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

Building method of on-line robust regular soft measurement model of ore grinding granularity

A method of establishment and soft measurement technology, applied in the fields of measurement device, particle size analysis, particle and sedimentation analysis, etc., can solve the problems of difficulty in meeting the requirements of estimation accuracy and real-time performance, low model reliability, etc., and achieve fast training speed. , good real-time performance, and the effect of improving robustness

Active Publication Date: 2019-01-04
荣托昆普(无锡)科技有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem that the reliability of the current model is not high and it is difficult to meet the requirements of the actual grinding process for estimation accuracy and real-time performance, the present invention proposes a method for establishing an online robust regular soft sensor model of the grinding particle size. And verified with the grinding process data

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
  • Building method of on-line robust regular soft measurement model of ore grinding granularity
  • Building method of on-line robust regular soft measurement model of ore grinding granularity
  • Building method of on-line robust regular soft measurement model of ore grinding granularity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0037] Such as figure 1 As shown, the establishment method of the online robust regular soft sensor model of the grinding particle size of the embodiment of the present invention comprises the following steps:

[0038] S1. Among the variables of the grinding process, the five process variables with the highest correlation with the grinding particle size are selected as input variables, and the grinding particle size is modeled and estimated.

[0039] Among them, the input variables include ball mill feed rate (t / h), ball mill in...

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 building method of an on-line robust regular soft measurement model of ore grinding granularity. The building method includes the following steps that 1, five process variables with the highest correlation with the ore grinding granularity are selected from ore grinding process variables to serve as input variables, and the ore grinding granularity is subjected to modelling estimation; 2, the structure and parameters of an on-line robust regular random vector functional link network are initialized, a regular random vector functional link network model with introducedL2-ridge regression is built, and initial residuals of samples are calculated; 3, in an initial learning stage of robust modelling, according to the initial residuals of the samples, the weight of each sample is calculated through a weight function based on M estimation of an IGG method when the samples participate in initial modelling, and an initial output weight of the network model is upgraded; 4, in an initial learning stage of on-line estimation and robust modelling, the network model is adopted, and according to ore grinding process data which is collected in real time, the ore grinding granularity at the present moment is estimated on line; output weight offset constraint is introduced, and the parameters of the random vector functional link network are upgraded in a self-adaptionmode.

Description

technical field [0001] The invention relates to the technical field of data-driven modeling, in particular to a method for establishing an online robust regular soft sensor model of grinding particle size. Background technique [0002] The grinding process is the most critical process in the ore beneficiation process, which plays an important role in linking the past and the future. The grinding process is mainly to crush ore raw materials to a suitable particle size, so that useful minerals can be dissociated from gangue monomers, or different useful minerals can be dissociated from each other to provide raw materials for subsequent sorting operations. Among them, the grinding particle size is a key operating index that characterizes the quality of the produced product in the grinding process. A suitable grinding particle size can not only realize the monomer dissociation of useful minerals, but also ensure that the obtained grinding products have a high metal recovery rat...

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): G01N15/02
CPCG01N15/02
Inventor 代伟胡金成李德鹏夏振兴褚菲杨瑞哲王雪松程玉虎马小平
Owner 荣托昆普(无锡)科技有限公司
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