Identification Method of Cement Clinker Composition Change Based on Locality Preserving Projections and K-medoids

The accurate identification of the change of cement clinker composition has great significance for improving the quality of cement clinker. In this paper, a method for identifying changes in cement clinker composition based on locality preserving projections and K-medoids algorithm was proposed. Fir...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu, Shizeng, Yu, Hongliang, Wang, Xiaohong, Li, Fanjun, Zhao, Peirui, Li, Qiangya
Format: Conference Proceeding
Language:English
Subjects:
Calcination
Cement clinker composition change
Clustering algorithms
Companies
Dimensionality reduction
Feature extraction
Identification method
K-medoids
Liquids
Locality preserving projections
Minerals
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The accurate identification of the change of cement clinker composition has great significance for improving the quality of cement clinker. In this paper, a method for identifying changes in cement clinker composition based on locality preserving projections and K-medoids algorithm was proposed. Firstly, the main features used to identify changes in the composition of cement clinker were determined according to the cement process. Then, the locality preserving projections algorithm was used to reduce high-dimensional features to low-dimensional ones. The K-medoids algorithm was used to cluster low-dimensional features to achieve the identification of changes in cement clinker composition. Finally, taking a cement company as an example, the method proposed in this paper has been verified. The verified results showed that the identification method of cement clinker composition change based on locality preserving projections and K-medoids was feasible. This paper provides a feasible method for the identification of cement clinker composition change.
ISSN:1948-9447
DOI:10.1109/CCDC.2019.8832496