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

An intelligent monitoring method for equipment faults based on event graph technology

A technology for equipment failure and intelligent monitoring, which is applied to computer components, unstructured text data retrieval, instruments, etc., can solve problems such as poor accuracy, poor learning ability, and small coverage, so as to improve adaptability, easy integration, The effect of reducing the difficulty of maintenance and troubleshooting

Active Publication Date: 2022-03-22
XIAMEN ETOM SOFTWARE TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of science and technology and the complexity of manufacturing processes, more and more factors affect equipment, which makes troubleshooting difficult and even requires the participation of industry experts. When equipment fails, it is usually impossible to respond in time and repair quickly. Not only the speed of repair Slow and expensive to repair
[0003] Compared with purely manual inspection, the existing auxiliary system for equipment maintenance can assist maintenance personnel to find the problem faster, and then propose a corresponding maintenance plan. However, the existing auxiliary system has poor accuracy, poor learning ability, and small coverage, so it cannot adapt New situations and new conditions make it difficult to quickly locate the cause of the fault, and the maintenance suggestions given are often wrong

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] An intelligent monitoring method for equipment faults based on event graph technology, which can establish a preliminary model based on historical data, and then learn current data in real time, continuously improve the model, and provide maintenance suggestions and fault warnings for equipment.

[0036] For realizing above-mentioned technical effect, described method comprises:

[0037] S10: Construct an event graph through historical data analysis, the event graph includes event elements, and a network-like event graph is formed between the event elements through event relationships.

[0038] The event element includes core nodes and event attributes. Wherein, the core node corresponds to a fault of a device, including a name, a type, a keyword describing a fault event, and a description that can be distinguished from other faults. The event attribute corresponds to the status of the device, including basic information of the device, time of failure, status informati...

Embodiment 2

[0047] On the basis of Embodiment 1, said S10 includes S11: establish a fault classification model, classify fault descriptions, and reduce fault types; perform event extraction for each fault and form an event element; use the fault classification model to identify event attributes, The event attributes also include: fault type, related accompanying state parameters, and fault consequences.

[0048] Specifically, when establishing a fault classification model, combined with expert knowledge and experience, natural language understanding technology and clustering algorithm are used to classify fault descriptions.

Embodiment 3

[0050] On the basis of any of the above-mentioned embodiments, the relationship between event elements and the relationship between the core node and each event attribute are strengthened according to historical data to obtain the strength of each relationship, and then obtain the relationship between each fault and its accompanying faults. Strong and weak ties and the strong and weak ties between each fault and its accompanying state.

[0051] Real-time analysis of faults is carried out through the strong and weak relationship between faults, and the accompanying state of the fault is analyzed. Through multi-dimensional analysis of the accompanying state, other faults that may exist can be found to realize real-time early warning of faults. Calculate the weight of each dimension in the event attribute through the strength relationship between the fault and its accompanying state, and obtain the similarity between the two faults according to the similarity between the weight an...

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 present invention provides an intelligent monitoring method for equipment faults based on event graph technology, which can learn historical data and current data, and provide maintenance suggestions and fault warnings for equipment maintenance. The method includes: S10: building an event graph through historical data analysis, The event graph includes event elements, and a network-like event graph is formed between the event elements and the event elements through event relationships; the event elements include core nodes and event attributes; S20: Compare the current device state with the event graphs in the event graph. The event attributes are compared, and the corresponding core nodes and event elements are matched; S30: update the event map in real time, and learn new faults, new states and corresponding maintenance plans of the equipment; S40: according to the event elements, determine the current equipment failure status, Analyze the causes of equipment failures, and provide a maintenance plan; S50: Predict the possible failures of the current equipment according to the relationship between event elements and event elements in the event map, and give a failure warning.

Description

technical field [0001] The invention relates to the technical field of equipment maintenance. Background technique [0002] With the development of science and technology and the complexity of manufacturing processes, more and more factors affect equipment, which makes troubleshooting difficult and even requires the participation of industry experts. When equipment fails, it is usually impossible to respond in time and repair quickly. Not only the speed of repair Slow and high maintenance costs. [0003] Compared with purely manual inspection, the existing equipment maintenance auxiliary system can assist maintenance personnel to find the problem faster and then propose corresponding maintenance solutions. However, the existing auxiliary system has poor accuracy, poor learning ability, and small coverage, so it cannot adapt New situations and new conditions make it difficult to quickly locate the cause of the fault, and the maintenance suggestions given are often wrong. ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/00G06F16/36G06K9/62
CPCG06Q10/20G06F16/367G06F18/23G06F18/24
Inventor 刘煜孙再连陈德忠
Owner XIAMEN ETOM SOFTWARE TECH CO LTD
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