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

Chemical process fault diagnosis method based on transfer entropy

A technology for chemical process and fault diagnosis, which is applied in the fields of instrumentation, calculation, and electrical digital data processing, etc. It can solve the problems of low accuracy in processing big data, failure to identify the root cause of faults, etc., and achieve the effect of improving accuracy

Pending Publication Date: 2019-10-25
SHENYANG HONGJI ELECTRICAL
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to provide a method for fault diagnosis of chemical process based on transfer entropy, to at least solve the problem that the existing fault diagnosis method cannot identify the root cause of the fault and has low accuracy in processing large data

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
  • Chemical process fault diagnosis method based on transfer entropy
  • Chemical process fault diagnosis method based on transfer entropy
  • Chemical process fault diagnosis method based on transfer entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further explained below in conjunction with specific embodiments, but the present invention is not limited thereto.

[0049] The invention provides a method for diagnosing chemical process faults based on transfer entropy, comprising the following steps:

[0050] S1: Establish a process monitoring model using relevant information entropy;

[0051] S11: Take the fault source with monitoring variables in the chemical process as the research object, collect historical monitoring data x∈M under normal working conditions m×n And it is normalized to eliminate the influence of dimension and value differences between different monitoring variables, where m represents the number of sampling time, n represents the number of monitoring variables contained in each sampling time, and n<m;

[0052] S12: According to the Bayesian information criterion, select N strongly correlated variables from the monitoring variables and use the formula (1) to calcul...

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 chemical process fault diagnosis method based on transfer entropy. Firstly, a process monitoring model is established by adopting related information entropy; then, judging areal-time working condition state by utilizing the established process monitoring model, and finally, for an abnormal working condition, establishing a fault root cause-fault characteristic variabledatabase by utilizing historical fault data and introducing transfer entropy, and judging a fault root cause by utilizing the fault root cause-fault characteristic variable database. According to thechemical process fault diagnosis method based on the transfer entropy, the defect that a principal component analysis method processes nonlinear data is overcome. The fault diagnosis accuracy is improved. The transfer entropy is introduced, and the fault occurrence mechanism can be described.

Description

technical field [0001] The invention relates to the field of chemical process fault diagnosis, and in particular provides a chemical process fault diagnosis method based on transfer entropy. Background technique [0002] In the field of fault diagnosis, information entropy and transfer entropy are methods developed in recent years. Information entropy can measure any type of data and can effectively avoid the limitations of principal component analysis (PCA). Entropy cannot identify the root cause of the fault, and transfer entropy can make up for the lack of information entropy, but if the transfer entropy is directly used to process big data, the accuracy is low. [0003] Therefore, it has become an urgent problem to develop a new method for fault diagnosis of chemical process based on transfer entropy to improve the fault diagnosis rate and accurately describe the fault mechanism. Contents of the invention [0004] In view of this, the purpose of the present invention ...

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): G06F17/50
CPCG06F30/20
Inventor 马胤刚蒋辉李昱辉
Owner SHENYANG HONGJI ELECTRICAL
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