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

Modelling method for predicating impurity component concentration for dimethyl benzene oxidation process

An oxidation process, paraxylene technology, applied in the direction of instrumentation, adaptive control, control/regulation system, etc., can solve the problems of outlier sensitivity, overfitting, etc.

Inactive Publication Date: 2006-10-25
ZHEJIANG SUPCON SOFTWARE
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In εSVR, the input samples are treated equally, and the relaxation item of each sample is given the same penalty factor c, which will cause the SVM to be very sensitive to isolated points, resulting in overfitting

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
  • Modelling method for predicating impurity component concentration for dimethyl benzene oxidation process
  • Modelling method for predicating impurity component concentration for dimethyl benzene oxidation process
  • Modelling method for predicating impurity component concentration for dimethyl benzene oxidation process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] Below in conjunction with accompanying drawing and by embodiment the present invention will be further described:

[0081] Taking the prediction of 4-CBA content in the PX oxidation process of a refining and chemical enterprise as an example, the modeling methods based on fuzzy support vector regression method and SVR method, fuzzy neural network and mechanism model were compared.

[0082] During the PX oxidation process, the DCS system collects data every half a minute, and there are hundreds of process variables collected. It is impractical to use all these variables as input variables of the model. On the one hand, it will complicate the model. , on the other hand, it will reduce the predictive ability of the model, so it is necessary to select the input variables of the model before establishing the soft sensor model. A relatively simple and practical variable selection method is the prior method, which selects the input variables of the model according to the field...

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

Present invention provides spatial distribution based blur membership grade functional: supporting vector data domain description based membership grade functional. It first obtains data field descriptive model of training centralizing sample, then assigning different membership grade according to each sample off-line data domain level. The present invention can effectively reduce regression error resulted from process updating load and raise model antinoise ability. The prediction result can completely satisfy technical application requirement with very high technical application value.

Description

technical field [0001] The present invention relates to a kind of fuzzy support vector machine prediction model modeling of impurity component 4-CBA (4-Carboxy-benzaldchydc, 4-carboxybenzaldehyde) concentration in the industrial PX (p-xylene, Para-Xylene) oxidation process method. Background technique [0002] PTA (Pure Terephthalic Acid, purified terephthalic acid), an important raw material in the polyester industry, is mainly oxidized from PX. PX oxidation process flow chart by figure 1 As shown, PX, acetic acid, accelerator (HBr) and catalyst (Co+Mn) are respectively continuously pumped into the mixing tank, and after staying in the mixing tank for about 25 minutes, they are pumped into the oxidation reactor, and at the same time, air flows from the reactor through four inlets. Bottom entry. The PX oxidation reaction is carried out in two stages, that is, in the oxidation reactor and the first crystallizer respectively. The PX oxidation reaction is an exothermic reac...

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
IPC IPC(8): G05B13/04
Inventor 张英苏宏业古勇
Owner ZHEJIANG SUPCON SOFTWARE
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