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

Early-warning method based on data and model fusion

A technology of model fusion and prediction method, applied in instruments, test/monitoring control systems, control/regulation systems, etc., can solve problems such as low accuracy and dynamic increase of deviation, so as to avoid abnormal system conditions, reduce casualties, and improve safety Effects of Sex and Reliability

Active Publication Date: 2017-06-20
QUANZHOU INST OF EQUIP MFG
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an early warning method based on data and model fusion, which overcomes the shortcomings of traditional early warning methods such as dynamic increase in deviation and low precision, and achieves good prediction results

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
  • Early-warning method based on data and model fusion
  • Early-warning method based on data and model fusion
  • Early-warning method based on data and model fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] An early warning method based on data and model fusion disclosed in this embodiment includes the following steps:

[0045] Step 1, collect system process operation data, and perform feature selection and extraction;

[0046] The feature selection and extraction is: selecting a corresponding algorithm according to the application environment of the system to select and extract the required features from the process operation data. The corresponding algorithm is feature selection and extraction method based on least squares or feature selection method based on neural network.

[0047] Step 2. Determine the normal state benchmark of the system according to the characteristic variables, track the degradation trajectory of these characteristic variables through state monitoring, and judge whether there is any abnormality;

[0048]If an abnormality occurs, continue to track the degradation trajectory of the characteristic variables, and perform state estimation or parameter ...

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 an early-warning method based on data and model fusion. Reliable prediction of a system operating degradation trend is realized sequentially through steps of data collection, feature extraction, establishment of a normal state standard, tracking of a feature variable degradation, a predication model based on data driving and continuous cyclic updating of parameters of the predication model. The early-warning method does not rely on a system mathematics model and prior knowledge, is capable of predicating change trends of a system in a future period of time only by relying on historical operating data and real-time data, and is capable of predicating faults that may occur in a short time during an abnormal change initial period of the system. Therefore, workers can timely eliminate latent risks, accidents are prevented effectively, the safety and the reliability of running of the system are improved, and economic losses and environment pollution are reduced.

Description

technical field [0001] The invention belongs to the technical field of safety monitoring, in particular to an early warning method based on fusion of data and models. Background technique [0002] With the increasing size and complexity of industrial machinery / equipment systems, people have higher and higher requirements for the safety and reliability of system operation. Since typical industrial equipment systems usually have characteristics such as nonlinearity, strong coupling, large time delay, and parameter distribution, once a certain component of the system fails, it may cause other components to fail, and even cause system paralysis or major accidents. In response to this problem, researchers have proposed data-driven fault diagnosis technology and alarm technology, which can detect and diagnose faults in time, determine the location of the fault, and notify the staff. However, the fault has already occurred, and the staff may not have enough time to troubleshoot the...

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 Applications(China)
IPC IPC(8): G05B23/02
CPCG05B23/0254
Inventor 陈豪张景欣蔡品隆王耀宗张丹
Owner QUANZHOU INST OF EQUIP MFG
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