An experimental modeling of cyclone separator efficiency with PCA-PSO-SVR algorithm

Accurate prediction of the complicated nonlinear relationship among the grade efficiency, geometrical dimensions, and operating parameters based on limited experimental data is the most effective way to design a high-efficiency cyclone separator. Herein, a hybrid PCA-PSO-SVR model is proposed to pre...

Full description

Saved in:
Bibliographic Details
Published in:Powder technology Vol. 347; pp. 114 - 124
Main Authors: Zhang, Wei, Zhang, Linlin, Yang, Jingxuan, Hao, Xiaogang, Guan, Guoqing, Gao, Zhihua
Format: Journal Article
Language:English
Published: Lausanne Elsevier B.V 01.04.2019
Elsevier BV
Subjects:
Algorithms
Correlation coefficient
Correlation coefficients
Cyclone separator
Cyclone separators
Efficiency
Experimental data
Grade efficiency
Kernel functions
Mathematical models
Model accuracy
Model testing
Parameters
Particle swarm optimization
powders
prediction
Predictions
Pretreatment
Principal component analysis
Principal components analysis
Random sampling
Regression analysis
sampling
Separators
Statistical sampling
Support vector machines
Support vector regression algorithm
Test sets
Grade efficiency
Cyclone separator
Particle swarm optimization
Support vector regression algorithm
Principal component analysis
ISSN:0032-5910, 1873-328X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate prediction of the complicated nonlinear relationship among the grade efficiency, geometrical dimensions, and operating parameters based on limited experimental data is the most effective way to design a high-efficiency cyclone separator. Herein, a hybrid PCA-PSO-SVR model is proposed to predict the grade efficiency of cyclone separators with the operating parameters based on 217 sets of experimental data provided in the literature. The experimental data are preprocessed using the random sampling technique together with the normalization method and principal component analysis (PCA) at first; subsequently, the particle swarm optimization (PSO) algorithm is incorporated to optimize the parameters for the support vector regression (SVR), including the penalty factor C, kernel function parameter g, and insensitive loss ε. Finally, the SVR model with the optimized parameters is trained with 80% pretreatment data, and the generalization ability of the model is tested with the remaining 20% data. The mean squared error of the test sets is 6.948 × 10−4 with a correlation coefficient of 0.982. The comparison results show that the PCA-PSO-SVR model has higher accuracy, better generalization ability, and stronger robustness than the existing models for predicting the cyclone separator efficiency in the case with only a few experimental data. [Display omitted] •The geometrical and operating parameters are both considered in modeling.•PCA is used to reduce the eight factors to five factors with minimal information loss.•SVR is used to create models with limited experimental data.•PSO is applied to improve the modeling accuracy.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0032-5910
1873-328X
DOI:10.1016/j.powtec.2019.01.070