CN116973668A - Power grid line fault diagnosis method and device, electronic equipment and storage medium - Google Patents
Power grid line fault diagnosis method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116973668A CN116973668A CN202310962247.0A CN202310962247A CN116973668A CN 116973668 A CN116973668 A CN 116973668A CN 202310962247 A CN202310962247 A CN 202310962247A CN 116973668 A CN116973668 A CN 116973668A
- Authority
- CN
- China
- Prior art keywords
- fault
- power grid
- grid line
- time sequence
- operation data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003745 diagnosis Methods 0.000 title claims abstract description 36
- 239000011159 matrix material Substances 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 34
- 230000007246 mechanism Effects 0.000 claims description 25
- 238000012360 testing method Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 8
- 230000000737 periodic effect Effects 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 5
- 238000013024 troubleshooting Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/58—Testing of lines, cables or conductors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power grid line fault diagnosis method, a device, electronic equipment and a storage medium, and relates to the technical field of power grids. The method comprises the following steps: after determining that a power grid line fails, acquiring multidimensional time sequence operation data of the power grid line; extracting fault-associated timing characteristics related to grid faults from the multi-dimensional timing operation data; and determining the fault type of the power grid fault according to the fault associated time sequence characteristics. The scheme of the invention realizes the rapid determination of the fault type of the power grid line by utilizing the time sequence operation data after the power grid is in fault, and compared with the gradual troubleshooting of the faults by technicians along the power grid line, the efficiency of the fault diagnosis of the power grid line can be effectively improved.
Description
Technical Field
The present invention relates to the field of power grid technologies, and in particular, to a method and apparatus for diagnosing a power grid line fault, an electronic device, and a storage medium.
Background
Because the rural power grid is limited by the topography and is mostly a long power transmission line distributed in a tree shape, the maintenance difficulty of the rural power grid is increased, and once faults occur, the faults are usually gradually checked along the power grid line by technicians, so that the efficiency of fault diagnosis of the power grid line is lower. Therefore, a method for quickly diagnosing the power grid line fault is needed.
Disclosure of Invention
The invention provides a power grid line fault diagnosis method, a power grid line fault diagnosis device, electronic equipment and a storage medium.
According to an aspect of the present invention, there is provided a power grid line fault diagnosis method, including:
after determining that a power grid line fails, acquiring multidimensional time sequence operation data of the power grid line;
extracting fault-associated timing characteristics related to grid faults from the multi-dimensional timing operation data;
and determining the fault type of the power grid fault according to the fault associated time sequence characteristics.
Optionally, extracting fault-related timing characteristics related to the grid fault from the multi-dimensional timing operation data includes:
representing the multidimensional time sequence operation data as a polynomial on time based on an adjacent matrix and a characteristic learning matrix corresponding to the power grid line;
encoding the polynomial in terms of time based on an encoder module with an attention mechanism in a pre-trained fault prediction model;
based on a graph neural network in a pre-trained fault prediction model, extracting characteristics of a coding result to obtain fault correlation time sequence characteristics related to power grid faults; the fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur.
Optionally, determining, according to the fault-associated timing characteristic, a fault type to which the grid fault belongs, including:
decoding the fault-associated timing feature based on a decoder module with an attention mechanism in a pre-trained fault prediction model;
and determining the type of the power grid fault based on the decoding result and a prediction matrix in a pre-trained fault prediction model.
Optionally, the process of training the fault prediction model includes:
acquiring historical time sequence operation data of a power grid line, and segmenting according to a preset time step to obtain a plurality of operation data fragments;
adding a time tag for each operation data segment according to the periodic performance of the time sequence operation data;
representing each piece of operational data as a polynomial in time;
constructing a training set and a testing set based on the operation data segments; wherein the training set and the testing set comprise polynomial operation data fragments;
constructing a network model comprising an encoder module with an attention mechanism, a graph neural network, a decoder module with an attention mechanism and a prediction matrix;
and training and testing the network model by using the training set and the testing set to obtain the fault prediction model.
Optionally, the adjacency matrix is determined according to connectivity of nodes of the grid line; the nodes of the power grid line are transfer stations or telegraph poles of the power grid line.
Optionally, the multi-dimensional time series operation data includes current data, voltage data, and phase angle data.
According to another aspect of the present invention, there is provided a power grid line fault diagnosis apparatus including:
the data acquisition module is used for acquiring multidimensional time sequence operation data of the power grid line after determining that the power grid line fails;
the feature extraction module is used for extracting fault-associated time sequence features related to power grid faults from the multidimensional time sequence operation data;
and the prediction module is used for determining the fault type of the power grid fault according to the fault associated time sequence characteristics.
Optionally, the feature extraction module is further configured to:
representing the multidimensional time sequence operation data as a polynomial on time based on an adjacent matrix and a characteristic learning matrix corresponding to the power grid line;
encoding the polynomial in terms of time based on an encoder module with an attention mechanism in a pre-trained fault prediction model;
based on a graph neural network in a pre-trained fault prediction model, extracting characteristics of a coding result to obtain fault correlation time sequence characteristics related to power grid faults; the fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur.
Optionally, the prediction module is further configured to:
decoding the fault-associated timing feature based on a decoder module with an attention mechanism in a pre-trained fault prediction model;
and determining the type of the power grid fault based on the decoding result and a prediction matrix in a pre-trained fault prediction model.
Optionally, the method further comprises a model training module for:
acquiring historical time sequence operation data of a power grid line, and segmenting according to a preset time step to obtain a plurality of operation data fragments;
adding a time tag for each operation data segment according to the periodic performance of the time sequence operation data;
representing each piece of operational data as a polynomial in time;
constructing a training set and a testing set based on the operation data segments; wherein the training set and the testing set comprise polynomial operation data fragments;
constructing a network model comprising an encoder module with an attention mechanism, a graph neural network, a decoder module with an attention mechanism and a prediction matrix;
and training and testing the network model by using the training set and the testing set to obtain the fault prediction model.
Optionally, the adjacency matrix is determined according to connectivity of nodes of the grid line; the nodes of the power grid line are transfer stations or telegraph poles of the power grid line.
Optionally, the multi-dimensional time series operation data includes current data, voltage data, and phase angle data.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the grid line fault diagnosis method according to the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the grid line fault diagnosis method according to the embodiment of the present invention when executed.
According to the technical scheme, the time sequence operation data after the power grid faults are utilized, the fault type of the power grid line is rapidly determined, and compared with the case that a technician checks the faults step by step along the power grid line, the power grid line fault diagnosis efficiency can be effectively improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a power grid line fault diagnosis method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a power grid line fault diagnosis method according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a power grid line fault diagnosis method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a power grid line fault diagnosis device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing the power grid line fault diagnosis method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Fig. 1 is a flowchart of a power grid line fault diagnosis method according to an embodiment of the present invention, where the present embodiment may be applicable to a scenario of determining a fault type in a power grid line, and the method may be performed by a power grid line fault diagnosis device, which may be implemented in the form of hardware and/or software, and the power grid line fault diagnosis device may be configured in an electronic device.
As shown in fig. 1, the power grid line fault diagnosis method includes:
s101, after determining that a power grid line fails, acquiring multidimensional time sequence operation data of the power grid line.
S102, extracting fault correlation time sequence characteristics related to power grid faults from the multidimensional time sequence operation data.
S103, determining the fault type of the power grid fault according to the fault associated time sequence characteristics.
In this embodiment, the grid line is a generic term for facilities/equipment that link power generation and power usage. The electric energy distributor mainly comprises a power transmission line, a power substation, a power distribution station and a power distribution line which are connected into a network. Sometimes, the power grid line fails due to external environmental influences or factors of the equipment itself constituting the power grid line, so that normal power transmission cannot be performed. At this time, in order to ensure normal power supply, it is necessary to quickly determine what kind of fault occurs in the power grid line, and then to perform targeted maintenance. In the prior art, after a power grid line fails, a worker usually adopts professional equipment to check and determine the power grid line step by step, and the failure type of the power grid line is difficult to quickly determine in the mode. Based on the above, in order to improve the efficiency of finding the fault type of the power grid line, the invention provides a method for rapidly determining the fault of the power grid line by utilizing the multidimensional operation time sequence data after the power grid line is in fault. Therefore, after determining that the power grid line fails, the multi-dimensional time sequence operation data of the power grid line is acquired, and a specific acquisition mode is not specifically limited herein. In the present invention, the multi-dimensional time series operation data includes current data, voltage data, and phase angle data.
After the multidimensional operation time sequence data after the power grid line is failed is obtained, the multidimensional operation time sequence data can be subjected to feature extraction so as to obtain the failure correlation time sequence features related to the power grid failure from the multidimensional operation time sequence data; the fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur. In the embodiment of the invention, the feature extraction can be performed by using a pre-trained neural network, or can be performed by using other modes, which is not particularly limited herein.
Further, when different faults occur to the power grid line, the extracted fault associated time sequence features are also different. In this embodiment, after obtaining the fault-related timing characteristic, the fault type to which the grid fault belongs may be determined directly according to the fault-related timing characteristic. In an optional implementation manner, a mapping table of mapping relations between different power grid faults and fault association time sequence features can be constructed in advance, and then after the fault association mapping relation is obtained, the fault type of the power grid fault can be rapidly determined by inquiring the mapping table. In addition, a fault prediction model can be used in advance, and the fault type of the power grid fault can be determined based on the fault prediction model and the acquired fault associated time sequence characteristics.
The scheme of the invention realizes the rapid determination of the fault type of the power grid line by utilizing the time sequence operation data after the power grid is in fault, and compared with the gradual troubleshooting of the faults by technicians along the power grid line, the efficiency of the fault diagnosis of the power grid line can be effectively improved.
Example two
Fig. 2 is a flowchart of a power grid line fault diagnosis method according to an embodiment of the present invention. In the embodiment, a pre-trained fault prediction model is utilized to perform fault diagnosis on the power grid line. Referring to fig. 2, the method flow includes the steps of:
s201, after determining that a power grid line fails, acquiring multidimensional time sequence operation data of the power grid line.
In this embodiment, the grid line is a generic term for facilities/equipment that link power generation and power usage. The electric energy distributor mainly comprises a power transmission line, a power substation, a power distribution station and a power distribution line which are connected into a network. Sometimes, the power grid line fails due to external environmental influences or factors of the equipment itself constituting the power grid line, so that normal power transmission cannot be performed. At this time, in order to ensure normal power supply, it is necessary to quickly determine what kind of fault occurs in the power grid line, and then to perform targeted maintenance. In the prior art, after a power grid line fails, a worker usually adopts professional equipment to check and determine the power grid line step by step, and the failure type of the power grid line is difficult to quickly determine in the mode. Based on the above, in order to improve the efficiency of finding the fault type of the power grid line, the invention provides a method for rapidly determining the fault of the power grid line by utilizing the multidimensional operation time sequence data after the power grid line is in fault. Therefore, after determining that the power grid line fails, the multi-dimensional time sequence operation data of the power grid line is acquired, and a specific acquisition mode is not specifically limited herein. In the present invention, the multi-dimensional time series operation data includes current data, voltage data, and phase angle data.
In the embodiment of the invention, in order to quickly extract the fault associated time sequence characteristics of the power grid line and determine the type of the fault occurring in the power grid line by utilizing the fault associated time sequence characteristics, the fault prediction model is pre-trained and comprises an encoder module with an attention mechanism, a graph neural network, a decoder module with an attention mechanism, a prediction matrix and the like. On this basis, the specific process of extracting the fault-related time sequence features related to the grid faults from the multidimensional time sequence operation data can be seen in steps S202-S204. The process of determining the fault type to which the grid fault belongs according to the fault-associated timing characteristics may refer to steps S205-S206.
And S202, representing the multidimensional time sequence operation data as a polynomial on time based on an adjacency matrix and a feature learning matrix corresponding to the power grid line.
In the embodiment of the invention, the adjacency matrix is determined according to the connectivity of the nodes of the power grid line; the nodes of the power grid line are transfer stations or telegraph poles of the power grid line. The adjacency matrix is optionally denoted as W.epsilon.R N*N . The characteristic learning matrix is used for learning the current, the voltage and the phase angle in the multidimensional time sequence operation data, and the values of all elements of the characteristic learning matrix are determined after the training of the fault prediction model is completed; the feature learning matrix may be denoted as A1. Alternatively, a matrix E with learning variables is first determined, and the matrix E is operated on by a ReLU function (activation function) and a SoftMax function (regression function) (e.g., according to the formula SoftMax (ReLU (EE) T ) Operation) to obtain an initial feature learning matrix, and continuously adjusting element values in the training process of the fault prediction model to obtain a final feature learning matrix. Based on the above, the multi-dimensional time sequence operation dataThe procedure expressed as a polynomial over time is as follows: firstly, a symmetric normalized Laplace matrix L of the adjacency matrix W is calculated, wherein +.>(I is an identity matrix and D is a degree matrix); the normalization is due to the dimension between different featuresOr the dimension units are often different, the change intervals are also in different orders of magnitude, and if normalization is not performed, certain indexes can be ignored, so that the data analysis result is influenced; adding L and A1 to obtain a result matrix which is represented by A; on the basis, multidimensional time sequence operation data +.>The polynomial in terms of time can be expressed as: />Wherein K is a preset constant. Since the polynomial coefficients are time-varying, W (t) The dynamic topological behavior is shown, so that the hidden fault characteristics in the multi-dimensional time sequence data of the power grid can be better represented, and the fault-related time sequence characteristics related to faults can be accurately found out later.
S203, encoding the polynomial related to time based on an encoder module with an attention mechanism in a pre-trained fault prediction model.
In this embodiment, after the multidimensional time sequence operation data is expressed as a polynomial related to time, the polynomial is input into an encoder module of the fault prediction model, and the encoder module firstly inputs the polynomial data into a time attention layer for operation, wherein the time attention layer can follow the design of a transducer, that is, the time attention mechanism of the invention is the time attention layer according to the design of the transducer; thus, the time sequence change rule of each variable is captured through the time attention layer; and further, the time attention layer output is subjected to coding operation, and the coding operation process can be seen in the following formula:wherein Z is (t) Is the encoding result; x is X (t) Representing the encoding matrix; w (W) k Representing a model parameter matrix; I.I F The Frobenius norm of the matrix; />Representing the results of the temporal attention layer output.
S204, extracting features of the coding result based on the graph neural network in the pre-trained fault prediction model to obtain fault correlation time sequence features related to the power grid faults.
In the embodiment of the invention, the encoder inputs the encoding result into the graph neural network in the pre-trained fault prediction model, so that the graph neural network can extract the characteristics of the encoding result and obtain the fault associated time sequence characteristics related to the power grid faults. In the model training phase, the graph neural network may learn the current, voltage, phase angle, and the like of the training data. The fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur.
S205, decoding the fault-associated timing features based on a decoder module with an attention mechanism in a pre-trained fault prediction model.
In the embodiment of the invention, after the fault associated time sequence feature is extracted, the fault associated time sequence feature is input into a decoder module with an attention mechanism (time attention layer) for decoding, and optionally, the decoder module can decode the fault associated time sequence feature by using a learnable token query data (BOS token) to obtain a decoding result.
S206, determining the type of the power grid fault based on the decoding result and a prediction matrix in a pre-training-based fault prediction model.
In this case, the direct decoding result may be multiplied by a prediction matrix in the pre-trained fault prediction model, and the type of the grid fault is determined according to the product result.
In the embodiment of the invention, based on the attention-enhanced graph neural network, fault-related time sequence characteristics related to faults in time sequence operation data can be effectively mined, and effective characteristics are provided for subsequent fault diagnosis; and by utilizing the pre-trained fault prediction model, the fault type of the power grid can be efficiently determined from the multidimensional time sequence operation data of the power grid.
Example III
Fig. 3 is a flowchart of a power grid line fault diagnosis method according to an embodiment of the present invention. The additional process of training a fault prediction model in this embodiment, see fig. 3, includes the following steps:
s301, acquiring historical time sequence operation data of a power grid line, and segmenting according to a preset time step to obtain a plurality of operation data segments.
The historical time sequence operation data comprise time sequence operation data when the power grid normally operates and time sequence operation data when the power grid fails. After the segmentation is performed according to the preset time step, the data of the segment when the power grid is normal or the data of the segment when the power grid fails can be represented by a label for each operation data segment.
S302, adding a time label to each operation data segment according to the periodic performance of the time sequence operation data.
Because the power grid operation data has a certain periodicity, in order to ensure normal training, a time tag (which can be a time stamp) is introduced, so that the operation data segment in each period can be determined, and the model training can be performed based on the operation data segment in the same period later.
S303, each piece of operation data is represented as a polynomial with respect to time.
Optionally, each piece of operational data is represented as a polynomial over time using a pre-constructed grid adjacency matrix and a feature learning matrix to be determined.
S304, constructing a training set and a testing set based on the operation data segments; wherein the training set and the test set comprise pieces of operational data in the form of polynomials.
S305, constructing a network model comprising an encoder module with an attention mechanism, a graph neural network, a decoder module with an attention mechanism and a prediction matrix.
And S306, training and testing the network model by using the training set and the testing set to obtain the fault prediction model.
Alternatively, the first 100 cycles are optimized quickly using a learning rate of 0.001, after which the learning rate is 0.0001 to smoothly converge the iterations.
In this embodiment, model parameters may be continuously adjusted according to the prediction loss during the training process, and a final feature learning matrix may be determined for use in actual prediction. By training the fault prediction model, time sequence characteristics related to faults in the power grid operation data are continuously learned, and the fault type of the power grid can be accurately determined based on the model.
Example IV
Fig. 4 is a schematic structural diagram of a power grid line fault diagnosis device according to an embodiment of the present invention, where the embodiment may be suitable for determining a fault type in a power grid line. Referring to fig. 4, the grid line fault diagnosis apparatus includes:
the data acquisition module 401 is configured to acquire multidimensional time sequence operation data of a power grid line after determining that the power grid line fails;
a feature extraction module 402, configured to extract fault-related timing features related to a grid fault from the multidimensional timing operation data;
and the prediction module 403 is configured to determine, according to the fault-associated timing characteristic, a fault type to which the grid fault belongs.
Optionally, the feature extraction module is further configured to:
representing the multidimensional time sequence operation data as a polynomial on time based on an adjacent matrix and a characteristic learning matrix corresponding to the power grid line;
encoding the polynomial in terms of time based on an encoder module with an attention mechanism in a pre-trained fault prediction model;
based on a graph neural network in a pre-trained fault prediction model, extracting characteristics of a coding result to obtain fault correlation time sequence characteristics related to power grid faults; the fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur.
Optionally, the prediction module is further configured to:
decoding the fault-associated timing feature based on a decoder module with an attention mechanism in a pre-trained fault prediction model;
and determining the type of the power grid fault based on the decoding result and a prediction matrix in a pre-trained fault prediction model.
Optionally, the method further comprises a model training module for:
acquiring historical time sequence operation data of a power grid line, and segmenting according to a preset time step to obtain a plurality of operation data fragments;
adding a time tag for each operation data segment according to the periodic performance of the time sequence operation data;
representing each piece of operational data as a polynomial in time;
constructing a training set and a testing set based on the operation data segments; wherein the training set and the testing set comprise polynomial operation data fragments;
constructing a network model comprising an encoder module with an attention mechanism, a graph neural network, a decoder module with an attention mechanism and a prediction matrix;
and training and testing the network model by using the training set and the testing set to obtain the fault prediction model.
Optionally, the adjacency matrix is determined according to connectivity of nodes of the grid line; the nodes of the power grid line are transfer stations or telegraph poles of the power grid line.
Optionally, the multi-dimensional time series operation data includes current data, voltage data, and phase angle data.
The power grid line fault diagnosis device provided by the embodiment of the invention can execute the power grid line fault diagnosis method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example five
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM12 and the RAM13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, for example, performs a grid line fault diagnosis method.
In some embodiments, the grid line fault diagnosis method may be implemented as a computer program tangibly embodied on a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM12 and/or the communication unit 19. When the computer program is loaded into RAM13 and executed by processor 11, one or more steps of the grid line fault diagnosis method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the grid line fault diagnosis method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable power grid line fault diagnosis device, such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for diagnosing a power grid line fault, comprising:
after determining that a power grid line fails, acquiring multidimensional time sequence operation data of the power grid line;
extracting fault-associated timing characteristics related to grid faults from the multi-dimensional timing operation data;
and determining the fault type of the power grid fault according to the fault associated time sequence characteristics.
2. The method of claim 1, wherein extracting fault-related timing characteristics associated with a grid fault from the multi-dimensional timing operation data comprises:
representing the multidimensional time sequence operation data as a polynomial on time based on an adjacent matrix and a characteristic learning matrix corresponding to the power grid line;
encoding the polynomial in terms of time based on an encoder module with an attention mechanism in a pre-trained fault prediction model;
based on a graph neural network in a pre-trained fault prediction model, extracting characteristics of a coding result to obtain fault correlation time sequence characteristics related to power grid faults; the fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur.
3. The method of claim 2, wherein determining the fault type to which the grid fault belongs based on the fault-related timing characteristics comprises:
decoding the fault-associated timing feature based on a decoder module with an attention mechanism in a pre-trained fault prediction model;
and determining the type of the power grid fault based on the decoding result and a prediction matrix in a pre-trained fault prediction model.
4. The method of claim 2, wherein training the fault prediction model comprises:
acquiring historical time sequence operation data of a power grid line, and segmenting according to a preset time step to obtain a plurality of operation data fragments;
adding a time tag for each operation data segment according to the periodic performance of the time sequence operation data;
representing each piece of operational data as a polynomial in time;
constructing a training set and a testing set based on the operation data segments; wherein the training set and the testing set comprise polynomial operation data fragments;
constructing a network model comprising an encoder module with an attention mechanism, a graph neural network, a decoder module with an attention mechanism and a prediction matrix;
and training and testing the network model by using the training set and the testing set to obtain the fault prediction model.
5. The method of claim 2, wherein the adjacency matrix is determined from connectivity of nodes of the grid line; the nodes of the power grid line are transfer stations or telegraph poles of the power grid line.
6. The method of any of claims 1-4, wherein the multi-dimensional time series operating data comprises current data, voltage data, and phase angle data.
7. A power grid line fault diagnosis device, characterized by comprising:
the data acquisition module is used for acquiring multidimensional time sequence operation data of the power grid line after determining that the power grid line fails;
the feature extraction module is used for extracting fault-associated time sequence features related to power grid faults from the multidimensional time sequence operation data;
and the prediction module is used for determining the fault type of the power grid fault according to the fault associated time sequence characteristics.
8. The apparatus of claim 7, wherein the feature extraction module is further to:
representing the multidimensional time sequence operation data as a polynomial on time based on an adjacent matrix and a characteristic learning matrix corresponding to the power grid line;
encoding the polynomial in terms of time based on an encoder module with an attention mechanism in a pre-trained fault prediction model;
based on a graph neural network in a pre-trained fault prediction model, extracting characteristics of a coding result to obtain fault correlation time sequence characteristics related to power grid faults; the fault association time sequence features are used for representing association relations among dimensions in the multidimensional time sequence operation data when faults occur.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310962247.0A CN116973668A (en) | 2023-08-01 | 2023-08-01 | Power grid line fault diagnosis method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310962247.0A CN116973668A (en) | 2023-08-01 | 2023-08-01 | Power grid line fault diagnosis method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116973668A true CN116973668A (en) | 2023-10-31 |
Family
ID=88476480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310962247.0A Pending CN116973668A (en) | 2023-08-01 | 2023-08-01 | Power grid line fault diagnosis method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116973668A (en) |
-
2023
- 2023-08-01 CN CN202310962247.0A patent/CN116973668A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115794578A (en) | Data management method, device, equipment and medium for power system | |
| CN113487182A (en) | Equipment health state evaluation method and device, computer equipment and medium | |
| CN116992274A (en) | Short-term wind speed prediction method and system based on improved principal component regression model | |
| CN116973668A (en) | Power grid line fault diagnosis method and device, electronic equipment and storage medium | |
| CN115687031A (en) | Method, device, equipment and medium for generating alarm description text | |
| CN115563507A (en) | Generation method, device and equipment for renewable energy power generation scene | |
| CN112581387B (en) | Intelligent operation and maintenance system, device and method for power distribution room | |
| CN113887101A (en) | Visualization method and device of network model, electronic equipment and storage medium | |
| CN116070138B (en) | State monitoring method, device, equipment and medium for pumped storage unit | |
| CN114881259A (en) | Method, device, equipment and medium for extracting typical fault of medium-voltage distribution line | |
| CN117131990A (en) | Power grid infrastructure information management method and device, electronic equipment and storage medium | |
| CN117251809A (en) | Power grid time sequence data anomaly detection method, device, equipment and storage medium | |
| CN117421377A (en) | Data processing method, device, equipment and medium for energy station | |
| CN117389828A (en) | Power supply server management method, device, system, equipment and storage medium | |
| CN116316890A (en) | Renewable energy source output scene generation method, device, equipment and medium | |
| CN116805176A (en) | Load prediction method, device and equipment for transformer area and storage medium | |
| CN117749676A (en) | Reverse analysis and vulnerability test method, device, equipment and medium of industrial control protocol | |
| CN116883198A (en) | Data quality evaluation method and device, electronic equipment and medium | |
| CN116933088A (en) | Secondary equipment fault data generation method and device, electronic equipment and medium | |
| CN117667587A (en) | Abnormality detection method and device, electronic equipment and storage medium | |
| CN117290688A (en) | Virtual loop verification method and device, electronic equipment and storage medium | |
| CN117687993A (en) | Data migration method, device, equipment and storage medium | |
| CN117455067A (en) | Electric quantity consumption prediction method and device, electronic equipment and storage medium | |
| CN116308284A (en) | Operation data detection method, device and equipment of pumped storage equipment | |
| CN116961229A (en) | Transformer substation fault positioning method and device, electronic equipment and storage medium |
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 |