CN118169517A - Power distribution network single-phase earth fault positioning method and system based on convolutional neural network - Google Patents
Power distribution network single-phase earth fault positioning method and system based on convolutional neural network Download PDFInfo
- Publication number
- CN118169517A CN118169517A CN202410602258.2A CN202410602258A CN118169517A CN 118169517 A CN118169517 A CN 118169517A CN 202410602258 A CN202410602258 A CN 202410602258A CN 118169517 A CN118169517 A CN 118169517A
- Authority
- CN
- China
- Prior art keywords
- power distribution
- distribution network
- phase
- network
- convolutional neural
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 38
- 238000010586 diagram Methods 0.000 claims abstract description 23
- 230000009466 transformation Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims 2
- 238000010801 machine learning Methods 0.000 abstract description 4
- 108091006146 Channels Proteins 0.000 description 14
- 238000001514 detection method Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000002847 impedance measurement Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/58—Testing of lines, cables or conductors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Locating Faults (AREA)
Abstract
The invention relates to a method and a system for locating single-phase earth faults of a power distribution network based on a convolutional neural network, wherein the method comprises the following steps: three-phase current signals and an electrical topological relation diagram of each node of a target power distribution network are obtained, and the three-phase current signals are converted into RGB images through symmetrical Hilbert transformation; constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network; extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network, and training a transducer model according to the feature map; and positioning the single-phase ground fault of the target power distribution network based on the trained transducer model. According to the invention, the current signals of the power distribution network are converted into RGB images and the map isomorphic network is constructed, and the characteristics of the RGB images are identified by machine learning, so that the accuracy and the robustness of fault location are improved.
Description
Technical Field
The invention belongs to the technical field of power detection, and particularly relates to a single-phase earth fault positioning method and system of a power distribution network based on a convolutional neural network.
Background
With the rapid development of smart grid technology and the increasing maturity of machine learning methods, the demands for 10kV power distribution network fault detection and positioning technology are also increasing. Particularly for single-phase earth faults, which is a common problem in power distribution networks, it becomes important to develop an efficient, accurate and cost-effective solution. Traditional fault locating methods, based on impedance measurement or voltage comparison techniques, often rely on complex hardware and extensive manual intervention, which not only increases the operational complexity of the system, but also increases maintenance costs.
In recent years, with the development of big data and artificial intelligence technology, a machine learning-based fault detection method provides a new view for automatic diagnosis and treatment of faults of a power distribution network. By analyzing the historical and real-time data, the methods can learn the complex mode of the power grid operation, so that potential faults can be predicted and identified. In particular, methods based on waveform correlation analysis demonstrate the potential to locate fault sections by analyzing current and voltage waveform data in a power distribution network.
The fault location technology based on waveform correlation can accurately identify the position of fault occurrence by calculating the correlation between waveforms, and the method not only responds rapidly, but also can greatly reduce the dependence on the traditional fault detection hardware and obviously reduce the operation and maintenance cost of the system.
In addition, the self-adaption and self-healing capabilities of the smart grid also provide new opportunities for fault handling. By combining the intelligent power grid technology with a machine learning algorithm, the real-time monitoring and dynamic response of the power grid can be realized, and the power grid can automatically isolate a fault area and reconfigure network resources when faults occur, so that normal power supply is recovered. The integrated and automatic fault response mechanism not only improves the operation efficiency of the power grid, but also enhances the safety and reliability of the power grid.
Disclosure of Invention
In order to improve the accuracy and the robustness of the fault detection and positioning of the 10kV power distribution network, the first aspect of the invention provides a power distribution network single-phase grounding fault positioning method based on a convolutional neural network, which comprises the following steps: three-phase current signals and an electrical topological relation diagram of each node of a target power distribution network are obtained, and the three-phase current signals are converted into RGB images through symmetrical Hilbert transformation; constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network; extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network, and training a transducer model according to the feature map; and positioning the single-phase ground fault of the target power distribution network based on the trained transducer model.
In some embodiments of the present invention, the obtaining a three-phase current signal and an electrical topology graph of each node of the target power distribution network, and converting the three-phase current signal into an RGB image through a symmetrical hilbert transformation includes: extracting instantaneous phase and amplitude from the three-phase current signal by symmetric hilbert transformation; the corresponding instantaneous phase and amplitude of each node is mapped to the color space of the RGB image.
Further, the mapping the instantaneous phase and amplitude corresponding to each node to the color space of the RGB image includes: mapping the instantaneous phase and amplitude corresponding to each node to the pixel intensity and tone of the RGB image respectively; the corresponding instantaneous phase and amplitude of each node are mapped to the color and brightness of the RGB image.
In some embodiments of the present invention, constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network includes: the connection between each power element and each power element is respectively used as a node and a side to construct a graph network; based on the graph neural network, a graph isomorphic network is constructed through a multi-layer perceptron and an autoregressive method.
Further, the method further comprises the following steps: and dynamically adjusting the graph isomorphic network based on parameterized adaptive graph learning.
In the above embodiment, the extracting the feature map from the RGB image and map isomorphic network through the depth separable convolutional neural network includes: normalizing and clipping the RGB image and the graph isomorphic network based on the size of a preset convolution kernel; based on the size of the preset convolution kernel, respectively extracting a plurality of channel features of the RGB image and the map isomorphic network through depth convolution; and fusing the channel characteristics through point-by-point convolution to obtain a characteristic diagram.
In a second aspect of the present invention, there is provided a single-phase earth fault locating device for a power distribution network based on a convolutional neural network, including: the acquisition module is used for acquiring three-phase current signals and an electrical topological relation diagram of each node of the target power distribution network, and converting the three-phase current signals into RGB images through symmetrical Hilbert transformation; the construction module is used for constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network; the extraction module is used for extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network and training a transducer model according to the feature map; and the positioning module is used for positioning the single-phase ground fault of the target power distribution network based on the trained transducer model.
In a third aspect of the present invention, there is provided an electronic apparatus comprising: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the single-phase grounding fault positioning method for the power distribution network based on the convolutional neural network provided by the first aspect of the invention.
In a fourth aspect of the present invention, a computer readable medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for locating single-phase ground faults of a power distribution network based on a convolutional neural network provided in the first aspect of the present invention.
The beneficial effects of the invention are as follows:
the invention relates to a method and a system for locating single-phase earth faults of a power distribution network based on a convolutional neural network, wherein the method comprises the following steps: three-phase current signals and an electrical topological relation diagram of each node of a target power distribution network are obtained, and the three-phase current signals are converted into RGB images through symmetrical Hilbert transformation; constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network; extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network, and training a transducer model according to the feature map; and positioning the single-phase ground fault of the target power distribution network based on the trained transducer model.
The invention converts the three-phase current signals into images through symmetrical Hilbert transformation, constructs a graph isomorphic network through topological relation, combines RGB images with the graph isomorphic network, and extracts features by utilizing a convolutional neural network; the single-phase ground fault of the target power distribution network is positioned through a transducer model with multi-mode characteristics, the complexity of a graph isomorphic network is compensated by an RGB image, the accuracy of RGB is improved due to the complexity of the graph isomorphic network, and the accuracy and the robustness of power distribution network fault detection and positioning are improved by organically combining the two.
Drawings
FIG. 1 is a schematic flow diagram of a method for locating single-phase earth faults of a power distribution network based on convolutional neural networks in some embodiments of the present invention;
Fig. 2 is a schematic flow chart of a method for locating a single-phase earth fault of a power distribution network based on a convolutional neural network according to some embodiments of the present invention;
FIG. 3 is a schematic diagram of a single-phase earth fault location system of a power distribution network based on convolutional neural networks in some embodiments of the invention;
Fig. 4 is a schematic structural diagram of an electronic device according to some embodiments of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Referring to fig. 1 and fig. 2, in a first aspect of the present invention, there is provided a method for locating a single-phase earth fault of a power distribution network based on a convolutional neural network, including: s100, acquiring a three-phase current signal and an electrical topological relation diagram of each node of a target power distribution network, and converting the three-phase current signal into an RGB image through symmetrical Hilbert transformation; s200, constructing a graph isomorphic network based on three-phase current signals and an electrical topological relation graph of each node of a target power distribution network; s300, extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network, and training a transducer model according to the feature map; s400, positioning the single-phase ground fault of the target power distribution network based on the trained transducer model.
In step S100 of some embodiments of the present invention, the obtaining a three-phase current signal and an electrical topology relation diagram of each node of the target power distribution network, and converting the three-phase current signal into an RGB image through a symmetrical hilbert transformation includes:
S101, extracting instantaneous phase and amplitude from the three-phase current signal through symmetrical Hilbert transform;
S102, mapping the instantaneous phase and amplitude corresponding to each node to a color space of the RGB image.
In particular, for 10kV distribution networks, high precision sensor systems need to be deployed to monitor critical point currents and voltages. And a sensor measuring unit is arranged at the key node and used for collecting waveform data of voltage and current in real time. By establishing a distributed sensing network, the comprehensiveness and redundancy of data acquisition are ensured, and the influence of single-point faults is reduced.
Hilbert transform is defined as the original signalCan be used to construct an analytic signal. Resolving signals/>Expressed as: /(I)Wherein/>Is/>Hilbert transform of/>The unbiased phase of each point of (2) is shifted by 90 degrees. The resolved signal may be further expressed as: /(I)，
Here the number of the elements is the number,Is the instantaneous amplitude of the signal: /(I)And/>Is the instantaneous phase:;
SHTP (Symmetric Hilbert Transform) -based image generation involves 、/>Which translates to pixel intensities and hues of the image. Typically, amplitude may be mapped to pixel intensity and phase may be mapped to hue, forming a color image in which different shades of each color represent different states of the signal.
Further, to express the intrinsic characteristics of the three-phase currents more variously and improve the robustness of the characteristic expression, in step S102, mapping the instantaneous phase and amplitude corresponding to each node to the color space of the RGB image includes: mapping the instantaneous phase and amplitude corresponding to each node to the pixel intensity and tone of the RGB image respectively; the corresponding instantaneous phase and amplitude of each node are mapped to the color and brightness of the RGB image.
It will be appreciated that in fault analysis of a power system, the SHTP method may capture minor changes in the current or voltage signal due to faults, which may be difficult to detect in conventional methods. The SHTP method provides more information to the deep learning model by converting the signal to a richer representation space (i.e., color image), thereby potentially improving the accuracy and efficiency of fault detection. In addition, the generated image is convenient for manual inspection and verification, and the transparency and the interpretability of the system are improved.
In step S200 of some embodiments of the present invention, constructing a graph isomorphic network based on the three-phase current signals and the electrical topology graph of each node of the target power distribution network includes:
s201, connecting each power element with each power element to be used as a node and a side respectively to construct a graph neural network;
In particular, the entire distribution network is considered as one diagram, wherein the nodes represent power elements (e.g., transformers, cables, etc.), and the edges represent electrical connections; processing the graph data over learning an embedded representation of the nodes, wherein the node representation is updated by the following recursive formula:
，
Wherein, Is node/>In/>Layer characterization,/>Is/>Is a neighbor node set of/>Is at the/>Multilayer perceptron (Multilayer Perceptron, MLP) for layer use, while/>Are learnable parameters that allow the model to adjust neighbor contributions in the autoregressive model.
S202, constructing a graph isomorphic network through a multi-layer perceptron and an autoregressive method based on the graph neural network.
Specifically, an initial graph model is constructed according to the physical layout and electrical connections of the power distribution network. Recursive updating of node features is performed using GIN (Graph Isomorphism Network, graph-isomorphic network), and advanced representations of nodes are learned through a multi-layer structure.
Further, the method further comprises the following steps: s203, dynamically adjusting the graph isomorphic network based on parameterized self-adaptive graph learning. The parameterized adaptive graph learning (AdapGL) can dynamically adjust the structure of the graph to better adapt to changes in the data, such as topology changes when a fault occurs.
Specifically, the structure of the graph is dynamically updated by AdapGL modules, particularly to adjust the edge weights between nodes when a system configuration change or failure occurs. The core of this module is a weight update mechanism that allows the network to learn and optimize the weight of the edges based on the data. This is typically achieved by an attention mechanism:
，
Wherein, Is node/>Pair node/>Attention weight of/>Is a parameter vector of the attention mechanism,/>Is a shared weight matrix for converting node features to higher-level representation space.
In step S300 of some embodiments of the present invention, the extracting the feature map from the RGB image and map homogeneous network through a depth separable convolutional neural network (DEPTHWISE SEPARABLE CONVOLUTIONAL NEURAL NETWORKS, DSCNN) includes:
S301, carrying out normalization and clipping processing on the RGB image and the graph isomorphic network based on the size of a preset convolution kernel;
s302, based on the size of the preset convolution kernel, respectively extracting a plurality of channel features of an RGB image and a map isomorphic network through depth convolution;
s303, fusing the channel features through point-to-point convolution to obtain a feature map.
In particular, the depth convolution applies a separate convolution kernel for each channel of the input independently, meaning that if there are c channels of input data, there will be c convolution kernels, each typically 3 x 3 or 5 x 5 in size. This step only spatially mixes the input data and does not combine the information across channels. The extraction process for each channel is expressed as:
，
Wherein, Is the output of the/>Channel,/>Input of/>Channel,/>Is applied to the/>The convolution kernel of the channel. After the depth convolution, the point-wise convolution combines and mixes the output channels of the depth convolution using a1 x1 convolution kernel. This step combines the outputs of all channels linearly at each location, thereby fusing information from different channels. The process of point-wise convolution is expressed as:
，
Wherein, Is a1 x 1 convolution kernel used for cross-channel information fusion.
It is understood that DSCNN models include multiple depth convolution layers and point-wise convolution layers. Each depth convolution is followed by a point-by-point convolution, thereby enhancing the learning ability and expressive power of the model. The transition learning strategy is applied, using model parameters pre-trained on a large-scale dataset as an initialization, the last few layers are adjusted to accommodate the specific failure detection task. And optimizing and evaluating the model by using methods such as cross verification and the like, so as to ensure that the model has stable and reliable performance under different conditions.
In step S400 of some embodiments of the present invention, a single-phase ground fault of the target distribution network is located based on the trained transducer model. Specifically, after a real-time three-phase current signal and an electrical topological relation diagram are obtained, the real-time three-phase current signal and the electrical topological relation diagram are input into a training completion transformer model, the characteristic diagram is decoded through the transformer model, topological nodes corresponding to abnormal pixels are determined, and then a ground fault interval is accurately and gradually determined according to the topological relation.
Example 2
Referring to fig. 3, in a second aspect of the present invention, there is provided a power distribution network single-phase earth fault locating device 1 based on a convolutional neural network, including: the acquisition module 11 is configured to acquire a three-phase current signal and an electrical topology relation diagram of each node of the target power distribution network, and convert the three-phase current signal into an RGB image through symmetrical hilbert transformation; the construction module 12 is configured to construct a graph isomorphic network based on the three-phase current signals and the electrical topology relationship graph of each node of the target power distribution network; an extracting module 13, configured to extract a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network, and train a transducer model according to the feature map; the positioning module 14 is configured to position a single-phase ground fault of the target power distribution network based on the trained transducer model.
Further, the acquisition module 1 includes: an extraction unit for extracting instantaneous phase and amplitude from the three-phase current signal by symmetrical hilbert transformation; and the mapping unit is used for mapping the instantaneous phase and amplitude corresponding to each node to the color space of the RGB image.
Example 3
Referring to fig. 4, a third aspect of the present invention provides an electronic device, including: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the single-phase grounding fault positioning method of the power distribution network based on the convolutional neural network in the first aspect.
The electronic device 500 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with programs stored in a Read Only Memory (ROM) 502 or loaded from a storage 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following devices may be connected to the I/O interface 505 in general: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 508 including, for example, a hard disk; and communication means 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 500 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 4 may represent one device or a plurality of devices as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In an embodiment of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. Whereas in embodiments of the present disclosure, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more computer programs which, when executed by the electronic device, cause the electronic device to:
Computer program code for carrying out operations of embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++, python and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Claims (10)
1. A power distribution network single-phase earth fault positioning method based on a convolutional neural network is characterized by comprising the following steps:
three-phase current signals and an electrical topological relation diagram of each node of a target power distribution network are obtained, and the three-phase current signals are converted into RGB images through symmetrical Hilbert transformation;
constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network;
extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network, and training a transducer model according to the feature map;
And positioning the single-phase ground fault of the target power distribution network based on the trained transducer model.
2. The method for locating single-phase earth faults of a power distribution network based on a convolutional neural network according to claim 1, wherein the step of obtaining three-phase current signals and an electrical topological relation diagram of each node of a target power distribution network, and the step of converting the three-phase current signals into RGB images through symmetrical Hilbert transformation comprises the steps of:
extracting instantaneous phase and amplitude from the three-phase current signal by symmetric hilbert transformation;
the corresponding instantaneous phase and amplitude of each node is mapped to the color space of the RGB image.
3. The method for locating single-phase earth faults in a power distribution network based on convolutional neural network according to claim 2, wherein said mapping the corresponding instantaneous phase and amplitude of each node to the color space of the RGB image comprises:
mapping the instantaneous phase and amplitude corresponding to each node to the pixel intensity and tone of the RGB image respectively;
the corresponding instantaneous phase and amplitude of each node are mapped to the color and brightness of the RGB image.
4. The method for locating single-phase earth faults of a power distribution network based on a convolutional neural network according to claim 1, wherein the constructing a graph isomorphic network based on three-phase current signals and an electrical topological relation graph of each node of a target power distribution network comprises:
The connection between each power element and each power element is respectively used as a node and an edge to construct a graph neural network;
based on the graph neural network, a graph isomorphic network is constructed through a multi-layer perceptron and an autoregressive method.
5. The convolutional neural network-based power distribution network single-phase earth fault location method of claim 4, further comprising: and dynamically adjusting the graph isomorphic network based on parameterized adaptive graph learning.
6. The method for locating single-phase earth faults of a power distribution network based on a convolutional neural network according to claim 1, wherein the extracting feature graphs from the RGB image and graph isomorphic network through a depth separable convolutional neural network comprises:
Normalizing and clipping the RGB image and the graph isomorphic network based on the size of a preset convolution kernel;
Based on the size of the preset convolution kernel, respectively extracting a plurality of channel features of the RGB image and the map isomorphic network through depth convolution;
And fusing the channel characteristics through point-by-point convolution to obtain a characteristic diagram.
7. The utility model provides a distribution network single-phase earth fault positioner based on convolutional neural network which characterized in that includes:
The acquisition module is used for acquiring three-phase current signals and an electrical topological relation diagram of each node of the target power distribution network, and converting the three-phase current signals into RGB images through symmetrical Hilbert transformation;
The construction module is used for constructing a graph isomorphic network based on the three-phase current signals and the electrical topological relation graph of each node of the target power distribution network;
The extraction module is used for extracting a feature map from the RGB image and map isomorphic network through a depth separable convolutional neural network and training a transducer model according to the feature map;
And the positioning module is used for positioning the single-phase ground fault of the target power distribution network based on the trained transducer model.
8. The convolutional neural network-based power distribution network single-phase earth fault locating device of claim 7, wherein the acquisition module comprises:
An extraction unit for extracting instantaneous phase and amplitude from the three-phase current signal by symmetrical hilbert transformation;
And the mapping unit is used for mapping the instantaneous phase and amplitude corresponding to each node to the color space of the RGB image.
9. An electronic device, comprising: one or more processors; storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the convolutional neural network based power distribution network single phase ground fault localization method of any one of claims 1 to 6.
10. A computer readable medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the convolutional neural network-based power distribution network single-phase earth fault localization method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410602258.2A CN118169517B (en) | 2024-05-15 | 2024-05-15 | Power distribution network single-phase earth fault positioning method and system based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410602258.2A CN118169517B (en) | 2024-05-15 | 2024-05-15 | Power distribution network single-phase earth fault positioning method and system based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118169517A true CN118169517A (en) | 2024-06-11 |
| CN118169517B CN118169517B (en) | 2024-08-09 |
Family
ID=91360876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410602258.2A Active CN118169517B (en) | 2024-05-15 | 2024-05-15 | Power distribution network single-phase earth fault positioning method and system based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118169517B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814731A (en) * | 2010-04-15 | 2010-08-25 | 中国石油大学(华东) | Distribution network fault line selection method using non-power frequency transient state component |
| US20210293873A1 (en) * | 2020-03-18 | 2021-09-23 | Mitsubishi Electric Research Laboratories, Inc. | Transient based Fault Location Method for Ungrounded Power Distribution Systems |
| CN114624551A (en) * | 2022-03-21 | 2022-06-14 | 保定市毅格通信自动化有限公司 | Distribution line fault positioning method based on spatial data fusion |
| CN116679161A (en) * | 2023-05-25 | 2023-09-01 | 国网江苏省电力有限公司南京供电分公司 | Power grid line fault diagnosis method, equipment and medium |
| CN116973677A (en) * | 2023-07-13 | 2023-10-31 | 国网吉林省电力有限公司电力科学研究院 | Distribution network single-phase earth fault line selection method based on cavity convolution and attention mechanism |
-
2024
- 2024-05-15 CN CN202410602258.2A patent/CN118169517B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814731A (en) * | 2010-04-15 | 2010-08-25 | 中国石油大学(华东) | Distribution network fault line selection method using non-power frequency transient state component |
| US20210293873A1 (en) * | 2020-03-18 | 2021-09-23 | Mitsubishi Electric Research Laboratories, Inc. | Transient based Fault Location Method for Ungrounded Power Distribution Systems |
| CN114624551A (en) * | 2022-03-21 | 2022-06-14 | 保定市毅格通信自动化有限公司 | Distribution line fault positioning method based on spatial data fusion |
| CN116679161A (en) * | 2023-05-25 | 2023-09-01 | 国网江苏省电力有限公司南京供电分公司 | Power grid line fault diagnosis method, equipment and medium |
| CN116973677A (en) * | 2023-07-13 | 2023-10-31 | 国网吉林省电力有限公司电力科学研究院 | Distribution network single-phase earth fault line selection method based on cavity convolution and attention mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 张科;朱永利;郑艳艳;高佳程;: "风电场输电线路单相接地故障定位研究", 太阳能学报, no. 05, 28 May 2020 (2020-05-28) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118169517B (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI425226B (en) | Method and system for fault detection, identification and location in high-voltage power transmission networks | |
| TWI692196B (en) | Fault detection system and method for solar photovoltaic | |
| Topaloglu | Deep learning based a new approach for power quality disturbances classification in power transmission system | |
| CN109784369A (en) | H5 page test method and device, electronic equipment, storage medium | |
| CN113409284B (en) | Circuit board fault detection method, device, equipment and storage medium | |
| CN116596916B (en) | Training of defect detection model and defect detection method and device | |
| Khan et al. | End-to-end partial discharge detection in power cables via time-domain convolutional neural networks | |
| CN114897032B (en) | Current transformer fault diagnosis method and device based on width learning | |
| CN114414955A (en) | Method and system for monitoring and evaluating state of switch cabinet | |
| Gjorgiev et al. | Simulation-driven deep learning for locating faulty insulators in a power line | |
| JP2015148934A (en) | Power generation amount prediction device and power generation amount prediction method | |
| Pang et al. | A deep learning based multiple signals fusion architecture for power system fault diagnosis | |
| CN110353688A (en) | The method for carrying out sitting posture analysis based on the buttocks of artificial intelligence and electronic skin contact data | |
| CN118169517B (en) | Power distribution network single-phase earth fault positioning method and system based on convolutional neural network | |
| CN117079005A (en) | Optical cable fault monitoring method, system, device and readable storage medium | |
| CN117892611A (en) | Method and device for generating pseudo measurement of medium-voltage distribution network based on space-time diagram neural network | |
| CN115239889B (en) | Training method of 3D reconstruction network, 3D reconstruction method, device, equipment and medium | |
| CN116363474A (en) | Relay protection device detection method and system based on space-time attention mechanism CNN | |
| CN112581387B (en) | Intelligent operation and maintenance system, device and method for power distribution room | |
| Bosma et al. | Estimating solar and wind power production using computer vision deep learning techniques on weather maps | |
| CN114626545A (en) | Data preparation for artificial intelligence models | |
| CN112861670A (en) | Transmission line hardware detection method and system | |
| Wang et al. | Harmonic state estimation based on graph signal processing | |
| CN110353687A (en) | The device of sitting posture analysis is carried out based on the buttocks of artificial intelligence and electronic skin contact data | |
| Sun et al. | Automatic Meter Pointer Reading Based on Knowledge Distillation |
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 |