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

A soft sensor method and system based on vine copula

A soft measurement and variable technology, applied in the field of soft measurement, can solve problems such as lack of information and affect the effect of soft measurement, and achieve the effects of avoiding information loss, good regression prediction ability, and reducing complexity

Active Publication Date: 2021-09-03
EAST CHINA UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the process is highly nonlinear and non-Gaussian, there will often be a significant lack of information and directly affect the final soft sensor effect

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 soft sensor method and system based on vine copula
  • A soft sensor method and system based on vine copula
  • A soft sensor method and system based on vine copula

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] The present invention discloses a complex chemical process soft-sensing method based on vine copula correlation modeling, and the specific steps are as follows:

[0099] [Step S1]: Select appropriate auxiliary variables for the soft sensor model according to actual industrial production conditions and expert knowledge.

[0100] [Step S2]: Obtain the transformed data conforming to copula modeling by using the monotone transformation method.

[0101] See formula (1) for the zero-mean standardization of the original data

[0102]

[0103] in,

[0104] x i is the variable before transformation, X i ′ is the variable after zero-mean standardization, u(X i ) is the variable X i mean of , var(X i ) is the variable X i Variance. Define the monotone transformation form, see formula (2):

[0105] Z i =(1-α i )X i '+α i x r 'i=(1,2,...,d) (2)

[0106] in

[0107] Z i is the variable after rolling pin transformation, X r ' is the reference variable, α i is the...

Embodiment 2

[0155] The description of the following examples will help to understand the present invention, but does not limit the content of the present invention. see figure 2 , the present embodiment realizes the prediction (PER) of the degree of ethylene cracking in the ethylene cracking process. The data of this implementation example comes from the SRT-III model ethylene cracking furnace, and the prediction target is the ethylene cracking rate, which is determined by PER (propylene / ethylene ratio) Said that 500 sets of data under normal working conditions were selected, 400 sets were used to train the copula model, and 100 sets were used for testing.

[0156] (1) According to the prior information, four auxiliary variables are selected: the average outlet temperature of the cracking furnace x 1 ;Density x of the pyrolysis feedstock 2 Total Feed x 3 and steam hydrocarbon ratio x 4 . The target variable y is the lysis depth index PER.

[0157] (2) Data preprocessing: standardiz...

Embodiment 3

[0163] see Figure 4 , this embodiment realizes the prediction of the concentration of butane at the bottom of the debutanizer tower, the data of this implementation example comes from the process of the debutanizer tower, the prediction target is the butane concentration at the bottom of the debutanizer tower, and the normal working condition is selected Of the 2000 sets of data, 1000 sets are used to train the copula model and 1000 are used for testing.

[0164] (1) According to the prior information, 7 auxiliary variables are selected: top temperature x 1 , top pressure x 2 , top return flow x 3 , the outflow of the top product x 4 , the temperature of the 6th tray x 5 , bottom temperature 1x 6 , bottom temperature 2x 7 , and put x 6 and x 7 merged into x 6 =(x 6 +x 7 ) / 2, the leading variable is the bottom butane concentration y.

[0165] (2) Data preprocessing: standardize the zero mean value of the training samples, and select the last one-dimensional auxilia...

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 present invention proposes a soft sensor method and system based on vine copula, including the following steps: selecting suitable auxiliary variables for the soft sensor model according to actual industrial production conditions and expert knowledge; standardizing and monotonically transforming the training data to obtain the transformed The final data that complies with copula modeling; use D‑vine copula for correlation modeling to obtain the joint probability density function of training sample auxiliary variables and target variables; online collection, standardization processing and monotone transformation calculation of auxiliary variables of samples to be predicted; calculation After processing the copula function values ​​of the auxiliary variable of the sample to be predicted and the target variable of all training samples, the weight of each training sample is calculated; according to the weight of the training sample calculated above, the target variable of the training sample is linearly weighted to obtain the sample to be predicted The predicted values ​​normalized by the target variable are then inversely transformed to obtain the final predicted values.

Description

technical field [0001] The invention belongs to the technical field of soft sensing, and in particular relates to a soft sensing method based on vine copula correlation description; at the same time, the invention also relates to a soft sensing system based on vine copula correlation description. Background technique [0002] With Industry 4.0 being put on the agenda, the competition between industries and manufacturing industries at home and abroad is becoming increasingly fierce, and the requirements for product quality, manufacturing costs, and energy consumption requirements in industrial production are gradually increasing. In order to reduce the cost of products, enterprises are developing towards complexity, scale and intelligence. Therefore, it plays an important role for industrial development to obtain key information of quality indicators of related process objects in time. However, the online measurement of some important process indicators will inevitably be af...

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 Patents(China)
IPC IPC(8): G06F30/20G06F17/15G06F17/18G06Q50/04G06F111/10
CPCG06F17/15G06F17/18G06Q50/04Y02P90/30
Inventor 李绍军蔡俊周洋倪佳能
Owner EAST CHINA UNIV OF SCI & TECH
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