Sintering process time series data dimension reduction method based on information granulation

A time-series, sintering process technology, applied in the direction of instruments, character and pattern recognition, calculation models, etc., can solve the problems of complex process reactions and many detection parameters in the sintering process, achieve broad application value, reduce information redundancy, and reduce costs. dimensional effect

Pending Publication Date: 2020-09-04
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] There are many detection parameters in the sintering process, and the process reaction is complex

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
  • Sintering process time series data dimension reduction method based on information granulation
  • Sintering process time series data dimension reduction method based on information granulation
  • Sintering process time series data dimension reduction method based on information granulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0039] An embodiment of the present invention provides a dimensionality reduction method for time series data of a sintering process based on information granulation. First, split the time series into multiple non-overlapping time series segments. Then, interval information granulation is performed on the time series data in each time series segment. Then, the particle swarm optimization algorithm is used to optimize the interval information granules to obtain the best multi-granularity interval information granules. Finally, the dimensionality-reduced time series is represented by the numerical representation of the best multi-granularity interval information granules.

[0040] Please refer to Figure 1~4 , figure 1 ...

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 provides a sintering process time series data dimension reduction method based on information granulation. According to the method, sintering process detection parameter time series datais divided into a plurality of non-overlapping time series fragments. Interval information granulation is carried out on the time sequence data in each time sequence segment to obtain multi-granularity interval information granules; and the interval information particles are optimized by using a particle swarm optimization algorithm to obtain optimal multi-granularity interval information particles; and finally, the time sequence subjected to dimensionality reduction is represented by using the numerical value of the optimal multi-granularity interval information particles. The method has theadvantages that dimensionality reduction of the detection parameter time series data can be effectively achieved, meanwhile, the dynamic characteristic of the detection parameter time series can be kept, and the method has wide application value in the aspect of sintering process time series data processing.

Description

technical field [0001] The invention relates to the field of iron ore sintering production, in particular to a dimensionality reduction method for time series data of sintering process based on information granulation. Background technique [0002] A time series is a set of random variables sorted by time, which is usually the result of observing a certain underlying process at a given sampling rate in an equally spaced time period. Time series data essentially reflects the trend of one or some random variables changing over time. As time goes by, the amount of time series data becomes larger and larger, which brings the curse of dimensionality problem to the subsequent processing and analysis of time series data. Considering the redundancy of time series data, a series of methods such as data dimension reduction and feature representation have been developed to solve the problem of time series dimensionality disaster. [0003] Time series data widely exist in all walks of...

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): G06K9/62G06N3/00
CPCG06N3/006G06F18/213
Inventor 杜胜吴敏陈略峰曹卫华
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)
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