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

Fault positioning method based on finite-state machine and graph neural network

A finite state machine and neural network technology, applied in the field of industrial process fault location, can solve problems such as difficult single point location, high complexity, and increased difficulty of fault location, so as to enhance interpretability, improve accuracy, and shorten maintenance the effect of time

Active Publication Date: 2020-11-20
GUANGDONG UNIV OF TECH
View PDF10 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the existing technology, fault location often still relies on the experience of maintenance personnel, so that troubleshooting is significantly affected by differences in personal experience. Experienced maintenance personnel are in place for investigation in time, which further increases the difficulty of fault location
In addition to personnel factors, the occurrence of faults in modern and contemporary industries often has the characteristics of "multi-point correlation and multi-factor intermingling", which is complex and difficult to locate at a single point

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 positioning method based on finite-state machine and graph neural network
  • Fault positioning method based on finite-state machine and graph neural network
  • Fault positioning method based on finite-state machine and graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0108] Model training is performed using the equipment maintenance manual containing the information shown in Table 1 as the data source:

[0109] Table 1 Schematic content of equipment maintenance manual

[0110]

[0111]

[0112] It can obtain a text dataset D containing multiple fault information source , each text in the text data set is segmented by Jieba word segmentation software, and stop words are removed to obtain dictionary set D cut-stopword .

[0113] via dictionary set D cut-stopword Train the CBOW model. The model parameters are set as: sliding window Windows=2, that is, two words are selected as the context words on the left and right of the center word; the model output word vector dimension=300, that is, each word can be represented by a 300-dimensional vector; the loss function is set for:

[0114]

[0115] where T is the length of the training text, 1≤i≤T; the parameters are updated using the gradient descent algorithm.

[0116] The text info...

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 positioning method based on a finite-state machine and a graph neural network. The method comprises the steps that fault information is converted into graph structure data, reasoning is conducted on the graph structure data through a graph neural network model, conversion is achieved through a finite-state machine model, and the accuracy, reliability and timelinessof fault diagnosis in the industrial process can be remarkably improved.

Description

technical field [0001] The present invention relates to the technical field of industrial process fault location methods. Background technique [0002] In modern and contemporary industrial processes, data is complex and there are many factors affecting process stability. In order to ensure safe and stable production, faults that occur require more precise positioning. However, in the prior art, fault location often still relies on the experience of maintenance personnel, so that fault troubleshooting is obviously affected by differences in personal experience. On the other hand, faults are sudden, and maintenance personnel often work shifts in a fluid manner, which is difficult to guarantee. Experienced maintenance personnel conduct timely investigations, which further increases the difficulty of fault location. In addition to the personnel factor, the occurrence of faults in modern and contemporary industries often has the characteristics of "multi-point correlation and m...

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): G05B23/02
CPCG05B23/0243G05B2219/24065Y04S10/52
Inventor 程良伦王德培张伟文
Owner GUANGDONG UNIV OF TECH
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