Soft measurement method for butane content in debutanizer based on Stacking

A technology of butane and soft measurement of a butane tower, applied in the field of industrial process prediction and soft measurement, can solve problems such as the inability to make good use of the Stacking model, and achieve the effect of improving the accuracy of real-time prediction

Active Publication Date: 2021-09-28
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, the first layer learner in the Stacking model reported in this patent has only one random weight neural network, and the second layer learner uses the same model as the first layer learner, which cannot make good use of the advantages of the Stacking model

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
  • Soft measurement method for butane content in debutanizer based on Stacking
  • Soft measurement method for butane content in debutanizer based on Stacking
  • Soft measurement method for butane content in debutanizer based on Stacking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045]The present invention is illustrated below in conjunction with a concrete debutanizer butane content prediction embodiment:

[0046] The debutanizer was continuously sampled to obtain 2394 samples. The first 1596 samples were used as the training set to train the integrated learning soft sensor model, and the last 798 samples were used as the test set to verify the integrated learning soft sensor model. effectiveness. In this process, seven process variables are selected to model the butane content at the bottom of the debutanizer, the seven process variables are tower top temperature, tower top pressure, reflux flow, flow to the next stage, sixth Plate temperature, tower bottom temperature 1, tower bottom temperature 2, such as figure 1 shown in .

[0047] Next, in conjunction with this specific process, the implementation steps of the present invention are described in detail, as image 3 As shown, specifically:

[0048] 1. Use 1596 training samples to train an XGB...

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 soft measurement method for the content of butane in a debutanizer based on Stacking. According to the method, feature expansion is performed on a process variable at a current sampling moment through a time sliding window, a process dynamic problem is solved by utilizing historical process data, and diversity between first-layer learners in an integrated learning model is enhanced by introducing a feature disturbance mechanism and adopting a non-homogeneous learner; and the output of the first-layer learner is combined by using a Stacking integration strategy and the second-layer learner to obtain a final prediction value of the butane content. The real-time prediction precision of the butane content of the debutanizer is effectively improved.

Description

technical field [0001] The invention belongs to the field of industrial process prediction and soft measurement, in particular to a stacking-based soft measurement method for butane content in a debutanizer. Background technique [0002] In the actual industrial process, there are many variables that are difficult to measure directly or have high cost, and these variables often affect product quality to a large extent. Industrial process soft measurement technology is a method to estimate the true value of the measured variable by establishing a mathematical model between the measured variable and other easy-to-measure variables. Soft sensor technology is mainly divided into two types: mechanism modeling and data-based modeling. The development of computer technology and machine learning makes the application of data-based modeling soft sensor more and more extensive. Common soft sensor methods based on data modeling include support vector machines, partial least squares, a...

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): G06F30/28G06F30/27G06K9/62G06N7/00G06N20/10G06F113/08G06F119/14
CPCG06F30/28G06F30/27G06N20/10G06F2113/08G06F2119/14G06N7/01G06F18/214Y02P90/30
Inventor 葛志强庄新镇孔祥印
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap