CN114581261A - Fault diagnosis method, system, equipment and storage medium based on quick graph calculation - Google Patents
Fault diagnosis method, system, equipment and storage medium based on quick graph calculation Download PDFInfo
- Publication number
- CN114581261A CN114581261A CN202210048196.6A CN202210048196A CN114581261A CN 114581261 A CN114581261 A CN 114581261A CN 202210048196 A CN202210048196 A CN 202210048196A CN 114581261 A CN114581261 A CN 114581261A
- Authority
- CN
- China
- Prior art keywords
- graph
- node group
- neural network
- scale
- fault diagnosis
- 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 41
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 title claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 claims abstract description 54
- 239000011159 matrix material Substances 0.000 claims abstract description 48
- 238000011176 pooling Methods 0.000 claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 239000012212 insulator Substances 0.000 description 9
- 229910052573 porcelain Inorganic materials 0.000 description 5
- 238000000547 structure data Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 241001229889 Metis Species 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 150000002148 esters Chemical class 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Neurology (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Public Health (AREA)
- Probability & Statistics with Applications (AREA)
- Animal Behavior & Ethology (AREA)
- Databases & Information Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a fault diagnosis method, a system, equipment and a storage medium based on quick graph calculation, which comprises the following steps: clustering nodes in a spectrogram of a knowledge graph in the electric power operation and detection field to generate a node group sequence of the graph; determining a sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph, and constructing the multi-scale graph neural network; the method, the system, the equipment and the storage medium can accurately and efficiently diagnose the fault type of the power equipment in the knowledge map spectrogram in the power operation detection field.
Description
Technical Field
The invention belongs to the technical field of deep learning, and relates to a fault diagnosis method, a fault diagnosis system, fault diagnosis equipment and a storage medium based on quick graph calculation.
Background
In diagnosing the fault type of the power equipment in the knowledge graph spectrogram in the power operation inspection field, the prior art generally adopts a graph neural network for diagnosis, and when a graph neural network model for graph classification and regression is constructed, graph pooling is a crucial step, because for graph structure input with continuously changing sizes and topological structures, a uniform representation of a graph hierarchy rather than a uniform representation of a node hierarchy is required. The most straightforward pooling approach provided by graph convolutional layers is to take the global mean and sum of the node features as a simple layer-level representation. This pooling operation is treated as one for all nodes and uses the global geometry information of the graph. However, the above-mentioned global pooling method does not use the hierarchical structure of the graph, and omits effective geometric information that may be carried in the graph structure data.
It is noted that if a differentiable, data-dependent pooling layer containing learnable operations or parameters can be constructed, substantial improvements can be made to the graph classification problem. In this regard, the spectrum-based pooling method proposes another design mode in which the pooling operation of the map can be performed in the frequency domain such as the fourier domain or the wavelet domain. By its very nature, the spectrum-based pooling approach can consolidate graph structure and node information, but has the potential drawback of being a bottleneck in computational efficiency and accuracy, resulting in an inability to efficiently and accurately diagnose the type of power equipment failure.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a fault diagnosis method, a fault diagnosis system, equipment and a storage medium based on quick graph calculation, wherein the fault diagnosis method, the fault diagnosis system, the fault diagnosis equipment and the storage medium can be used for accurately and efficiently diagnosing the fault type of the electric equipment in a knowledge graph spectrogram in the electric power operation detection field.
The calculation efficiency and the calculation precision are higher.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the present invention provides a fault diagnosis method based on quick graph calculation, including:
clustering nodes in a spectrogram of a knowledge graph in the electric power operation and detection field to generate a node group sequence of the graph;
determining a sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph, and constructing the multi-scale graph neural network;
and inputting the node group sequence of the graph into a multi-scale graph neural network to complete the calculation of the rapid graph neural network, so as to obtain the fault type of the power equipment in the power operation detection field knowledge graph spectrogram.
The fault diagnosis method based on the quick graph calculation is further improved in that:
the specific process of clustering the nodes in the spectrogram of the knowledge graph in the electric power operation detection field to generate the node group sequence of the graph is as follows:
clustering nodes in the power operation detection field knowledge graph spectrogram G through a clustering algorithm to generate a node group sequence (G) of the graph0,G1,...,GK) Wherein G is0G, graph Gj+1Node of (D) corresponds to graph GjJ-0.., K-1.
The specific process of determining the sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph and constructing the multi-scale graph neural network comprises the following steps:
carrying out vector representation on each node group in the node group sequence of the graph, and representing a representation matrix forming the node group through the vector representation of each node group;
and respectively taking the representation matrix of each node group as a sparse representation matrix of each pooling layer in the multi-scale graph neural network to construct the multi-scale graph neural network.
Before the step of using the representation matrix of each node group as the sparse representation matrix of each pooling layer in the multi-scale graph neural network, the method further comprises the following steps:
and discarding the high-frequency fine information in the representation matrix through the characteristic value of the representation matrix of each node group.
The multi-scale graph neural network is represented as:
wherein phijFor the jth pooling layer, the size is Nj+1×NjIs used to represent the matrix in a sparse manner,is of size NjThe input feature matrix of x d is,is of size Nj+1And d, K is the number of pooling layers in the hole multi-scale map neural network.
The node group sequence of the graph is input into the multi-scale graph neural network, and in the process of outputting the result of the multi-scale graph neural network,
pooling the node group sequence of the graph through each pooling layer, aggregating the output results of each pooling layer, and transmitting the aggregated results to a reading operation and a multilayer perceptron.
In a second aspect of the present invention, the present invention provides a fault diagnosis system based on quick graph calculation, including:
the clustering module is used for clustering nodes in a spectrogram of a knowledge graph in the electric power operation detection field to generate a node group sequence of the graph;
the determining module is used for determining a sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph and constructing the multi-scale graph neural network;
and the calculation module is used for inputting the node group sequence of the graph into a multi-scale graph neural network to complete the calculation of the rapid graph neural network so as to obtain the fault type of the power equipment in the power operation detection field knowledge graph spectrogram.
The fault diagnosis system based on the quick graph calculation is further improved in that:
the determining module comprises:
the data processing module is used for carrying out vector representation on each node group in the node group sequence of the graph, and representing a representation matrix forming the node group through the vector of each node group;
and the building module is used for respectively taking the representation matrix of each node group as the sparse representation matrix of each pooling layer in the multi-scale graph neural network to build the multi-scale graph neural network.
In one aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the fault diagnosis method based on fast graph computation when executing the computer program.
In a fourth aspect of the present invention, the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the fault diagnosis method based on quick graph computation.
The invention has the following beneficial effects:
the invention relates to a fault diagnosis method, a system, equipment and a storage medium based on rapid graph calculation, which determine a sparse representation matrix of each pooling layer in a multi-scale graph neural network according to a node group sequence of a graph during specific operation, filter fine information and simultaneously keep structural information of a knowledge graph spectrogram in the electric power operation detection field based on a sparse representation mode so as to solve the problem of low calculation efficiency of the traditional graph neural network.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of the processing of the pooling layer;
FIG. 3 is a block diagram of a multi-scale graph neural network;
fig. 4 is a system configuration diagram of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the accompanying drawings:
example one
Referring to fig. 1, the fault diagnosis method based on the fast graph calculation according to the present invention includes:
1) acquiring structural data of a spectrogram of a knowledge map in the electric power operation detection field, clustering nodes in the spectrogram of the knowledge map in the electric power operation detection field, and generating a node group sequence of the map;
specifically, a node group sequence (G) of a map is generated by a clustering algorithm for nodes in a spectrogram G of a knowledge map in the electric power operation detection field0,G1,...,GK) Wherein G is0G, and for j 0, K-1, there is a graph Gj+1Node of (D) corresponds to graph GjNode cluster in (1), set Nj=|V(Gj) Is | is graph GjIf the number of nodes in (1) is NjA node and Nj+1Graph G of individual nodesjAnd graph Gj+1In the presence of Nj>Nj+1. Analyzing the graph structure data characteristics by using a clustering algorithm to generate a node group sequence (G) of the graph0,G1,...,GK)。
It should be noted that, for example, in the field of electric power inspection, the clustering algorithm may use spectral clustering (Shi & Malik,2000), k-means clustering (Pakhira,2014), DBSCAN (Ester et al, 1996), OPTICS (ankert et al, 1999) and METIS (Karypis & Kumar,1998) as candidate algorithms, and may also use the clustering structure information carried by the electric power inspection knowledge map data itself.
The spectrogram of the knowledge graph in the electric power operation detection field contains data of common fault defects of electric power equipment, entities in the knowledge graph have subordination relations according to the existing standard and definition, and a hierarchical structure can be naturally formed without a clustering algorithm. For example, the insulators include porcelain insulators, glass insulators, composite insulators and the like, the porcelain insulators include porcelain insulator dirt, porcelain insulator spontaneous explosion, porcelain insulator zero values and the like, and the insulators can be further divided downwards according to different defect degrees.
2) Carrying out vector representation on each node group in the node group sequence of the graph, and representing a representation matrix forming the node group through the vector representation of each node group;
specifically, the node group sequence (G) generated after clustering0,G1,...,GK) Due to the diagram Gj+1N in (1)j+1The node is a slave graph GjN in (1)jSelected from individual nodes and clustered, thus graph GjEach node in (a) can be represented as a size of Nj+1The vector of (A), the NjA vector may be formed of size Nj+1×NjI.e. the sparse representation matrix phi of the jth pooling layerj。
In the present invention, the eigenvalue is calculated by spectral transformation, and the eigenvalue is used as a representation matrix Φ of the graph structure data, the representation matrix Φ has orthogonality and parameter learnability, and represents information of different frequencies by the eigenvalue, and the eigenvalue of the representation matrix ΦDiscarding the high-frequency fine information in the value to obtain a sparse representation matrix phij;
Note that the spectrogram transform includes fourier transform, dyadic wavelet transform, and Daubechies wavelet transform.
The fourier transform of the spectrogram is similar to the conventional fourier transform, but a corresponding fourier basis and a laplacian matrix need to be found on the graph structure data, wherein the laplacian matrix L-D-a is calculated from a degree matrix D and an adjacency matrix a of the graph; referring to fig. 2, for an arbitrary signal x, the spectrogram fourier transform is:
wherein phi is [ phi ]1,...,φN]Is a feature vector of L, L ═ Φ Λ ΦT,The fourier coefficients of the signal x on the kth fourier basis, which are essentially the projections of the signal on the fourier basis, can reflect the intensities of the map signal on different frequency components, defined by the frequency of the map signal, providing conditions for subsequent filtering.
3) Respectively taking the representation matrix of each node group as a sparse representation matrix of each pooling layer in the multi-scale graph neural network to construct the multi-scale graph neural network;
specifically, referring to fig. 3, the node group sequence (G) of the graph0,G1,...,GK) Inputting the data into a multi-scale map neural network as input, pooling the data by using a pooling layer in the multi-scale map neural network, and obtaining a corresponding coarsened map after poolingOne node of the coarsened graph is clustered by one node group before coarsening, so the number of the nodes of the coarsened graph is relatively reduced, and only approximate characteristic information can be reflected, and the final result of the pooling layer is composed of one node which comprises all the nodes of the previous layerPoint information, i.e.
It should be noted that, the present invention aggregates the output results of each pooling layer, and then transmits the aggregated output results to the reading operation and the multi-layer sensor, so as to retain the characteristic information of the graph structure data on each layer, so that the final graph representation result includes the node information sum of different layers, and the problem of insufficient precision of the traditional graph neural network is solved.
4) And inputting the node group sequence of the graph into a multi-scale graph neural network to complete the calculation of the rapid graph neural network, so as to obtain the fault type of the power equipment in the power operation detection field knowledge graph spectrogram.
Example two
Referring to fig. 4, the fault diagnosis system based on the fast graph calculation according to the present invention includes:
the clustering module 1 is used for clustering nodes in a spectrogram of a knowledge graph in the electric power operation detection field to generate a node group sequence of the graph;
the determining module 2 is used for determining a sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph and constructing the multi-scale graph neural network;
and the calculation module 3 is used for inputting the node group sequence of the graph into a multi-scale graph neural network to obtain the fault type of the power equipment in the power operation detection field knowledge graph spectrogram.
Preferably, the determining module 2 includes:
a data processing module 21, configured to perform vector representation on each node group in the node group sequence of the graph, and represent a representation matrix forming the node group through the vector of each node group;
and the building module 22 is configured to secondly use the representation matrix of each node group as a sparse representation matrix of each pooling layer in the multi-scale graph neural network, respectively, to build the multi-scale graph neural network.
EXAMPLE III
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the fault diagnosis method based on fast graph calculation when executing the computer program, wherein the memory may comprise a memory such as a high speed random access memory, and may further comprise a non-volatile memory such as at least one disk memory; the processor, the network interface and the memory are connected with each other through an internal bus, wherein the internal bus can be an industrial standard system structure bus, a peripheral component interconnection standard bus, an extended industrial standard structure bus and the like, and the bus can be divided into an address bus, a data bus, a control bus and the like. The memory is used for storing programs, and particularly, the programs can comprise program codes which comprise computer operation instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
Example four
A computer-readable storage medium, storing a computer program which, when executed by a processor, implements the steps of the fast graph computation based fault diagnosis method, in particular, including, but not limited to, volatile memory and/or non-volatile memory, for example. The volatile memory may include Random Access Memory (RAM) and/or cache memory (cache), among others. The non-volatile memory may include a Read Only Memory (ROM), hard disk, flash memory, optical disk, magnetic disk, and the like.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A fault diagnosis method based on quick graph calculation is characterized by comprising the following steps:
clustering nodes in a spectrogram of a knowledge graph in the electric power operation and detection field to generate a node group sequence of the graph;
determining a sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph, and constructing the multi-scale graph neural network;
and inputting the node group sequence of the graph into a multi-scale graph neural network to obtain the fault type of the power equipment in the power operation detection field knowledge graph spectrogram.
2. The fault diagnosis method based on the fast graph calculation as claimed in claim 1, wherein the specific process of clustering the nodes in the spectrogram of the knowledge graph in the electric power operation and inspection field to generate the node group sequence of the graph is as follows:
clustering nodes in the power operation detection field knowledge graph spectrogram G through a clustering algorithm to generate a node group sequence (G) of the graph0,G1,...,GK) Wherein G is0G, graph Gj+1Node of (D) corresponds to graph GjJ-0.., K-1.
3. The method of fault diagnosis based on fast graph computation of claim 1,
the specific process of determining the sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph and constructing the multi-scale graph neural network comprises the following steps:
carrying out vector representation on each node group in the node group sequence of the graph, and representing a representation matrix forming the node group through the vector representation of each node group;
and respectively taking the representation matrix of each node group as a sparse representation matrix of each pooling layer in the multi-scale graph neural network to construct the multi-scale graph neural network.
4. The method according to claim 3, wherein before the using the representation matrix of each node group as the sparse representation matrix of each pooling layer in the multi-scale graph neural network, the method further comprises:
and discarding the high-frequency fine information in the representation matrix through the characteristic value of the representation matrix of each node group.
5. The fast graph computation-based fault diagnosis method according to claim 1, wherein the multi-scale graph neural network is represented as:
6. The method for fault diagnosis based on rapid graph calculation according to claim 1, wherein the node group sequence of the graph is input into a multi-scale graph neural network, and in the process of outputting the result of the multi-scale graph neural network, the node group sequence of the graph is pooled through each pooling layer, the output results of each pooling layer are aggregated, and the aggregated result is transmitted to a reading operation and a multi-layer sensing machine.
7. A fault diagnosis system based on a quick graph calculation, comprising:
the clustering module (1) is used for clustering nodes in a spectrogram of a knowledge graph in the electric power operation detection field to generate a node group sequence of the graph;
the determining module (2) is used for determining a sparse representation matrix of each pooling layer in the multi-scale graph neural network according to the node group sequence of the graph to construct the multi-scale graph neural network;
and the calculation module (3) is used for inputting the node group sequence of the graph into a multi-scale graph neural network to obtain the fault type of the power equipment in the power operation detection field knowledge graph spectrogram.
8. The rapid-graph-computation-based fault diagnosis system according to claim 7, wherein the determination module (2) comprises:
a data processing module (21) for performing vector representation on each node group in the node group sequence of the graph, and representing a representation matrix forming the node group through the vector of each node group;
and the building module (22) is used for building the multi-scale graph neural network by respectively taking the representation matrix of each node group as the sparse representation matrix of each pooling layer in the multi-scale graph neural network.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method for fault diagnosis based on fast graph computation according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for fault diagnosis based on a fast-graph computation according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210048196.6A CN114581261A (en) | 2022-01-17 | 2022-01-17 | Fault diagnosis method, system, equipment and storage medium based on quick graph calculation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210048196.6A CN114581261A (en) | 2022-01-17 | 2022-01-17 | Fault diagnosis method, system, equipment and storage medium based on quick graph calculation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114581261A true CN114581261A (en) | 2022-06-03 |
Family
ID=81772870
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210048196.6A Pending CN114581261A (en) | 2022-01-17 | 2022-01-17 | Fault diagnosis method, system, equipment and storage medium based on quick graph calculation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114581261A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115828170A (en) * | 2023-01-06 | 2023-03-21 | 山东拓新电气有限公司 | Fault detection method based on electric control data of tunneling machine |
CN118194151A (en) * | 2024-05-15 | 2024-06-14 | 成都摩尔环宇测试技术有限公司 | Aeroengine bearing fault diagnosis method based on graph multi-scale approximate entropy |
-
2022
- 2022-01-17 CN CN202210048196.6A patent/CN114581261A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115828170A (en) * | 2023-01-06 | 2023-03-21 | 山东拓新电气有限公司 | Fault detection method based on electric control data of tunneling machine |
CN115828170B (en) * | 2023-01-06 | 2023-06-16 | 山东拓新电气有限公司 | Fault detection method based on electronic control data of tunneling machine |
CN118194151A (en) * | 2024-05-15 | 2024-06-14 | 成都摩尔环宇测试技术有限公司 | Aeroengine bearing fault diagnosis method based on graph multi-scale approximate entropy |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109120462B (en) | Method and device for predicting opportunistic network link and readable storage medium | |
CN114581261A (en) | Fault diagnosis method, system, equipment and storage medium based on quick graph calculation | |
CN112785016A (en) | New energy automobile maintenance and fault monitoring and diagnosis method based on machine learning | |
CN113361578B (en) | Training method and device for image processing model, electronic equipment and storage medium | |
CN112289391B (en) | Anode aluminum foil performance prediction system based on machine learning | |
CN111144548A (en) | Method and device for identifying working condition of pumping well | |
CN113554175B (en) | Knowledge graph construction method and device, readable storage medium and terminal equipment | |
CN114548199A (en) | Multi-sensor data fusion method based on deep migration network | |
CN116578843A (en) | Centrifugal pump diagnostic model training method, diagnostic method, system, device and medium | |
CN115310594A (en) | Method for improving expandability of network embedding algorithm | |
CN115809596A (en) | Digital twin fault diagnosis method and device | |
KR102189811B1 (en) | Method and Apparatus for Completing Knowledge Graph Based on Convolutional Learning Using Multi-Hop Neighborhoods | |
CN115062779A (en) | Event prediction method and device based on dynamic knowledge graph | |
Srinivasan et al. | Application of graph sparsification in developing parallel algorithms for updating connected components | |
CN111710360A (en) | Method, system, device and medium for predicting protein sequence | |
CN116109004A (en) | Insulator leakage current prediction method, device, equipment and medium | |
CN113449626B (en) | Method and device for analyzing vibration signal of hidden Markov model, storage medium and terminal | |
CN115865713A (en) | Importance ordering method, system and terminal for high-order structure in high-order network | |
CN114419339A (en) | Method and device for training data reconstruction model based on electric power portrait | |
CN114565794A (en) | Bearing fault classification method, device, equipment and storage medium | |
Mansuri et al. | Modified DMGC algorithm using ReLU-6 with improved learning rate for complex cluster associations | |
CN114152454A (en) | Mechanical equipment fault diagnosis method based on CEEMDAN-CSE model and establishment method of model | |
CN111767980A (en) | Model optimization method, device and equipment | |
Kim et al. | Filter-Wise Quantization of Deep Neural Networks for IoT Devices | |
CN115641330B (en) | Flexible circuit board defect detection method and system based on image processing |
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 |