Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fault diagnosis method, system and equipment based on rapid graph calculation and storage medium

A fault diagnosis and graph computing technology, applied in the field of deep learning, can solve the problems of computational efficiency and accuracy bottlenecks, achieve high-efficiency diagnosis, and solve the effect of low computational accuracy

Pending Publication Date: 2022-06-03
CHINA ELECTRIC POWER RES INST +3
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In essence, the spectrum-based pooling method can combine graph structure and node information, but its potential defect lies in the bottleneck of computational efficiency and accuracy, which leads to the inability to efficiently and accurately diagnose the types of power equipment faults

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fault diagnosis method, system and equipment based on rapid graph calculation and storage medium
  • Fault diagnosis method, system and equipment based on rapid graph calculation and storage medium
  • Fault diagnosis method, system and equipment based on rapid graph calculation and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] refer to figure 1 , the fault diagnosis method based on fast graph calculation of the present invention includes:

[0046] 1) Obtain the structural data of the knowledge graph in the field of electric power operation and inspection, and cluster the nodes in the knowledge graph in the field of electric power inspection and inspection to generate a node group sequence of the graph;

[0047] Specifically, for the nodes in the knowledge graph graph G in the field of electric power operation and inspection, a clustering algorithm is used to generate the node group sequence (G 0 ,G 1 ,...,G K ), where G 0 =G, and for j=0,...,K-1, there are graphs G j+1 The nodes of the corresponding graph G j node cluster in , let N j =|V(G j )| is the graph G j the number of nodes in , then for Nj nodes and N j+1 A graph G of nodes j and Figure G j+1 , there is N j >N j+1 . Use the clustering algorithm to analyze the characteristics of the graph structure data, and generate the...

Embodiment 2

[0062] refer to Figure 4 , the fault diagnosis system based on fast graph calculation of the present invention includes:

[0063] The clustering module 1 is used to cluster the nodes in the knowledge graph graph in the field of electric power operation and inspection, and generate a sequence of node groups of the graph;

[0064] The determination module 2 is used for 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;

[0065] The calculation module 3 is used for inputting the node group sequence of the graph into the multi-scale graph neural network to obtain the fault type of the power equipment in the knowledge graph in the field of electric power operation and inspection.

[0066] Preferably, the determining module 2 includes:

[0067] The data processing module 21 is used to represent each node group in the nod...

Embodiment 3

[0070] A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the fast graph computation-based fault diagnosis when the processor executes the computer program The steps of the method, wherein the memory may include memory, such as high-speed random access memory, and may also include non-volatile memory, such as at least one disk memory, etc.; the processor, the network interface, and the memory are connected to each other through an internal bus, the The internal bus can be an industry standard architecture bus, a peripheral component interconnection standard bus, an extended industry standard structure bus, etc. The bus can be divided into an address bus, a data bus, a control bus, and the like. The memory is used to store programs, and specifically, the programs may include program codes, and the program codes include computer operation instructions. The memory may include ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fault diagnosis method, system and device based on rapid graph calculation and a storage medium, and the method comprises the steps: clustering nodes in a power operation and inspection field knowledge graph, and generating a node group sequence of the graph; determining a sparse representation matrix of each pooling layer in a 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, completing rapid calculation of the graph neural network, obtaining an output result of the multi-scale graph neural network, and completing fault type diagnosis of the power equipment. According to the method, the system, the equipment and the storage medium, the fault type of the power equipment in the knowledge graph in the power operation and maintenance field can be accurately and efficiently diagnosed.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and relates to a fault diagnosis method, system, device and storage medium based on fast graph computing. Background technique [0002] When diagnosing the fault types of power equipment in the knowledge graph graph in the field of electric power inspection, graph neural network is generally used for diagnosis in the prior art. When constructing graph neural network model for graph classification and regression problems, graph pooling is the most important A crucial step, because for graph-structured inputs that are constantly changing in size and topology, a unified representation at the graph level is more desirable than a unified representation at the node level. The most straightforward pooling method provided by graph convolutional layers is to represent the global average and sum of node features as a simple graph level representation. This pooling operation treats all nodes equally ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q50/06G06N3/063G06V10/422G06K9/62G06N3/04G06F16/36G06N5/02
CPCG06Q50/06G06N3/063G06N3/04G06F16/367G06N5/02G06F18/23213G06F18/241Y04S10/50
Inventor 马震媛谈元鹏徐会芳何可嘉郑渠岸贺春刘力卿
Owner CHINA ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com