Modeling on SCR process of a coal-fired boiler using LSSVM method

Author

Yang Tingting ; Cui Chao ; Lv You ; Li Jian

Author_Institution

Key Lab. of Meas. & Control New Technol. & Syst. for Ind. Process, North China Electr. Power Univ., Beijing, China

fYear

2015

Firstpage

4025

Lastpage

4028

Abstract

Selective catalytic reduction (SCR) is widely applied in coal-fired power plants. SCR process is a complex physical and chemical process with multi-input, strong coupling, nonlinear, and time delay characteristics. An effective model is the basis of conducting control and optimization. In this paper, influencing factors of catalytic reaction in SCR converter are analyzed and five measurable parameters are selected as the model input variables. NOx emission and NH₃ slip are separately taken as output variables. The LSSVM algorithm is employed to build the SCR models using real plant operation data from a 1000 MW coal-fired boiler. Simulation results have shown satisfied model accuracy and effectiveness are achieved.

Keywords

boilers; least squares approximations; power engineering computing; support vector machines; LSSVM method; SCR converter; SCR process; coal-fired boiler; coal-fired power plants; least squares support vector machines; power 1000 MW; selective catalytic reduction process; Boilers; Data models; Mathematical model; Power generation; Predictive models; Process control; Thyristors; LSSVM; coal-fired power plant; data-driven model; selective catalytic reduction;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (CCDC), 2015 27th Chinese

Print_ISBN

978-1-4799-7016-2

Type

conf

DOI

10.1109/CCDC.2015.7162627

Filename

7162627