CN111404130B - Novel power distribution network fault detection method and fault self-healing system based on quick switch - Google Patents
Novel power distribution network fault detection method and fault self-healing system based on quick switch Download PDFInfo
- Publication number
- CN111404130B CN111404130B CN202010287847.8A CN202010287847A CN111404130B CN 111404130 B CN111404130 B CN 111404130B CN 202010287847 A CN202010287847 A CN 202010287847A CN 111404130 B CN111404130 B CN 111404130B
- Authority
- CN
- China
- Prior art keywords
- fault
- signal
- traveling wave
- power distribution
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000013075 data extraction Methods 0.000 claims abstract description 15
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000005457 optimization Methods 0.000 claims abstract description 6
- 239000002245 particle Substances 0.000 claims abstract description 6
- 230000000875 corresponding effect Effects 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 9
- 238000013473 artificial intelligence Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000009471 action Effects 0.000 abstract description 6
- 238000000691 measurement method Methods 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H7/00—Emergency protective circuit arrangements specially adapted for specific types of electric machines or apparatus or for sectionalised protection of cable or line systems, and effecting automatic switching in the event of an undesired change from normal working conditions
- H02H7/26—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured
- H02H7/265—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured making use of travelling wave theory
-
- 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
-
- 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)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The embodiment of the invention provides a novel power distribution network fault detection method based on a quick switch. The method comprises the steps of fault current signal acquisition, data extraction, neural network training and fault classification and rapid switching action control; collecting current information by adopting a multilayer sensor, and diagnosing layered information by using a particle swarm optimization algorithm; estimating the position of the fault by adopting a line E type traveling wave distance measurement method, and judging the position of the fault by combining an Attention mechanism; the eddy repulsion force is used as a quick switch of the driving mechanism, and the breaking can be realized within 3ms after the action signal of the fault is received. The method improves the fault detection level, improves the utilization rate of the power supply equipment, and reduces the electric energy loss, thereby improving the overall operation level of the power distribution network; the power distribution network fault self-healing capability is improved, and the power supply reliability is effectively improved. The embodiment of the invention also provides a novel power distribution network fault self-healing system based on the method.
Description
Technical Field
The invention belongs to the technical field of power distribution network fault detection and isolation, and particularly relates to a novel power distribution network fault detection method based on a quick switch. The invention also provides a fault self-healing system applying the power distribution network fault detection method.
Background
With the development of the modern intelligent power distribution technology, the construction scale of a power distribution network is larger and larger, the traditional passive power distribution network is changed into an active power distribution network containing distributed power supplies, the topological structure of the power distribution network is complex and changeable, the number of branch points is large, the line length is long, the area is wide, the operation condition is severe, and single-phase earth faults and short-circuit faults are easy to occur. The infiltration of the distributed power supply causes the bidirectional flow of the power distribution network, and causes new problems to the power distribution network, such as fault misjudgment, protection misoperations and the like, and the traditional fault detection method is not suitable due to larger errors. Therefore, the fault detection method and the system self-healing for the modern power distribution network are concerned widely.
In the fault diagnosis of the power distribution network, a power distribution network fault signal needs to be detected, the power distribution network fault signal radiated by the power distribution network is detected and subjected to parameter estimation, the power distribution network fault signal detection and the fault signal identification are realized through the power distribution network fault signal detection, and the accuracy and the automation level of the fault diagnosis are improved. In the traditional method, a time-frequency coupling algorithm is adopted for detecting the fault signals of the power distribution network, a time-frequency characteristic decomposition method is adopted for signal separation, the fault detection performance is improved, and if the fault signals and the interference noise have strong coupling, the detection performance is poor.
A power distribution network fault signal detection algorithm based on fractional order Fourier time-frequency coupling solves a phase ambiguity number to search an optimal solution of a power distribution network signal characteristic quantity, obtains a power distribution network fault signal parameter phase compensation result, and improves fault detection capability.
In recent years, a power distribution network synchronous phasor measurement unit PMU is rapidly developed, and the device can provide high-frequency, high-precision and voltage and current phasor data with time scales, so that the possibility of cooperatively processing power distribution network fault diagnosis by utilizing multipoint information is provided. By means of an intuitive expression mode and simple matrix operation, the Petri network is applied to the aspect of power grid fault diagnosis. However, when the scale of the power distribution network is huge, the number of nodes of a diagnosis model established by the Petri network is too many, combination explosion is easy to generate, and the weight of matrix operation is given by artificial experience, so that the uncertainty of a diagnosis result is increased.
In addition, regarding fault breaking when a power distribution network has a fault, the inherent breaking time of the conventional power distribution vacuum switch is about 60m generally, and the total fault breaking time is equal to the sum of the time of the detection device and the time of the breaker action, and is about 100ms generally. The novel eddy current repulsion breaker is used as a quick switch applied to an actuating mechanism, can realize circuit breaking in a short time of 3ms, but the quick switch does not have the function of judging faults and needs to be controlled by combining with a program algorithm.
In summary, in view of the defects of long detection time, undefined fault type, high misjudgment rate, poor fault tolerance and the like of the conventional power distribution network fault detection technology, a new power distribution network fault signal detection method and system are researched and developed, so that the defects of the detection methods are overcome, and the intelligent detection and fault self-healing of the power distribution network fault signal are urgent.
Disclosure of Invention
The invention provides a power distribution network fault detection method and a fault self-healing system based on a neural network and a quick switch, aiming at the problems of long detection time, undefined fault type, high misjudgment rate, poor fault tolerance and the like of the existing power distribution network fault detection technology, so that the power distribution network fault detection level and the fault self-healing capability are improved, and the overall operation level and the power supply reliability of a power distribution network are improved.
In order to solve the technical problem, an embodiment of the present invention provides a novel power distribution network fault detection method based on a fast switch, including the following steps:
1. collecting fault current signals, including collecting the fault current signals at the same time under the same frequency;
2. data extraction, comprising: decomposing the collected fault current signal into nine levels by using an MRA (Multi-Resolution Analysis) wavelet transform algorithm; inputting 512 samples passing through a high-pass filter and a low-pass filter, recording corresponding approximate detailed coefficients, and filtering high-frequency signals;
3. neural network training and fault classification, comprising:
31. fault traveling wave signal capture, comprising: capturing a traveling wave signal from the decomposed fault current signal data under different frequencies to simulate the traveling wave waveform characteristics of the line during fault;
32. and (3) normal traveling wave signal simulation, comprising: capturing a traveling wave signal in current signal data generated by the power system in a simulation mode under a normal condition so as to simulate the waveform characteristics of the traveling wave when a circuit is normal;
33. artificial intelligence neural network training, comprising: inputting fault traveling wave signal and normal traveling wave signal data, performing model training on the data by adopting a Particle Swarm Optimization (PSO) algorithm, and extracting signal characteristics;
34. fault classification, comprising: using the signal characteristics extracted by neural network training as learning weights for artificial intelligence network detection, classifying the collected fault current signals by adopting an Attention mechanism, and judging a fault result;
4. fault self-healing, comprising: and controlling the fast switch to make corresponding action according to the fault result.
As a preferable example of step 1, a PMU (phase Measurement Unit) based WAMS (Wide Area Measurement System) is used to collect the fault current signal.
Preferably, in the step 31, the traveling wave signal is captured within a range of 99 to 199 Hz.
Preferably, in the step 4, the fast switch is an eddy current repulsion breaker.
The embodiment of the invention also provides a novel power distribution network fault self-healing system, and a novel power distribution network fault detection method based on a quick switch comprises a fault signal acquisition module, a data extraction module, a neural network training module, a fault detection classification module and a fault removal module, wherein the fault signal acquisition module, the data extraction module, the neural network training module, the fault detection classification module and the fault removal module are respectively connected with the following modules:
the fault signal acquisition module is used for acquiring the fault current signal, and the fault signal acquisition module inputs the acquired fault current signal into the data extraction module; the data extraction module is used for extracting the data of the input fault current signal through multi-resolution analysis wavelet transform, and the extracted fault current signal data are respectively input into the neural network training module and the fault detection classification module; the neural network training module is used for capturing the fault traveling wave signal, simulating the normal traveling wave signal and training the artificial intelligent neural network, performing model training on the fault traveling wave signal and the normal traveling wave signal data by adopting PSO (particle swarm optimization), extracting signal characteristics and inputting the signal characteristics as learning weight into the fault detection classification module; the fault detection classification module is used for classifying the faults, classifying the fault current signals acquired from the fault signal acquisition module by adopting an Attention mechanism based on learning weight, and judging a fault result; the fault removing module is connected with the fault detection and classification module and comprises a quick switch, and the quick switch is used for performing corresponding action according to the fault result output by the fault detection and classification module to remove the fault.
Preferably, the fault signal acquisition module comprises a wide area measurement system based on a power distribution synchronization vector measurement unit.
Preferably, the fast switch is an eddy current repulsion breaker. The eddy repulsion force is used as a quick switch of the driving mechanism, so that breaking can be realized within 3ms after a fault action signal is received, and the requirement of zero-second quick action is met.
According to the technical scheme of the embodiment of the invention, the fault detection and positioning of different types of fault transmission lines are well performed, the current information is acquired by adopting the multilayer sensor, and the layered information is diagnosed by using the PSO, so that the fault in the power distribution network is effectively and quickly detected; estimating the position of the fault by adopting a line E type traveling wave distance measurement method, and judging the position of the fault by combining an Attention mechanism according to different waveform characteristics when a plurality of branches exist in the power distribution network; and the quick switch is adopted to quickly respond to the fault judgment result, so that fault removal can be quickly realized after a fault action signal is received. The beneficial effects are as follows:
1. the defects of long detection time, undefined fault type, high misjudgment rate, poor fault tolerance and the like of the conventional power distribution network fault detection technology are overcome, the fault detection level is improved, the utilization rate of power supply equipment is improved, and the electric energy loss is reduced, so that the overall operation level of the power distribution network is improved;
2. the power distribution network fault self-healing capability is improved, the fault detection algorithm is combined with the rapid switching hardware, the fault removal time is shortened to millisecond level, and the power supply reliability is effectively improved.
Drawings
Fig. 1 is a schematic step diagram of a novel power distribution network fault detection method based on a fast switch according to an embodiment of the present invention;
fig. 2 is a system schematic diagram of a novel power distribution network fault detection method based on a fast switch according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an Attention mechanism model for the artificial intelligence network inspection shown in FIG. 2;
fig. 4 is a schematic structural diagram of the novel power distribution network fault self-healing system provided in the embodiment of the present invention;
[ main component symbol description ]
1-a fault signal acquisition module; 2-a data extraction module; 3-a neural network training module; 4-fault detection classification module; 5-fault removal module.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
Aiming at the existing problems, the invention provides the power distribution network fault detection method and the power distribution network fault detection system based on the neural network and the rapid switch, which can improve the power distribution network fault detection level and the fault self-healing capability and improve the overall operation level and the power supply reliability of the power distribution network.
The embodiment of the invention provides a novel power distribution network fault detection method based on a quick switch, which is shown in fig. 1 and fig. 2 and comprises the following steps:
1. fault current signal acquisition, comprising: by adopting WAMS based on PMU, PMU measures line current i on power transmission line of power distribution network at the same time under the same frequencylFor distinguishing the fault types in the abnormal state and the normal state;
2. data extraction, comprising: decomposing the collected fault current signals into nine levels by using an MRA wavelet transform algorithm; inputting samples containing 512 types of signals passing through a high-pass filter and a low-pass filter, recording corresponding approximate detailed coefficients, filtering high-frequency signals, and calculating corresponding seventh-layer detailed microwave coefficients for knowing second and third harmonic components of the fault current signals;
3. neural network training and fault classification, comprising:
31. fault traveling wave signal capture, comprising: capturing a traveling wave signal from the decomposed fault current signal data in a frequency range of 99-199 Hz to simulate the waveform characteristics of the traveling wave during line fault;
32. and (3) normal traveling wave signal simulation, comprising: capturing a traveling wave signal in current signal data generated by the power system in a simulation mode under a normal condition so as to simulate the waveform characteristics of the traveling wave when a circuit is normal;
33. artificial intelligence neural network training, comprising: inputting fault traveling wave signal and normal traveling wave signal data, performing model training on the data by adopting PSO (particle swarm optimization), and extracting signal characteristics;
34. fault classification, comprising: using the signal characteristics extracted by neural network training as learning weights for artificial intelligence network detection, classifying the collected fault current signals by adopting an Attention mechanism, and judging a fault result;
4. fault self-healing, comprising: the quick switch adopts an eddy current repulsion breaker and is controlled to make corresponding action according to a fault result.
The method is based on the fault location principle of the E-type traveling wave distance measurement method, and mainly utilizes the fact that when a breaker is switched on after a fault, transient traveling wave signals are generated on a transmission line due to voltage mutation between contacts. The transient traveling wave signal is transmitted to two sides at a speed close to the speed of light, is refracted and reflected back and forth between discontinuous points of wave impedance such as fault points, breaker contacts and the like, and is accurately positioned by analyzing the refracted and reflected waveforms.
The WAMS based on the PMU is mainly used for collecting and detecting phase angles and frequencies of voltage, current and power on an inlet wire of a transformer substation, and information such as the state of an inlet wire protection system and the voltage of a standby power supply, wherein the PMU can measure the voltage and the current of a real-time electric power system with accurate time synchronization time, and can also measure the voltage and the current at different positions.
Fig. 3 shows an Attention mechanism model, in which an encoder processes an input sequence, and then the processed input sequence is used as an input sequence of a decoder model, and the input sequence is iterated continuously to obtain a classification state. As shown in the figure, x1、x2、x3……xtThe code is the input sequence of the encoder, and C is a hidden vector with fixed length, and has two functions: 1. initializing the model of the encoder as an initial vector, predicting y as the encoder model1The initial vector of (a); 2. as a background vector, the yield of y for each step in the y sequence is guided. The decoder is mainly based on vector C and y output from the previous stept-1Decoding to obtain the output y at the moment tt。
In order to better implement the above technical solution, as shown in fig. 4, the present invention further provides a novel power distribution network fault self-healing system, which includes a fault signal acquisition module 1, a data extraction module 2, a neural network training module 3, a fault detection classification module 4, and a fault removal module 5, wherein:
the fault signal acquisition module 1 is a WAMS based on PMU and is used for acquiring line current i on a power transmission line of a power distribution networklThe fault signal acquisition module 1 inputs the acquired fault current signal into the data extraction module 2; the data extraction module 2 is used for extracting data of the input fault current signal through MRA wavelet transformation, and the extracted fault current signal data are respectively input into the neural network training module 3 and the fault detection classification module 4 after being subjected to standardization processing; the neural network training module 3 is used for capturing fault traveling wave signals, simulating normal traveling wave signals and training an artificial intelligent neural network, model training is carried out on the fault traveling wave signals and the normal traveling wave signal data by adopting PSO, signal characteristics are extracted and input into the fault detection classification module 4 as learning weight; the fault detection classification module 4 is used for classifying faults, classifying the collected fault current signals from the fault signal collection module 1 by adopting an Attention mechanism based on the learning weight, and judging a fault result; the fault removing module 5 is connected with the fault detection and classification module 4 and comprises a vortex repulsion breaker, and the vortex repulsion breaker makes corresponding actions according to fault results output by the fault detection and classification module 4.
For convenience of description, each part of the above-described apparatus is separately described as functionally divided into various modules. Of course, the functionality of the various modules may be implemented in the same one or more pieces of software or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the embodiments of the present invention without departing from the spirit and scope of the present invention, which is set forth in the claims of the present application.
Claims (7)
1. A novel power distribution network fault detection method based on a quick switch is characterized by comprising the following steps:
s1, collecting fault current signals, including collecting the fault current signals at the same time under the same frequency;
s2, data extraction, including: decomposing the collected fault current signals into nine levels by using a multi-resolution analysis wavelet transform algorithm; inputting 512 samples passing through a high-pass filter and a low-pass filter, recording corresponding approximate coefficients, and filtering high-frequency signals;
s3, neural network training and fault classification, including:
s31, capturing fault traveling wave signals, comprising: capturing a traveling wave signal from the decomposed fault current signal data under different frequencies to simulate the traveling wave waveform characteristics of the line during fault;
s32, simulating a normal traveling wave signal, which comprises the following steps: capturing a traveling wave signal in current signal data generated by the power system in a simulation mode under a normal condition so as to simulate the waveform characteristics of the traveling wave when a circuit is normal;
s33, training an artificial intelligence neural network, comprising: inputting fault traveling wave signal and normal traveling wave signal data, performing model training on the data by adopting PSO (particle swarm optimization), and extracting signal characteristics;
s34, fault classification, including: using the signal characteristics extracted by neural network training as learning weights for artificial intelligence network detection, classifying the collected fault current signals by adopting an Attention mechanism, and judging a fault result;
s4, fault self-healing, comprising: and controlling the fast switch to make corresponding action according to the fault result.
2. The method according to claim 1, wherein in step S1, a fault current signal is collected using a wide area measurement system based on a synchronous vector measurement unit.
3. The method according to claim 1, wherein in step S31, the traveling wave signal is captured within an interval of 99-199 Hz.
4. The method according to claim 1, wherein in the step S4, the fast switch employs eddy current repulsion breaker.
5. The fault self-healing system applying the novel power distribution network fault detection method based on the rapid switch according to claim 1, is characterized by comprising a fault signal acquisition module, a data extraction module, a neural network training module, a fault detection classification module and a fault removal module, wherein:
the fault signal acquisition module is used for acquiring the fault current signal, and the fault signal acquisition module inputs the acquired fault current signal into the data extraction module;
the data extraction module is used for extracting the data of the input fault current signal through multi-resolution analysis wavelet transform, and the extracted fault current signal data are respectively input into the neural network training module and the fault detection classification module;
the neural network training module is used for capturing the fault traveling wave signal, simulating the normal traveling wave signal and training the artificial intelligent neural network, performing model training on the fault traveling wave signal and the normal traveling wave signal data by adopting PSO (particle swarm optimization), extracting signal characteristics and inputting the signal characteristics as learning weight into the fault detection classification module;
the fault detection classification module is used for classifying the faults, classifying the fault current signals acquired from the fault signal acquisition module by adopting an Attention mechanism based on learning weight, and judging a fault result;
the fault removing module is connected with the fault detection and classification module and comprises a quick switch, and the quick switch is used for performing corresponding action according to the fault result output by the fault detection and classification module to remove the fault.
6. The system of claim 5, wherein the fault signal acquisition module comprises a wide area measurement system based on a power distribution synchronization vector measurement unit.
7. The system of claim 5, wherein the fast switch is an eddy current repulsion circuit breaker.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010287847.8A CN111404130B (en) | 2020-04-14 | 2020-04-14 | Novel power distribution network fault detection method and fault self-healing system based on quick switch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010287847.8A CN111404130B (en) | 2020-04-14 | 2020-04-14 | Novel power distribution network fault detection method and fault self-healing system based on quick switch |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111404130A CN111404130A (en) | 2020-07-10 |
| CN111404130B true CN111404130B (en) | 2022-03-22 |
Family
ID=71431550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010287847.8A Active CN111404130B (en) | 2020-04-14 | 2020-04-14 | Novel power distribution network fault detection method and fault self-healing system based on quick switch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111404130B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858977B (en) * | 2021-01-06 | 2022-08-30 | 南京能晶电子科技有限公司 | Hall current sensor chip fault detection circuit and detection method |
| CN113376479B (en) * | 2021-06-25 | 2022-08-16 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Power distribution network fault detection system |
| CN113589100A (en) * | 2021-07-26 | 2021-11-02 | 国电南瑞科技股份有限公司 | Abnormal discharge identification method based on bidirectional long-short term memory and attention mechanism |
| CN113985733B (en) * | 2021-10-26 | 2023-11-17 | 云南电网有限责任公司电力科学研究院 | Power distribution network fault identification method based on self-adaptive probability learning |
| EP4366104A1 (en) * | 2022-11-02 | 2024-05-08 | Supergrid Institute | Transient based method for controlling protection actions in an electric power transmission and/ or distribution system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103091603A (en) * | 2013-01-14 | 2013-05-08 | 华北电力大学 | Breakdown intelligent classification and positioning method of electric transmission line |
| CN105548862A (en) * | 2016-01-25 | 2016-05-04 | 合肥工业大学 | Simulation circuit fault diagnosis method on the basis of generalized multi-nuclear support vector machine |
| CN108279364A (en) * | 2018-01-30 | 2018-07-13 | 福州大学 | Wire selection method for power distribution network single phase earthing failure based on convolutional neural networks |
| CN110059357A (en) * | 2019-03-19 | 2019-07-26 | 中国电力科学研究院有限公司 | A kind of intelligent electric energy meter failure modes detection method and system based on autoencoder network |
-
2020
- 2020-04-14 CN CN202010287847.8A patent/CN111404130B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103091603A (en) * | 2013-01-14 | 2013-05-08 | 华北电力大学 | Breakdown intelligent classification and positioning method of electric transmission line |
| CN105548862A (en) * | 2016-01-25 | 2016-05-04 | 合肥工业大学 | Simulation circuit fault diagnosis method on the basis of generalized multi-nuclear support vector machine |
| WO2017128455A1 (en) * | 2016-01-25 | 2017-08-03 | 合肥工业大学 | Analogue circuit fault diagnosis method based on generalized multiple kernel learning-support vector machine |
| CN108279364A (en) * | 2018-01-30 | 2018-07-13 | 福州大学 | Wire selection method for power distribution network single phase earthing failure based on convolutional neural networks |
| CN110059357A (en) * | 2019-03-19 | 2019-07-26 | 中国电力科学研究院有限公司 | A kind of intelligent electric energy meter failure modes detection method and system based on autoencoder network |
Non-Patent Citations (1)
| Title |
|---|
| 一种基于自愈策略的网络故障诊断系统;李千目等;《仪器仪表学报》;20050831;第26卷(第8期);第764-766页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111404130A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111404130B (en) | Novel power distribution network fault detection method and fault self-healing system based on quick switch | |
| WO2023216553A1 (en) | Multi-fault diagnosis method for power distribution network, and system | |
| CN109635928B (en) | Voltage sag reason identification method based on deep learning model fusion | |
| CN110082640B (en) | Distribution network single-phase earth fault identification method based on long-time memory network | |
| Zhang et al. | Novel fault location method for power systems based on attention mechanism and double structure GRU neural network | |
| CN202404166U (en) | On-line monitoring system for vibration performance of transformer | |
| CN106330095B (en) | Collect system fault locating method in a kind of large-sized photovoltaic power station | |
| CN111308260B (en) | Electric energy quality monitoring and electric appliance fault analysis system based on wavelet neural network and working method thereof | |
| CN108802566B (en) | Grounding line selection method based on HHT signal analysis | |
| CN102508076A (en) | Fault diagnosis device and method based on multi-agent system and wavelet analysis | |
| CN102510044A (en) | Excitation inrush current identification method based on wavelet transformation and probabilistic neural network (PNN) | |
| Souhe et al. | Fault detection, classification and location in power distribution smart grid using smart meters data | |
| Rui et al. | Fault location for power grid based on transient travelling wave data fusion via asynchronous voltage measurements | |
| Kezunovic | Translational knowledge: From collecting data to making decisions in a smart grid | |
| CN108872743A (en) | A kind of electric energy quality real-time monitoring analysis system and method based on wavelet transformation | |
| Damala et al. | A simple decision tree-based disturbance monitoring system for VSC-based HVDC transmission link integrating a DFIG wind farm | |
| CN106646138B (en) | Distribution net work earthing fault localization method based on the conversion of more sample frequency wavelet character energy | |
| CN113325269A (en) | Distribution network high-resistance fault monitoring method, system, equipment and storage medium | |
| CN117368645A (en) | Power distribution network cable fault point distance measuring method, system, computer equipment and medium | |
| Geng et al. | Fault diagnosis of modular multilevel converter based on RNN and wavelet analysis | |
| CN111369179A (en) | Closed-loop detection method and device for distribution automation terminal equipment | |
| CN111521905A (en) | Power grid fault diagnosis method based on intelligent fusion of multi-dimensional data fault degrees | |
| Zeng et al. | Fault Detection of Flexible DC Distribution Network Based on GAF and Improved Deep Residual Network | |
| Tian et al. | Intermittent Arc Fault Detection Based on Machine Learning in Resonant Grounding Distribution Systems | |
| Ding et al. | Research on power grid fault diagnosis method based on PMU data and convolutional neural network |
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 |