CN118114022A - Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults - Google Patents

Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults Download PDF

Info

Publication number
CN118114022A
CN118114022A CN202410303990.XA CN202410303990A CN118114022A CN 118114022 A CN118114022 A CN 118114022A CN 202410303990 A CN202410303990 A CN 202410303990A CN 118114022 A CN118114022 A CN 118114022A
Authority
CN
China
Prior art keywords
power grid
abnormal
feature
feature extraction
knowledge graph
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.)
Withdrawn
Application number
CN202410303990.XA
Other languages
Chinese (zh)
Inventor
刘俊楠
韦啸
夏新武
徐子安
朱泰亨
杨雪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Institute of Technology
Original Assignee
Nanjing Institute of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Institute of Technology filed Critical Nanjing Institute of Technology
Priority to CN202410303990.XA priority Critical patent/CN118114022A/en
Publication of CN118114022A publication Critical patent/CN118114022A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • 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
    • G06F18/2431—Multiple classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • 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
    • G06N3/08—Learning methods
    • G06N3/092—Reinforcement learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Business, Economics & Management (AREA)
  • Evolutionary Biology (AREA)
  • Biomedical Technology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention discloses an intelligent feature extraction and tracing method, system, equipment and medium for power grid faults, and relates to the technical field of power system analysis. The method comprises the following steps: acquiring power grid operation parameters under the new energy grid connection condition; extracting the characteristics of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based characteristic extraction network to obtain the current characteristic quantity fused with related sequence characteristics and time sequence characteristics; constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity; tracing in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find out abnormal events. The invention can perform abnormal searching and tracing analysis on the power grid faults and improve the stability of the new energy grid-connected system.

Description

Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults
Technical Field
The invention relates to the technical field of power system analysis, in particular to a method, a system, equipment and a medium for intelligent feature extraction and tracing of power grid faults.
Background
Along with energy development, the construction of a novel power system taking new energy as a main body accelerates, and a regional power grid as an important main body for energy use becomes a main construction direction of the novel power system. The novel power system presents novel characteristics such as high-proportion penetration of new energy, large-scale application of power electronic equipment, equipment isomerization such as wide access of distributed adjustable resources and the like, and power grid polymorphism. The mass multi-type measurement data generated by the multi-element resources in the fusion system has important significance for power system state estimation, equipment evaluation, accident analysis and the like, so that the power grid operation characteristics can be obtained through analysis of the power grid operation measurement data, and the related power faults under the new energy grid connection condition can be traced.
With more and more renewable energy sources accessing to a power grid, as new energy sources are required to be directly or indirectly connected to a large power grid through a power electronic interface, the supporting characteristics of voltage, frequency and the like of the new energy sources are greatly different from those of the traditional generator set, and the new energy sources have the characteristics of uncertainty, large fluctuation range, intermittence and the like, so that the stability of a high-proportion new energy source grid-connected system is greatly challenged. Meanwhile, when new energy is connected in a grid through the power electronic interface in an extremely high proportion, the power grid strength is characterized by changing in a wider range, large-range impact is caused to the operation of the power system, various fault abnormal events are easy to cause, and if the fault event characteristics cannot be clearly mastered, the stability problem of the high-proportion new energy grid-connected system cannot be fundamentally solved by tracing and analyzing the events.
Disclosure of Invention
The invention aims to provide a method, a system, equipment and a medium for intelligent feature extraction and tracing of power grid faults, which can improve the stability of a new energy grid-connected system.
In order to achieve the above object, the present invention provides the following solutions:
an intelligent feature extraction and tracing method for power grid faults comprises the following steps:
acquiring power grid operation parameters under the new energy grid connection condition;
Extracting the characteristics of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based characteristic extraction network to obtain the current characteristic quantity fused with related sequence characteristics and time sequence characteristics;
Constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity;
Tracing in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find out abnormal events.
Optionally, the feature extraction method uses a ResNet-LSTM-based feature extraction network to perform feature extraction on abnormal parameters in the power grid operation parameters to obtain a current feature quantity fused with related sequence features and time sequence features, and specifically includes:
constructing a sequence feature matrix by using a depth residual neural network and the power grid operation parameters, and performing imaging processing on the sequence feature matrix to obtain a first associated feature;
extracting time sequence characteristics of the power grid operation parameters by utilizing an LSTM long-term memory countering network to obtain second associated characteristics;
and determining the current feature quantity of the fusion related sequence feature and the sequence feature according to the first association feature and the second association feature.
Optionally, the specific process of the imaging processing is as follows:
and (3) sequentially mapping the j-th operation parameter data of the i-th operation parameter in the sequence feature matrix into values of [0, 255] in the RGB color space by using a conversion formula.
Optionally, the conversion formula specifically includes:
wherein C ij represents an RGB pixel value corresponding to the jth operating parameter data of the ith operating parameter; d ij denotes the jth operating parameter data of the ith operating parameter; MIN (d i) represents the smallest operating parameter data among the ith operating parameters; MAX (d i) represents the maximum operating parameter data in the ith operating parameter.
Optionally, the map relationship is specifically: one feature quantity corresponds to a plurality of abnormal change trends, and each abnormal change trend corresponds to one possibly caused abnormal event.
The invention also provides a power grid fault intelligent feature extraction and tracing method, which comprises the following steps:
the parameter acquisition unit is used for acquiring power grid operation parameters under the new energy grid connection condition;
The feature extraction unit is used for extracting features of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based feature extraction network to obtain current feature quantities fusing related sequence features and time sequence features;
The knowledge graph construction unit is used for constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity;
And the abnormal trace source unit is used for tracing sources in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find abnormal events.
The invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the intelligent characteristic extraction and tracing method according to the power grid fault.
The invention also provides a computer readable storage medium storing a computer program which when executed by a processor implements the intelligent feature extraction and tracing method for power grid faults as described above.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a method, a system, equipment and a medium for intelligent feature extraction and tracing of power grid faults, wherein the method comprises the steps of obtaining power grid operation parameters under the condition of new energy grid connection; extracting the characteristics of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based characteristic extraction network to obtain the current characteristic quantity fused with related sequence characteristics and time sequence characteristics; constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity; tracing in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find out abnormal events. The invention can perform abnormal searching and tracing analysis on the power grid faults and improve the stability of the new energy grid-connected system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a diagram illustrating mapping of an operation parameter matrix D to RGB color space according to the present embodiment;
fig. 2 is a schematic diagram of a depth residual network structure in the present embodiment;
FIG. 3 is a schematic diagram of LSTM neuron structure in this example;
fig. 4 is a schematic diagram of a knowledge graph of a transaction event under the new energy grid-connected condition in the present embodiment;
fig. 5 is a schematic flow chart of the intelligent feature extraction and tracing method for the power grid faults.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a method, a system, equipment and a medium for intelligent feature extraction and tracing of power grid faults, which can improve the stability of a new energy grid-connected system.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1-5, the present invention provides a method for extracting and tracing intelligent characteristics of power grid faults, which includes:
Step 100: acquiring power grid operation parameters under the new energy grid connection condition;
step 200: and extracting the characteristics of the abnormal parameters in the power grid operation parameters by using a ResNet-LSTM-based characteristic extraction network to obtain the current characteristic quantity fused with the related sequence characteristics and the time sequence characteristics.
Step 300: constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity; the map relation is specifically as follows: one feature quantity corresponds to a plurality of abnormal change trends, and each abnormal change trend corresponds to one possibly caused abnormal event.
Step 400: tracing in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find out abnormal events.
As a specific embodiment of step 200, it includes:
Constructing a sequence feature matrix by using a depth residual neural network and the power grid operation parameters, and performing imaging processing on the sequence feature matrix to obtain a first associated feature; extracting time sequence characteristics of the power grid operation parameters by utilizing an LSTM long-term memory countering network to obtain second associated characteristics; and determining the current feature quantity of the fusion related sequence feature and the sequence feature according to the first association feature and the second association feature.
The specific process of the imaging processing is as follows:
and (3) sequentially mapping the j-th operation parameter data of the i-th operation parameter in the sequence feature matrix into values of [0, 255] in the RGB color space by using a conversion formula.
And, the conversion formula is specifically:
Wherein, C ij represents the RGB pixel value corresponding to the j-th operation parameter data of the i-th operation parameter; d ij denotes the jth operating parameter data of the ith operating parameter; MIN (d i) represents the smallest operating parameter data among the ith operating parameters; MAX (d i) represents the maximum operating parameter data in the ith operating parameter.
Based on the above technical solutions, the following embodiments are provided.
Aiming at the characteristics that the power system data has a plurality of operation parameters and each parameter has correlation characteristics, a ResNet-LSTM-based characteristic extraction network is adopted to obtain an output result of fusing related sequence characteristics and time sequence characteristics.
Firstly, the advantage of the depth residual neural network in the field of image feature extraction is utilized to construct a high-dimensional data sequence feature matrix D of the power grid operation parameters, and then the feature matrix D is mapped to an RGB color space, so that the imaging of the power grid operation parameter features is realized, as shown in figure 1. The matrix D comprises n operation parameters and m operation parameter data, and the j operation parameter data of the i operation parameters are mapped into values of [0, 255] in the RGB color space in sequence, wherein i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to m.
After the imaged feature matrix is obtained, a front depth residual feature extraction network (shown in figure 2) is used for extracting the relevance features of the operation parameters aiming at the characteristics of high latitude and large oscillation range of the operation parameters of the power grid under the condition of new energy grid connection.
The characteristic matrix is input into the residual unit for characteristic extraction, and in the depth residual network, the gradient can be continuously transmitted in a very deep network through a short-circuit path on the network without being overlapped by the gradient of the excessive convolution layer, so that the problems of gradient disappearance and gradient explosion are essentially avoided, the hidden characteristics among data sequences can be better extracted, and the discovery and tracing of fault abnormal events are better facilitated.
For the time sequence characteristics of the power grid operation parameters under the new energy grid connection condition, the relevant time characteristic extraction can be carried out on the LSTM long-term memory reactance network as shown in figure 3. The LSTM improves part of the network based on the cyclic neural network and is divided into a forgetting gate, an input gate and an output gate. The forget gate can select the useful memory of the previous time node, the input gate can extract the useful information of the current time node, and the output gate can integrate the information of the current time node and the cell state to finish the output.
On the other hand, the construction process of the linkage knowledge graph in the embodiment is as follows:
Based on the data feature extraction tool, the power grid fault feature event is matched with the selected feature quantity, and a map relationship between a plurality of feature quantities and a plurality of feature times can be established by combining expert experience, as shown in fig. 4. Analyzing the abnormal change of the selected feature quantity before and after the occurrence of the fault event by the data feature extraction tool, and establishing a relation, wherein for example, the abnormal change trend 1 of the feature quantity a leads to an event e, and the event e leads to an event f; the abnormal change trend 2 of the feature quantity a will lead to an event g, which will trigger an event h; the abnormal variation trend 1 of the feature quantity b will lead to an event i, which will trigger an event j, etc. Therefore, a knowledge relation graph of the change of the characteristic quantity and the fault characteristic event is established, and the structure can be continuously expanded. Finally, the power grid operation measurement data feature extraction and relation extraction tool based on reinforcement learning provided by the embodiment performs abnormal searching and tracing analysis on the power grid faults with the generated knowledge graph.
In addition, the invention also provides an intelligent feature extraction and tracing method for the power grid faults, which comprises the following steps:
the parameter acquisition unit is used for acquiring power grid operation parameters under the new energy grid connection condition;
The feature extraction unit is used for extracting features of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based feature extraction network to obtain current feature quantities fusing related sequence features and time sequence features;
The knowledge graph construction unit is used for constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity;
And the abnormal trace source unit is used for tracing sources in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find abnormal events.
The invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the intelligent characteristic extraction and tracing method according to the power grid fault.
The invention also provides a computer readable storage medium storing a computer program which when executed by a processor implements the intelligent feature extraction and tracing method for power grid faults as described above.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the core concept of the invention; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.

Claims (8)

1. The intelligent feature extraction and tracing method for the power grid faults is characterized by comprising the following steps of:
acquiring power grid operation parameters under the new energy grid connection condition;
Extracting the characteristics of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based characteristic extraction network to obtain the current characteristic quantity fused with related sequence characteristics and time sequence characteristics;
Constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity;
Tracing in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find out abnormal events.
2. The intelligent feature extraction and tracing method for power grid faults according to claim 1, wherein the feature extraction method is characterized in that feature extraction is carried out on abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based feature extraction network to obtain current feature quantities fusing related sequence features and time sequence features, and specifically comprises the following steps:
constructing a sequence feature matrix by using a depth residual neural network and the power grid operation parameters, and performing imaging processing on the sequence feature matrix to obtain a first associated feature;
extracting time sequence characteristics of the power grid operation parameters by utilizing an LSTM long-term memory countering network to obtain second associated characteristics;
and determining the current feature quantity of the fusion related sequence feature and the sequence feature according to the first association feature and the second association feature.
3. The intelligent feature extraction and tracing method for power grid faults according to claim 1, wherein the specific process of the imaging processing is as follows:
and (3) sequentially mapping the j-th operation parameter data of the i-th operation parameter in the sequence feature matrix into values of [0, 255] in the RGB color space by using a conversion formula.
4. The intelligent feature extraction and tracing method for power grid faults according to claim 3, wherein the conversion formula is specifically as follows:
wherein C ij represents an RGB pixel value corresponding to the jth operating parameter data of the ith operating parameter; d ij denotes the jth operating parameter data of the ith operating parameter; MIN (d i) represents the smallest operating parameter data among the ith operating parameters; MAX (d i) represents the maximum operating parameter data in the ith operating parameter.
5. The intelligent feature extraction and tracing method for power grid faults according to claim 1, wherein the map relation is specifically: one feature quantity corresponds to a plurality of abnormal change trends, and each abnormal change trend corresponds to one possibly caused abnormal event.
6. The intelligent feature extraction and tracing method for the power grid faults is characterized by comprising the following steps of:
the parameter acquisition unit is used for acquiring power grid operation parameters under the new energy grid connection condition;
The feature extraction unit is used for extracting features of abnormal parameters in the power grid operation parameters by utilizing a ResNet-LSTM-based feature extraction network to obtain current feature quantities fusing related sequence features and time sequence features;
The knowledge graph construction unit is used for constructing a linkage knowledge graph; the linkage knowledge graph is used for representing graph relations between abnormal events and the selected characteristic quantity;
And the abnormal trace source unit is used for tracing sources in the chain knowledge graph according to the current abnormal change trend of the characteristic quantity to find abnormal events.
7. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the grid fault intelligent feature extraction and tracing method according to claims 1-5.
8. A computer readable storage medium, characterized in that it stores a computer program, which when executed by a processor implements the intelligent feature extraction and tracing method of power grid faults as claimed in claims 1-5.
CN202410303990.XA 2024-03-18 2024-03-18 Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults Withdrawn CN118114022A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410303990.XA CN118114022A (en) 2024-03-18 2024-03-18 Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410303990.XA CN118114022A (en) 2024-03-18 2024-03-18 Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults

Publications (1)

Publication Number Publication Date
CN118114022A true CN118114022A (en) 2024-05-31

Family

ID=91216817

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410303990.XA Withdrawn CN118114022A (en) 2024-03-18 2024-03-18 Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults

Country Status (1)

Country Link
CN (1) CN118114022A (en)

Similar Documents

Publication Publication Date Title
Abbassi et al. Parameterization of photovoltaic solar cell double-diode model based on improved arithmetic optimization algorithm
CN113935562B (en) Intelligent grading and automatic early warning method for health condition of power equipment
CN114896472B (en) Knowledge graph machine reasoning system and method based on multi-source space-time data
CN110232476A (en) A kind of micro-grid load prediction technique based on deep learning
CN116467674B (en) Intelligent fault processing fusion updating system and method for power distribution network
CN116298902A (en) Lithium battery aging prediction method and system based on multitask learning
CN114117921A (en) Intelligent diagnosis method for faults of photovoltaic array
CN112865089A (en) Improved large-scale scene analysis method for active power distribution network
CN115469184A (en) New energy transmission line fault identification method based on convolutional network
CN116299002A (en) Transformer-based lithium battery health state estimation method and system
CN116779202A (en) Digital twinning-based intelligent fault diagnosis method and system for rotating equipment of nuclear power plant
CN115345297A (en) Platform area sample generation method and system based on generation countermeasure network
CN117421992B (en) Transformer winding hot spot temperature inversion method
CN118191628A (en) Machine learning-based mining lithium ion battery SOC prediction method and system
CN116960487B (en) Sodium ion battery system capacity estimation method and device considering monomer inconsistency
CN117669656A (en) TCN-Semi PN-based direct-current micro-grid stability real-time monitoring method and device
CN118095891A (en) Active power distribution network payload prediction method and system considering source load meteorological characteristic decoupling
CN118114022A (en) Intelligent feature extraction and tracing method, system, equipment and medium for power grid faults
CN116737943A (en) News field-oriented time sequence knowledge graph link prediction method
CN113092934B (en) Single-phase earth fault judgment method and system based on clustering and LSTM
CN115905360A (en) Abnormal data measurement identification method and device based on random construction matrix
CN113988395A (en) Wind power ultra-short-term power prediction method based on SSD and dual attention mechanism BiGRU
CN114861791A (en) Interpretable voltage sag classification method based on knowledge graph
CN114611990A (en) Method and device for evaluating contribution rate of element system of network information system
CN112183823A (en) Electric energy metering device model selection method and system based on rule tree

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20240531