrum and the like of the recording data. Combining multiple fault signatures forms a fault signature vector. And the power distribution network detection terminal uploads the fault characteristic vector to the master station.
And 101, analyzing the fault feature vector by a fault feature collection part of the main station, and simultaneously carrying out protocol on interaction between the main station and the power distribution network detection terminal. The fault feature vector is encapsulated in a specific message in the protocol, and the master station analyzes the message and extracts the fault feature vector from the message. The interaction process of the fault feature vector information of the master station and the power distribution terminal in the embodiment is described below by taking a specification specified in the national grid < < operation and detection three [ 2017 ] 6 > > as an example. Firstly, the power distribution terminal initiates connection to the master station, then both sides carry out a link establishment process, and after the link is successfully established, both sides are in a ready state to carry out normal data interaction. After the power distribution terminal collects a plurality of fault characteristic elements, the fault characteristic elements are packaged in a burst telemetry message, the burst telemetry message comprises a plurality of information bodies, each information body corresponds to one fault characteristic element, finally, the power distribution terminal transmits the packaged burst telemetry message to a main station, and the main station analyzes all the information bodies from the burst telemetry message to obtain all the fault characteristic elements to form fault characteristic vectors and outputs the fault characteristic vectors to a subsequent processing process.
And step 102, according to the fault characteristic vector, calling the physical position of the power distribution network detection terminal uploading the fault characteristic vector from the power distribution network topology information storage part, and simultaneously calling a power distribution network topology structure and a bus topology structure which are obtained from the physical position. And classifying and collecting all fault characteristic vectors according to the information, and collecting the fault characteristic vectors uploaded by the power distribution network detection terminals under the same bus into a ground fault event, wherein the ground fault event data comprises the fault characteristic vectors uploaded by the power distribution network detection terminals under the same bus and the power distribution network line topological structure of the bus.
Step 103 is to input the fault-to-ground event to the ground fault determination unit, perform fault determination using a ground fault determination model incorporated therein, and output a fault location result.
Step 104 is to generate a fault handling strategy for handling the fault based on the fault location result outputted from the fault determination unit 24, and to output the fault handling strategy to the power maintenance personnel.
And 105, carrying out actual overhaul of the power distribution network by power maintenance personnel, and feeding back an actual fault processing result to the master station.
And 106, matching the fed-back actual fault processing result with the ground fault event generated by the fault characteristic collecting part, thereby forming a machine learning item.
Step 107 is to train the ground fault determination model using the machine learning entry, and update the fault determination model in the ground fault determination unit.
Distribution terminals can be divided into two types according to the relative positions of the distribution network detection terminal 1 and the ground fault point. One class is denoted by 1 indicating that the distribution network test terminal 1 is on the fault path, i.e. on the path of the earth fault current flowing back to the substation, and the other class is denoted by 0, i.e. the distribution terminal is not on the fault path. The aim of machine learning in the invention is to train a prediction model, so that after a fault characteristic vector X collected by a certain power distribution network detection terminal 1 is input, the model can predict the probability Y of the terminal in a fault path. Wherein Y is a decimal between 0 and 1, and a larger value indicates a higher probability that the distribution network detection terminal is in a fault path. Fig. 3 shows a training process of machine learning according to the present invention, in which the failure determination model generation unit 28 optimizes an original failure determination model according to an input learning item and a machine learning algorithm, the optimized model is detected according to the model evaluation index, if the model passes the detection, the newly generated failure determination model is replaced with the original model, and if the model does not pass the detection, the model needs to be further adjusted and optimized again. The model evaluation indexes comprise accuracy, missing judgment rate and error judgment rate.
In this embodiment, a machine learning algorithm used in the present invention is described by taking a decision tree algorithm as an example, a prediction model finally obtained by using the decision tree algorithm is a tree-shaped decision chain, and when a new fault feature vector is input to the prediction model, a fault prediction result is obtained according to the decision chain. Fig. 4 is a schematic diagram of a decision process of the decision tree prediction model according to this embodiment.
As shown in fig. 5, in this embodiment, the process of extracting the fault feature vector by the distribution network detection terminal is as follows: the power distribution terminal synthesizes zero-sequence current by collecting three-phase current, or directly collects the zero-sequence current by using a power distribution network detection terminal, and then obtains the amplitude of the zero-sequence current by using FFT (fast Fourier transform), namely the amplitude of the zero-sequence current.
Therefore, the advantages of the invention are mainly as follows:
1. the invention can utilize the fault characteristics collected by a plurality of terminals to carry out comprehensive fault judgment, and has higher accuracy than that of directly judging the fault by a single terminal.
2. In the invention, each terminal is required to transmit the collected fault characteristics to the master station, and the master station can carry out deeper analysis on the fault according to the characteristic information.
3. The terminal is only responsible for collecting fault characteristics, and the fault judgment is completed by the master station, so that the terminal is not required to be modified when a fault judgment algorithm is updated.
4. The terminal only needs to transmit the fault characteristics instead of fault recording, and the transmitted data volume is small, so that the data transmission time is short, and the real-time influence on fault judgment is small.
5. The terminal only needs to transmit the fault characteristics, one-time fault characteristic transmission can be completed only through one or two times of data interaction, long-time large flow is not easy to occur even in high-fault seasons, and the requirement on the performance of the main station is low.
6. The terminal only needs to transmit the fault characteristics instead of fault recording, and the transmitted data volume is small, so that the network expense is low, and the operation cost is low.
The above description is only an embodiment of the present invention, and the protection scope of the present invention is not limited thereto, and any person skilled in the art should modify or replace the present invention within the technical specification of the present invention.

Claims (9)

1. The utility model provides a distribution network earth fault positioning system, distribution network earth fault positioning system includes distribution network detection terminal (1) and main website (2), be provided with a plurality of program modules in the main website, a plurality of program modules include:
a fault feature collection unit (21) that receives a fault feature vector transmitted by the power distribution network detection terminal;
the power distribution network topology information storage part (22) is used for storing physical position descriptions of all power distribution network detection terminals (1) in the main station jurisdiction and a topology structure of a power distribution network in the main station jurisdiction;
a fault event collection part (23) which classifies and collects all fault feature vectors according to the fault feature vectors input by the fault feature collection part (21) and the physical positions of the power distribution network detection terminals corresponding to the fault feature vectors provided by the power distribution network topology information storage part (22), collects the fault feature vectors uploaded by the power distribution network detection terminals under the same bus into a ground fault event according to the power distribution network topology structure, wherein the ground fault event data comprises the fault feature vectors uploaded by the power distribution network detection terminals under the same bus and the power distribution network line topology structure of the bus;
a ground fault determination unit (24) that performs a fault determination using a ground fault determination model based on the ground fault event data and outputs a fault location result;
a fault processing strategy generating part (25) which generates a corresponding strategy for processing the fault according to the fault positioning result;
a failure processing information feedback unit (26) for receiving an actual processing result of the failure event;
a matching information storage unit (27) for matching the fed-back actual failure processing result with the ground failure event generated by the failure event aggregation unit to form a machine learning entry;
and a fault determination model generation unit (28) that performs machine learning training on the ground fault determination model based on the machine learning entries, and updates the ground fault determination model in the ground fault determination unit (24) based on the training result.
2. The distribution network ground fault location system of claim 1, wherein the machine learning training is performed by a decision tree, a support vector machine, a random forest, a CNN, or an RNN.
3. A distribution network ground fault positioning method is characterized by comprising the following steps:
the power distribution network detection terminal uploads the fault characteristic vector to the master station;
classifying and collecting all fault characteristic vectors according to the input fault characteristic vectors and the physical positions of the power distribution network detection terminals corresponding to the fault characteristic vectors, collecting the fault characteristic vectors uploaded by the power distribution network detection terminals under the same bus into a ground fault event according to the power distribution network topological structure, wherein the ground fault event data comprises the fault characteristic vectors uploaded by the power distribution network detection terminals under the same bus and the power distribution network line topological structure of the bus;
inputting the earth fault event into an earth fault judgment model for fault judgment, and outputting a fault positioning result;
generating a fault processing strategy according to the fault positioning result, and feeding back an actual fault processing result;
matching the fed-back actual fault processing result with the ground fault event generated by the fault event collecting part so as to form a machine learning item;
and training the ground fault judgment model by using the machine learning entries, and updating the fault judgment model.
4. The power distribution network ground fault positioning method of claim 3, characterized in that after receiving the fault feature vector, the master station performs an interaction protocol for data communication with the power distribution network detection terminal and simultaneously analyzes the fault feature vector data.
5. The method for locating the ground fault of the power distribution network according to claim 4, wherein the method adopted by the training is decision tree, support vector machine, random forest, CNN or RNN.
6. A distribution network detection terminal for use in the ground fault location system of claim 1, the distribution network detection terminal comprising:
the ground fault recording module can record faults according to the operation parameters of the power distribution network;
and the fault feature extraction module is used for performing feature extraction operation on the expected power distribution operation parameters according to the fault recording so as to obtain fault feature vectors.
7. The power distribution network detection terminal of claim 6, wherein the parameters for recording the ground fault include three-phase current, three-phase voltage, three-phase ground electric field, zero-sequence current or zero-sequence voltage of the power distribution network.
8. The power distribution network detection terminal according to claim 6, wherein the fault feature extraction module performs feature extraction operation on the recording waves, and the operation includes amplitude, average value, differential value, integral value, steady state zero sequence active power, zero sequence reactive power or zero sequence current spectrum.
9. The power distribution network detection terminal of claim 6, wherein the power distribution network detection terminal is an FTU, a DTU, a smart switch, or a fault indicator.
CN201710643117.5A 2017-07-31 2017-07-31 Power distribution network ground fault positioning method based on multi-dimensional feature vectors Active CN107609569B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710643117.5A CN107609569B (en) 2017-07-31 2017-07-31 Power distribution network ground fault positioning method based on multi-dimensional feature vectors

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710643117.5A CN107609569B (en) 2017-07-31 2017-07-31 Power distribution network ground fault positioning method based on multi-dimensional feature vectors

Publications (2)

Publication Number Publication Date
CN107609569A CN107609569A (en) 2018-01-19
CN107609569B true CN107609569B (en) 2020-11-03

Family

ID=61064154

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710643117.5A Active CN107609569B (en) 2017-07-31 2017-07-31 Power distribution network ground fault positioning method based on multi-dimensional feature vectors

Country Status (1)

Country Link
CN (1) CN107609569B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019216878A1 (en) * 2018-05-07 2019-11-14 Inhand Networks Inc. System for locating fault in power distribution network based on mixed mode wave recording
CN108535572B (en) * 2018-05-10 2020-10-23 长沙理工大学 Metering system secondary circuit monitoring method and device based on fundamental wave zero sequence characteristics
CN109188195A (en) * 2018-08-17 2019-01-11 国网江苏省电力有限公司电力科学研究院 A kind of distribution small current grounding fault localization method and system
CN109490704A (en) * 2018-10-16 2019-03-19 河海大学 A kind of Fault Section Location of Distribution Network based on random forests algorithm
CN109814004A (en) * 2019-03-19 2019-05-28 广东电网有限责任公司 Distribution Fault Location System and method
CN109884475A (en) * 2019-04-02 2019-06-14 云南电网有限责任公司大理供电局 A kind of electric network fault detection method, device, system and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103914735A (en) * 2014-04-17 2014-07-09 北京泰乐德信息技术有限公司 Failure recognition method and system based on neural network self-learning
CN103941156A (en) * 2014-04-16 2014-07-23 华北电力大学 Multi-message fusion section locating method based on extreme learning machine
CN106771870A (en) * 2016-12-26 2017-05-31 北京国电通网络技术有限公司 A kind of distribution net work earthing fault localization method and system

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101452039A (en) * 2007-11-29 2009-06-10 上海蓝瑞电气有限公司 Earth fault synthesis diagnostic equipment for medium pressure electrical power distribution network
WO2013035110A2 (en) * 2011-09-09 2013-03-14 Enersys Astra Limited System and method for monitoring and restoring a fault occurring in an electric transmission and distribution network
CN103558511A (en) * 2013-11-18 2014-02-05 国家电网公司 Online earth fault positioning system for power distribution network
CN104155574B (en) * 2014-07-31 2017-12-15 国网湖北省电力公司武汉供电公司 Distribution network failure sorting technique based on Adaptive Neuro-fuzzy Inference
CN104599193A (en) * 2015-01-16 2015-05-06 国家电网公司 Rule base based single-phase ground fault positioning method of distribution network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103941156A (en) * 2014-04-16 2014-07-23 华北电力大学 Multi-message fusion section locating method based on extreme learning machine
CN103914735A (en) * 2014-04-17 2014-07-09 北京泰乐德信息技术有限公司 Failure recognition method and system based on neural network self-learning
CN106771870A (en) * 2016-12-26 2017-05-31 北京国电通网络技术有限公司 A kind of distribution net work earthing fault localization method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
配电线路在线故障识别与诊断方法研究;翟进乾;《中国博士学位论文全文数据库》;20130228;正文第33-35页 *

Also Published As

Publication number Publication date
CN107609569A (en) 2018-01-19

Similar Documents

Publication Publication Date Title
CN102937675B (en) The method of work of Real-time Electrical Distribution Network Data collection and fault location system
CN103235221B (en) Fault detecting system and fault detecting method for photovoltaic power station remote monitoring
Kezunovic Smart fault location for smart grids
CN103414251B (en) A kind of substation network communication analogue system based on IEC61850
CN104239437B (en) A kind of intelligent alarm analysis method towards dispatching of power netwoks
CN103647276B (en) A kind of quality of power supply early warning system and method thereof
CN103166323B (en) System for monitoring secondary circuit model on line in real time based on protection device
CN102288879B (en) Ultrasonic detection device for partial discharge of switchgear based on wireless network
US7725295B2 (en) Cable fault detection
CN101267116B (en) An automatic positioning method for power quality interference source of distribution grid
CN102184625B (en) Third generation (3G) communication network-based transmission line fault area positioning system
CN102508076B (en) Fault diagnosis device and method based on multi-agent system and wavelet analysis
CN102074956B (en) Power grid risk management method and system
CN105868075A (en) System and method for monitoring and analyzing great deal of logs in real time
CN106124935B (en) Middle and low voltage network Fault Locating Method
CN103827678B (en) Method for distributed waveform recording in a power distribution system
CN103033703B (en) A kind of online, intelligent substation analysis test method of off-line integral type
CN107994539B (en) A kind of distribution line failure detection system based on Cloud Server
CN101968525B (en) Fault positioning method for power distribution network by combining simulation calculation and real-time monitoring
CN102142716B (en) Power grid online fault diagnosis method based on three-state data multidimensional cooperative processing
EP2082246B1 (en) Cable fault detection
CN103312037B (en) Device and method for testing pressure of intelligent substation
US9874593B2 (en) Decision support system for outage management and automated crew dispatch
CN104502795A (en) Intelligent fault diagnosis method suitable for microgrid
CN104753178A (en) Power grid fault handling system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant