Dynamic Data Modeling of SCR Denitration System Based on Mutual Information

DOI

10.2991/csece-18.2018.69How to use a DOI?

Keywords

coal-fired unit; SCR de-NOx system; mutual information; least squares support vector machine

Abstract

The establishment of accurate models is vital in parametric optimization of control systems, and the choice of input variables can directly affect the accuracy and complexity of the model. Therefore, this paper proposed a modeling method based on mutual information (MI) and least squares support vector machine (LSSVM). On the basis of MI, the problem of delay, the correlation and redundancy among variables were considered synthetically. The optimal ones were screened through field measured variables by MI, and chosen as the input of LSSVM for predictions of output NOx concentration. The results proved the method can decrease complexity, improve approximation and generalization capability.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wenjie Zhao
AU  - Luyao Zhang
PY  - 2018/02
DA  - 2018/02
TI  - Dynamic Data Modeling of SCR Denitration System Based on Mutual Information
BT  - Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)
PB  - Atlantis Press
SP  - 321
EP  - 324
SN  - 2352-538X
UR  - https://doi.org/10.2991/csece-18.2018.69
DO  - 10.2991/csece-18.2018.69
ID  - Zhao2018/02
ER  -