CN118518984B - Intelligent fault positioning system and method for power transmission and distribution line - Google Patents
Intelligent fault positioning system and method for power transmission and distribution line Download PDFInfo
- Publication number
- CN118518984B CN118518984B CN202410994275.5A CN202410994275A CN118518984B CN 118518984 B CN118518984 B CN 118518984B CN 202410994275 A CN202410994275 A CN 202410994275A CN 118518984 B CN118518984 B CN 118518984B
- Authority
- CN
- China
- Prior art keywords
- frequency
- semantic
- key node
- current time
- node current
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 146
- 230000005540 biological transmission Effects 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 97
- 238000012545 processing Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 72
- 238000012549 training Methods 0.000 claims description 64
- 238000011176 pooling Methods 0.000 claims description 33
- 238000010586 diagram Methods 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 229940050561 matrix product Drugs 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000003993 interaction Effects 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 abstract description 5
- 238000012098 association analyses Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 13
- 230000006870 function Effects 0.000 description 9
- 230000001149 cognitive effect Effects 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000004807 localization Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000001364 causal effect Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002847 impedance measurement Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000000126 substance Substances 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
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- 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
- 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/26—Discovering frequent patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Emergency Protection Circuit Devices (AREA)
Abstract
The application discloses an intelligent fault positioning system and method for a power transmission and distribution line, which are characterized in that current detection signals are monitored and collected in real time through circuit transformers arranged on a plurality of key nodes of the power transmission and distribution line, and the collaborative and association analysis of the current detection signals of different key nodes are carried out by introducing a data processing and signal analysis algorithm based on artificial intelligence and deep learning technology at the rear end, so that the time-frequency semantic characteristics of the current detection signals of all the key nodes are learned and captured, and the correlation and interaction information among the current time-frequency semantics of different key nodes are utilized to identify and detect fault nodes. Therefore, the fault position of the oil field power transmission and distribution line can be automatically identified and positioned, and more intelligent powerful support is provided for the safe and stable operation of the oil field power transmission and distribution line.
Description
Technical Field
The application relates to the field of intelligent positioning, in particular to an intelligent fault positioning system and method for a power transmission and distribution line.
Background
In oilfield transmission and distribution networks, transmission and distribution lines are an important tie connecting oilfield production facilities and power supply systems. Because of the particularities of oilfield environments, power transmission and distribution lines often face various complex conditions, such as extreme climates, mechanical shock, chemical corrosion, etc., which can cause the lines to fail. Once the power transmission and distribution line fails, normal production of an oil field is affected, and serious economic loss and safety accidents can be caused. Therefore, the fault detection device can timely and accurately detect and position faults of power transmission and distribution lines, and has important significance for guaranteeing the production safety of oil fields and improving the reliability of a power system.
However, the conventional power transmission and distribution line fault detection and positioning method, such as based on an impedance measurement method, a traveling wave method and the like, can realize fault detection to a certain extent, but often has the problems of low detection speed, low positioning accuracy, large environmental influence and the like.
Accordingly, an intelligent fault locating system for power transmission and distribution lines is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The application provides an intelligent fault positioning system and method for a power transmission and distribution line, which are characterized in that current detection signals are monitored and collected in real time through circuit transformers arranged on a plurality of key nodes of the power transmission and distribution line, and the collaborative and association analysis of the current detection signals of different key nodes are carried out by introducing a data processing and signal analysis algorithm based on artificial intelligence and deep learning technology at the rear end, so that the time-frequency semantic characteristics of the current detection signals of all the key nodes are learned and captured, and the correlation and interaction information among the current time-frequency semantics of different key nodes are utilized to identify and detect fault nodes. Therefore, the fault position of the oil field power transmission and distribution line can be automatically identified and positioned, and more intelligent powerful support is provided for the safe and stable operation of the oil field power transmission and distribution line.
According to one aspect of the present application, there is provided a fault intelligent positioning system for a power transmission and distribution line, comprising: the key node current detection signal acquisition module is used for acquiring current detection signals acquired by circuit transformers of a plurality of key nodes deployed on the power transmission and distribution line to obtain a plurality of key node current detection signals; the key node current detection time-frequency diagram conversion module is used for carrying out wavelet conversion on each key node current detection signal in the plurality of key node current detection signals so as to obtain a plurality of key node current detection time-frequency diagrams; the current time-frequency characteristic extraction module is used for extracting current time-frequency characteristics of the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic characteristic graphs; the distribution cluster center semantic association calculation module is used for calculating the semantic association degree between the distribution cluster centers of the plurality of key node current time-frequency semantic feature graphs and the plurality of key node current time-frequency semantic feature graphs based on the plurality of key node current time-frequency semantic feature graphs so as to obtain a sequence of the semantic association degree; the fault node judging module is used for determining a fault node based on the sequence of the semantic association degree; the distribution cluster center semantic association calculation module comprises: the sequence distribution cluster center calculating unit is used for calculating the position-based mean value characteristic map of the plurality of key node current time-frequency semantic characteristic maps to serve as a sequence distribution cluster center; the semantic association calculation unit is used for calculating the semantic association degree between each key node current time-frequency semantic feature graph in the plurality of key node current time-frequency semantic feature graphs and the sequence distribution cluster center so as to obtain a sequence of the semantic association degree.
According to another aspect of the present application, there is provided a fault intelligent positioning method for a power transmission and distribution line, including: acquiring current detection signals acquired by circuit transformers arranged at a plurality of key nodes of a power transmission and distribution line to obtain a plurality of key node current detection signals; performing wavelet transformation on each key node current detection signal in the plurality of key node current detection signals to obtain a plurality of key node current detection time-frequency diagrams; carrying out current time-frequency characteristic extraction on the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic feature graphs; calculating the semantic association degree between the current time-frequency semantic feature graphs of the plurality of key nodes and the distribution cluster center of the current time-frequency semantic feature graphs of the plurality of key nodes based on the current time-frequency semantic feature graphs of the plurality of key nodes to obtain a sequence of the semantic association degree; determining a fault node based on the sequence of semantic relatedness; based on the plurality of key node current time-frequency semantic feature graphs, calculating the semantic association degree between the key node current time-frequency semantic feature graphs and the distribution cluster center of the plurality of key node current time-frequency semantic feature graphs to obtain a sequence of the semantic association degree, wherein the sequence comprises the following steps: calculating a position-based mean value characteristic map of the current time-frequency semantic characteristic maps of the plurality of key nodes as a sequence distribution cluster center; and respectively calculating the semantic association degree between each key node current time-frequency semantic feature map in the plurality of key node current time-frequency semantic feature maps and the center of the sequence distribution cluster to obtain a sequence of the semantic association degree.
Compared with the prior art, the intelligent fault positioning system and method for the power transmission and distribution line provided by the application have the advantages that the circuit transformers deployed on a plurality of key nodes of the power transmission and distribution line are used for monitoring and collecting current detection signals in real time, and the data processing and signal analysis algorithm based on artificial intelligence and deep learning technology is introduced at the rear end to carry out the collaboration and association analysis of the current detection signals of different key nodes, so that the time-frequency semantic characteristics of the current detection signals of all the key nodes are learned and captured, and the correlation and interaction information among the current time-frequency semantics of different key nodes are utilized to identify and detect the fault nodes. Therefore, the fault position of the oil field power transmission and distribution line can be automatically identified and positioned, and more intelligent powerful support is provided for the safe and stable operation of the oil field power transmission and distribution line.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a block diagram of an intelligent fault locating system for a power transmission and distribution line according to an embodiment of the present application.
Fig. 2 is a system architecture diagram of a fault intelligent positioning system for a power transmission and distribution line according to an embodiment of the present application.
Fig. 3 is a block diagram of a semantic association calculation module of a distribution cluster center in the fault intelligent positioning system of a power transmission and distribution line according to an embodiment of the present application.
Fig. 4 is a flowchart of a fault intelligent positioning method for a power transmission and distribution line according to an embodiment of the present application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
With the rapid development of artificial intelligence technology, especially the successful application of deep learning technology in the fields of image recognition, voice processing and the like, attempts have been made to apply the technology to fault detection and positioning of oil field power transmission and distribution lines.
In the technical scheme of the application, an intelligent fault positioning system for a power transmission and distribution line is provided. Fig. 1 is a block diagram of an intelligent fault locating system for a power transmission and distribution line according to an embodiment of the present application. Fig. 2 is a system architecture diagram of a fault intelligent positioning system for a power transmission and distribution line according to an embodiment of the present application. As shown in fig. 1 and 2, the intelligent fault locating system 300 for a power transmission and distribution line according to an embodiment of the present application includes: a key node current detection signal acquisition module 310, configured to acquire current detection signals acquired by circuit transformers disposed at a plurality of key nodes of the power transmission and distribution line to obtain a plurality of key node current detection signals; the key node current detection time-frequency diagram conversion module 320 is configured to perform wavelet conversion on each key node current detection signal in the plurality of key node current detection signals to obtain a plurality of key node current detection time-frequency diagrams; the current time-frequency feature extraction module 330 is configured to perform current time-frequency feature extraction on the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic feature graphs; the distribution cluster center semantic association calculation module 340 is configured to calculate, based on the plurality of key node current time-frequency semantic feature graphs, a semantic association degree between the plurality of key node current time-frequency semantic feature graphs and a distribution cluster center of the plurality of key node current time-frequency semantic feature graphs to obtain a sequence of semantic association degrees; a fault node determination module 350, configured to determine a fault node based on the sequence of semantic relevance.
In particular, the critical node current detection signal acquisition module 310 is configured to acquire current detection signals acquired by circuit transformers disposed at a plurality of critical nodes of the power transmission and distribution line to obtain a plurality of critical node current detection signals. In a power transmission and distribution line, a circuit transformer is a sensor device for measuring a current. These transformers are typically installed at key nodes in the power system, such as substations, power distribution cabinets, etc., for monitoring and detecting changes in current. The current detection signals at each node can be obtained in real time through the circuit transformers arranged at different key nodes, so that the monitoring, the management and the control of the power system are realized.
In particular, the key node current detection time-frequency chart conversion module 320 is configured to perform wavelet conversion on each key node current detection signal in the plurality of key node current detection signals to obtain a plurality of key node current detection time-frequency charts. In other words, in the technical scheme of the application, in order to better facilitate the subsequent time-frequency analysis of the current detection signals of the key nodes so as to reflect the inherent characteristics and fault information of the current signals more deeply, the wavelet transformation is further performed on each key node current detection signal in the plurality of key node current detection signals so as to obtain a plurality of key node current detection time-frequency diagrams. It will be appreciated that wavelet transformation is a mathematical tool that can decompose a signal into wavelet functions that constitute the critical node current sense signal, which can reflect the frequency content of the signal at different points in time. That is, wavelet transform provides a method of analyzing a signal while considering both time and frequency, which enables it to reveal local characteristics of the signal, such as a sudden point or a specific time when a fault occurs, which is particularly useful for non-stationary signals (whose frequency components vary with time), while fault signals of power transmission and distribution lines tend to be non-stationary. Furthermore, wavelet transforms allow the signal to be analyzed on different time scales, which means that both low frequency trends and high frequency details of the signal can be observed at the same time, helping to identify small changes in the fault signal, revealing abnormal patterns of the current signal when the fault occurs.
In particular, the current time-frequency feature extraction module 330 is configured to perform current time-frequency feature extraction on the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic feature graphs. In particular, in one specific example of the present application, each of the plurality of key node current detection time-frequency charts is respectively passed through a current time-frequency feature extractor based on a hole convolutional neural network model to obtain the plurality of key node current time-frequency semantic feature charts. It should be appreciated that a hole convolutional neural network is a special convolutional operation in a convolutional neural network that increases the receptive field (i.e., the range of input data covered by the convolutional kernel) by introducing holes in the convolutional kernel (i.e., inserting zero padding between the convolutional kernel elements) while keeping the number of parameters unchanged. This enables the network to capture a wider range of context information with less computational effort, suitable for processing signals with long range dependence characteristics. Therefore, by using the current time-frequency characteristic extractor based on the cavity convolutional neural network model, the current time-frequency semantic characteristics of each key node can be extracted from different current detection time-frequency graphs of the key nodes, and the characteristics can reflect the inherent characteristics and fault information of the current signals more deeply. That is, the hole convolution network can effectively extract characteristics related to faults from the time-frequency diagrams, the characteristics possibly comprise time and frequency ranges of occurrence of the faults, and the like, so that the fault modes and types of different key nodes can be identified.
Accordingly, in one possible implementation manner, each of the plurality of key node current detection time-frequency graphs may be respectively passed through a current time-frequency feature extractor based on a hole convolutional neural network model to obtain the plurality of key node current time-frequency semantic feature graphs, for example: inputting the current detection time-frequency diagrams of the plurality of key nodes; and constructing a cavity convolutional neural network model, wherein the cavity convolutional neural network model comprises a plurality of cavity convolutional layers, an activation function layer, a pooling layer and the like. The combination of these layers can effectively extract meaningful features from the time-frequency diagram; the cavity convolutional neural network model is trained using the prepared current detection time-frequency plot dataset. Model parameters are optimized through a back propagation algorithm, so that semantic features of a current time-frequency diagram can be accurately extracted; inputting the current detection time-frequency diagram of each key node into a trained cavity convolutional neural network model, and extracting semantic features through a forward propagation process; and combining semantic features extracted from the current detection time-frequency graphs of each key node together to obtain current time-frequency semantic feature graphs of the plurality of key nodes.
In particular, the distribution cluster center semantic association calculating module 340 is configured to calculate, based on the plurality of key node current time-frequency semantic feature graphs, a semantic association degree between the plurality of key node current time-frequency semantic feature graphs and the distribution cluster center of the plurality of key node current time-frequency semantic feature graphs to obtain a sequence of semantic association degrees. In particular, in one specific example of the present application, as shown in fig. 3, the distribution cluster center semantic association calculation module 340 includes: the sequence distribution cluster center calculating unit 341 is configured to calculate a position-based mean feature map of the current time-frequency semantic feature maps of the plurality of key nodes as a sequence distribution cluster center; the semantic association calculating unit 342 is configured to calculate semantic association degrees between each of the plurality of key node current time-frequency semantic feature graphs and the center of the sequence distribution cluster to obtain a sequence of the semantic association degrees.
Specifically, the sequence distribution cluster center calculating unit 341 is configured to calculate a position-wise mean feature map of the plurality of current time-frequency semantic feature maps of the key nodes as a sequence distribution cluster center. Because the current time-frequency semantic features of each key node do not exist independently, the correlation relationship and the interaction influence exist, and the correlation mode can reflect a normal current time-frequency mode so as to be beneficial to the subsequent identification and detection of the fault node. Based on the above, in the technical scheme of the application, the position-based mean value characteristic diagram of the plurality of key node current time-frequency semantic characteristic diagrams is further calculated to serve as a sequence distribution cluster center. By calculating the current time-frequency semantic feature graphs of all key nodes according to the position average value, the features of different nodes can be aggregated to a central point to obtain a distribution cluster center representing the overall feature, and the distribution cluster center can reflect the general characteristics and the behavior patterns of the whole power transmission and distribution line.
Specifically, the semantic association calculating unit 342 is configured to calculate the semantic association degree between each of the plurality of key node current time-frequency semantic feature graphs and the center of the sequence distribution cluster to obtain a sequence of the semantic association degree. It should be understood that by comparing the feature map of each key node with the feature map of the sequence distribution cluster center according to the position average value, the association degree and the implicit interaction relation between the current time-frequency semantic features of each key node can be automatically learned and captured, so that the similarity degree between the feature map of each node and the overall feature center can be measured, the deviation between each node and the normal general mode can be conveniently identified, and therefore possible abnormality or fault can be found, and the key nodes for judging the abnormality or fault can be conveniently used subsequently.
In a specific example of the present application, the semantic association calculating unit includes: the multi-dimensional global pooling calculation subunit is used for carrying out multi-dimensional global pooling treatment on the key node current time-frequency semantic feature map so as to obtain a key node current time-frequency semantic feature multi-scale pooling representation vector; the central semantic association information representation subunit is used for calculating the semantic association degree between the multi-scale pooled representation vector of the key node current time-frequency semantic features and the center of the sequence distribution cluster.
Specifically, the multidimensional global pooling computation subunit is configured to: carrying out global pooling processing based on maximum values, global pooling processing based on random values and global pooling processing based on average values on all feature matrixes along the channel dimension in the key node current time-frequency semantic feature graph to obtain global maximum value pooling feature vectors of key node current time-frequency semantic features, global average value pooling feature vectors of key node current time-frequency semantic features and global random value pooling feature vectors of key node current time-frequency semantic features; and calculating a position weighted sum among the global maximum value pooling feature vector of the key node current time-frequency semantic features, the global average pooling feature vector of the key node current time-frequency semantic features and the global random value pooling feature vector of the key node current time-frequency semantic features to obtain the multi-scale pooling representation vector of the key node current time-frequency semantic features.
More specifically, the central semantic association information represents a subunit for: calculating the global average value of each feature matrix of the sequence distribution cluster center along the channel dimension to obtain a sequence distribution cluster center representation vector; calculating the matrix product between the multi-scale pooled representation vector of the key node current time-frequency semantic features and the weight coefficient matrix to obtain a key node current time-frequency semantic weighted feature vector; the time-frequency semantic weighted feature vector of the key node current and the bias vector are added according to positions to obtain a time-frequency semantic weighted bias adjustment feature vector of the key node current; inputting the key node current time-frequency semantic weighted bias adjustment feature vectorPerforming activation processing on the function to obtain a key node current time-frequency semantic activation feature vector; and calculating the product of the key node current time-frequency semantic activation feature vector and the transpose vector of the sequence distribution cluster center representation vector to obtain the semantic association degree.
In summary, in the above embodiment, calculating the semantic association degree between each of the plurality of key node current time-frequency semantic feature graphs and the sequence distribution cluster center to obtain the sequence of the semantic association degree includes: respectively calculating the semantic relevance between each key node current time-frequency semantic feature map in the plurality of key node current time-frequency semantic feature maps and the center of the sequence distribution cluster according to the following semantic relevance calculation formula to obtain a sequence of the semantic relevance; the semantic association degree calculation formula is as follows: ; wherein, Is each of the plurality of key node current time-frequency semantic feature graphs,、AndRespectively carrying out global average value pooling treatment, maximum value pooling treatment and random value pooling treatment on each feature matrix of the feature graph along the channel dimension,、AndAre all the preset trainable weight values,A multi-scale pooling representation vector of the time-frequency semantic features of the key node current corresponding to each time-frequency semantic feature map of the key node current,Represent the firstThe current time-frequency semantic features of the key nodes are multi-scale pooled to represent vectors,A transpose vector representing a vector for the center of the sequence distribution cluster,Represent the firstA matrix of the weight coefficients is provided,Is the firstThe number of offset vectors is chosen such that,Representation ofThe function of the function is that,Is the first in the sequence of semantic relatednessSemantic association.
In a preferred embodiment, calculating the semantic association between each of the plurality of key node current time-frequency semantic feature graphs and the center of the sequence distribution cluster to obtain the sequence of semantic associations includes: expanding each key node current time-frequency semantic feature map in the plurality of key node current time-frequency semantic feature maps into a plurality of key node current time-frequency semantic feature vectors; cascading the plurality of key node current time-frequency semantic feature vectors into a key node current time-frequency joint semantic feature vector; multiplying the key node current time-frequency joint semantic feature vector with the length of the key node current time-frequency joint semantic feature vector and the square root point of the length of the key node current time-frequency joint semantic feature vector to obtain a key node current time-frequency joint semantic full-width vector and a key node current time-frequency joint semantic half-width vector; performing point subtraction on the critical node current time-frequency joint semantic full-width vector and a norm of the critical node current time-frequency joint semantic feature vector, and calculating square roots of absolute values of all positions of a point subtraction result vector to obtain a critical node current time-frequency joint semantic full-width semantic change vector; performing point subtraction on the key node current time-frequency joint semantic half-amplitude vector and the two norms of the key node current time-frequency joint semantic feature vector, and calculating the square root of the absolute value of each position of a point subtraction result vector to obtain a key node current time-frequency joint semantic half-amplitude semantic change vector; calculating the base 2 logarithmic value of each characteristic value of the key node current time-frequency joint semantic full-width semantic change vector and the key node current time-frequency joint semantic half-width semantic change vector respectively to obtain a key node current time-frequency joint semantic full-width semantic change information vector and a key node current time-frequency joint semantic half-width semantic change information vector; calculating the weighted sum of the key node current time-frequency joint semantic full-width semantic change information vector and the key node current time-frequency joint semantic half-width semantic change information vector by taking the balance super parameters as weights to obtain an optimized key node current time-frequency joint semantic feature vector; splitting the optimized key node current time-frequency joint semantic feature vector into a plurality of optimized key node current time-frequency semantic feature vectors according to cascade connection of the plurality of key node current time-frequency semantic feature vectors; restoring the optimized time-frequency semantic feature vectors of the plurality of key node currents into the optimized time-frequency semantic feature graphs of the plurality of key node currents according to the expansion of the time-frequency semantic feature graphs of the plurality of key node currents; and respectively calculating the semantic association degree between each optimized key node current time-frequency semantic feature map in the optimized plurality of key node current time-frequency semantic feature maps and the sequence distribution cluster center to obtain a sequence of the semantic association degree.
In the above-mentioned optimized embodiment, the present application is directed to the multiple key node current time-frequency semantic feature graphs as feature sets, where the change semantics of the feature values of the multiple key node current time-frequency semantic feature graphs are used as change semantics of units, in order to dynamically aggregate the whole semantic set formed by different change semantics of the multiple key node current time-frequency semantic feature graphs without neglecting individual semantic change information, the aggregate expressions of the individual features of the multiple key node current time-frequency semantic feature graphs and the aggregate dimensions of the multiple key node current time-frequency semantic feature graphs are used as feature full-amplitude and half-amplitude, and the low rank negative correlations of different dimensions of the whole semantics of the feature sets of the multiple key node current time-frequency semantic feature graphs are used as phases and scaled, so as to dynamically adjust the change relation of the semantic content of the multiple key node current time-frequency semantic feature graphs, thereby improving the consistency of the semantic information expression aggregation of the whole semantic feature sets of the multiple key node current time-frequency semantic feature graphs and the correlation between each key node current time-frequency feature graph and the sequence distribution center. Therefore, the fault position of the oil field power transmission and distribution line can be accurately and automatically identified and positioned, and more intelligent powerful support is provided for safe and stable operation of the oil field power transmission and distribution line.
It should be noted that, in other specific examples of the present application, the semantic association degree between the plurality of key node current time-frequency semantic feature graphs and the distribution cluster center of the plurality of key node current time-frequency semantic feature graphs may be calculated in other manners based on the plurality of key node current time-frequency semantic feature graphs to obtain a sequence of semantic association degrees, for example: inputting the current time-frequency semantic feature graphs of the plurality of key nodes; for the current time-frequency semantic feature map of each key node, a clustering algorithm (such as K-means clustering) is used to calculate the distribution cluster center of the feature map. These center points represent the cluster center of each feature map in the feature space; and calculating the semantic association degree between each pair of key node current time-frequency semantic feature graphs for the center of the distribution cluster between the key node current time-frequency semantic feature graphs. One common approach is to calculate a similarity or distance measure between them, such as euclidean distance, cosine similarity, etc.; and combining the semantic association degree between each pair of the calculated key node current time-frequency semantic feature graphs into a sequence to obtain the sequence of the semantic association degree.
In particular, the fault node determination module 350 is configured to determine a fault node based on the sequence of semantic associations. That is, in a specific example of the present application, a key node corresponding to the minimum semantic association in the sequence of semantic associations is used as a fault node. This is because the lower the association between a node and the cluster center, the greater the difference between its characteristics and normal mode, and thus the closer the failure point is likely. Therefore, the minimum semantic association degree is larger in deviation between the current time-frequency semantic feature of the key node and the general normal mode semantic, and the key node corresponding to the minimum semantic association degree in the semantic association degree sequence is used as a fault node, so that the fault position of the oil field power transmission and distribution line can be accurately identified and positioned, and more intelligent powerful support is provided for safe and stable operation of the oil field power transmission and distribution line.
In particular, in one embodiment of the present application, the intelligent fault locating system for a power transmission and distribution line further includes: the training module is used for updating the counter-propagation parameters of the model based on gradient descent; wherein, training module includes: the training data acquisition module is used for acquiring a plurality of training key node current detection signals and true semantic association degrees; the training key node current detection time-frequency chart conversion module is used for carrying out wavelet conversion on each training key node current detection signal in the plurality of training key node current detection signals so as to obtain a plurality of training key node current detection time-frequency charts; the current time-frequency characteristic extraction module is used for enabling each training key node current detection time-frequency chart in the plurality of training key node current detection time-frequency charts to respectively pass through a current time-frequency characteristic extractor based on a cavity convolutional neural network model so as to obtain a plurality of training key node current time-frequency semantic characteristic charts; the training distribution cluster center semantic association calculation module is used for calculating the semantic association degree between the training distribution cluster center semantic association calculation module and the distribution cluster centers of the training key node current time-frequency semantic feature graphs based on the training key node current time-frequency semantic feature graphs so as to obtain a sequence of prediction semantic association degree; and the back propagation parameter updating module is used for updating the back propagation parameter based on gradient descent for the model based on a difference loss function between the real semantic association degree and the prediction semantic association degree, wherein in the training process, each group of training key node current time-frequency semantic feature map and training sequence distribution cluster center are optimized based on the prediction semantic association degree when each iteration of each group of training key node current time-frequency semantic feature map and training sequence distribution cluster center is performed.
Here, for the image semantic feature spatial distribution difference caused by the source image semantic difference of the plurality of training key node current time-frequency semantic feature graphs based on each training key node current detection time-frequency graph, when the per-position mean value calculation of each feature graph is performed, the problem of insufficient image semantic information spatial expression aggregation may exist, so that the training sequence distribution cluster center has a posterior-prior feature representation causal association deletion relative to each training key node current time-frequency semantic feature graph in the plurality of training key node current time-frequency semantic feature graphs, and therefore when the semantic association degree between the training key node current time-frequency semantic feature graphs is calculated, mapping association deletion mapped to a common semantic association domain exists, which may affect the calculation accuracy of the semantic association degree.
Therefore, in the training process, when the model is updated with the backward propagation parameters based on gradient descent for each iteration of each group of the training key node current time-frequency semantic feature map and the training sequence distribution cluster center, namely based on the difference loss function between the real semantic association degree and the predicted semantic association degree, the method optimizes the group of the training key node current time-frequency semantic feature map and the training sequence distribution cluster center based on the predicted semantic association degree, and comprises the following steps: carrying out probability activation function based on probability, such as softmax function, on the training key node current time-frequency semantic feature map and each feature value of the training sequence distribution cluster center so as to obtain each probability feature value; determining a cognitive symbol value based on a comparison of the respective probabilistic eigenvalue and the predicted semantic association, wherein the cognitive symbol value is equal to one, zero and negative one in response to the respective probabilistic eigenvalue being greater than, equal to, and less than the predicted semantic association, respectively; multiplying each probabilistic characteristic value by the cognitive symbol value and a first weight serving as a super parameter, multiplying each probabilistic characteristic value by a characteristic average value of each probabilistic characteristic value and a second weight serving as a super parameter, and carrying out differential calculation on the two products and taking an absolute value to obtain an optimized characteristic value.
Another formulated expression of the above optimization procedure is as follows: ; wherein, Is the individual probabilistic eigenvalue of each group of the key node current time-frequency semantic eigenvector graph and the center of the sequence distribution cluster,Is the optimized characteristic value of each group of the key node current time-frequency semantic characteristic diagram and the center of the sequence distribution cluster,Is the degree of correlation of the predicted semantics,AndA first weight as a superparameter and a second weight as a superparameter,Is the value of the cognitive symbol in question,Is the feature mean of the individual probabilistic feature values.
The method comprises the steps of comparing the probability amplitude of the characteristic value of each group of the training key node current time-frequency semantic characteristic diagram and the training sequence distribution cluster center with the prediction semantic association degree to obtain semantic association degree cognition phase transformation response of the training key node current time-frequency semantic characteristic diagram and the training sequence distribution cluster center, and carrying out feature distribution sequence invariance transformation based on differential distribution expansion on the phase-shifting response of the characteristic value of the training key node current time-frequency semantic characteristic diagram and the training sequence distribution cluster center relative to the semantic association degree representation of the whole characteristic, so as to realize causal constraint of posterior-prior characteristic distribution representation of the training key node current time-frequency semantic characteristic diagram and the training sequence distribution cluster center, and compensate mapping association loss when the training key node current time-frequency semantic characteristic diagram and the training sequence distribution cluster center are mapped to a common semantic association domain, thereby improving the calculation accuracy of the semantic association degree.
As described above, the fault intelligent localization system 300 of the power transmission and distribution line according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server or the like having a fault intelligent localization algorithm of the power transmission and distribution line. In one possible implementation, the fault intelligent localization system 300 of the power transmission and distribution line according to the embodiment of the present application may be integrated into the wireless terminal as one software module and/or hardware module. For example, the fault intelligent locator system 300 of the power transmission and distribution line may be a software module in the operating system of the wireless terminal or may be an application developed for the wireless terminal; of course, the intelligent fault location system 300 for a power transmission and distribution line can also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the fault intelligent positioning system 300 of the power transmission and distribution line and the wireless terminal may be separate devices, and the fault intelligent positioning system 300 of the power transmission and distribution line may be connected to the wireless terminal through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Further, an intelligent fault positioning method for the power transmission and distribution line is also provided.
Fig. 4 is a flowchart of a fault intelligent positioning method for a power transmission and distribution line according to an embodiment of the present application. As shown in fig. 4, the fault intelligent positioning method for the power transmission and distribution line according to the embodiment of the application includes the following steps: s1, acquiring current detection signals acquired by circuit transformers arranged on a plurality of key nodes of a power transmission and distribution line to obtain a plurality of key node current detection signals; s2, performing wavelet transformation on each key node current detection signal in the plurality of key node current detection signals to obtain a plurality of key node current detection time-frequency diagrams; s3, extracting current time-frequency characteristics of the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic characteristic graphs; s4, calculating the semantic association degree between the current time-frequency semantic feature graphs of the plurality of key nodes and the distribution cluster center of the current time-frequency semantic feature graphs of the plurality of key nodes based on the current time-frequency semantic feature graphs of the plurality of key nodes to obtain a sequence of the semantic association degree; s5, determining a fault node based on the sequence of the semantic association degree.
In summary, the fault intelligent positioning method for the power transmission and distribution line according to the embodiment of the application is explained, wherein the circuit transformers deployed on a plurality of key nodes of the power transmission and distribution line are used for monitoring and collecting current detection signals in real time, and the data processing and signal analysis algorithm based on artificial intelligence and deep learning technology is introduced into the rear end to carry out the collaboration and association analysis of the current detection signals of different key nodes, so that the time-frequency semantic features of the current detection signals of all the key nodes are learned and captured, and the correlation and interaction information between the current time-frequency semantics of different key nodes are utilized to identify and detect the fault nodes. Therefore, the fault position of the oil field power transmission and distribution line can be automatically identified and positioned, and more intelligent powerful support is provided for the safe and stable operation of the oil field power transmission and distribution line.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (4)
1. An intelligent fault positioning system for a power transmission and distribution line, comprising:
the key node current detection signal acquisition module is used for acquiring current detection signals acquired by circuit transformers of a plurality of key nodes deployed on the power transmission and distribution line to obtain a plurality of key node current detection signals;
The key node current detection time-frequency diagram conversion module is used for carrying out wavelet conversion on each key node current detection signal in the plurality of key node current detection signals so as to obtain a plurality of key node current detection time-frequency diagrams;
the current time-frequency characteristic extraction module is used for extracting current time-frequency characteristics of the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic characteristic graphs;
The distribution cluster center semantic association calculation module is used for calculating the semantic association degree between the distribution cluster centers of the plurality of key node current time-frequency semantic feature graphs and the plurality of key node current time-frequency semantic feature graphs based on the plurality of key node current time-frequency semantic feature graphs so as to obtain a sequence of the semantic association degree;
The fault node judging module is used for determining a fault node based on the sequence of the semantic association degree;
the distribution cluster center semantic association calculation module comprises:
The sequence distribution cluster center calculating unit is used for calculating the position-based mean value characteristic map of the plurality of key node current time-frequency semantic characteristic maps to serve as a sequence distribution cluster center;
The semantic association calculation unit is used for calculating the semantic association degree between each key node current time-frequency semantic feature graph in the plurality of key node current time-frequency semantic feature graphs and the sequence distribution cluster center so as to obtain a sequence of the semantic association degree;
Wherein the semantic association calculating unit includes:
The multi-dimensional global pooling calculation subunit is used for carrying out multi-dimensional global pooling treatment on the key node current time-frequency semantic feature map so as to obtain a key node current time-frequency semantic feature multi-scale pooling representation vector;
the central semantic association information representation subunit is used for calculating the semantic association degree between the multi-scale pooled representation vector of the key node current time-frequency semantic features and the center of the sequence distribution cluster;
wherein the multi-dimensional global pooling computation subunit is configured to:
Carrying out global pooling processing based on maximum values, global pooling processing based on random values and global pooling processing based on average values on all feature matrixes along the channel dimension in the key node current time-frequency semantic feature graph to obtain global maximum value pooling feature vectors of key node current time-frequency semantic features, global average value pooling feature vectors of key node current time-frequency semantic features and global random value pooling feature vectors of key node current time-frequency semantic features;
calculating a position-weighted sum among the global maximum pooling feature vector of the key node current time-frequency semantic features, the global average pooling feature vector of the key node current time-frequency semantic features and the global random value pooling feature vector of the key node current time-frequency semantic features to obtain a multi-scale pooling representation vector of the key node current time-frequency semantic features;
wherein the central semantic association information represents a subunit for:
Calculating the global average value of each feature matrix of the sequence distribution cluster center along the channel dimension to obtain a sequence distribution cluster center representation vector;
Calculating the matrix product between the multi-scale pooled representation vector of the key node current time-frequency semantic features and the weight coefficient matrix to obtain a key node current time-frequency semantic weighted feature vector;
the time-frequency semantic weighted feature vector of the key node current and the bias vector are added according to positions to obtain a time-frequency semantic weighted bias adjustment feature vector of the key node current;
inputting the key node current time-frequency semantic weighted bias adjustment feature vector Performing activation processing on the function to obtain a key node current time-frequency semantic activation feature vector;
calculating the product between the key node current time-frequency semantic activation feature vector and the transpose vector of the sequence distribution cluster center representation vector to obtain the semantic association degree;
Wherein, still include: the training module is used for updating the counter-propagation parameters of the model based on gradient descent;
Wherein, training module includes:
The training data acquisition module is used for acquiring a plurality of training key node current detection signals and true semantic association degrees;
The training key node current detection time-frequency chart conversion module is used for carrying out wavelet conversion on each training key node current detection signal in the plurality of training key node current detection signals so as to obtain a plurality of training key node current detection time-frequency charts;
The training current time-frequency characteristic extraction module is used for enabling each training key node current detection time-frequency chart in the plurality of training key node current detection time-frequency charts to respectively pass through a current time-frequency characteristic extractor based on a cavity convolutional neural network model so as to obtain a plurality of training key node current time-frequency semantic characteristic charts;
The training distribution cluster center semantic association calculation module is used for calculating the semantic association degree between the training distribution cluster center semantic association calculation module and the distribution cluster centers of the training key node current time-frequency semantic feature graphs based on the training key node current time-frequency semantic feature graphs so as to obtain a sequence of prediction semantic association degree;
And the back propagation parameter updating module is used for updating the back propagation parameter based on gradient descent for the model based on a difference loss function between the real semantic association degree and the prediction semantic association degree, wherein in the training process, each group of training key node current time-frequency semantic feature map and training sequence distribution cluster center are optimized based on the prediction semantic association degree when each iteration of each group of training key node current time-frequency semantic feature map and training sequence distribution cluster center is performed.
2. The intelligent fault locating system of a power transmission and distribution line according to claim 1, wherein the current time-frequency feature extraction module is configured to: and respectively passing each key node current detection time-frequency chart in the plurality of key node current detection time-frequency charts through a current time-frequency characteristic extractor based on a cavity convolutional neural network model to obtain a plurality of key node current time-frequency semantic characteristic charts.
3. The intelligent fault location system of a power transmission and distribution line according to claim 2, wherein the fault node determination module is configured to: and taking the key node corresponding to the minimum semantic association in the sequence of the semantic association as a fault node.
4. A fault intelligent positioning method for a power transmission and distribution line, using the fault intelligent positioning system for a power transmission and distribution line according to claim 1, comprising:
acquiring current detection signals acquired by circuit transformers arranged at a plurality of key nodes of a power transmission and distribution line to obtain a plurality of key node current detection signals;
Performing wavelet transformation on each key node current detection signal in the plurality of key node current detection signals to obtain a plurality of key node current detection time-frequency diagrams;
Carrying out current time-frequency characteristic extraction on the plurality of key node current detection time-frequency graphs to obtain a plurality of key node current time-frequency semantic feature graphs;
calculating the semantic association degree between the current time-frequency semantic feature graphs of the plurality of key nodes and the distribution cluster center of the current time-frequency semantic feature graphs of the plurality of key nodes based on the current time-frequency semantic feature graphs of the plurality of key nodes to obtain a sequence of the semantic association degree;
determining a fault node based on the sequence of semantic relatedness;
Based on the plurality of key node current time-frequency semantic feature graphs, calculating the semantic association degree between the key node current time-frequency semantic feature graphs and the distribution cluster center of the plurality of key node current time-frequency semantic feature graphs to obtain a sequence of the semantic association degree, wherein the sequence comprises the following steps:
Calculating a position-based mean value characteristic map of the current time-frequency semantic characteristic maps of the plurality of key nodes as a sequence distribution cluster center;
and respectively calculating the semantic association degree between each key node current time-frequency semantic feature map in the plurality of key node current time-frequency semantic feature maps and the center of the sequence distribution cluster to obtain a sequence of the semantic association degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410994275.5A CN118518984B (en) | 2024-07-24 | 2024-07-24 | Intelligent fault positioning system and method for power transmission and distribution line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410994275.5A CN118518984B (en) | 2024-07-24 | 2024-07-24 | Intelligent fault positioning system and method for power transmission and distribution line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118518984A CN118518984A (en) | 2024-08-20 |
| CN118518984B true CN118518984B (en) | 2024-09-27 |
Family
ID=92281505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410994275.5A Active CN118518984B (en) | 2024-07-24 | 2024-07-24 | Intelligent fault positioning system and method for power transmission and distribution line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118518984B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118312923A (en) * | 2024-06-05 | 2024-07-09 | 珠海绎至科技有限公司 | Intelligent park-oriented equipment measurement method and computer equipment |
| CN118362831A (en) * | 2024-04-22 | 2024-07-19 | 上海鑫智柔电线电缆有限公司 | Cable fault intelligent positioning system and method based on big data |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9158760B2 (en) * | 2012-12-21 | 2015-10-13 | The Nielsen Company (Us), Llc | Audio decoding with supplemental semantic audio recognition and report generation |
| CN109697285B (en) * | 2018-12-13 | 2022-06-21 | 中南大学 | Hierarchical BilSt Chinese electronic medical record disease coding and labeling method for enhancing semantic representation |
| CN114429524B (en) * | 2022-04-07 | 2022-09-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Construction method and detection method of three-dimensional target detection model under monocular vision |
| CN115235612B (en) * | 2022-08-09 | 2023-04-07 | 爱尔达电气有限公司 | Intelligent fault diagnosis system and method for servo motor |
| CN117110791A (en) * | 2023-09-18 | 2023-11-24 | 湖州晓建智能科技有限公司 | Intelligent transmission and distribution network fault early warning management system and method |
| CN117269644A (en) * | 2023-09-18 | 2023-12-22 | 德清思正电力设备有限公司 | Line fault monitoring system and method for current transformer |
| CN117907735A (en) * | 2023-12-08 | 2024-04-19 | 国网信息通信产业集团有限公司北京分公司 | Online intelligent monitoring system and method for power transmission line |
| CN118070786B (en) * | 2024-02-27 | 2024-10-15 | 中国医学科学院医学信息研究所 | Theme monitoring method and device, electronic equipment and readable storage medium |
| CN118154169A (en) * | 2024-04-23 | 2024-06-07 | 漳州市鸿创电子科技有限公司 | Intelligent street lamp fault quick response system and method |
| CN118381980B (en) * | 2024-06-21 | 2024-08-27 | 珠海安士佳电子有限公司 | Intelligent video editing and abstract generating method and device based on semantic segmentation |
-
2024
- 2024-07-24 CN CN202410994275.5A patent/CN118518984B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118362831A (en) * | 2024-04-22 | 2024-07-19 | 上海鑫智柔电线电缆有限公司 | Cable fault intelligent positioning system and method based on big data |
| CN118312923A (en) * | 2024-06-05 | 2024-07-09 | 珠海绎至科技有限公司 | Intelligent park-oriented equipment measurement method and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118518984A (en) | 2024-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yu et al. | Telemetry data-based spacecraft anomaly detection with spatial–temporal generative adversarial networks | |
| CN112069398A (en) | Information pushing method and device based on graph network | |
| Shomorony et al. | Sampling large data on graphs | |
| JP2019061565A (en) | Abnormality diagnostic method and abnormality diagnostic device | |
| CN110082579A (en) | A kind of area's Intelligent power-stealing prevention monitoring method, system, equipment and medium | |
| CN108435819B (en) | Energy consumption abnormity detection method for aluminum profile extruder | |
| CN114169091B (en) | Method for establishing prediction model of residual life of engineering machinery part and prediction method | |
| Lin et al. | A new regularized recursive dynamic factor analysis with variable forgetting factor and subspace dimension for wireless sensor networks with missing data | |
| Harish et al. | Fault detection and classification for wide area backup protection of power transmission lines using weighted extreme learning machine | |
| Huang et al. | False phasor data detection under time synchronization attacks: A neural network approach | |
| CN117269644A (en) | Line fault monitoring system and method for current transformer | |
| Mestav et al. | Universal data anomaly detection via inverse generative adversary network | |
| CN117272196A (en) | Industrial time sequence data anomaly detection method based on time-space diagram attention network | |
| Li et al. | A fault diagnosis method for rotating machinery with semi-supervised graph convolutional network and images converted from vibration signals | |
| CN118518984B (en) | Intelligent fault positioning system and method for power transmission and distribution line | |
| CN116292130A (en) | Wind driven generator state monitoring system and method based on cooperative analysis | |
| CN111162945A (en) | Method, device, equipment and storage medium for determining alarm association relationship | |
| CN113824707A (en) | Website performance dial testing measurement method and device based on knowledge graph | |
| Tang et al. | Soft fault diagnosis of analog circuits based on classification of GAF_RP images with ResNet | |
| CN115762558B (en) | Performance detection system and method for escalator production | |
| Valabhoju et al. | Optimized ensemble of regression tree-based location of evolving faults in dual-circuit line | |
| CN117388893A (en) | Multi-device positioning system based on GPS | |
| CN114997216B (en) | Bearing fault identification method based on tensor multi-mode feature high-order matching | |
| Li et al. | Orthogonal Wavelet Transform‐Based Gaussian Mixture Model for Bearing Fault Diagnosis | |
| CN117056842A (en) | Method, device, equipment, medium and product for constructing equipment abnormality monitoring model |
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 |