A new method of chemical process quality prediction

A chemical process and quality prediction technology, applied in the field of automation, can solve problems such as inability to deal with nonlinear processes and high modeling complexity, and achieve the effects of improving interpretation ability, strengthening prediction performance, and reducing complexity

Inactive Publication Date: 2019-01-18
HANGZHOU DIANZI UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problems that the traditional partial least squares algorithm cannot handle the nonlinear process and the

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 new method of chemical process quality prediction
  • A new method of chemical process quality prediction
  • A new method of chemical process quality prediction

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0053] In the following, the present invention will be further described in conjunction with the embodiments.

[0054] Take the Tennessee-Eastman process as an example:

[0055] The Tennessee-Eastman process consists of five parts: reactor, condenser, separator, compressor and stripper, and contains 12 operating variables and 41 measurement variables. There are 21 fault variables.

[0056] Step 1. Collect sensor data in the chemical process, process it, and establish a new process prediction model.

[0057] The specific steps are:

[0058] 1.1 Collect the data in the chemical process for offline modeling. The data is divided into two categories, process data X and quality data Y. There are a total of N samples.

[0059] X=[x 1 ,x 2 ,...X m ],x 1 ,x 2 …X m ∈R N×1

[0060] Y=[y 1 ,y 2 ,...Y p ],y 1 ,y 2 …Y p ∈R N×1

[0061] Where x 1 ,x 2 ,...X m Etc. respectively represent the reactant concentration, pressure, temperature... valve opening and other variables in the Tennessee-Eastman chemic...

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 novel chemical process quality prediction method, comprising the following steps: step 1, collecting sensor data in the chemical process, processing and establishing a novelprocess prediction model; Step 2: Collecting the newly obtained data during the chemical process operation, and using the prediction model obtained in step 1 to carry out on-line prediction. First, the orthogonal signal correction algorithm is used to deal with the historical data collected from the process, and then the prediction model is established by using the processed data. In order to improve the ability of the model to deal with nonlinear data, support vector machine is introduced into the prediction model. This method improves the disadvantage of the traditional prediction model thatthe modeling process is complex and can not deal with the nonlinear data, and improves the ability of the model to track the real data.

Description

technical field [0001] The invention belongs to the technical field of automation and relates to a novel chemical process quality prediction method. Background technique [0002] As the modern chemical process continues to develop towards large-scale, integrated, and complex directions, more and more sensors are used in the chemical process, and more process information can be collected. Even so, in the chemical process control system, there are still some important quality variables that cannot be measured in real time. Failure to know the values ​​of these quality variables can seriously affect the quality of the product and the safety of production. A major goal of chemical process data analysis is to build a regression model based on experimental data or historical data, and then use the built model to predict product quality. The high-latitude nature of process data makes it difficult to accurately measure product quality, which leads to the development of multivariat...

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): G06Q10/04G06Q10/06G06Q50/04
CPCG06Q10/04G06Q10/06395G06Q50/04Y02P90/30
Inventor 张日东李翔
Owner HANGZHOU DIANZI 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