Prediction of Alumina Density Based on LSSVM

Authors

Guimei Cui, 1. School Of Information Engineering, Inner Mongolia University Of Science & Technology, Baotou 014010, China;; ;
Haijin Yang, 1. School Of Information Engineering, Inner Mongolia University Of Science & Technology, Baotou 014010, China;; ;
Piliang Liu, 1. School Of Information Engineering, Inner Mongolia University Of Science & Technology, Baotou 014010, China;; ;
Yu Kai, 2. School Of Mathematics Physics, Inner Mongolia University Of Science & Technology, Baotou 014010, China;;

Abstract

Abstract: The prediction model of alumina density based on the PSO algorithm with swarm activity to optimize LSSVM method is built. According to the production process characteristics of aluminum electrolysis and historical data, the input variables of the model is determined. It can solve these problems that Particle Swarm Optimization (PSO) algorithm is with the risk of premature convergence and least square support vector machine is time consuming with parameter selection. The method uses swarm activity as diversity index. When swarm activity is quickened to descend, evolution operation is added to modify the positions or velocities of particles to improve standard PSO algorithm. Study shows that, the improved PSO-LSSVM prediction method has better estimating performance and less computational time than the traditional LSSVM method.

Recommended Citation

Cui, Guimei; Yang, Haijin; Liu, Piliang; and Kai, Yu (2019) "Prediction of Alumina Density Based on LSSVM," Journal of System Simulation: Vol. 30: Iss. 5, Article 29.
DOI: 10.16182/j.issn1004731x.joss.201805029
Available at: https://dc-china-simulation.researchcommons.org/journal/vol30/iss5/29

First Page

1844

Revised Date

2016-12-22

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201805029

Last Page

1849

CLC

TP391.9

Recommended Citation

Cui Guimei, Yang Haijin, Liu Piliang, Yu Kai. Prediction of Alumina Density Based on LSSVM[J]. Journal of System Simulation, 2018, 30(5): 1844-1849.

DOI

10.16182/j.issn1004731x.joss.201805029