Energy consumption prediction in ironmaking process using hybrid algorithm of SVM and PSO

Authors:
Yanyan Zhang;Xiaolei Zhang;Lixin Tang
Affiliations:
Liaoning Key Laboratory of Manufacturing System and Logistics, China,The Logistics Institute, Northeastern University, Shenyang, China;State Key Laboratory of Synthetical Automation for Process Industries, China,The Logistics Institute, Northeastern University, Shenyang, China;Liaoning Key Laboratory of Manufacturing System and Logistics, China,The Logistics Institute, Northeastern University, Shenyang, China
Venue:
ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II
Year:
2012

Citing 3
Cited 0

Least Squares Support Vector Machine Classifiers

Neural Processing Letters
Time Series Analysis, Forecasting and Control

Time Series Analysis, Forecasting and Control
Choosing Multiple Parameters for Support Vector Machines

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a support vector machine (SVM) classifier is designed for predicting the energy consumption level of Ironmaking process. To improve the accuracy, particle swarm optimization (PSO) is introduced to optimize the parameters of SVM. First, the consuming structure of Ironmaking process is analyzed so as to accurately modeling the prediction problem. Then the improved SVM algorithm is presented. Finally, the experimental test is implemented based on the practical data of a Chinese Iron and Steel enterprise. The results show that the proposed method can predict the consumption of the addressed Ironmaking process with satisfying accuracy. And that the results can provide the enterprise with effective quantitative analysis support.