Real time prediction for converter gas tank levels based on multi-output least square support vector regressor

被引：94

作者：

Han, Zhongyang ^{[1
]}

Liu, Ying ^{[1
]}

Zhao, Jun ^{[1
]}

Wang, Wei ^{[1
]}

机构：

[1] Dalian Univ Technol, Sch Control Sci & Engn, Dalian, Peoples R China

来源：

CONTROL ENGINEERING PRACTICE | 2012年 / 20卷 / 12期

关键词：

LDG system; Gas tank level; Multi-output LSSVM; Regression prediction; Parameter optimization; EVOLUTIONARY ALGORITHMS; MACHINES; SYSTEM;

D O I：

10.1016/j.conengprac.2012.08.006

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Linz Donawitz converter gas (LOG) is the significant secondary energy resource that plays a crucial role in the energy system of steel industry. Since the real-time prediction for the gas tank level of LOG system is the foundation of energy balance scheduling that directly affects the energy costs of enterprise, more and more attentions has been paid to this issue. In this study, taking the LOG system of Ma'anshan Steel Co., Ltd, China into account, a multi-output least square support vector regressor is proposed, which considers not only the single fitting error of each tank level but also the combined one. Then, a prediction model for the multi-tank LOG system is derived, and a particle swarm optimization is designed to determine the parameters of this model for the sake of improving the prediction accuracy. The experimental results based on the real data from the plant demonstrate that the proposed method is effective to the practical application. (c) 2012 Elsevier Ltd. All rights reserved.

引用

页码：1400 / 1409

页数：10

共 31 条

[21]

Perkins S., 2003, J MACHINE LEARNING R, P3

[22]

Scholkopf B., 2001, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond

[23]

Smola A.J., 2001, Learning with Kernels

[24] Multioutput Support Vector Regression for Remote Sensing Biophysical Parameter Estimation [J].

Tuia, Devis ;

Verrelst, Jochem ;

Alonso, Luis ;

Perez-Cruz, Fernando ;

Camps-Valls, Gustavo .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2011, 8 (04) :804-808

[25] Financial time series prediction using least squares support vector machines within the evidence framework [J].

Van Gestel, T ;

Suykens, JAK ;

Baestaens, DE ;

Lambrechts, A ;

Lanckriet, G ;

Vandaele, B ;

De Moor, B ;

Vandewalle, J .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (04) :809-821

[26]

Van Gestel T., 2002, Least Squares Support Vector Machines

[27]

Vapnik V., 1995, The nature of statistical learning theory

[28] Support vector regression model predictive control on a HVAC plant [J].

Xi, Xue-Cheng ;

Poo, Aun-Neow ;

Chou, Slaw-Kiang .

CONTROL ENGINEERING PRACTICE, 2007, 15 (08) :897-908

[29] An optimal method for prediction and adjustment on byproduct gas holder in steel industry [J].

Zhang, Xiaoping ;

Zhao, Jun ;

Wang, Wei ;

Cong, Liqun ;

Feng, Weimin .

EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (04) :4588-4599

[30] Online Parameter Optimization-Based Prediction for Converter Gas System by Parallel Strategies [J].

Zhao, Jun ;

Wang, Wei ;

Pedrycz, Witold ;

Tian, Xiangwei .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2012, 20 (03) :835-845

← 1 2 3 4 →