CN210923872U - Online discrimination system of distribution terminal trouble - Google Patents
Online discrimination system of distribution terminal trouble Download PDFInfo
- Publication number
- CN210923872U CN210923872U CN201921425673.6U CN201921425673U CN210923872U CN 210923872 U CN210923872 U CN 210923872U CN 201921425673 U CN201921425673 U CN 201921425673U CN 210923872 U CN210923872 U CN 210923872U
- Authority
- CN
- China
- Prior art keywords
- neural network
- module
- time
- distribution terminal
- bus
- 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
Images
Abstract
The utility model discloses a power distribution terminal fault on-line discrimination system, which comprises a data acquisition unit, a time-frequency transformation module, a confrontation neural network data processing module, a convolution neural network training module and an output communication interface; the data acquisition device is in communication connection with the time-frequency transformation module through an I2C bus, the time-frequency transformation module is in communication connection with the antagonistic neural network data processing module through an I2C bus, the time-frequency transformation module is also in communication connection with the convolutional neural network training module through an I2C bus, the antagonistic neural network data processing module is connected with the convolutional neural network training module, and the convolutional neural network training module is connected with the output communication interface. The time-frequency transformation module transforms the time-domain electrical data to obtain a time-frequency map training set, and the countermeasure neural network data processing module and the convolution neural network training module are used for carrying out fault discrimination model training, so that the fault of the power distribution terminal is discriminated on line in time, and the stability and the reliability of the operation of the power system are ensured.
Description
Technical Field
The utility model belongs to power system distribution terminal fault diagnosis field, concretely relates to online discrimination system of distribution terminal trouble.
Background
At present, the fault of a power distribution terminal in an electric power system is overhauled in an off-line state by manpower, when the power distribution terminal has a fault, an overhaul technician needs to know the situation on site to judge the fault type and then overhaul the fault, the fault finding and overhauling mode is passively delayed, the fault cannot be eliminated at the initial stage, the fault influence result is deepened, the influence range is enlarged, the stable operation of the electric power system is not facilitated, and the mode cannot meet the requirement of the maintenance of the electric power system along with the increase of the scale of the electric power network; the detection objects in the prior art are mostly power distribution terminal equipment, the fault type is judged easily by mistake, and the problem is difficult to solve fundamentally.
Therefore, it is important to provide a tool capable of identifying the fault type of the power distribution terminal in real time.
SUMMERY OF THE UTILITY MODEL
Based on this, the utility model provides a system that can carry out the trouble to distribution terminal on line and distinguish solves the technical problem that can't in time judge the trouble among the prior art.
The utility model relates to a power distribution terminal trouble discriminates system on line, include:
the system comprises a data acquisition device, a time-frequency transformation module, a countermeasure neural network data processing module, a convolution neural network training module and an output communication interface;
the data acquisition device is in communication connection with the time-frequency transformation module through an I2C bus, the time-frequency transformation module is in communication connection with the antagonistic neural network data processing module through an I2C bus, the time-frequency transformation module is also in communication connection with the convolutional neural network training module through an I2C bus, the antagonistic neural network data processing module is connected with the convolutional neural network training module, and the convolutional neural network training module is connected with the output communication interface.
Preferably, the time-frequency transformation module and the antagonistic neural network data processing module are connected with the convolutional neural network training module through the same I2C bus communication interface.
Preferably, the online fault determination system for a power distribution terminal further includes:
the device comprises a filtering module and a wave recording module.
Preferably, the data collector is configured with a filtering module and a wave recording module.
Preferably, the online power distribution terminal fault determination system is integrated on a board card, and the board card is embedded into an intelligent control terminal.
Preferably, the power distribution terminal fault online judging system further comprises a liquid crystal display.
The utility model provides a pair of online discrimination system of distribution terminal trouble has following beneficial effect:
the data acquisition unit receives alternating current electrical data measured by the power distribution terminal measurement system when a power distribution terminal fails and transmits the alternating current electrical data to the time-frequency transformation module to perform time-domain to frequency-domain conversion, the electrical data are converted into an imaged time-frequency map training set, the time-frequency map training set is transmitted to the countermeasure neural network data processing module through the communication interface to generate capacity expansion, a new time-frequency map subset with new characteristics is obtained, the training set and the subset are transmitted to the convolutional neural network training module through the communication interface to perform fault discrimination model training, and a fault discrimination result is output through the output communication interface. Through right the utility model discloses an implement, can distinguish the trouble of distribution terminal on line, overhaul the technical staff and need not to go to the equipment scene and overhaul the judgement; the analysis object is not limited to the equipment, but the alternating current electrical data measured by the measuring system is analyzed, so that the problem of misjudgment of fault types is solved, and the information potential of system data is fully mined; the utility model discloses to timely differentiate on line of distribution terminal equipment trouble and can guarantee the stability and the reliability of electric power system operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 the utility model discloses a distribution terminal trouble is system structure sketch map on line judges of embodiment
Fig. 2 is a schematic diagram of a power distribution terminal fault online determination system according to another embodiment of the present invention
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Referring to fig. 1, the present embodiment provides an online power distribution terminal fault determination system, which includes an ac electrical quantity data collector 100, a short-time fourier transform processor 110, a neural network data processor 120, a convolutional neural network training processor 130, and a fault type determination output device 140;
the online judging system is in communication connection with the on-site power distribution terminal equipment through a bus, and a communication interface between each power distribution terminal and the bus receives a fault type judging result of the power distribution terminal fault online judging system when the power distribution terminal has a fault.
The alternating current data acquisition device 100 is in communication connection with the short-time Fourier transformer 110 through an I2C bus, the short-time Fourier transformer 110 is in communication connection with the antagonistic neural network data processor 120 through an I2C bus, meanwhile, the short-time Fourier transformer 110 is also in communication connection with the convolutional neural network trainer 130 through an I2C bus, the antagonistic neural network data processor 120 is connected with the convolutional neural network trainer 130, the convolutional neural network trainer 130 is connected with the fault type judgment output device 140, and the fault type judgment output device 140 issues the judgment result to each power distribution terminal through a communication bus.
In this embodiment, the ac electrical data collector 100 is further configured with a filter circuit and a wave recording module to filter and record fault waves of the ac electrical data.
When the power distribution terminal fault online judging system in this embodiment works, the ac electrical data collector 100 receives the ac electrical quantity measured by the power distribution terminal measurement system on the communication bus, and after preprocessing such as filtering and wave recording, transmits the electrical data to the short-time fourier transform processor 110, the short-time fourier transform processor 110 performs time-frequency conversion on the electrical data to obtain the training set X, the training set X is transmitted to the anti-neural network data processor 120 through the I2C bus to generate capacity expansion, the anti-neural network data processor 120 generates a new time-frequency map subset M, the subset M is transmitted to the convolutional neural network training processor 130 through the I2 bus 2C, the convolutional neural network training processor 130 also receives the training set M transmitted by the short-time fourier transform processor 110 through the I2C bus, the training set X and the subset M in the convolutional neural network training processor 130 are used as a total training set to perform fault judging model training, and finally, outputting the judgment result by the fault type judgment output device 140, and transmitting the judgment result to each power distribution terminal on the site through a communication bus.
Referring to fig. 2, the present embodiment provides an online fault determination system for a power distribution terminal, which is integrated on a board card embedded in an intelligent management and control device of a monitoring platform of an electrical power system. The system comprises: the system comprises a data acquisition unit 200, a time-frequency conversion circuit module 210, an anti-neural network data processing circuit module 220, a convolutional neural network training circuit module 230 and an output communication interface 240;
the data acquisition unit 200 is connected with the time-frequency transformation circuit module 210 by using an I2C bus in a communication way, the time-frequency transformation circuit module 210 is connected with the antagonistic neural network data processing circuit module 220 by using an I2C bus in a communication way, and the convolutional neural network training circuit 230 module is connected with the output communication interface 240.
In this embodiment, the time-frequency transform circuit module 210 and the antagonistic neural network data processing circuit module 220 are connected to the convolutional neural network training circuit module 230 through the same I2C bus communication interface.
The data acquisition unit 200 in this embodiment is configured with an ac flow filter circuit and a fault recording module.
When the power distribution terminal fault online judging system of this embodiment works, the data collector 200 receives ac electrical data measured by the power distribution terminal measuring system when a fault occurs at the power distribution terminal, including line voltage, bus voltage, zero sequence current, line protection current and line measurement current, and transmits the ac electrical data to the time-frequency conversion circuit module 210 through the I2C bus for time-domain to frequency-domain conversion, the electrical data is converted into an imaged time-frequency map training set, the time-frequency map training set is transmitted to the neural network data processing circuit module 220 and the convolutional neural network training circuit module 230 through the I2C communication interface, the neural network data processing circuit module 220 generates an expanded volume for the time-frequency map training set, obtains a new time-frequency map subset with new characteristics, and transmits the expanded volume to the convolutional neural network training circuit module 230 through the I2C communication interface, the time-frequency pattern training set obtained by the time-frequency transformation circuit module 210 and the new time-frequency pattern subset generated by the antagonistic neural network data processing circuit module 220 are used as a total training set to perform fault discrimination model training on the convolutional neural network training circuit module 230, and the fault discrimination result is output through the output communication interface 240.
It is to be understood that the embodiments described are only some embodiments of the invention, and not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention.
Claims (5)
1. The utility model provides a distribution terminal trouble online discrimination system which characterized in that includes:
the system comprises a data acquisition device, a time-frequency transformation module, a countermeasure neural network data processing module, a convolution neural network training module and an output communication interface;
the data acquisition device is in communication connection with the time-frequency transformation module through an I2C bus, the time-frequency transformation module is in communication connection with the antagonistic neural network data processing module through an I2C bus, the time-frequency transformation module is also in communication connection with the convolutional neural network training module through an I2C bus, the antagonistic neural network data processing module is connected with the convolutional neural network training module, and the convolutional neural network training module is connected with the output communication interface.
2. The power distribution terminal fault online discrimination system of claim 1,
the time-frequency transformation module and the antagonistic neural network data processing module are connected with the convolutional neural network training module through the same I2C bus communication interface.
3. The system of claim 1, further comprising:
the device comprises a filtering module and a wave recording module.
4. The system for online judging the fault of the power distribution terminal as claimed in claim 1, wherein the data collector is configured with a filtering module and a wave recording module.
5. The system according to claim 1, wherein the system is integrated on a board embedded with an intelligent management and control terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201921425673.6U CN210923872U (en) | 2019-08-28 | 2019-08-28 | Online discrimination system of distribution terminal trouble |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201921425673.6U CN210923872U (en) | 2019-08-28 | 2019-08-28 | Online discrimination system of distribution terminal trouble |
Publications (1)
Publication Number | Publication Date |
---|---|
CN210923872U true CN210923872U (en) | 2020-07-03 |
Family
ID=71351500
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201921425673.6U Active CN210923872U (en) | 2019-08-28 | 2019-08-28 | Online discrimination system of distribution terminal trouble |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN210923872U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516742A (en) * | 2019-08-28 | 2019-11-29 | 广东电网有限责任公司 | A kind of distribution terminal fault distinguishing method and system based on Combination neural network model |
-
2019
- 2019-08-28 CN CN201921425673.6U patent/CN210923872U/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516742A (en) * | 2019-08-28 | 2019-11-29 | 广东电网有限责任公司 | A kind of distribution terminal fault distinguishing method and system based on Combination neural network model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102288857B (en) | Fault arc identification and detection method and detection protection device | |
CN209102839U (en) | Movable type cable monitors prior-warning device on-line | |
CN110703009B (en) | Abnormal analysis and processing method for line loss rate of transformer area | |
CN108535598B (en) | Online detection method and device for cable fault of track circuit | |
CN105676088A (en) | Device and method for testing fault arc detection apparatus | |
CN108548962A (en) | A kind of grounded screen alternating current and direct current and impulse resistance integrated test system and method | |
CN105301552A (en) | Electric energy metering device online verification system | |
CN216848010U (en) | Cable partial discharge online monitoring device for edge calculation | |
CN106569165A (en) | Electronic watt-hour meter measuring performance remote online detection system | |
CN210923872U (en) | Online discrimination system of distribution terminal trouble | |
CN111856313B (en) | Double-circuit power supply real-time monitoring device | |
CN204101641U (en) | High-tension cable is at cross interconnected lower insulation dielectric loss angle trend on-line monitoring system | |
CN101957436B (en) | Power supply quality tester of IT (Information Technology) server equipment and test method | |
CN116317171B (en) | Electric quantity and non-electric quantity internet of things monitoring device | |
CN203164360U (en) | Transformer device insulation online monitoring system | |
CN204882853U (en) | Electric energy meter pressure resistance test installation | |
CN207964994U (en) | Grounding net of transformer substation health status detection device | |
CN102435914B (en) | Portable aircraft wire comprehensive performance tester | |
CN215833533U (en) | Intelligent diagnosis and accurate positioning device for high-voltage cable state | |
CN106526303B (en) | A kind of the C-V characteristic test device and method of solid decoupling device | |
CN113295962A (en) | Intelligent diagnosis and accurate positioning device for high-voltage cable state | |
CN209432403U (en) | A kind of optical fiber detector | |
CN203825111U (en) | Zinc oxide lightning arrester on-line monitoring device | |
CN112542075A (en) | XLPE cable partial discharge simulation method and system | |
CN208888359U (en) | A kind of full-time inspection on-line monitoring system of gate energy meter |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room 501-503, annex building, Huaye building, No.1-3 Chuimao new street, Xihua Road, Yuexiu District, Guangzhou City, Guangdong Province 510000 Patentee after: China Southern Power Grid Power Technology Co.,Ltd. Address before: Room 501-503, annex building, Huaye building, No.1-3 Chuimao new street, Xihua Road, Yuexiu District, Guangzhou City, Guangdong Province 510000 Patentee before: GUANGDONG ELECTRIC POWER SCIENCE RESEARCH INSTITUTE ENERGY TECHNOLOGY Co.,Ltd. |