Check patentability & draft patents in minutes with Patsnap Eureka AI!

Industrial processes principal process analysis and neural network optimization modeling method

A neural network model and neural network technology are applied in the field of industrial process principal component analysis and neural network optimization modeling. The effect of enhancing monitoring performance

Inactive Publication Date: 2018-07-24
HANGZHOU DIANZI UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of this invention is to propose a new modeling method for the problem that the nonlinear characteristics of the process data existing in the current industrial process are difficult to be accurately extracted

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
  • Industrial processes principal process analysis and neural network optimization modeling method
  • Industrial processes principal process analysis and neural network optimization modeling method
  • Industrial processes principal process analysis and neural network optimization modeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Take the pressure control in the coke oven as an example:

[0042] Coke oven is an important equipment for producing fuel and petrochemical products, and its chamber pressure operation is very important to ensure the safety of combustion. However, due to its non-linear characteristics, time delay, fuel quantity and pressure coupling and other interferences, building a model is a very complex task. Because there are so many disturbances, the main disturbances are relatively difficult to obtain. How to select disturbance variables and construct disturbance models is still a challenge. The method proposed by the present invention is used in the coke oven production process.

[0043] Step 1. Design a radial basis function neural network model based on principal component analysis. specifically is:

[0044] 1.1 Determine the random variable criterion for selecting the variables for principal component analysis. The optimal solution for the sub-set P is equivalent to the criterio...

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 an industrial processes principal process analysis and neural network optimization modeling method. According to the method, a random variable quasi-measurement function in principal component analysis is adopted to select variables; a non-dominated sorting genetic algorithm is adopted to solve a neural network modeling problem; and the method provided by the invention is combined with an actual industrial process, that is, the control of pressure in a coke oven, results show that the method provided by the invention has high data extraction precision. According to thetechnical schemes of the invention, the industrial processes principal process analysis and neural network optimization modeling method is established by means of data acquisition, variable selection,model establishment, iterative control, optimization and the like, and therefore, data extraction precision can be improved, and monitoring performance can be enhanced.

Description

Technical field [0001] The invention belongs to the field of automation technology, and relates to an industrial process principal component analysis and neural network optimization modeling method. Background technique [0002] In the process industry, we often want to extract the fewest process variables with correlations, so that the modeling, control, and monitoring processes for improving product quality will become easier. By using a subset of process variables instead of the entire process data, the complexity of the model can be reduced and the nature of the industrial process can be better captured. However, with the development of industrial processes, modeling becomes more and more complex, and it is difficult to obtain satisfactory accuracy in data feature extraction based on linear models, and more advanced nonlinear feature extraction algorithms are required. [0003] Artificial neural network is currently a relatively advanced method of non-linear feature extraction...

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
CPCG05B13/042
Inventor 张日东陶吉利侯平智
Owner HANGZHOU DIANZI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com