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

Chemical process fault diagnosis method for Bayesian network based on mechanism correlation analysis

A technology of Bayesian network and correlation analysis, applied in the field of chemical process fault diagnosis based on Bayesian network based on mechanism correlation analysis, to achieve good fault propagation path interpretation, improve calculation accuracy, and improve root cause diagnosis capabilities

Inactive Publication Date: 2020-02-07
QINGDAO UNIV OF SCI & TECH
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above methods are insufficient in explaining the fault propagation path and diagnosing the root cause of the fault

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 for Bayesian network based on mechanism correlation analysis
  • Chemical process fault diagnosis method for Bayesian network based on mechanism correlation analysis
  • Chemical process fault diagnosis method for Bayesian network based on mechanism correlation analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] like Figure 1-6 As shown, Embodiment 1 of the present disclosure provides a chemical process fault diagnosis method based on mechanism correlation analysis Bayesian network, including the construction of Bayesian network and Bayesian model reasoning, the steps are as follows:

[0058] (1) Collect the historical data of the chemical process, divide the variables of the chemical process into units, analyze the mechanism correlation relationship between the unit variables of the chemical process, and obtain the relationship matrix;

[0059] (2) Use the confidence interval estimation of historical data to calculate the conditional probability of the Bayesian network, and combine the relationship matrix to establish the Bayesian network;

[0060] (3) The process is monitored by principal component analysis, and when a fault is detected, the data state transition is performed and the Bayesian contribution of the variable is calculated;

[0061] (4) Add the evidence of the f...

Embodiment 2

[0103] Embodiment 2 of the present disclosure provides a chemical process fault diagnosis method based on mechanism correlation analysis Bayesian network. Taking depropanization fault 1 as an example for fault diagnosis, the obtained GeNIe software visualized depropanization Bayesian network, as shown in Figure 7 as shown, Figure 8 The Bayesian network under the depropanization fault 1 visualized by GeNIe software can clearly see the relationship between the variables; the Bayesian contribution degree diagram of the variables under the depropanization fault 1 is as follows Figure 9 As shown, the obtained fault propagation path, such as Figure 10 shown by Figure 8 , Figure 9 and Figure 10 , the corresponding fault propagation path and fault root node can be clearly found, and the real cause of the fault can be obtained according to the fault propagation path and root node, combined with the mechanism-related process knowledge, the root cause of the fault can be found ...

Embodiment 3

[0105] Embodiment 3 of the present disclosure provides a chemical process fault diagnosis system based on mechanism correlation analysis Bayesian network, including:

[0106] The data acquisition and preprocessing module is configured to: collect historical data of the chemical process, divide the variables of the chemical process into units, analyze the mechanism correlation relationship between the unit variables of the chemical process, and obtain a relationship matrix;

[0107] The Bayesian network construction module is configured to: calculate the conditional probability of the Bayesian network by using the confidence interval estimation of historical data, and establish the Bayesian network in combination with the relationship matrix;

[0108] The failure analysis module is configured to: monitor the process by principal component analysis, perform data state transition when a failure is detected, and calculate Bayesian contributions of variables;

[0109] The fault dia...

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 provides a chemical process fault diagnosis method for Bayesian networkbased on a mechanism correlation analysis and the method comprises the steps: analyzing the mechanism correlationsbetween unit variables of a chemical process, and obtaining a relation matrix; calculating the conditional probability of the Bayesian network by using confidence interval estimation of historical data, and establishing the Bayesian network in combination with the relationship matrix; adopting a principal component analysis method to monitor the process; when a fault is detected, conversing data state, and calculating Bayesian contribution of a variable; adding evidences of fault nodes into the Bayesian network, finding out propagation paths and root nodes of faults, obtaining real reasons ofthe faults according to the propagation paths and the root nodes of the faults, and finding out root reasons of the faults from the Bayesian network in combination with mechanism-related process knowledge. The graph theory modeling of the technological process model is realized, the priori knowledge of the mechanism model and the quantitative calculation of the historical data are combined, and the method has the characteristics of simplifying the calculation amount and improving the calculation precision.

Description

technical field [0001] The disclosure relates to the technical field of chemical process fault diagnosis, in particular to a chemical process fault diagnosis method based on mechanism correlation analysis Bayesian network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the development of large-scale industrialization and automation, the dimensionality of process variables is increasing, and the correlation between variables is becoming more and more complex, making the task of fault diagnosis more difficult to achieve than ever. Therefore, it is of great significance to monitor the process in time and effectively isolate the faults to ensure the safe and stable operation of the chemical process. After a fault occurs, many variables in the process are out of the normal range, how to find out the root cause of the fault is a matter ...

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): G06Q10/00G06N7/00
CPCG06Q10/20G06N7/01
Inventor 田文德任玉佳王骥柳楠
Owner QINGDAO UNIV OF SCI & 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