A soft sensing method for a melt index of polypropylene based on a selective integrated limit learning machine

A technology of extreme learning machine and melt index, which is applied in forecasting, data processing applications, instruments, etc., can solve problems such as inability to guarantee forecasting accuracy and weak model stability, achieve good forecasting performance and generalization ability, and improve generalization performance, the effect of achieving quality control

Inactive Publication Date: 2018-12-11
ZHEJIANG UNIV OF TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Purpose of the present invention: In order to overcome the shortcomings of the existing polypropylene melt index soft sensor model that cannot guarantee the prediction accuracy in the global scope, the model stability is not strong, etc., to provide a polypropylene melt index soft sensor model based on selective integration extreme learning machine Measurement methods

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 sensing method for a melt index of polypropylene based on a selective integrated limit learning machine
  • A soft sensing method for a melt index of polypropylene based on a selective integrated limit learning machine
  • A soft sensing method for a melt index of polypropylene based on a selective integrated limit learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The implementation of the present invention will be further described below in conjunction with the accompanying drawings and examples, so that how the present invention uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0031] The main steps of the technical solution adopted in the present invention are as follows:

[0032] (1) The process diagram of a double-loop polypropylene production unit in a petrochemical enterprise is as follows figure 1 As shown, on the basis of detailed analysis of propylene polymerization kinetics and Spheripol double-loop process characteristics, appropriate auxiliary variables are selected. The auxiliary variables of the polypropylene melt index soft sensor model include the first loop hydrogen concentration u 1 (ppm), second loop hydrogen concentration u 2 (ppm), catalyst flow rate u 3 (kg / h), the first loop propylene monomer flow rate u 4 (t / h), second ...

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

A soft sensing method for a melt index of polypropylene based on a selective integrated limit learning machine includes: firstly, an original sample data set is divided into training sample set and evaluation sample set, multiple subsets of training samples are established by random resampling method, and each subset is trained to establish the limit learning machine submodel, then the performanceof each submodel is evaluated by using the evaluation sample set, and the submodel for integration is screened, and finally, the predicted value of polypropylene melt index of each submodel is obtained by calculating the weight coefficient of each submodel. The invention has the characteristics of high prediction accuracy and high generalization ability. According to the soft sensing result obtained by the invention, the melt index change trend of the polypropylene production process can be well tracked, and effective technical support is provided for operation optimization and quality control of the polypropylene production process.

Description

technical field [0001] The invention belongs to the field of research and application of soft-sensing methods in the production process of polypropylene, and in particular relates to a soft-sensing method for polypropylene melt index based on a selective integrated extreme learning machine. Background technique [0002] Polypropylene products are widely used in the production of daily necessities, food packaging, electrical components and mechanical parts due to their low price, easy molding and excellent performance. Product quality control is a key link in the production process of polypropylene industry. The quality of the product is not only directly related to the processing performance of the product, but also affects the normal operation of the polymerization production device, raw material consumption, production cost and other economic indicators. [0003] Melt Index (MI for short) is a quality index to distinguish different grades of polypropylene products. Differe...

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): G06Q10/06G06Q10/04
CPCG06Q10/04G06Q10/06393G06Q10/06395
Inventor 夏陆岳李卓潘海天蔡亦军张洪德
Owner ZHEJIANG 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