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

A method for determining causality of key variables in complex industrial processes

A causal relationship and industrial process technology, applied in the field of determining the causal relationship of key variables in complex industrial processes, can solve the problem of less parameter selection, achieve the effect of reducing interference items, reducing human judgment, and eliminating pseudo-causal relationship

Active Publication Date: 2019-02-12
CENT SOUTH UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method that is easy to calculate, has less parameter selection, fully considers the coupling problem between key variables, and can solve the causal relationship identification between key variables in a nonlinear complex dynamic system with moderate and strong coupling. The Method of Retrospective Analysis of Process Abnormal Conditions

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
  • A method for determining causality of key variables in complex industrial processes
  • A method for determining causality of key variables in complex industrial processes
  • A method for determining causality of key variables in complex industrial processes

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0075] The actual operation data of a refinery hydrocracking process in my country will be used as an example below, and the causal relationship of key variables in the hydrocracking process is determined based on the improved convergence cross-mapping algorithm proposed in the present invention, according to figure 1 Execute in the flow chart and give detailed instructions. It should be emphasized that the following description is only exemplary, and the following examples are only some of the key variables in the hydrocracking process, and are not intended to limit the scope of the present invention and its application. The provided method includes the following steps:

[0076] Step 1, collecting historical production data of key variables in the hydrocracking process, and performing sample data preprocessing. That is, for the 7 key variables in the hydrofinishing reaction part of the hydrocracking process whose causal relationship is to be determined, the simplified schema...

specific Embodiment 2

[0092] Taking tobacco shredded production as an example again, tobacco shredded production is a typical intermittent production process, and shredded drying is the most critical process. Leaves shredded as required. The production process is relatively complicated, and the shredded leaves are affected by factors such as moisture and temperature. Therefore, taking the shredded shredded drying process as an example, the causal relationship between key variables in the process is analyzed. The main steps are as follows:

[0093] Step 1: Select five key variables during the silk drying process: inlet moisture, hot air volume, wall pressure in the first zone, wall pressure in the second zone, and outlet moisture, and the length of the sample is 300;

[0094] Step 2, determine the optimal timing embedding dimension E of the reconstructed manifold, the G(k) graph of each key variable is as follows Figure 7 As shown, the optimal timing embedding dimensions of each key variable are 7...

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 method for determining the causal relationship of key variables in a complex industrial process. The optimal time-series embedding dimension of each key variable is calculated by using the pseudo-nearest neighbor idea on the historical data of the key variables whose causal relationship is to be determined in the industrial process; Two key variables, assuming a causal relationship, using the assumed optimal time-series embedding dimension of the dependent variable as the standard, construct the time-series reconstruction manifold of the two key variables, and use the convergent cross-mapping algorithm to calculate the convergent cross-mapping ability between the two; based on Monte Carlo simulation determines the threshold of CCM capability judgment, so as to determine the correctness of the assumed causal relationship between key variables, so as to construct the preliminary causal relationship network of key variables in the industrial process; use the time-delay detection method to correct the preliminary causal relationship network, and obtain the final Key variable causality network. The invention makes full use of production off-line data, has no interference effect on the production process, and improves safety and economic benefits.

Description

technical field [0001] The invention relates to technical fields such as the analysis of the causal relationship of key variables in the abnormal working condition diagnosis and retrospective analysis of industrial processes, and specifically relates to a method for determining the causal relationship of key variables in complex industrial processes. Background technique [0002] In large and complex industrial systems such as petroleum refining and iron and steel smelting, there are many operating variables in the process, the coupling between variables is serious, and the integration degree is high. For example, the hydrocracking process is a sub-process in the petroleum refining process. It is a processing process in which hydrogen is converted into light oil by hydrogenation, cracking and isomerization reactions of heavy oil through catalyst action at relatively high pressure and temperature. , mainly including four important parts: hydrofining reaction, hydrocracking re...

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): G06K9/00G06F17/18
CPCG06F17/18G06F2218/04
Inventor 王雅琳胡芳香曹跃袁小锋阳春华桂卫华
Owner CENT SOUTH UNIV
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