Online fuzzy least square support vector machine sintering process kinetics modeling algorithm

A technology of fuzzy least squares and support vector machines, which is applied in the direction of instruments, adaptive control, control/regulation systems, etc., and can solve problems such as expensive equipment, difficult and practical detection methods, and increased image processing complexity

Inactive Publication Date: 2016-11-09
GUANGDONG UNIV OF TECH
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For increasing the data detection method, because the internal temperature of most sintering processes is relatively high, the general detection method is difficult to be practical. At present, more research is to use the image signal of the sintering flame and use the method of image processing to obtain the temperature distribution in it. Data information
This type of model depends on the pros and cons of the imaging technology of the detection equipment and the image processing software. When there are many process disturbances, fuel performance changes and other factors, the complexity of image processing may be greatly increased; in addition, for this type of high-temperature process Most of the equipment for imaging processing is relatively expensive, and it is rarely used in most similar chemical sintering production in China.

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
  • Online fuzzy least square support vector machine sintering process kinetics modeling algorithm
  • Online fuzzy least square support vector machine sintering process kinetics modeling algorithm
  • Online fuzzy least square support vector machine sintering process kinetics modeling algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The online fuzzy least squares support vector machine sintering process dynamics modeling algorithm includes the following steps:

[0033] Step 1: Adopt fuzzy c-means objective function For online input of k+L groups of data space vectors (x 1 ,y 1 ),(x 2 ,y 2 ),…,(x l ,y l ) for fuzzy division to get its fuzzy membership degree (u 1 ,u 2 ,...u l ), then the fuzzy division of k+L group data space vectors is (x 1 ,y 1 ,μ 1 ), (x 2 ,y 2 ,μ 2),…,(x l ,y l ,μ l );in, is the cluster center vector; μ ik Indicates that the input vector of the fuzzy model at time k belongs to the membership degree of the i-th rule; d ik =||z i -x k || is space R M Inner product norm on ; q∈[1,∞] is the weighted exponent; n c is the rule number; U is the input data space; For each sampled data is the cluster center value; T is the transpose calculation; z i For each sampled data is the cluster center value; x k is the sampling data;

[0034] The fuzzy c-means object...

Embodiment 2

[0051] The online fuzzy least squares support vector machine sintering process dynamics modeling algorithm includes the following steps.

[0052] Step 1: According to the process reaction kinetics, establish the nonlinear relationship of process input and output parameters, apply LS-SVM modeling, and establish the objective function:

[0053] m i n ω , b , ξ J ( ω , b , ξ ) = m i n w , b , e ( 1 2 ω T ω + γ ...

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 online fuzzy least square support vector machine sintering process kinetics modeling algorithm. The algorithm fuzzily divides online input k+L groups of data vector space by using a fuzzy c mean value objective function, provides an input space fuzzy membership computing method, constructs a Langrange function according to a structural risk minimization principle, designs a model optimization object of the k+L groups of data according to a KKT optimal solution condition, and solves a model parameter and a model solution, determines the rolling characteristic of the data and whether to roll the online data to k+L+1 to update the model. The modeling algorithm introduces an input data fuzzy clustering idea so as to enhance the generalization capability of the model, and introduces the concept of a rolling time window so as to enhance similar solid sintering process online modeling practical performance.

Description

technical field [0001] The invention relates to the field of process dynamics intelligent modeling, in particular to a sintering process dynamics modeling algorithm of an online fuzzy least square support vector machine. Background technique [0002] The research on kinetic modeling of sintering process can be divided into two categories according to the different process characteristics of concern: one is to start from the microscopic characteristics of the sintering process, to study the chemical reaction heat balance and kinetic Quantitative experiments or mechanism function derivation are carried out on the sintering chemical reaction process, and parameters such as reaction type, order, and molar reaction enthalpy are obtained, and an accurate chemical kinetic reaction experimental model is obtained. This type of model is mainly used in theoretical research in the chemical industry. This type of model is far from the actual production and control reaction model when the...

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): G05B13/04
CPCG05B13/042
Inventor 朱燕飞徐训郑卜松
Owner GUANGDONG UNIV OF TECH
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