Soft measurement method for beating degree of papermaking process based on gradient enhanced regression tree

A regression tree, beating degree technology, applied in pulp beating methods and other directions, can solve the problems of high model complexity and limited generalization ability.

Active Publication Date: 2019-03-08
广州博依特智能信息科技有限公司
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are certain limitations in the research on beating degree soft measurement at home and abroad, such as t

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
  • Soft measurement method for beating degree of papermaking process based on gradient enhanced regression tree
  • Soft measurement method for beating degree of papermaking process based on gradient enhanced regression tree
  • Soft measurement method for beating degree of papermaking process based on gradient enhanced regression tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0061] like figure 1 As shown, a soft measurement method of beating degree in papermaking process based on gradient enhanced regression tree, including the following steps:

[0062] S1. According to the actual situation of production, collect the fiber shape data and initial beating degree data of the original pulp, collect the refining process data, and do data processing;

[0063] S2. Based on the principle of gradient-enhanced regression tree, establish a soft-sensing model of beating degree; record the gradient-enhanced regression tree F generated by the mth iteration m (x) is the beating degree soft measurement model, the specific formula is as follows:

[0064]

[0065] where F m-1 (x) is the gradient enhanced regression tree generated by the m-1th iteration, x represents the independent variable of the data set, and y represents the dependent variable, Indicates the choice of square loss function, T m (x i ) represents the regression tree generated by the mth ...

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 soft measurement method for the beating degree of the papermaking process based on a gradient enhanced regression tree. The method comprises the following steps of S1, collecting fiber morphology data of an original slurry and initial pulping degree data, collecting the refining process data, and conducting data processing; S2, based on the principle of gradient enhancedregression tree, establishing a soft measurement model of the beating degree; S3, using a cross-validation method according to the training data set, and training the soft measurement model of the beating degree; S4, adjusting the parameters of the soft measurement model of the beating degree according to the training data set; S5, using the aforementioned training and the adjusted model to conduct the soft measurement of the beating degree on a sample to be tested; the method is based on the gradient enhanced regression tree, the soft measurement model of the beating degree is established, the model is convenient and highly precise, and the method has strong generalization ability and good prospects for popularization and application.

Description

technical field [0001] The invention relates to wireless communication technology, in particular to a soft measurement method of beating degree in papermaking process based on gradient enhanced regression tree. Background technique [0002] The refining process in the pulp preparation stage is the only process that changes the morphology of pulp fibers, increases the binding ability of fibers, and has a great influence on the properties of paper, such as the tensile strength of paper sheets, so that paper products have the required physical properties . Such as figure 2 Shown is a flow chart of the refining process, in which freeness is a pulp property related to pulp drainage. In actual production, the degree of beating is used to explain the operating efficiency of the refining process and indirectly monitor product quality, which is a very important intermediate variable. He regulates by adjusting the dilution water flow, refiner power, feeding speed, slurry concentrat...

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): D21D1/02
CPCD21D1/02
Inventor 李继庚洪蒙纳满奕孟子薇
Owner 广州博依特智能信息科技有限公司
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