Soft measurement modeling method for PVC (polyvinyl chloride) polymerization process

A modeling method and soft-sensing technology, which is applied in the field of soft-sensing modeling of PVC polymerization process, can solve the problems of difficult real-time acquisition of vinyl chloride conversion rate and conversion rate, and difficult realization of quality closed-loop control.

Inactive Publication Date: 2013-07-10
SHENYANG INSTITUTE OF CHEMICAL TECHNOLOGY
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the limitation of on-site conditions and the lack of mature detection devices, it is difficult to obtain the conversion rate and conversion rate of vinyl chloride in real time in the actual production process, and it is difficult to achieve closed-loop quality control

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0016] 1 Initialize population size m, search space dimension D (the number of prerequisite parameters), harmony memory HMS, memory selection probability , the pitch adjustment probability Ppar and the number of loop iterations n ; the number of loop iterations n =1 , the population individuals are randomly initialized in the search space, and the ith individual vector is

[0017] .

[0018] 2 Take each individual vector in the population as the premise parameter of the T-S fuzzy neural network in turn, calculate the excitation intensity and normalized excitation intensity of all rules, and then use the least square method to identify the conclusion parameters; finally

[0019] According to the following formula, the root mean square error (RMSE) of the model corresponding to the individual is calculated as the fitness value of the individual ,in: .

[0020] 3 Select the original harmony library individual and the population (metabolism mode) fitness value before HMS i...

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

A soft measurement modeling method for the PVC (polyvinyl chloride) polymerization process relates to a soft measurement modeling method for the chemical engineering polymerization process, and comprises the following steps: firstly, according to the technological characteristics of a polymerization reaction, collecting 10 process variables related to VCM (vinyl chloride monomer) conversion rate and VCM conversion speed rate and regarding the 10 process variables as the auxiliary variables for the soft measurement modeling; processing the data, assorting the data by adopting the FCM clustering algorithm, and establishing a plurality of submodels based on T-S fuzzy neural network by using the various types of sorted data; then, performing dimensionality reduction on T-S model high-dimensional input vector by adopting PCA; performing principal component analysis on the history data consisting of the soft measurement modeling input to determine the number of the principal components; and finally, optimizing the T-S fuzzy neural network based on harmony search. The soft measurement modeling method for a PVC polymerization process can remarkably improve the accuracy and robustness of economic and technical indicator prediction during the PVC polymerization process, and meet the real-time control requirement of a polymerization kettle production process.

Description

technical field [0001] The invention relates to a soft-sensing modeling method of a chemical polymerization process, in particular to a soft-sensing modeling method of a PVC polymerization process. Background technique [0002] It is a typical batch chemical production process to produce polyvinylchlorid (polyvinylchlorid, PVC) resin by suspension polymerization process using vinyl chloride monomer (VCM) as raw material. Due to the limitation of on-site conditions and the lack of mature detection devices, it is difficult to obtain the conversion rate and conversion rate of vinyl chloride in real time in the actual production process, and it is difficult to achieve closed-loop quality control. Therefore, how to predict the conversion rate and conversion rate of PVC has always been the focus of people's research. Contents of the invention [0003] The purpose of the present invention is to provide a soft sensor modeling method for the PVC aggregation process. The present in...

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): G06F17/50G06N3/02
Inventor 高淑芝赵娜
Owner SHENYANG INSTITUTE OF CHEMICAL TECHNOLOGY
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