Data-driven thermal efficiency modeling and optimization for co-firing boiler

Author

Jian-Guo Wang ; Juan-Juan Wang ; Qian-Ping Xiao ; Shi-Wei Ma ; Wen-Tao Rao ; Yong-Jie Zhang

Author_Institution

Shanghai Key Lab. of Power Station Autom. Technol., Shanghai Univ., Shanghai, China

fYear

2014

fDate

May 31 2014-June 2 2014

Firstpage

3608

Lastpage

3611

Abstract

The changes of flow rate and heating value of blast furnace gas (BFG) make the boiler operation more like art than science. In this paper, statistics analysis methods are utilized to justify the significance of the derived variables for the thermal efficiency modeling. By employing nonnegative garrote (NNG) variable selection and auto-regression integrated moving average (ARIMA) correction, an adaptive scheme for thermal efficiency modeling and adjustment is proposed and virtually implemented for a BFG/coal co-firing boiler. The detail analysis shows that there is large room for energy conservation when the boiler operation shifts from the present practice to the model-based control.

Keywords

autoregressive moving average processes; blast furnaces; boilers; fossil fuels; statistical analysis; syngas; ARIMA correction; BFG-coal co-firing boiler; NNG variable selection; adaptive scheme; autoregression integrated moving average correction; blast furnace gas; data-driven thermal efficiency modeling; data-driven thermal efficiency optimization; energy conservation; flow rate changes; heating value changes; model-based control; nonnegative garrote variable selection; statistics analysis methods; Adaptation models; Atmospheric modeling; Boilers; Coal; Input variables; Mathematical model; Multi-fuel boiler; data-driven; statistics analysis; thermal efficiency; variable selection;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (2014 CCDC), The 26th Chinese

Conference_Location

Changsha

Print_ISBN

978-1-4799-3707-3

Type

conf

DOI

10.1109/CCDC.2014.6852805

Filename

6852805